Faculty - Dashboard

@inproceedings{bib_Qual_2025, AUTHOR = {Raju, Nithin Kadakampallil and Thomas, Bejoy and Sivaswamy, Jayanthi and Yohannan, Doris George and Oommen, Aswathy Maria and Kumar, Amruth S. and Devanand, S. and Resivi, U. T. Minha and Sajan, Navya and Thomas, Neha Elizabeth and Anzer, Nasreen }, TITLE = {Qualitative Analysis of the Student Perspectives on AnaVu – A Three-dimensional Stereoscopic Neuroanatomy Visualization Tool}, BOOKTITLE = {National Journal of Clinical Anatomy}. YEAR = {2025}}

Background Prior research by the authors studied the objective impact on medical students’ academic course, the perceived cognitive load, quantified subjective feedback while teaching using AnaVu, a low resource stereoscopic projection system. The qualitative data from opinions, and comparative educational results reported by undergraduate medical students following their participation in stereoscopic (AnaVu) and monoscopic learning sessions are explored in this study. This study was done to evaluate and compare the effectiveness of stereoscopic and monoscopic teaching methods in enhancing spatial understanding of anatomical structures among first-year undergraduate medical students using AnaVu. Methodology This research study was conducted as a three-limb randomized controlled trial. Among those who provided informed consent, a sample of MBBS students from the 2022 cohort was chosen at random. Following a one-hour brainstem introduction lecture and a dissection session, students were assigned at random to one of three groups: S for stereo; M for mono; or C for control. A 20-minute stereoscopic demonstration of the brainstem module in AnaVu has been delivered to S. The identical presentation, albeit in monoscopic mode, was delivered to M. Diagrams drawn on a whiteboard were used to instruct the C group. Pre-intervention and post-intervention tests were given in four domains: basic recall, analytical, radiological anatomy and diagram-based questions. Finally, the groups were swapped – S→M, M→S and C→S, and they were asked to compare the modes. Data were processed using RQDA (R package for Qualitative Data Analysis). Theme identification and analysis of the qualitative data was done using the thematic analysis. Results 152 students participated in the study. Five themes and fourteen subthemes were identified. General advantages included size comparisons, software features, and improved attention, while specific benefits for learning radiological and sectional anatomy were noted. Disadvantages included eye strain, software glitches, costs, and concerns about teacher adaptation. Conclusion The findings of this study emphasize the potential of AnaVu in enhancing anatomical and radiological education, while highlighting key disadvantages to help teachers and students make informed choices between stereo and mono display methods.

@inproceedings{bib_Visu_2024, AUTHOR = {, and Sivaswamy, Jayanthi }, TITLE = {Visualization matters stereoscopic visualization of 3D graphic neuroanatomic models through AnaVu enhances basic recall and radiologic anatomy learnin}, BOOKTITLE = {BMC Medical Education}. YEAR = {2024}}

Background The authors had previously developed AnaVu, a low-resource 3D visualization tool for stereoscopic/ monoscopic projection of 3D models generated from pre-segmented MRI neuroimaging data. However, its utility in neuroanatomical education compared to conventional methods (specifically whether the stereoscopic or mono- scopic mode is more effective) is still unclear. Methods A three-limb randomized controlled trial was designed. A sample (n = 152) from the 2022 cohort of MBBS students at Government Medical College, Thiruvananthapuram (GMCT), was randomly selected from those who gave informed consent. After a one-hour introductory lecture on brainstem anatomy and a dissection session, students were randomized to three groups (S – Stereo; M – Mono and C – Control). S was given a 20-min demonstration on the brainstem lesson module in AnaVu in stereoscopic mode. M was given the same demonstration, but in mono- scopic mode. The C group was taught using white-board drawn diagrams. Pre-intervention and post-intervention tests for four domains (basic recall, analytical, radiological anatomy and diagram-based questions) were conducted before and after the intervention. Cognitive loads were measured using a pre-validated tool. The groups were then swapped -S→ M, M →S and C→S, and they were asked to compare the modes. Results For basic recall questions, there was a statistically significant increase in the pre/post-intervention score difference of the S group when compared to the M group [p = 0.03; post hoc analysis, Bonferroni corrections applied] and the C group [p = 0.001; ANOVA test; post hoc analysis, Bonferroni corrections applied]. For radiological anatomy questions, the difference was significantly higher for S compared to C [p < 0.001; ANOVA test; post hoc analysis, Bon- ferroni corrections applied]. Cognitive load scores showed increased mean germane load for S (33.28 ± 5.35) and M

@inproceedings{bib_CheX_2024, AUTHOR = {J, Naren Akash R and Tadanki, Arihanth Srikar and Sivaswamy, Jayanthi }, TITLE = {CheXtriev: Anatomy-Centered Representation for Case-Based Retrieval of Chest Radiographs}, BOOKTITLE = {International Conference on Medical Image Computing and Computer Assisted Intervention}. YEAR = {2024}}

We present CheXtriev, a graph-based, anatomy-aware framework for chest radiograph retrieval. Unlike prior methods focussed on global features, our method leverages graph transformers to extract informative features from specific anatomical regions. Furthermore, it captures spatial context and the interplay between anatomical location and findings. This contextualization, grounded in evidence-based anatomy, results in a richer anatomy-aware representation and leads to more accurate, effective and efficient retrieval, particularly for less prevalent findings. CheXtriv outperforms state-of-the-art global and local approaches by to in retrieval accuracy and to in ranking quality.

@inproceedings{bib_A_Me_2024, AUTHOR = {Thottupattu, Alphin J and Sivaswamy, Jayanthi }, TITLE = {A Method for Comparing Time Series by Untangling Time-Dependent and Independent Variations in Biological Processes}, BOOKTITLE = {ACM Transactions on Computing for Healthcare}. YEAR = {2024}}

Biological processes like growth, aging, and disease progression are generally studied with follow-up scans taken at different time points, i.e., image time series (TS) based analysis. Image TS represents the evolution of anatomy over time, but different anatomies may have different structural characteristics and temporal paths. Therefore, separating the time-dependent path difference and time-independent basic anatomy/shape changes is important when comparing two image TS to understand the causes of the observed differences better. A method to untangle and quantify the path and shape difference between the TS is presented in this paper. The proposed method is evaluated with simulated and adult and fetal neuro templates. Results show that the metric can separate and quantify the path and shape differences between TS.

@inproceedings{bib_A_Me_2024, AUTHOR = {Thottupattu, Alphin J and Sivaswamy, Jayanthi }, TITLE = {A Method for Comparing Time Series by Untangling Time-Dependent and Independent Variations in Biological Processes}, BOOKTITLE = {ACM Transactions on Computing for Healthcare}. YEAR = {2024}}

Biological processes like growth, aging, and disease progression are generally studied with follow-up scans taken at different time points, i.e., image time series (TS) based analysis. Image TS represents the evolution of anatomy over time, but different anatomies may have different structural characteristics and temporal paths. Therefore, separating the time-dependent path difference and time-independent basic anatomy/shape changes is important when comparing two image TS to understand the causes of the observed differences better. A method to untangle and quantify the path and shape difference between the TS is presented in this paper. The proposed method is evaluated with simulated and adult and fetal neuro templates. Results show that the metric can separate and quantify the path and shape differences between TS.

@inproceedings{bib_Nerv_2024, AUTHOR = {Tyagi, Abhishek and Tyagi, Abhay and Kaur, Manpreet and Aggarwal, Richa and Soni, Kapil D. and Sivaswamy, Jayanthi and Trikha, Anjan }, TITLE = {Nerve Block Target Localization and Needle Guidance for Autonomous Robotic Ultrasound Guided Regional Anesthesia}, BOOKTITLE = {International Conference on Intelligent Robots and Systems}. YEAR = {2024}}

Visual servoing for the development of autonomous robotic systems capable of administering UltraSound (US) guided regional anesthesia requires real-time segmentation of nerves, needle tip localization and needle trajectory extrapolation. First, we recruited 227 patients to build a large dataset of 41,000 anesthesiologist annotated images from US videos of brachial plexus nerves and developed models to localize nerves in the US images. Generalizability of the best suited model was tested on the datasets constructed from separate US scanners. Using these nerve segmentation predictions, we define automated anesthesia needle targets by fitting an ellipse to the nerve contours. Next, we developed an image analysis tool to guide the needle toward their targets. For the segmentation of the needle, a natural RGB pre-trained neural network was first fine-tuned on a large US dataset for domain transfer and then adapted for the needle using a small dataset. The segmented needle’s trajectory angle is calculated using Radon transformation and the trajectory is extrapolated from the needle tip. The intersection of the extrapolated trajectory with the needle target guides the needle navigation for drug delivery. The needle trajectory’s average error was within acceptable range of 5 mm as per experienced anesthesiologists. The entire dataset has been released publicly for further study by the research community at https://github.com/Regional-US/

@inproceedings{bib_CheX_2024, AUTHOR = {J, Naren Akash R and Tadanki, Arihanth Srikar and Sivaswamy, Jayanthi }, TITLE = {CheXtriev: Anatomy-Centered Representation for Case-Based Retrieval of Chest Radiographs}, BOOKTITLE = {International Conference on Medical Image Computing and Computer Assisted Intervention}. YEAR = {2024}}

We present CheXtriev, a graph-based, anatomy-aware frame- work for chest radiograph retrieval. Unlike prior methods focussed on global features, our method leverages graph transformers to extract in- formative features from specific anatomical regions. Furthermore, it cap- tures spatial context and the interplay between anatomical location and findings. This contextualization, grounded in evidence-based anatomy, results in a richer anatomy-aware representation and leads to more accu- rate, effective and efficient retrieval, particularly for less prevalent find- ings. CheXtriv outperforms state-of-the-art global and local approaches by 18% to 26% in retrieval accuracy and 11% to 23% in ranking quality. The code is available at https://github.com/cvit-mip/chextriev.

@inproceedings{bib_Leve_2024, AUTHOR = {Shastri, Samruddhi and J, Naren Akash R and Sivaswamy, Jayanthi }, TITLE = {Leveraging Spatial Guidance for Accurate Multi-Organ Segmentation in Abdominal CT}, BOOKTITLE = {International conference on Pattern Recognition}. YEAR = {2024}}

Accurate multi-organ segmentation in abdominal CT is essential for diagnosis, treatment planning, and disease monitoring. However, it suffers from inaccurate segmentation due to intricate spatial relationships and varying organ shapes. Existing deep learning methods often struggle with imbalanced classes, size bias, and ambiguous boundaries, hindering segmentation accuracy. To address these challenges, this paper proposes Guided-nnUNet, a two-stage segmentation framework that decomposes abdominal multi-organ segmentation into organ localization and then localization-guided fine segmentation. In the first stage, a ResNet-50 model generates a low-dimensional localization map guiding organ locations. This spatial guidance is then fed into the second stage, where a 3D U-Net with dynamic affine feature-map transform performs the fine-grained segmentation by integrating spatial context from the localization map. Our evaluation on the publicly available AMOS and BTCV datasets demonstrates the effectiveness of the model. Guided-nnUNet achieves an average improvement of 7% and 9% on the AMOS and BTCV datasets, respectively, compared to the baseline nnUNet model. Additionally, our model outperforms the state-of-the-art MedNeXt by 3.6% and 5.3% on the AMOS and BTCV datasets, respectively. These results suggest that our two-stage solution offers a promising approach for accurate abdominal organ segmentation, particularly for overcoming the challenges associated with complex organ structures.

@inproceedings{bib_Loca_2024, AUTHOR = {Shastri, Samruddhi and J, Naren Akash R and M, Lokesh Gautham B and Sivaswamy, Jayanthi }, TITLE = {Locate-Then-Delineate: A Free-text Report Guided Approach for Pneumothorax Segmentation in Chest Radiographs}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2024}}

We present a novel solution for accurate segmentation of pneumothorax from chest radiographs utilizing free-text radiology reports. Our solution employs text-guided attention to leverage the findings in the report to initially produce a low-dimensional region-localization map. These prior region maps are integrated at multiple scales in an encoder-decoder segmentation framework via dynamic affine feature map transform (DAFT). Extensive experiments on a public dataset CANDID-PTX, show that the integration of free-text reports significantly reduces the false positive predictions, while the DAFT-based fusion of localization maps improves the positive cases. Our method achieves a DSC of 0.60 for positive and 0.052 FPR for positive and negative cases, respectively, and 0.70 to 0.85 DSC for medium and large pneumothoraces.

@inproceedings{bib_Glob_2023, AUTHOR = {Thottupattu, Alphin J and Sivaswamy, Jayanthi and Krishnan, Venkateswaran }, TITLE = {Global Space Modelling Of Biological Processes With Cross-sectional Data}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2023}}

@inproceedings{bib_Evid_2023, AUTHOR = {J, Naren Akash R and Kaushik, Anirudh and Sivaswamy, Jayanthi }, TITLE = {Evidence-Driven Differential Diagnosis of Malignant Melanoma}, BOOKTITLE = {International Conference on Medical Image Computing and Computer Assisted Intervention}. YEAR = {2023}}

We present a modular and multi-level framework for the differential diagnosis of malignant melanoma. Our framework integrates contextual information and evidence at the lesion, patient, and population levels, enabling decision-making at each level. We introduce an anatomic-site aware masked transformer, which effectively models the patient context by considering all lesions in a patient, which can be variable in count, and their site of incidence. Additionally, we incorporate patient metadata via learnable demographics embeddings to capture population statistics. Through extensive experiments, we explore the influence of specific information on the decision-making process and examine the tradeoff in metrics when considering different types of information. Validation results using the SIIM-ISIC 2020 dataset indicate including the lesion context with location and metadata improves specificity by 17.15% and 7.14%, respectively, while enhancing balanced accuracy. The code is available at https://github.com/narenakash/meldd. Keywords: Melanoma Diagnosis · Differential Recognition · Ugly Duckling Context · Patient Demographics · Evidence-Based Medicine.

@inproceedings{bib_Arti_2023, AUTHOR = {Trikha, Anjan and Tyagi, Abhay and Tyagi, Abhishek and Sivaswamy, Jayanthi and Aggarwal, Richa and Soni, Kapil Dev }, TITLE = {Artificial intelligence; Deep learning; Machine learning; Computer vision, Neural networks; Ultrasonography; Regional anesthesia; Musculoskeletal system; Medical Image Analysis}, BOOKTITLE = {Technical Report}. YEAR = {2023}}

Peripheral nerve blocks are crucial to treatment of post-surgical pain and are associated with reduction in perioperative opioid use and hospital stay. Accurate interpretation of sono-anatomy is critical for the success of ultrasound (US) guided peripheral nerve blocks and can be challenging to the new operators. This prospective study enrolled 227 subjects who were systematically scanned for supraclavicular and interscalene brachial plexus in various settings using three different US machines to create a dataset of 227 unique videos. In total, 41,000 video frames were annotated by experienced anaesthesiologists using partial automation with object tracking and active contour algorithms. Four baseline neural network models were trained on the dataset and their performance was evaluated for object detection and segmentation tasks. Generalizability of the best suited model was then tested on the datasets constructed from separate US scanners with and without fine-tuning. The results demonstrate that

@inproceedings{bib_Auto_2023, AUTHOR = {Tyagi, Abhay and Tyagi, Abhishek and Kaur, Manpreet and Sivaswamy, Jayanthi and Aggarwal, Richa and Soni, Kapil Dev and Trikha, Anjan }, TITLE = {Automated Real Time Delineation of Supraclavicular BrachialPlexus in Neck Ultrasonography Videos: A Deep Learning Approach}, BOOKTITLE = {Technical Report}. YEAR = {2023}}

Peripheral nerve blocks are crucial to treatment of post-surgical pain and are associated with reduction in perioperative opioid use and hospital stay. Accurate interpretation of sono-anatomy is critical for the success of ultrasound (US) guided peripheral nerve blocks and can be challenging to the new operators. This prospective study enrolled 227 subjects who were systematically scanned for supraclavicular and interscalene brachial plexus in various settings using three different US machines to create a dataset of 227 unique videos. In total, 41,000 video frames were annotated by experienced anaesthesiologists using partial automation with object tracking and active contour algorithms. Four baseline neural network models were trained on the dataset and their performance was evaluated for object detection and segmentation tasks. Generalizability of the best suited model was then tested on the datasets constructed

@inproceedings{bib_Towa_2023, AUTHOR = {Tyagi, Abhishek and Tyagi, Abhay and Kaur, Manpreet and Sivaswamy, Jayanthi }, TITLE = {Towards Autonomous Robotic Ultrasound Guided Regional Anesthesia using Real Time Needle Localization and Trajectory Extrapolation}, BOOKTITLE = {IEEE International Conference on Robotics and Automation Workshop}. YEAR = {2023}}

A method for real-time detection of nerves together with a needle and its trajectory in ultrasound videos to autonomously guide the needle towards nerve block target. We also publicly release needle annotations for further research.

@inproceedings{bib_A_me_2023, AUTHOR = {Thottupattu, Alphin J and Sivaswamy, Jayanthi }, TITLE = {A metric to compare the anatomy variation betweenimage time series}, BOOKTITLE = {Technical Report}. YEAR = {2023}}

Biological processes like growth, aging, and disease progression are generally studied with follow-up scans taken at different time points, i.e., with image time series (TS) based analysis. Comparison between TS representing a biological process of two individuals/populations is of interest. A metric to quantify the difference between TS is desirable for such a comparison. The two TS represent the evolution of two different subject/population average anatomies through two paths. A method to untangle and quantify the path and inter-subject anatomy(shape) difference between the TS is presented in this paper. The proposed metric is a generalized version of Fréchet distance designed to compare curves. The proposed method is evaluated with simulated and adult and fetal neuro templates. Results show that the metric is able to separate and quantify the path and shape differences between TS. Keywords: Image TS · Time-dependant variation · Time dependant variation.

@inproceedings{bib_Fast_2022, AUTHOR = {Dhere, Abhinav and Vazhayi, Vikas and Sivaswamy, Jayanthi }, TITLE = {Fast detection of sulcal regions for classification of Alzheimer’s disease and Mild Cognitive Impairment}, BOOKTITLE = {International Conference on Signal Processing and Communications}. YEAR = {2022}}

Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) are neurogenerative impairments with similar symptoms and risk factors. Sulcal width and depth are known biomarkers for discriminating between AD and MCI. This paper presents a novel 2D image representation for a brain mesh surface, called a height map. The basic idea behind the height map is to represent the surface as a function of spherical coordinates of the mesh vertices. We present a method to derive a height map from a given neuroimage (MRI) and extract sulcal regions from the height map. We demonstrate the height map’s utility for classifying a given neuroimage into healthy, MCI and AD classes. Two approaches for extracting sulcal regions are explored. The proposed method is computationally light, and obtaining sulcal regions from a brain surface mesh takes about 24 seconds on a standard Intel i5-7200 CPU. The proposed method achieves 76.1% accuracy, and 76.3% F1-score for healthy, MCI, AD classification on a publicly available dataset.

@inproceedings{bib_A_di_2022, AUTHOR = {Thottupattu, Alphin J and Sivaswamy, Jayanthi and Krishnan, Venkateswaran P. }, TITLE = {A diffeomorphic aging model for adult human brain from cross-sectional data}, BOOKTITLE = {Scientific Reports}. YEAR = {2022}}

Normative aging trends of the brain can serve as an important reference in the assessment of neurological structural disorders. Such models are typically developed from longitudinal brain image data—follow-up data of the same subject over diferent time points. In practice, obtaining such longitudinal data is difcult. We propose a method to develop an aging model for a given population, in the absence of longitudinal data, by using images from diferent subjects at diferent time points, the so-called cross-sectional data. We defne an aging model as a difeomorphic deformation on a structural template derived from the data and propose a method that develops topology preserving aging model close to natural aging. The proposed model is successfully validated on two public crosssectional datasets which provide templates constructed from diferent sets of subjects at diferent age points.

@inproceedings{bib_COVI_2022, AUTHOR = {Dhere, Abhinav and Sivaswamy, Jayanthi }, TITLE = {COVID detection from Chest X-Ray Images using multi-scale attention}, BOOKTITLE = {IEEE Journal of Biomedical and Health Informatics}. YEAR = {2022}}

Deep learning based methods have shown great promise in achieving accurate automatic detection of Coronavirus Disease (COVID) - 19 from Chest X-Ray ( CXR) images.However, incorporating explainability in these so- lutions remains relatively less explored. We present a hi- erarchical classification approach for separating normal, non- COVID pneumonia (NCP ) and COVID cases using CXR im- ages. We demonstrate that the proposed method achieves clinically consistent explainations. We achieve this using a novel multi-scale attention architecture called Multi-scale Attention Residual Learning (MARL ) and a new loss function based on conicity for training the proposed architecture. The proposed classification strategy has two stages. The first stage uses a model derived from DenseNet to sepa- rate pneumonia cases from normal cases while the second stage uses the MARL architecture to discriminate between COVID and NCP cases. With a five-fold cross validation the proposed method achieves 93%, 96.28%, and 84.51% accu- racy respectively over three large, public datasets for nor- mal vs. NCP vs. COVID classification. This is competitive to the state-of-the-art methods. We also provide explanations in the form of GradCAM attributions, which are well aligned with expert annotations. The attributions are also seen to clearly indicate that MARL deems the peripheral regions of the lungs to be more important in the case of COVID cases while central regions are seen as more important in NCP cases. This observation matches the criteria described by radiologists in clinical literature, thereby attesting to the utility of the derived explanations.

@inproceedings{bib_A_Me_2022, AUTHOR = {RJ, Naren Akash and Mythri, V and Thottupattu, Alphin J and Sivaswamy, Jayanthi }, TITLE = {A Method to Remove Size Bias in Sub-Cortical Structure Segmentation}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2022}}

Segmentation and analysis of sub-cortical structures is of interest in diagnosing some neurological diseases. Segmentation is a challenging task because of brain tissue ambiguity and data scarcity. Deep learning (DL) solutions are widely used for this purpose by considering the problem as a semantic segmentation of the brain. In general, DL approaches exhibit a bias towards larger structures when training is done on the whole brain. We propose a method to address this problem wherein a pre-training step is used to learn tissue characteristics and a rough ROI extraction step aids focusing on local context. We use a Residual U-net for demonstrating the proposed method. Experiments on the IBSR and MICCAI datasets show that our proposed solution leads to an improvement in segmentation performance in general with medium and small size structures benefiting significantly. The performance with the proposed method is also marginally better than a more complex, state of art sub-cortical structure segmentation method. A strength of the proposed method is that it can also be applied as a modification to any existing segmentation solution.

@inproceedings{bib_INCR_2022, AUTHOR = {Akundi, Prathyusha and Sivaswamy, Jayanthi }, TITLE = {INCREMENTAL LEARNING FOR A FLEXIBLE CAD SYSTEM DESIGN}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2022}}

Deep neural networks suffer from Catastrophic Forgetting (CF) on old tasks when they are trained to learn new tasks sequentially, since the parameters of the model will change to optimize on the new class. The problem of alleviating CF is of interest to Computer aided diagnostic (CAD) sys- tems community to facilitate class incremental learning (IL): learn new classes as and when new data/annotations are made available and old data is no longer accessible. However, IL has not been explored much in CAD development. We pro- pose a novel approach that ensures that a model remembers the causal factor behind the decisions on the old classes, while incrementally learning new classes. We introduce a common auxiliary task during the course of incremental training, whose hidden representations are shared across all the classification heads. Since the hidden representation is no longer task-specific, it leads to a significant reduction in CF. We demonstrate our approach by incrementally learning 5 different tasks on Chest-Xrays and compare the results with the state-of-the-art regularization methods. Our approach performs consistently well in reducing CF in all the tasks with almost zero CF in most of the cases unlike standard regularisation-based approaches.

@inproceedings{bib_A_me_2022, AUTHOR = {Thottupattu, Alphin J and Sivaswamy, Jayanthi and Krishnan, Venkateswaran P }, TITLE = {A method for image registration via broken geodesics}, BOOKTITLE = {International Workshop on Biomedical Image Registration}. YEAR = {2022}}

Anatomical variabilities seen in longitudinal data or inter- subject data is usually described by the underlying deformation, cap- tured by non-rigid registration of these images. Stationary Velocity Field (SVF) based non-rigid registration algorithms are widely used for reg- istration. However, these methods cover only a limited degree of defor- mations. We address this limitation and define an approximate metric space for the manifold of diffeomorphisms G. We propose a method to break down the large deformation into finite set of small sequential defor- mations. This results in a broken geodesic path on G and its length now forms an approximate registration metric. We illustrate the method using a simple, intensity-based, log-demon implementation. Validation results of the proposed method show that it can capture large and complex de- formations while producing qualitatively better results than state-of-the- art methods. The results also demonstrate that the proposed registration metric is a good indicator of the degree of deformation.

@inproceedings{bib_Lung_2021, AUTHOR = {, Aniket Joshi and Sivaswamy, Jayanthi and Joshi, Gopal Datt }, TITLE = {Lung nodule malignancy classification with weakly supervised explanation generation}, BOOKTITLE = {Journal of Medical Imaging}. YEAR = {2021}}

Explainable AI aims to build systems that not only give high performance but also are able to provide insights that drive the decision making. However, deriving this explanation is often dependent on fully annotated (class label and local annotation) data, which are not readily available in the medical domain. Approach: This paper addresses the above-mentioned aspects and presents an innovative approach to classifying a lung nodule in a CT volume as malignant or benign, and generating a morphologically meaningful explanation for the decision in the form of attributes such as nodule margin, sphericity, and spiculation. A deep learning architecture that is trained using a multi-phase training regime is proposed. The nodule class label (benign/malignant) is learned with full supervision and is guided by semantic attributes that are learned in a weakly supervised manner. Results: Results of an extensive evaluation of the proposed system on the LIDC-IDRI dataset show good performance compared with state-of-the-art, fully supervised methods. The proposed model is able to label nodules (after full supervision) with an accuracy of 89.1% and an area under curve of 0.91 and to provide eight attributes scores as an explanation, which is learned from a much smaller training set. The proposed system's potential to be integrated with a sub-optimal nodule detection system was also tested, and our system handled 95% of false positive or random regions in the input well by labeling them as benign, which underscores its robustness. Conclusions: The proposed approach offers a way to address computer-aided diagnosis system design under the constraint of sparse availability of fully annotated images.

@inproceedings{bib_Mani_2021, AUTHOR = {Prathyusha, Akundi and Sivaswamy, Jayanthi }, TITLE = {Manifold Learning to address Catastrophic Forgetting}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2021}}

A major challenge that deep learning systems face is the Catastrophic Forgetting (CF) phenomenon that is observed when finetuning is used to try and adapt a system to a new task or a sequence of datasets with different distributions. CF refers to the significant degradation in performance on the old task/dataset. In this paper, a novel approach is proposed to address CF in computer aided diagnosis (CAD) system design in the medical domain. CAD systems often need to handle a sequence of datasets collected over time from different sites with different imaging parameters/populations. The solution we propose is to move samples from all the datasets closer to a common manifold via a reformer at the front end of a CAD system. The utility of this approach is demonstrated on two common tasks, namely segmentation and classification, using publicly available datasets. Results of extensive experiments show that manifold learning can yield about 74% improvement on an average in the reduction of CF over the baseline fine-tuning process and the state-of-the-art regularization based methods. The results also indicate that a Reformer when used in conjunction with the state-of-the-art regularization methods, has the potential to yield further improvement in CF reduction.

@inproceedings{bib_Sub-_2021, AUTHOR = {Sivaswamy, Jayanthi and Thottupattu, Alphin J and Mythri, V and Mehta, Raghav and Sheelakumari, R and Kesavadas, Chandrasekharan }, TITLE = {Sub-cortical structure segmentation database for young population}, BOOKTITLE = {Technical Report}. YEAR = {2021}}

Segmentation of sub-cortical structures from MRI scans is of interest in many neurological diagnosis. Since this is a laborious task machine learning and specifically deep learning (DL) methods have become explored. The structural complexity of the brain demands a large, high quality segmentation dataset to develop good DL-based solutions for sub-cortical structure segmentation. Towards this, we are releasing a set of 114, 1.5 Tesla, T1 MRI scans with manual delineations for 14 sub-cortical structures. The scans in the dataset were acquired from healthy young (21-30 years) subjects ( 58 male and 56 female) and all the structures are manually delineated by experienced radiology experts. Segmentation experiments have been conducted with this dataset and results demonstrate that accurate results can be obtained with deep-learning methods.

@inproceedings{bib_Glau_2021, AUTHOR = {JYOTHI, G DIVYA and Sivaswamy, Jayanthi }, TITLE = {Glaucoma Assessment from Fundus Images with Fundus to OCT Feature Space Mapping}, BOOKTITLE = {ACM Transactions on Computing for Healthcare}. YEAR = {2021}}

Early detection and treatment of glaucoma is of interest as it is a chronic eye disease leading to an irreversible loss of vision. Existing automated systems rely largely on fundus images for assessment of glaucoma due to their fast acquisition and costeffectiveness. Optical Coherence Tomographic (OCT) images provide vital and unambiguous information about nerve fiber loss and optic cup morphology, which are essential for disease assessment. However, the high cost of OCT is a deterrent for deployment in screening at large scale. In this article, we present a novel CAD solution wherein both OCT and fundus modality images are leveraged to learn a model that can perform a mapping of fundus to OCT feature space. We show how this model can be subsequently used to detect glaucoma given an image from only one modality (fundus). The proposed model has been validated extensively on four public andtwo private datasets. It attained an AUC/Sensitivity value of 0.9429/0.9044 on a diverse set of 568 images, which is superior to the figures obtained by a model that is trained only on fundus features. Cross-validation was also done on nearly 1,600 images drawn from a private (OD-centric) and a public (macula-centric) dataset and the proposed model was found to outperform the state-of-the-art method by 8% (public) to 18% (private). Thus, we conclude that fundus to OCT feature space mapping is an attractive option for glaucoma detection.

@inproceedings{bib_Self_2021, AUTHOR = {Dhere, Abhinav and Sivaswamy, Jayanthi }, TITLE = {Self-Supervised Learning for Segmentation}, BOOKTITLE = {Technical Report}. YEAR = {2021}}

Self-supervised learning is emerging as an effective substitute for transfer learning from large datasets. In this work, we use kidney segmentation to explore this idea. The anatomical asymmetry of kidneys is leveraged to define an effective proxy task for kidney segmentation via self-supervised learning. A siamese convolutional neural network (CNN) is used to classify a given pair of kidney sections from CT volumes as being kidneys of the same or different sides. This knowledge is then transferred for the segmentation of kidneys using another deep CNN using one branch of the siamese CNN as the encoder for the segmentation network. Evaluation results on a publicly available dataset containing computed tomography (CT) scans of the abdominal region shows that a boost in performance and fast convergence can be had relative to a network trained conventionally from scratch. This is notable given that no additional data/expensive annotations or augmentation were used in training.

@inproceedings{bib_A_me_2020, AUTHOR = {Thottupattu, Alphin J and Sivaswamy, Jayanthi and P.Krishnan, Venkateswaran }, TITLE = {A method for large diffeomorphic registration via broken geodesics}, BOOKTITLE = {Technical Report}. YEAR = {2020}}

Anatomical variabilities seen in longitudinal data or inter-subject data is usually described by the underlying deformation, captured by non-rigid registration of these images. Stationary Velocity Field (SVF) based non-rigid registration algorithms are widely used for registration. SVF based methods form a metric-free framework which captures a finite dimensional submanifold of deformations embedded in the infinite dimensional smooth manifold of diffeomorphisms. However, these methods cover only a limited degree of deformations. In this paper, we address this limitation and define an approximate metric space for the manifold of diffeomorphisms . We propose a method to break down the large deformation into finite compositions of small deformations. This results in a broken geodesic path on and its length now forms an approximate registration metric. We illustrate the method using a simple, intensity-based, log-demon implementation. Validation results of the proposed method show that it can capture large and complex deformations while producing qualitatively better results than the state-of-the-art methods. The results also demonstrate that the proposed registration metric is a good indicator of the degree of deformation.

@inproceedings{bib_A_Fa_2020, AUTHOR = {Thottupattu, Alphin J and Sivaswamy, Jayanthi }, TITLE = {A Fast Method For Shape Template Generation}, BOOKTITLE = {International Conference on Image Processing}. YEAR = {2020}}

Disease diagnosis often requires segmentation of structures from a given image followed by shape analysis. Shape analysis entails quantifying the variability in a shape by constructing a template for a given population. We propose an orientation-invariant representation using varifolds for the shape elements in a given shape population and present a novel diffeomorphic Log-demons based template creation pipeline. The proposed method generates a good quality template at a significantly less computation time compared to state of the art method.

@inproceedings{bib_Expl_2020, AUTHOR = {Joshi, Aniket and MISHRA, GAURAV and Sivaswamy, Jayanthi }, TITLE = {Explainable Disease Classification via weakly-supervised segmentation}, BOOKTITLE = {Interpretable and Annotation-Efficient Learning for Medical Image Computing}. YEAR = {2020}}

Deep learning based approaches to Computer Aided Diagnosis (CAD) typically pose the problem as an image classification (Normal or Abnormal) problem. These systems achieve high to very high accuracy in specific disease detection for which they are trained but lack in terms of an explanation for the provided decision/classification result. The activation maps which correspond to decisions do not correlate well with regions of interest for specific diseases. This paper examines this problem and proposes an approach which mimics the clinical practice of looking for an evidence prior to diagnosis. A CAD model is learnt using a mixed set of information: class labels for the entire training set of images plus a rough localisation of suspect regions as an extra input for a smaller subset of training images for guiding the learning. The proposed approach is illustrated with detection of diabetic macular edema (DME) from …

@inproceedings{bib_Imag_2020, AUTHOR = {Himanshu, Desai Alakh and Chauhan, Ruchi and Sivaswamy, Jayanthi }, TITLE = {Image Segmentation Using Hybrid Representations}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2020}}

This work explores a hybrid approach to segmentation as an alternative to a purely data-driven approach. We introduce an end-to-end U-Net based network called DU-Net, which uses additional frequency preserving features, namely the Scattering Coefficients (SC), for medical image segmentation. SC are translation invariant and Lipschitz continuous to deformations which help DU-Net outperform other conventional CNN counterparts on four datasets and two segmentation tasks: Optic Disc and Optic Cup in color fundus images and fetal Head in ultrasound images. The proposed method shows remarkable improvement over the basic U-Net with performance competitive to state-of-the-art methods. The results indicate that it is possible to use a lighter network trained with fewer images (without any augmentation) to attain good segmentation results.

@inproceedings{bib_FPD-_2019, AUTHOR = {V, SUKESH ADIGA and Sivaswamy, Jayanthi }, TITLE = {FPD-M-net: Fingerprint Image Denoising and Inpainting Using M-Net Based Convolutional Neural Networks}, BOOKTITLE = {Technical Report}. YEAR = {2019}}

Fingerprint is a common biometric used for authentication and verification of an individual. These images are degraded when fingers are wet, dirty, dry or wounded and due to the failure of the sensors, etc. The extraction of the fingerprint from a degraded image requires denoising and inpainting. We propose to address these problems with an endto-end trainable Convolutional Neural Network based architecture called FPD-M-net, by posing the fingerprint denoising and inpainting problem as a segmentation (foreground) task. Our architecture is based on the M-net with a change: structure similarity loss function, used for better extraction of the fingerprint from the noisy background. Our method outperforms the baseline method and achieves an overall 3rd rank in the Chalearn LAP Inpainting Competition Track 3 −Fingerprint Denoising and Inpainting, ECCV 2018.

@inproceedings{bib_Cons_2019, AUTHOR = {Sivaswamy, Jayanthi and Thottupattu, Alphin J and KIRANBHAI, MEHTA RAGHAV and Sheelakumari, R and Kesavadas, Chandrasekharan }, TITLE = {Construction of Indian human brain atlas}, BOOKTITLE = {Neurology India}. YEAR = {2019}}

: A brain magnetic resonanace imaging (MRI) atlas plays an important role in many neuroimage analysis tasks as it provides an atlas with a standard coordinate system which is needed for spatial normalization of a brain MRI. Ideally, this atlas should be as near to the average brain of the population being studied as possible.

@inproceedings{bib_Matc_2019, AUTHOR = {V, SUKESH ADIGA and Sivaswamy, Jayanthi }, TITLE = {Matching The Characteristics Of Fundus And Smartphone Camera Images}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2019}}

Fundus imaging with a Smartphone camera (SC) is a cost effective solution for the assessment of retina. However, imaging at high magnification and low light levels, results in loss of details, uneven illumination and noise especially in the peripheral region. We address these problems by matching the characteristics of images from SC to those from a regular fundus camera (FC) with an architecture called ResCycleGAN. It is based on the CycleGAN with two significant changes: A residual connection is introduced to aid learning only the correction required; A structure similarity based loss function is used to improve the clarity of anatomical structures and pathologies. The proposed method can handle variations seen in normal and pathological images, acquired even without mydriasis, which is attractive in screening. The method produces consistently balanced results, outperforms CycleGAN both qualitatively and quantitatively, and has more pleasing results.

@inproceedings{bib_SYNT_2019, AUTHOR = {DESHMUKH, ANURAG A and Sivaswamy, Jayanthi }, TITLE = {SYNTHESIS OF OPTICAL NERVE HEAD REGION OF FUNDUS IMAGE}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2019}}

The Optic Disc (OD) and Optic Cup (OC) boundaries play a critical role in the detection of glaucoma. However, very few annotated datasets are available for both OD and OC that are required for segmentation. Recently, Convolutional Neural Networks have shown significant improvements in segmentation performance. However, the full potential of CNNs is hindered by the lack of a large amount of annotated training images. To address this issue, we explore a method to generate synthetic images which can be used to augment the training data. Given the segmentation masks of OD, OC and vessels from arbitrarily different fundus images, the proposed method employs a combination of B-spline registration and GAN to generate high quality images that ensure that the vessels bend at the edge of the OC in a realistic manner. In contrast, the existing GAN based methods for fundus image synthesis fail to capture the local details and vasculature in the Optic Nerve Head (ONH) region. The utility of the proposed method in training deep networks for the challenging problem of OC segmentation is explored and an improvement in the dice score from 0.85 to 0.902 is seen with the inclusion of the synthetic images in the training set.

@inproceedings{bib_Glau_2019, AUTHOR = {JYOTHI, G DIVYA and Himanshu, Desai Alakh and Sivaswamy, Jayanthi and Vermeer, Koenraad A. }, TITLE = {Glaucoma Assessment from OCT images using Capsule Network}, BOOKTITLE = {International Conference of the IEEE Engineering in Medicine and Biology Society}. YEAR = {2019}}

Optical coherence tomographic (OCT) images provide valuable information for understanding the changes occurring in the retina due to glaucoma, specifically, related to the retinal nerve fiber layer and the optic nerve head. In this paper, we propose a deep learning approach using Capsule network for glaucoma classification, which directly operates on 3D OCT volumes. The network is trained only on labelled volumes and does not attempt any region/structure segmentation. The proposed network was assessed on 50 volumes and found to achieve 0.97 for the area under the ROC curve (AUC). This is considerably higher than the existing approaches which are majorly based on machine learning or rely on segmentation of the required structures from OCT. Our network also outperforms 3D convolutional neural networks despite the fewer network parameters and fewer epochs needed for training.

@inproceedings{bib_Segm_2018, AUTHOR = {G, KARTHIK and Sivaswamy, Jayanthi }, TITLE = {Segmentation of retinal cysts from Optical Coherence Tomography volumes via selective enhancement}, BOOKTITLE = {IEEE Journal of Biomedical and Health Informatics}. YEAR = {2018}}

Automated and accurate segmentation of cystoid structures in Optical Coherence Tomography (OCT) is of interest in the early detection of retinal diseases. It is however a challenging task. We propose a novel method for localizing cysts in 3D OCT volumes. The proposed work is biologically inspired and based on selective enhancement of the cysts, by inducing motion to a given OCT slice. A Convolutional Neural Network (CNN) is designed to learn a mapping function that combines the result of multiple such motions to produce a probability map for cyst locations in a given slice. The final segmentation of cysts is obtained via simple clustering of the detected cyst locations. The proposed method is evaluated on two public datasets and one private dataset. The public datasets include the one released for the OPTIMA Cyst segmentation challenge (OCSC) in MICCAI 2015 and the DME dataset. After training on the OCSC train set, the method achieves a mean Dice Coefficient (DC) of 0.71 on the OCSC test set. The robustness of the algorithm was examined by cross validation on the DME and AEI (private) datasets and a mean DC values obtained were 0.69 and 0.79, respectively. Overall, the proposed system outperforms all benchmarks. These results underscore the strengths of the proposed method in handling variations in both data acquisition protocols and scanners.

@inproceedings{bib_Topo_2018, AUTHOR = {Mansoor, Tarannum and Sivaswamy, Jayanthi and JAHNAVI, GAMALAPATI SAI and Balakrishna, Nagalla }, TITLE = {Topography and correlation of radial peripapillary capillary density network with retinal nerve fibre layer thickness}, BOOKTITLE = {International ophthalmology}. YEAR = {2018}}

Purpose To analyse the expansion of radial peripapillary capillary (RPC) network with optical coherence tomography angiography (OCT-A) in normal human eyes and correlate RPC density with retinal nerve fibre layer thickness (RNFLT) at various distances from the optic nerve head (ONH) edge. Methods Fifty eyes of 50 healthy subjects underwent imaging with RTVue XR-100 Avanti OCT. OCT-A scans of Angio disc (6 9 6 mm) and Angio retina (8 9 8 mm) were combined to create a wide-field montage image of the RPC network. RPC density and RNFLT was calculated at different circle diameter around the ONH, and their correlation was measured. Results In the arcuate region, RPC was detected as far as 8.5 mm from the ONH edge, but not around the perifoveal area within 0.025 ± 0.01 mm2.The mean RPC density (0.1556 ± 0.015) and RNFLT (245.96 ± 5.79) were highest at 1.5 mm from ONH margin, and there was a trend in its decline, in a distance-dependent manner, with the least density at 8.5 mm (all P\0.0001). Highest RPC density was noted in the arcuate fibre region at all the distances. Overall mean RPC density correlated significantly (P\0.0001) with the overall mean RNFLT. Conclusions Wide-field montage OCT-A angiograms can visualize expansion of the RPC network, which is useful in obtaining information about various retinal disorders. The results obtained support the hypothesis that the RPC network could be responsible for RNFL nourishment.

@inproceedings{bib_Cons_2018, AUTHOR = {CHAKRAVARTY, ARUNAVA and JYOTHI, G DIVYA and Sivaswamy, Jayanthi }, TITLE = {Construction of a Retinal Atlas for Macular OCT Volumes}, BOOKTITLE = {International Conference Image Analysis and Recognition}. YEAR = {2018}}

Optical Coherence Tomography (OCT) plays an important role in the analysis of retinal diseases such as Age-Related Macular Degeneration (AMD). In this paper, we present a method to construct a normative atlas for macula centric OCT volumes with a mean intensity template (MT) and probabilistic maps for the seven intra-retinal tissue layers. We also propose an AMD classification scheme where the deviation of the local similarity of a test volume with respect to the MT is used to characterize AMD. The probabilistic atlas was used for layer segmentation where we achieved an average dice score of 0.82 across the eight layer boundaries. On the AMD detection task, the classification accuracy and Area under the Receiver Operating Characteristic curve were 98% and 0.996 respectively, on 170 OCT test volumes.

@inproceedings{bib_Reti_2018, AUTHOR = {PUJITHA, A K and Sivaswamy, Jayanthi }, TITLE = {Retinal Image Synthesis for CAD development}, BOOKTITLE = {International Conference Image Analysis and Recognition}. YEAR = {2018}}

Automatic disease detection and classification have been attracting much interest. High performance is critical in adoption of such systems, which generally rely on training with a wide variety of annotated data. Availability of such varied annotated data in medical imaging is very scarce. Synthetic data generation is a promising solution to address this problem. We propose a novel method, based on generative adversarial networks (GAN), to generate images with lesions such that the overall severity level can be controlled. We demonstrate the reliability of the generated synthetic images independently as well as by training a computer aided diagnosis (CAD) system with the generated data. We showcase this approach for heamorrhage detection in retinal images with 4 levels of severity. Quantitative assessment results show that the generated synthetic images are very close to the real data. Haemorrhage detection was found to improve with inclusion of synthetic data in the training set with improvements in sensitivity ranging from 20% to 27% over training with just expert marked data.

@inproceedings{bib_RACE_2018, AUTHOR = {CHAKRAVARTY, ARUNAVA and Sivaswamy, Jayanthi }, TITLE = {RACE-Net: A Recurrent Neural Network for Biomedical Image Segmentation}, BOOKTITLE = {IEEE Journal of Biomedical and Health Informatics}. YEAR = {2018}}

The level set based deformable models (LDM) are commonly used for medical image segmentation. However, they rely on a handcrafted curve evolution velocity that needs to be adapted for each segmentation task. The Convolutional Neural Networks (CNN) address this issue by learning robust features in a supervised end-to-end manner. However, CNNs employ millions of network parameters, which require a large amount of data during training to prevent over-fitting and increases the memory requirement and computation time during testing. Moreover, since CNNs pose segmentation as a region-based pixel labeling, they cannot explicitly model the high-level dependencies between the points on the object boundary to preserve its overall shape, smoothness or the regional homogeneity within and outside the boundary. We present a Recurrent Neural Network based solution called the RACE-net to address the above issues. RACE-net models a generalized LDM evolving under a constant and mean curvature velocity. At each time-step, the curve evolution velocities are approximated using a feed-forward architecture inspired by the multiscale image pyramid. RACE-net allows the curve evolution velocities to be learned in an end-to-end manner while minimizing the number of network parameters, computation time, and memory requirements. The RACEnet was validated on three different segmentation tasks: optic disc and cup in color fundus images, cell nuclei in histopathological images, and the left atrium in cardiac MRI volumes. Assessment on public datasets was seen to yield high Dice values between 0.87 and 0.97, which illustrates its utility as a generic, off-the-shelf architecture for biomedical segmentation.

@inproceedings{bib_To_L_2018, AUTHOR = {MAJUMDAR, AABHAS and KIRANBHAI, MEHTA RAGHAV and Sivaswamy, Jayanthi }, TITLE = {To Learn or Not to Learn Features for Deformable Registration ?}, BOOKTITLE = {International Conference on Medical Imaging Computing & Computer Assisted Intervention Workshop}. YEAR = {2018}}

Feature-based registration has been popular with a variety of features ranging from voxel intensity to Self-Similarity Context (SSC). In this paper, we examine the question of how features learnt using various Deep Learning (DL) frameworks can be used for deformable registration and whether this feature learning is necessary or not. We investigate the use of features learned by different DL methods in the current state-ofthe-art discrete registration framework and analyze its performance on 2 publicly available datasets. We draw insights about the type of DL framework useful for feature learning. We consider the impact, if any, of the complexity of different DL models and brain parcellation methods on the performance of discrete registration. Our results indicate that the registration performance with DL features and SSC are comparable and stable across datasets whereas this does not hold for low level features. This shows that when handcrafted features are designed based on good insights into the problem at hand, they perform better or are comparable to features learnt using deep learning framework.

@inproceedings{bib_A_Su_2018, AUTHOR = {CHAKRAVARTY, ARUNAVA and Sivaswamy, Jayanthi }, TITLE = {A Supervised Joint Multi-layer Segmentation Framework for Retinal Optical Coherence Tomography Images using Conditional Random Field}, BOOKTITLE = {Computer Methods and Programs in Biomedicine}. YEAR = {2018}}

Background and Objective: Accurate segmentation of the intra-retinal tissue layers in Optical Coherence Tomography (OCT) images plays an important role in the diagnosis and treatment of ocular diseases such as Age-Related Macular Degeneration (AMD) and Diabetic Macular Edema (DME). The existing energy minimization based methods employ multiple, manually handcrafted cost terms and often fail in the presence of pathologies. In this work, we eliminate the need to handcraft the energy by learning it from training images in an end-to-end manner. Our method can be easily adapted to pathologies by re-training it on an appropriate dataset. Methods: We propose a Conditional Random Field (CRF) framework for the joint multi-layer segmentation of OCT B-scans. The appearance of each retinal layer and boundary is modeled by two convolutional filter banks and the shape priors are modeled using Gaussian distributions. The total CRF energy is linearly parameterized to allow a joint, end-to-end training by employing the Structured Support Vector Machine.

@inproceedings{bib_Opti_2018, AUTHOR = {Mansoori, Tarannum and JAHNAVI, GAMALAPATI SAI and Sivaswamy, Jayanthi and Balakrishna, Nagalla }, TITLE = {Optical coherence tomography angiography measured capillary density in the normal and glaucoma eyes}, BOOKTITLE = {Saudi journal of ophthalmology}. YEAR = {2018}}

Purpose: To compare the diagnostic ability of optical coherence tomography angiography (OCT-A) derived radial peripapillary capillary (RPC) measured capillary density (CD) and inside the optic nerve head (ONH) CD measurements to differentiate between the normal and primary open angle glaucoma (POAG) eyes. Methods: AngioVue disc OCT-A images were obtained and assessed in 83 eyes of POAG patients and 74 age matched healthy eyes. RPC CD was quantitatively measured in the peripapillary area within 3.45 mm circle diameter around the ONH and inside the ONH in 8 equally divided sectors, using Bar – Selective Combination of Shifted Filter Responses method after the suppressing large vessels. Area under receiver operating characteristic (AUROC) curve was used to assess the diagnostic accuracy of the two scanning regions of CD to differentiate between the normal and POAG eyes. Results: The mean peripapillary RPC density (0.12 ± 0.03) and mean ONH CD (0.09 ± 0.03) were significantly lower in POAG eyes when compared to the normal eyes (RPC CD: 0.17 ± 0.05, p < 0.0001 and ONH CD 0.11 ± 0.02, p = 0.01 respectively). The POAG patients showed 29% reduction in the RPC CD and 19% reduction in the ONH CD when compared to the normal eyes. The AUROC for discriminating between healthy and glaucomatous eyes was 0.784 for mean RPC CD and 0.743 for the mean ONH CD. Conclusions: Diagnostic ability of OCT-A derived peripapillary CD and ONH CD was moderate for differentiating between the normal and glaucomatous eyes. Diagnostic ability of even the best peripapillary average and inferotemporal sector for RPC CD and average and superonasal sector for the ONH CD was moderate.

@inproceedings{bib_Scan_2018, AUTHOR = {BHARATKUMAR, RANGREJ SAMRUDHDHI and Sivaswamy, Jayanthi and Srivastava, Priyanka }, TITLE = {Scan, dwell, decide: Strategies for detecting abnormalities in diabetic retinopathy}, BOOKTITLE = {Plos One}. YEAR = {2018}}

Diabetic retinopathy (DR) is a disease which is widely diagnosed using (colour fundus) images. Efficiency and accuracy are critical in diagnosing DR as lack of timely intervention can lead to irreversible visual impairment. In this paper, we examine strategies for scrutinizing images which affect diagnostic performance of medical practitioners via an eye-tracking study. A total of 56 subjects with 0 to 18 years of experience participated in the study. Every subject was asked to detect DR from 40 images. The findings indicate that practitioners use mainly two types of strategies characterized by either higher dwell duration or longer track length. The main findings of the study are that higher dwell-based strategy led to higher average accuracy (> 85%) in diagnosis, irrespective of the expertise of practitioner; whereas, the average obtained accuracy with a long-track length-based strategy was dependent on the expertise of the practitioner. In the second part of the paper, we use the experimental findings to recommend a scanning strategy for fast and accurate diagnosis of DR that can be potentially used by image readers. This is derived by combining the eyetracking gaze maps of medical experts in a novel manner based on a set of rules. This strategy requires scrutiny of images in a manner which is consistent with spatial preferences found in human perception in general and in the domain of fundus images in particular. The Levenshtein distance-based assessment of gaze patterns also establish the effectiveness of the derived scanning pattern and is thus recommended for image readers.

@inproceedings{bib_Solu_2018, AUTHOR = {PUJITHA, A K and Sivaswamy, Jayanthi }, TITLE = {Solution to overcome the sparsity issue of annotated data in medical domain}, BOOKTITLE = {CAAI Transactions on Intelligence Technology}. YEAR = {2018}}

Annotations are critical for machine learning and developing computer aided diagnosis (CAD) algorithms. Good performance of CAD is critical to their adoption, which generally rely on training with a wide variety of annotated data. However, a vast amount of medical data is either unlabeled or annotated only at the image-level. This poses a problem for exploring data driven approaches like deep learning for CAD. In this paper, we propose a novel crowdsourcing and synthetic image generation for training deep neural net-based lesion detection. The noisy nature of crowdsourced annotations is overcome by assigning a reliability factor for crowd subjects based on their performance and requiring region of interest markings from the crowd. A generative adversarial network-based solution is proposed to generate synthetic images with lesions to control the overall severity level of the disease. We demonstrate the reliability of the crowdsourced annotations and synthetic images by presenting a solution for training the deep neural network (DNN) with data drawn from a heterogeneous mixture of annotations. Experimental results obtained for hard exudate detection from retinal images show that training with refined crowdsourced data/synthetic images is effective as detection performance in terms of sensitivity improves by 25%/27% over training with just expert-markings.

@inproceedings{bib_Shar_2018, AUTHOR = {V, SUKESH ADIGA and Sivaswamy, Jayanthi }, TITLE = {Shared Encoder based Denoising of Optical Coherence Tomography Images}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2018}}

Optical coherence tomography (OCT) images are corrupted by speckle noise due to the underlying coherence-based strategy. Speckle suppression/removal in OCT images plays a significant role in both manual and automatic detection of diseases, especially in early clinical diagnosis. In this paper, we propose a new method for denoising OCT images based on Convolutional Neural Network by learning common features from unpaired noisy and clean OCT images in an unsupervised, end-to-end manner. The proposed method consists of a combination of two autoencoders with shared encoder layers, which we call as Shared Encoder (SE) architecture. The SE is trained to reconstruct noisy and clean OCT images with respective autoencoders. The denoised OCT image is obtained using a cross-model prediction. The proposed method can be used for denoising OCT images with or without pathology from any scanner. The SE architecture was assessed using public datasets and found to perform better than baseline methods exhibiting a good balance of retaining anatomical integrity and speckle reduction.

@inproceedings{bib_Brai_2017, AUTHOR = {KIRANBHAI, MEHTA RAGHAV and MAJUMDAR, AABHAS and Sivaswamy, Jayanthi }, TITLE = {BrainSegNet: a convolutional neural network architecture for automated segmentation of human brain structures}, BOOKTITLE = {Journal of Medical Imaging}. YEAR = {2017}}

Automated segmentation of cortical and noncortical human brain structures has been hither to approached using nonrigid registration followed by label fusion. We propose an alternative approach for this using a convolutional neural network (CNN) which classifies a voxel into one of many structures. Four different kinds of two-dimensional and three-dimensional intensity patches are extracted for each voxel, providing local and global (context) information to the CNN. The proposed approach is evaluated on five different publicly available datasets which differ in the number of labels per volume. The obtained mean Dice coefficient varied according to the number of labels, for example, it is0.8440.031and0.7430.019for datasets with the least(32) and the most (134) number of labels, respectively. These figures are marginally better or on par with those obtained with the current state-of-the-art methods on nearly all datasets, at a reduced computational time. The consistently good performance of the proposed method across datasets and no requirement for registration make it attractive for many applications where reduced computational time is necessary.

@inproceedings{bib_A_VE_2017, AUTHOR = {Srinidhi, Chetan L and RATH, PRIYADARSHI and Sivaswamy, Jayanthi }, TITLE = {A VESSEL KEYPOINT DETECTOR FOR JUNCTION CLASSIFICATION}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2017}}

Retinal vessel keypoint detection and classification is a fundamental step in tracking the physiological changes that occur in the retina which is linked to various retinal and systemic diseases. In this paper, we propose a novel Vessel Keypoint Detector (VKD) which is derived from the projection of log-polar transformed binary patches around vessel points.VKD is used to design a two stage solution for junction detection and classification. In the first stage, the keypoints detected using VKD are refined using curvature orientation information to extract candidate junctions. True junctions from these candidates are identified in a supervised manner using a Random Forest classifier. In the next stage, a novel combination of local orientation and shape based features is extracted from the junction points and classified using asecond Random Forest classifier. Evaluation results on five datasets show that the designed system is robust to changes in resolution and other variations across datasets, with average values of accuracy/sensitivity/specificity for junction detection being 0.78/0.79/0.75 and for junction classification being 0.87/0.85/0.88. Our system outperforms the state of the art method [1] by at least 11%, on the DRIVE and IOSTAR datasets. These results demonstrate the effectiveness of VKDfor vessel analysis.

@inproceedings{bib_DETE_2017, AUTHOR = {PUJITHA, A K and JAHNAVI, GAMALAPATI SAI and Sivaswamy, Jayanthi }, TITLE = {DETECTION OF NEOVASCULARIZATION IN RETINAL IMAGES USING SEMI-SUPERVISED LEARNING}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2017}}

Retinal Neovascularization (NV) is a critical stage of Diabetic Retinopathy (DR) and its detection is important to prevent blindness. Existing fully supervised frameworks typically take a patch-based approach and report good results only on limited number of images due to sparsity of annotated data.We propose a patch-based semi-supervised framework which paves the way for including unlabeled data in training. In this framework, NV patches are modeled using oriented energy and vesselness based features. These features are fused within a co-training based semi-supervised framework by using neighborhood information in feature space. Rule-based criteria on patch-level neovascularity scores is used to derive the final image-level decision. The proposed approach was evaluated on 1 private and 3 public datasets, both at patch and image level detection on nearly 200,000 patches. An AUCof 0.985 with sensitivity of 96.2% at specificity of 92.6% was obtained for abnormality detection at patch-level, while at the image-level, a sensitivity of 96.76% at a specificity of 91.85%were obtained. The achieved performance on a large number of patches indicates the robustness of our approach.

@inproceedings{bib_M-NE_2017, AUTHOR = {KIRANBHAI, MEHTA RAGHAV and Sivaswamy, Jayanthi }, TITLE = {M-NET: A CONVOLUTIONAL NEURAL NETWORK FOR DEEP BRAIN STRUCTURESEGMENTATION}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2017}}

In this paper, we propose an end-to-end trainable Convolutional Neural Network (CNN) architecture called the M-net,for segmenting deep (human) brain structures from Magnetic Resonance Images (MRI). A novel scheme is used to learn to combine and represent 3D context information of a given slice in a 2D slice. Consequently, the M-netutilizes only 2D convolution though it operates on 3D data, which makes M-net memory efficient. The segmentation method is evaluated on two publicly available datasets and is compared against publicly available model based segmentation algorithms as well as other classification based algorithms such as Random For-rest and 2D CNN based approaches. Experiment results show that the M-net out performs all these methods in terms of dice coefficient and is at least 3 times faster than other methods in segmenting a new volume which is attractive for clinical use

@inproceedings{bib_Assi_2017, AUTHOR = {BHARATKUMAR, RANGREJ SAMRUDHDHI and Sivaswamy, Jayanthi }, TITLE = {Assistive lesion-emphasis system: an assistive system for fundus image readers}, BOOKTITLE = {Journal of Medical Imaging}. YEAR = {2017}}

Computer-assisted diagnostic (CAD) tools are of interest as they enable efficient decision-making in clinics and the screening of diseases. The traditional approach to CAD algorithm design focuses on the automated detection of abnormalities independent of the end-user, who can be an image reader or an expert.We propose a reader-centric system design wherein a reader’s attention is drawn to abnormal regions in a least-obtrusive yet effective manner, using saliency-based emphasis of abnormalities and without altering the appearance of the background tissues. We present an assistive lesion-emphasis system (ALES) based on the above idea, for fundus image-based diabetic retinopathy diagnosis. Lesion-saliency is learnt using a convolutional neural network (CNN), inspired by the saliency model of Itti and Koch. The CNN is used to fine-tune standard low-level filters and learn high-level filters for deriving a lesion-saliency map, which is then used to perform lesion-emphasis via a spatially variant version of gamma correction. The proposed system has been evaluated on public datasets and bench marked against other saliency models. It was found to outperform other saliency models by 6% to 30% and boost the contrast-to-noise ratio of lesions by more than 30%. Results of a perceptual study also underscore the effectiveness and, hence, the potential of ALES as an assistive tool for readers

@inproceedings{bib_End-_2017, AUTHOR = {CHAKRAVARTY, ARUNAVA and Sivaswamy, Jayanthi }, TITLE = {End-to-end learning of a Conditional Random Field for Intra-retinal Layer Segmentation in Optical Coherence Tomography}, BOOKTITLE = {Conference on Medical Image Understanding and Analysis}. YEAR = {2017}}

Intra-retinal layer segmentation of Optical Coherence Tomography images is critical in the assessment of ocular diseases. Existing Energy minimization based methods employ handcrafted cost terms to define their energy and are not robust to the presence of abnormalities.We propose a novel, Linearly Parameterized, Conditional Random Field(LP-CRF) model whose energy is learnt from a set of training images in an end-to-end manner. The proposed LP-CRF comprises two convolution filter banks to capture the appearance of each tissue region and boundary, the relative weights of the shape priors and an additional term based on the appearance similarity of the adjacent boundary points. All the energy terms are jointly learnt using the Structured Support Vector Machine. The proposed method segments all retinal boundaries in a single step. Our method was evaluated on 107 Normal and 220 AMDB-scan images and found to outperform three publicly available OCT segmentation software. The average unsigned boundary localization error is 1.52±0.29 pixels for segmentation of 8 boundaries on the Normal data set and 1.9±0.65 pixels for 3 boundaries on the combined AMD and Normal data set establishing the robustness of the proposed method.

@inproceedings{bib_Join_2017, AUTHOR = {CHAKRAVARTY, ARUNAVA and Sivaswamy, Jayanthi }, TITLE = {Joint optic disc and cup boundary extraction from monocular fundus images}, BOOKTITLE = {Computer Methods and Programs in Biomedicine}. YEAR = {2017}}

Background and objective: Accurate segmentation of optic disc and cup from monocular color fundus images plays a significant role in the screening and diagnosis of glaucoma. Though optic cup is characterized by the drop in depth from the disc boundary, most existing methods segment the two structures separately and rely only on color and vessel kink based cues due to the lack of explicit depth information in color fundus images. Methods: We propose a novel boundary-based Conditional Random Field formulation that extracts both the optic disc and cup boundaries in a single optimization step. In addition to the color gradients, the proposed method explicitly models the depth which is estimated from the fundus image itself using a coupled, sparse dictionary trained on a set of image-depth map (derived from Optical Coherence Tomography) pairs. Results: The estimated depth achieved a correlation coefficient of 0.80 with respect to the ground truth. The proposed segmentation method outperformed several state-of-the-art methods on five public datasets. The average dice coefficient was in the range of 0.87–0.97 for disc segmentation across three datasets and 0.83 for cup segmentation on the DRISHTI-GS1 test set. The method achieved a good glaucoma classification performance with an average AUC of 0.85 for five fold cross-validation on RIM-ONE v2.

@inproceedings{bib_A_de_2017, AUTHOR = {G, KARTHIK and BHARATKUMAR, RANGREJ SAMRUDHDHI and Sivaswamy, Jayanthi }, TITLE = {A deep learning framework for segmentation of retinal layers from OCT images}, BOOKTITLE = {Asian Conference on Pattern Recognition}. YEAR = {2017}}

Segmentation of retinal layers from Optical Coherence Tomography (OCT) volumes is a fundamental problem for any computer aided diagnostic algorithm development.This requires preprocessing steps such as denoising, region of interest extraction, flattening and edge detection all of which involve separate parameter tuning. In this paper,we explore deep learning techniques to automate all these steps and handle the presence/absence of pathologies. A model is proposed consisting of a combination of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). The CNN is used to extract layers of interest image and extract the edges, while the LSTM is used to trace the layer boundary. This model is trained on a mixture of normal and AMD cases using minimal data. Validation results on three public datasets show that the pixel-wise mean absolute error obtained with our system is1.30±0.48whichis lower than the inter-marker error of1.79±0.76. Our model’s performance is also on par with the existing methods

@inproceedings{bib_Crow_2017, AUTHOR = {PUJITHA, A K and Sivaswamy, Jayanthi }, TITLE = {Crowdsourced annotations as an additional form of data augmentation for CAD development}, BOOKTITLE = {Asian Conference on Pattern Recognition}. YEAR = {2017}}

Annotations are critical for machine learning and developing Computer Aided Detection (CAD) algorithms. However, a majority of medical data is either unlabeled or annotated only at the image-level. This poses a problem specifically for employing deep learning based approaches for CAD development as they require large amounts of annotated data for training. Data augmentation is a popular solution to address this need. We explore crowdsourcing as a solution for training a deep neural network (DNN) for lesion detection. Our solution employs a strategy to overcome the noisy nature of crowdsourced annotations by i) assigning a reliability factor for each subject of the crowd based on their performance (at global and local levels) and experience and ii) requiring region of interest(ROI) markings rather than pixel-level markings from the crowd. We present a solution for training the DNN with data drawn from a heterogeneous mixture of annotations, namely,very limited number of pixel-level markings by experts and crowdsourced ROI markings. Experimental results obtained for hard exudate detection from color fundus images show that training with processed/refined crowdsourced data is effective as detection performance improves by 25% over training with just expert-markings and by 11% over training with annotation derived using majority voting among the crowd

@inproceedings{bib_A_Ge_2017, AUTHOR = {YADAV, SHIVIN and G, KARTHIK and Sivaswamy, Jayanthi }, TITLE = {A Generalized Motion Pattern and FCN based approach for retinal fluid detection and segmentation}, BOOKTITLE = {International Conference on Medical Imaging Computing & Computer Assisted Intervention Workshop}. YEAR = {2017}}

SD-OCT is a non invasive cross sectional imaging modality useful for diagnosis of macular defects. Efficient detection and segmentation of the abnormalities seen as biomarkers in OCT can help in analyzing the progression of the disease and advising effective treatment for the associated disease. In this work we proposes a fully automated Generalized Motion Pattern(GMP) based segmentation method using a cascade of fully convolutional networks for detection and segmentation of retinal fluids from SD-OCT scans. General methods for segmentation depend on domain knowledge based feature extraction , whereas we pro-pose a method based on Generalized Motion Pattern (GMP) [1] which is derived by inducing motion to an image to suppress the background.The proposed method is parallelizable and handles inter-scanner variability efficiently. Our method achieves a mean Dice score of 0.61,0.70 and0.73 during segmentation and a mean AUC of 0.85,0.84 and 0.87 during detection for the 3 types of fluids IRF,SRF and PDE respectively

@inproceedings{bib_Glau_2016, AUTHOR = {CHAKRAVARTY, ARUNAVA and Sivaswamy, Jayanthi }, TITLE = {Glaucoma Classification with a Fusion of Segmentation and Image-based Features}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2016}}

Automated classification of glaucoma is of interest in early detection and treatment. Existing methods employ featureswhich are either image-based or derived from Optic Disc(OD) and Cup (OC) segmentation. While the latter suffers from segmentation inaccuracies, the image-based features tend to overf it in limited availability of training data. We propose a solution to overcome these issues and present a classification framework that fuses both type of features within a co-training based semi-supervised setting to over-come the paucity of labelled data. A novel set of features is proposed to represent the segmented OD-OC regions. Additionally, features based on Texture of projections and color Bag of Visual Words have been designed to be sensitive to the sector-wise deformations in OD. The proposed method was trained on 386 labelled and 717 unlabelled images. It outperformed existing methods with an accuracy and AUC of73.28%,0.79on a private test set of 696 unseen images and76.77%,0.78when cross-tested on DRISHTI-GS1 dataset

@inproceedings{bib_Auto_2016, AUTHOR = {G, KARTHIK and Sivaswamy, Jayanthi and Mansoori, Tarannum }, TITLE = {Automatic glaucoma assessment from angio-OCT images}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2016}}

A variety of imaging modalities have been used for developing diagnostic aids for glaucoma assessment. Structural imaging modalities such as colour fundus imaging and optical coherence tomography (OCT) have been investigated for automatically estimating key parameters for glaucoma assessment such as cup to disc diameter ratio and thickness of there tinal nerve fibre layer (RNFL). OCT-based angiography or OCTA is a new modality which provides structural and angiographic information about the retinal layers. We present a method for glaucoma detection using OCTA images. Specifically, the capillary density at various layers and thickness of RNFL are estimated and used to classify a given OCTA volume as glaucamatous or not. RNFL thickness is estimated using polynomial fitting to intensity profiles of OCT slices. The capillary density is estimated from the angio flow images using morphological processing to extract the optic nerve head(ONH) and vessel detection in a region of interest define daround the ONH. A system trained on these two features was evaluated on a dataset of 67 eyes (49 normal and 18 glaucomatous) and found to have a sensitivity of 94.44%and specificity of 91.67%. This demonstrates the potential of the new modality for glaucoma assessment.

@inproceedings{bib_A_Hy_2016, AUTHOR = {KIRANBHAI, MEHTA RAGHAV and Sivaswamy, Jayanthi }, TITLE = {A Hybrid Approach to Tissue-based Intensity Standardization of Brain MRI Images}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2016}}

The variations in the intensity scale in Magnetic Resonance Images pose a problem for many tasks and Intensity Standardization (IS) aims to solve this problem. Existing methods generally use landmark values of the image histogram and match it to a standard scale. The landmarks are often chosen to be percentiles from different segmented tissues. We propose a method for IS in which tissue information (via segmentation) is needed during training but not during testing by using landmark propagation. A KL divergence-based technique is employed for identifying volumes from the training set, which are similar to a given non-standardized testing volume. The landmarks from the similar volumes are then propagated to the given test volume. Evaluation of the proposed method on 24 MRI volumes from 3 different scanners shows that the IS results are better than L4 and at par with a method which uses prior segmentation, to get percentile-based land-marks. The proposed method aids speeding up and expanding the scope of IS to volumes with no tissue information

@inproceedings{bib_CARD_2016, AUTHOR = {VEERAVASARAPU, V S RAO and Sivaswamy, Jayanthi and Karani, Vishanji }, TITLE = {CARDIAC MOTION ANALYSIS BY TEMPORAL FLOW GRAPHS}, BOOKTITLE = {Technical Report}. YEAR = {2016}}

Cardiac motion analysis from B-mode ultrasound sequence is a key task in assessing the health of the heart. The paper proposes a new methodology for cardiac motion analysis based on the temporal behaviour of points of interest on the myocardium. We define a new signal called the Temporal Flow Graph(TFG) which depicts the movement of a point of interest over time. It is a graphical representation derived from a flow field and describes the temporal evolution of a point. We prove that TFG for an object undergoing periodic motion is also periodic. This principle can be utilized to derive both global and local information from a given sequence. We demonstrate this for detecting motion irregularities at the sequence, as well as regional levels on real and synthetic data. A coarse localisation of anatomical landmarks such as centres of left/right cavities and valve points is also demonstrated using TFGs.

@inproceedings{bib_Auto_2016, AUTHOR = {Chakrabarty, Lipi and JOSHI, GOPAL DATT and CHAKRAVARTY, ARUNAVA and Raman, Ganesh V. and Krishnadas, S.R. and Sivaswamy, Jayanthi }, TITLE = {Automated Detection of Glaucoma From Topographic Features of the Optic Nerve Head in Color Fundus Photographs}, BOOKTITLE = {Journal of Glaucoma}. YEAR = {2016}}

Color fundus photographs of 2252 eyes from1126 subjects were collected from 2 centers: Aravind Eye Hospital,Madurai and Coimbatore, India. The images of 1926 eyes (963 subjects) were used to train an automated image analysis-based system,which was developed to provide a decision on a given fundus image.A total of 163 subjects were clinically examined by 2 ophthalmologists independently and their diagnostic decisions were recorded. The consensus decision was defined to be the clinical reference (gold standard). Fundus images of eyes with disagreement in diagnosis were excluded from the study. The fundus images of the remaining 314eyes (157 subjects) were presented to 4 graders and their diagnostic decisions on the same were collected. The performance of the system was evaluated on the 314 images, using the reference standard. The sensitivity and specificity of the system and 4 independent graders were determined against the clinical reference standard

@inproceedings{bib_Nume_2016, AUTHOR = {ABBAS, SYED TABISH and Krishnan, Venkateswaran P. and Sivaswamy, Jayanthi }, TITLE = {Numerical Inversion of Circular arc Radon Transform}, BOOKTITLE = {IEEE Transactions on Computational Imaging}. YEAR = {2016}}

Circular arc Radon (CAR) transforms associate to a function, its integrals along arcs of circles. The inversion of such transforms is of natural interest in several imaging modalities such as thermoacoustic and photoacoustic tomography, ultrasound, and intravascular imaging. Unlike the full circle counterpart—the circular Radon transform—which has attracted significant attention in recent years, the CAR transforms are scarcely studied objects.In this paper, we present an efficient algorithm for the numerical inversion of the CAR transform with fixed angular span, for the cases in which the support of the function lies entirely inside or outside the acquisition circle. The numerical algorithm is noniterative and is very efficient as the entire scheme, once processed,can be stored and used repeatedly for reconstruction of images. A modified numerical inversion algorithm is also presented to reduce the artifacts in the reconstructed image which are induced due to the limited angular span.

@inproceedings{bib_Doma_2016, AUTHOR = {G, KARTHIK and Sivaswamy, Jayanthi }, TITLE = {Domain knowledge assisted cyst segmentation in OCT retinal images}, BOOKTITLE = {Technical Report}. YEAR = {2016}}

3D imaging modalities are becoming increasingly popular and relevant in retinal imaging owing to their effectiveness in highlighting structures in sub-retinal layers. OCT is one such modality which has great importance in the context of analysis of cystoid structures in subretinal layers. Signal to noise ratio(SNR) of the images obtained from OCT is less and hence automated and accurate determination of cystoid structures from OCT is a challenging task. We propose an auto-mated method for detecting/segmenting cysts in 3D OCT volumes. The proposed method is biologically inspired and fast aided by the domain-knowledge about the cystoid structures. An ensemble learning method-Random forests is learnt for classification of detected region into cyst region. The method achieves detection and segmentation in a unified set-ting. We believe the proposed approach with further improvements can be a promising starting point for more robust approach. This methodis validated against the training set achieves a mean dice coefficient of0.3893 with a standard deviation of 0.2987

@inproceedings{bib_A_bi_2016, AUTHOR = {BHARATKUMAR, RANGREJ SAMRUDHDHI and Sivaswamy, Jayanthi }, TITLE = {A biologically inspired saliency model for color fundusimages}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2016}}

Saliency computation is widely studied in computer vision but not in medical imaging. Existing computational saliency models have been developed for general (natural) images and hence may not be suitable for medical images. This is due to the variety of imaging modalities and the requirement of the models to capture not only normal but also deviations from normal anatomy. We present a biologically inspired model for colour fundus images and illustrate it for the case of diabetic retinopathy. The proposed model uses spatially-varying morphological operations to enhance lesions locally and combines an ensemble of results, of such operations, to generate the saliency map. The model is validated against an average Human Gaze map of 15 experts and found to have 10% higher recall (at 100% precision) than four leading saliency models proposed for natural images. The F-score for match with manual lesion markings by 5 experts was0.4 (as opposed to 0.532 for gaze map) for our model and very poor for existing models. The model’s utility is shown via a novel enhancement method which employs saliency to selectively enhance the abnormal regions and this was found to boost their contrast to noise ratio by∼30%

@inproceedings{bib_A_Co_2015, AUTHOR = {Sivaswamy, Jayanthi and S.R.Krishnadas, and CHAKRAVARTY, ARUNAVA and JOSHI, GOPAL DATT and UJJWAL, and ABBAS, SYED TABISH }, TITLE = {A Comprehensive Retinal Image Dataset for the Assessment of Glaucoma from the Optic Nerve Head Analysis}, BOOKTITLE = {JSM BIOMEDICAL IMAGING DATA PAPERS}. YEAR = {2015}}

Optic nerve head (ONH) segmentation problem is of interest for automated glaucoma assessment. Although various segmentation methods have been proposed in the recent past, it is difficult to evaluate and compare the performance of individual methods due to a lack of a benchmark dataset. The assessment involves segmentation of optic disk and cup region within the ONH. In this paper, we present a comprehensive dataset of retinal images of both normal and glaucomatous eyes with manual segmentations from multiple human experts. The dataset also provides expert opinion on an image representing a normal or glaucomatous eye and on the presence of notching in an image. Several state of the art methods are assessed against this dataset using cup to disc diameter ratio (CDR), area and boundary-based evaluation measures. These are presented to aid benchmarking of new methods. A supervised, notch detection method based on the segmentation results is also proposed and its assessment results are included for benchmarking.

@inproceedings{bib_An_a_2015, AUTHOR = {UJJWAL, and CHAKRAVARTY, ARUNAVA and Sivaswamy, Jayanthi }, TITLE = {An assistive annotation system for retinal images}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2015}}

Annotated data is critical for the development of many computer assisted diagnostic (CAD) algorithms. The process of manual annotation is very strenuous, time-consuming and an expensive component in CAD development. In this paper,we propose the idea of an interactive Assistive Annotation System (AAS) aimed at helping annotators by automatically marking possible regions of interest for further refinement by an annotator. We propose an unsupervised, biologically inspired method for bright lesion annotation. The performance of the proposed system has been evaluated against region-level ground truth in DiaretDB1 dataset and was found to have a sensitivity of60%at7false positives per image. Preliminary testing was also done on public datasets which do not provide any lesion level annotations. A visual assessment of the obtained results affirm a good agreement with lesions visible in images. The system with a simple modification is shown to have the potential to handle dark lesion annotation,which is a significantly more challenging problem. Thus, the proposed system is a good starting point for exploring the AAS idea for retinal images. Such systems can help extend the use of many existing datasets by enriching the image-level annotations with localised information.

@inproceedings{bib_PET__2015, AUTHOR = {ABBAS, SYED TABISH and Sivaswamy, Jayanthi }, TITLE = {PET image reconstruction and denoising on hexagonal lattices}, BOOKTITLE = {International Conference on Image Processing}. YEAR = {2015}}

Nuclear imaging modalities like Positron emission tomography (PET) are characterized by a low SNR value due to the underlying signal generation mechanism. Given the significant role images play in current-day diagnostics, obtaining noise-free PET images is of great interest. With its higher packing density and larger and symmetrical neighbourhood,the hexagonal lattice offers a natural robustness to degradation in signal. Based on this observation, we propose an alternate solution to denoising, namely by changing the sampling lattice. We use filtered back projection for reconstruction, fol-lowed by a sparse dictionary based denoising and compare noise-free reconstruction on the Square and Hexagonal lattices. Experiments with PET phantoms (NEMA, Hoffman)and the Shepp-Logan phantom show that the improvement indenoising, post reconstruction, is not only at the qualitative but also quantitative level. The improvement in PSNR in the hexagonal lattice is on an average between 2 to 10 dB. These results establish the potential of the hexagonal lattice for re-construction from noisy data, in general.

@inproceedings{bib_Rege_2015, AUTHOR = {Paul, Angshuman and DEY, ANISHA and Mukherjee, Dipti Prasad and Sivaswamy, Jayanthi and Tourani, Vijaya }, TITLE = {Regenerative Random Forest with Automatic Feature Selection to Detect Mitosis in Histopathological Breast Cancer Images}, BOOKTITLE = {International Conference on Medical Image Computing and Computer Assisted Intervention}. YEAR = {2015}}

We propose a fast and accurate method for counting themitotic figures from histopathological slides using regenerative random forest. Our method performs automatic feature selection in an integratedmanner with classification. The proposed random forest assigns a weight to each feature (dimension) of the feature vector in a novel manner based on the importance of the feature (dimension). The forest also assigns amis classification-based penalty term to each tree in the forest. The trees are then regenerated to make a new population of trees (new forest)and only the more important features survive in the new forest. The feature vector is constructed from domain knowledge using the intensity features of nucleus, features of nuclear membrane and features of the possible stroma region surrounding the cell. The use of domain knowledge improves the classification performance. Experiments show at least 4%improvement in F-measure with an improvement in time complexity on the MITOS dataset from ICPR 2012 grand challenge

@inproceedings{bib_Late_2015, AUTHOR = {ABBAS, SYED TABISH and Sivaswamy, Jayanthi }, TITLE = {Latent factor model based classification for detecting abnormalities in retinal images}, BOOKTITLE = {Asian Conference on Pattern Recognition}. YEAR = {2015}}

Abnormality detection in medical images is a critical problem across image modalities and organs. Many ap-proaches to automatic abnormality detection use discrim-inative methods, based on domain knowledge, to address the problem. In this paper, we investigate the effective-ness of a generative model with no assumption of domain knowledge. We propose a method for classification of tis-sues based on Latent Factor analysis, and demonstrate iton colour retinal images with Diabetic Retinopathy-related abnormalities. A generative model based on Gaussian la-tent dictionaries is used to model various structures present at a patch level in an image. The model is used to classify a given patch into one of 5 classes: namely dark and bright lesions, neo-vascularisation (NV), plain tissue background and background with vessel. Evaluation of the proposed method was done on 3 different datasets. Same and crossdataset validation of the method yields an area under the receiver operating characteristic curve (AUC) of 0.85 for abnormality detection. The method was also modified to address a challenging problem of NV detection by posing it as a 2-class problem and the AUC for the same was found to be 0.92. This establishes the potential of LF model for abnormality detection.

@inproceedings{bib_Opti_2015, AUTHOR = {MITTAL, GAURAV and Sivaswamy, Jayanthi }, TITLE = {Optic Disk and Macula Detection from RetinalImages using Generalized Motion Pattern}, BOOKTITLE = {National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics}. YEAR = {2015}}

Accurate detection of optic disk and macula areof interest in automated analysis of retinal images as they are landmarks in retina and their detection aids in assessing these verity of diseases based on the locations of abnormalities relative to these landmarks. The general strategy is to design different methods to these landmarks. In contrast, we propose a novel and unified approach for Optic disk and macula detection in this paper using the Generalized Motion Pattern (GMP)[10] [19] which is derived by inducing motion to an image to smooth out unwanted information. The proposed method is unsupervised, parallelizable and handles illumination differences efficiently but assumes a fixed protocol in image acquisition. The proposed method has been tested on five public datasets and obtained results indicate comparable performance to supervised approaches for the same problem.

@inproceedings{bib_Onli_2015, AUTHOR = {AGGARWAL, RAJAT and SWETHA, SIRNAM and Namboodiri, Anoop and Sivaswamy, Jayanthi and V, Jawahar C }, TITLE = {Online handwriting recognition using depth sensors}, BOOKTITLE = {International Conference on Document Analysis and Recognition}. YEAR = {2015}}

In this work, we propose an online handwriting solution, where the data is captured with the help of depth sensors. Users may write in the air and our method recognizes it in real time using the proposed feature representation. Our method uses an efficient fingertip tracking approach and reduces the necessity of pen-up/pen-down switching. We validate our method on two depth sensors, Kinect and Leap Motion Controller. On a dataset collected from 20 users, we achieve a recognition accuracy of 97.59% for character recognition. We also demonstrate how this system can be extended for lexicon recognition with reliable performance. We have also prepared a dataset containing 1,560 characters and 400 words with the intention of providing common benchmark for handwritten character recognition using depth sensors and related research.

@inproceedings{bib_Dris_2014, AUTHOR = {Sivaswamy, Jayanthi and Krishnadas, S.R. and JOSHI, GOPAL DATT and JAIN, MADHULIKA and UJJWAL, and ABBAS, SYED TABISH }, TITLE = {Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2014}}

Optic nerve head (ONH) segmentation problem has been of interest for automated glaucoma assessment. Although various segmentation methods have been proposed in the recent past, it is difficult to evaluate and compare the performance of individual methods due to a lack of a benchmark dataset. The problem of segmentation involves segmentation of optic disk and cup region within ONH region. Available datasets do not incorporate challenges present in this problem. In this data paper, we present a comprehensive dataset of retinal images which include both normal and glaucomatous eyes and manual segmentations from multiple human experts. Both area and boundary-based evaluation measures are presented to evaluate a method on various aspects relevant to the problem of glaucoma assessment.

@inproceedings{bib_Bila_2014, AUTHOR = {Tiwari, Aayush and GUPTA, DHWANIT and Sivaswamy, Jayanthi }, TITLE = {Bilateral symmetry based approach for joint detection of landmarks in retinal images}, BOOKTITLE = {International Conference on Signal Processing and Communications}. YEAR = {2014}}

Optic disk (OD) and macula are anatomical structures in retinal images. Their detection is of interest in computer assisted diagnostic (CAD) algorithm development. We propose a joint detection algorithm which exploits the bilateral symmetry present in retinal images and present a method to detect OD and macula. A vessel density based metric is proposed to determine the axis of symmetry which is used along with appearance features and geometric constraint on the OD and macula for their detection. The proposed method has been evaluated on a large number of images drawn from 4 public and one private dataset. Obtained results show that our method has consistently high detection rate across the datasets. Since the detection is also very fast, the proposed method offers a good solution for CAD based disease screening.

@inproceedings{bib_Coup_2014, AUTHOR = {CHAKRAVARTY, ARUNAVA and Sivaswamy, Jayanthi }, TITLE = {Coupled sparse dictionary for depth-based cup segmentation from single color fundus image}, BOOKTITLE = {International Conference on Medical Image Computing and Computer Assisted Intervention}. YEAR = {2014}}

We present a novel framework for depth based optic cup boundary extraction from asingle2D color fundus photograph per eye.Multiple depth estimates from shading, color and texture gradients in the image are correlated with Optical Coherence Tomography (OCT)based depth using a coupled sparse dictionary, trained on image-depth pairs. Finally, a Markov Random Field is formulated on the depth map to model the relative depth and discontinuity at the cup boundary. Leave-one-out validation of depth estimation on the INSPIRE dataset gave average correlation coefficient of 0.80. Our cup segmentation out performs several state-of-the-art methods on the DRISHTI-GS dataset with an average F-score of 0.81 and boundary-error of 21.21 pixels on test set against manual expert markings. Evaluation on an additional set of 28images against OCT scanner provided ground truth showed an average rms error of 0.11 on Cup-Disk diameter and 0.19 on Cup-disk area ratios.

@inproceedings{bib_A_no_2013, AUTHOR = {CHAKRAVARTY, ARUNAVA and Sivaswamy, Jayanthi }, TITLE = {A novel approach for quantification of retinal vessel tortuosity using quadratic polynomial decomposition}, BOOKTITLE = {Indian Conference on Medical Informatics and Telemedicine}. YEAR = {2013}}

This paper describes a novel tortuosity measure, based on the premise that tortuosity is a measure of deviation from an ideal non-tortuous vessel. Hence, we propose to model the overall shape of an ideal vessel as a quadratic polynomial at a larger scale while the deviations are modeled as quadratic polynomials at smaller scales. Thus, a given vessel center-line is decomposed as a sum of quadratic polynomials of decreasing scale. This Quadratic Polynomial Decomposition is used as a framework for defining a quantitative measure of tortuosity. As opposed to the existing proposed measures, our method can distinguish between the relative size, shapes and orientations of the vessel bends. The measure is position and scale invariant and satisfies two key desired properties: it varies directly with frequency of twists at fixed amplitude and it varies directly with amplitude of twists when their frequency is fixed. The proposed method has been tested on a standard data set containing 30 artery and 30 vein vessel segments, and shown to be among the best measures as compared to the results of existing methods.

@inproceedings{bib_Auto_2013, AUTHOR = {MUJUMDAR, SHASHANK D and Sivaswamy, Jayanthi and Kishore, L.T. and Varma, R. }, TITLE = {Auto-windowing of ischemic stroke lesions in diffusion weighted imaging of the brain}, BOOKTITLE = {Indian Conference on Medical Informatics and Telemedicine}. YEAR = {2013}}

Diffusion Weighted Magnetic Resonance Imaging (DWI) is routinely used for early detection of cerebral ischemic changes in acute stroke. Fast acquisition with a standard echoplanar imaging technique generally compromises the image signal-to-noise ratio and in-plane resolution resulting in a reduction of the conspicuity and definition of lesions in the acquired data when viewed on a standard 8-bit display. We present a novel method for automatically and adaptively determining the window settings that enhance the contrast of the image relative to the ischemic lesions. The method performs a coarse segmentation of the lesions followed by contrast-to-noise ratio based computation of the optimal window parameters. The proposed method was tested on 24 datasets acquired with different protocols. The contrast improvement of the lesions is validated through a mirror region of interest analysis and by using the contrast improvement ratio metric. The average obtained improvement in contrast ranges from 25% to 60%. Preliminary results of segmentation showed a good reduction in the false positives and improvement in the lesion boundaries. A perception study of the windowed results against 8 radiologists was conducted. Reduction of 14.17% in the mean response time of detection was observed. Statistical analysis performed using t-test validates the reduction in mean response time to be significant. Results presented in the study show promise in the method.

@inproceedings{bib_A_ba_2013, AUTHOR = {Grinsven, M.J.J.P. Van and CHAKRAVARTY, ARUNAVA and Sivaswamy, Jayanthi and Theelen, T. and Ginneken, B. Van and ́anchez, C.I. S }, TITLE = {A bag of words approach for discriminating between retinal images containing exudates or drusen}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2013}}

Population screening for sight threatening diseases based on fundus imaging is in place or being considered worldwide. Most existing programs are focussed on a specific disease and are based on manual reading of images, though automated image analysis based solutions are being developed. Exudates and drusen are bright lesions which indicate very different diseases, but can appear to be similar. Discriminating between them is of interest to increase screening performance. In this paper, we present a Bag of Words approach which can be used to design a system that can play the dual role of content based retrieval (of images with exudates or drusen) system and a decision support system to address the problem of bright lesion discrimination. The approach consists of a novel partitioning of an image into patches from which color, texture, edge and granulometry based features are extracted to build a dictionary. A bag of Words approach is then employed to help retrieve images matching a query image as well as derive a decision on the type of bright lesion in the given (query) image. This approach has been implemented and tested on a combination of public and local dataset of 415 images. The area under the curve for image classification is 0.90 and retrieved precision is 0.76.

@inproceedings{bib_Visu_2013, AUTHOR = {UJJWAL, and Deepak, K Sai and CHAKRAVARTY, ARUNAVA and Sivaswamy, Jayanthi }, TITLE = {Visual saliency based bright lesion detection and discrimination in retinal images}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2013}}

Abnormality detection is the first step performed by doctors during evaluation of medical images in image based diagnosis, followed by disease-specific evaluation of abnormalities. Perception studies have shown that experts primarily focus on abnormal structures during visual examination for diagnosis. One way to model this behavior in automated image analysis is through visual saliency computation. In this paper, we investigate the potential role of visual saliency for computer aided diagnosis algorithm design. We propose a framework for detecting abnormalities that uses visual saliency computation for sparse representation of the image data that preserves the essential features of a normal image. The proposed method is evaluated for the task of bright lesion detection and classification in color retinal images which is of significance in disease screening. An evaluation of the proposed approach on 5 publicly available datasets yielded area under ROC curve of 0.88 to 0.98 for the detection task and accuracies ranging from 0.93 to 0.96 for lesion discrimination. These results establish visual saliency as an alternate avenue for automated abnormality detection.

@inproceedings{bib_Semi_2013, AUTHOR = {M, SUSHMA and GUPTA, ANUBHAV and Sivaswamy, Jayanthi }, TITLE = {Semi-automated magnification of small motions in videos}, BOOKTITLE = {Conference on Pattern Recognition and Machine Intelligence}. YEAR = {2013}}

In this paper, we present a semi-automated method to magnify small motions in videos. This method amplifies invisible or hidden motions in videos. To achieve motion magnification, we process the spatial and temporal information obtained from the video itself. Advantage of this work is that it is application independent. Proposed technique estimates required parameters to get desirable results. We demonstrate performance on 9 different videos. Motion magnification performance is equivalent to existing manual methods.

@inproceedings{bib_Time_2013, AUTHOR = {M, SUSHMA and GUPTA, ANUBHAV and Sivaswamy, Jayanthi }, TITLE = {Time-frequency analysis based motion detection in perfusion weighted MRI}, BOOKTITLE = {National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics}. YEAR = {2013}}

In this paper, we present a novel automated method to detect motion in perfusion weighted images (PWI), which is a type of magnetic resonance imaging (MRI). In PWI, blood perfusion is measured by injecting an exogenous tracer called bolus into the blood flow of a patient and then tracking it in the brain. PWI requires a long data acquisition time to forma time series of volumes. Hence, motion occurs due to patient’s unavoidable movements during a scan, which in turn results into motion corrupted data. There is a necessity of detection of these motion artifacts on captured data for correct disease diagnosis.In PWI, intensity profile gets disturbed due to occurrence of motion and/or bolus passage through the blood vessels. There is no way to distinguish between motion occurrence and bolus passage. In this paper, we propose an efficient time-frequency analysis based motion detection method. We show that proposed method is computationally inexpensive and fast. This method is evaluated on a DSC-MRI sequence with simulated motion of different degrees. We show that our approach detects motion in a few seconds.

@inproceedings{bib_Dept_2012, AUTHOR = {JOSHI, GOPAL DATT and Sivaswamy, Jayanthi and Krishnadas, S. R. }, TITLE = {Depth discontinuity-based cup segmentation from multiview color retinal images}, BOOKTITLE = {IEEE Transactions on Biomedical Engineering}. YEAR = {2012}}

Accurate segmentation of the cup region from retinal images is needed to derive relevant measurements for glaucoma assessment. A novel, depth discontinuity (in the retinal surface)-based approach to estimate the cup boundary is proposed in this paper. The proposed approach shifts focus from the cup region used by existing approaches to cup boundary. The given set of images, acquired sequentially, are related via a relative motion model and the depth discontinuity at the cup boundary is determined from cues such as motion boundary and partial occlusion. The information encoded by these cues is used to approximate the cup boundary with a set of best-fitting circles. The final boundary is found by considering points on these circles at different sectors using a confidence measure. Four different kinds of data sets ranging from synthetic to real image pairs, covering different multiview scenarios, have been used to evaluate the proposed method. The proposed method was found to yield an error reduction of 16% for cup-to-disk vertical diameter ratio (CDR) and 13% for cup-to-disk area ratio (CAR) estimation, over an existing monocular image-based cup segmentation method. The error reduction increased to 33% in CDR and 18% in CAR with the addition of a third view (image) which indicates the potential of the proposed approach.

@inproceedings{bib_Imag_2012, AUTHOR = {AKHILESH, B S R and Sivaswamy, Jayanthi and Pappuru, Rajeev R }, TITLE = {Image mosaicing of low quality neonatal retinal images}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2012}}

Retinopathy of prematurity (ROP) is a vascular disease in premature infants. This is characterized by abnormal vessel growth and subsequent fibrosis in the peripheral retina. The prognosis of ROP relies on information on the presence of abnormal growth and their location. Diagnosis is based on a series of images obtained with a wide field of view camera (such as RetCam), to capture the complete retina. In this paper, we present a novel and efficient hierarchal mosaicing algorithm, for neonatal images of varying quality. We employ a vessel-based quality metric and exploit the knowledge of the retinal structure to automatically select a subset of images from a given set, to construct a good quality mosaic. Such mosaics can aid the assessment of ROP by providing a comprehensive and complete view of the entire retina. The hierarchal approach underlying the method makes it possible to complete the mosaicing task in close to real time. The proposed method has been tested on 14 sets of data with each set consisting of 6-35 retinal images acquired using RetCam and the generated mosaics are found to be of good quality as validated by a clinical expert.

@inproceedings{bib_Dete_2012, AUTHOR = {JOSHI, GOPAL DATT and Sivaswamy, Jayanthi and R, Prashanth and Krishnadas, S. R. }, TITLE = {Detection of peri-papillary atrophy and RNFL defect from retinal images}, BOOKTITLE = {International Conference Image Analysis and Recognition}. YEAR = {2012}}

The task of detecting peri-papillary indicators associated with the glaucoma is challenging due to the high degree of intra and inter-image variations commonly seen in colour retinal images. The existing approaches based on direct modeling of the region of interest failto handle such image variations which compromises detection accuracy.In this paper, a novel detection strategy is proposed which exploits the saliency property associated with these indicators. The region of interest is modeled as a region substantially different from the adjacent image regions. This dissimilarity information is derived at the feature level, be-tween the target and its adjacent regions. Based on the proposed strategy,two novel methods are presented for the detection of peri-papillary atrophy and RNFL defect from colour retinal images. Two different datasets have been used to evaluate the performance of developed solutions. The obtained results are encouraging and establish the strength of the pro-posed strategy in handling high degree of image variations. The preliminary results and comparative evaluation with direct modeling strategy show viability of proposed strategy to be used in the glaucoma assessment task.

@inproceedings{bib_A_co_2012, AUTHOR = {S, HARINI A and Indurkhya, Bipin and Sivaswamy, Jayanthi }, TITLE = {A communication system on smart phones and tablets for non-verbal children with autism}, BOOKTITLE = {International Conference on Computers Helping People with Special Needs}. YEAR = {2012}}

We designed, developed and evaluated an Augmentative and Alternative Communication (AAC) system,AutVisComm,for children with autism that can run on smart phones and tablets. An iterative de-sign and development process was followed, where the prototypes were developed in close collaboration with the user group, and the usability testing was gradually expanded to larger groups. In the last evaluation stage described here, twenty-four children with autism used AutVisCommto learn to request the desired object. We measured their learning rates and correlated them with their behavior traits (as observed by their teachers) like joint attention, symbolic processing and imitation.We found that their ability for symbolic processing did not correlate with the learning rate, but their ability for joint attention did. This suggests that this system (and this class of AACs) helps to compensate for a lack of symbolic processing, but not for a lack of joint-attention mechanism.

@inproceedings{bib_Fast_2012, AUTHOR = {VEERAVASARAPU, V S RAO and Sivaswamy, Jayanthi }, TITLE = {Fast and fully automated video colorization}, BOOKTITLE = {International Conference on Signal Processing and Communications}. YEAR = {2012}}

Colorization is the process of adding colors to gray scale images. This is done to restore or enhance old films or photographs. Most of the techniques for the colorization of an image or video require manual designation of the locations to be colored and the colors themselves which is an expensive and time consuming process. In this paper, we propose a fast but effective fully automated technique for coloring the gray scale image sequences. We define a notion of a most informative frame which is to be coloured manually and exploit the motion field between frames for propagation of the colors to the remaining frames. The proposed technique attempts to provide a method to minimize the amount of labour required for colorization and to decrease the computational cost of this task. The most informative frame is one which has almost all the objects present in that scene. The motion field estimation is based on optical flow. A final refinement step uses similarity based colour filling. Extensive testing of the proposed technique on a large set of videos from movies and animation confirms that it is efficient and effective without any loss of quality.

@inproceedings{bib_Dete_2012, AUTHOR = {DEEPAK, K SAI and MEDATHATI, N V KARTHEEK and Sivaswamy, Jayanthi }, TITLE = {Detection and discrimination of disease-related abnormalities based on learning normal cases}, BOOKTITLE = {Pattern Recognition}. YEAR = {2012}}

Detection of abnormalities from medical images is of key interest in developing computer-aided diagnostic tools. In this paper, we observe the key challenges for representation and feature extraction schemes to be met for detection of abnormalities by learning normal cases. We introduce an image representation, motivated by the effect of motion on perception of structures. This representation is based on a set of patterns called generalized moment patterns (GMP) generated via induced motion over regions of interest, for learning normal. The proposed GMP has been utilized to develop a scheme for addressing two well-known problems: lesion classification in mammograms and detection of macular edema in color fundus images. The strengths of this scheme are that it does not require anylesion-level segmentation and relies largely on normal images for training which is attractive for developing screening tools. The proposed scheme has been assessed on two public domain datasets,namely, MIAS and MESSIDOR. A comparison against the performance of state of the art method sindicates the proposed scheme to be superior

@inproceedings{bib_A_No_2012, AUTHOR = {MUJUMDAR, SHASHANK D and Varma, R. and Kishore, L T and Sivaswamy, Jayanthi }, TITLE = {A Novel Framework for Segmentation of Stroke Lesions in Diffusion Weighted MRI Using Multiple b-Value Data}, BOOKTITLE = {International conference on Pattern Recognition}. YEAR = {2012}}

Diffusion Weighted MR Imaging (DWI) is routinely used for early detection of cerebral ischemic stroke.DWI with higher b-values (b=2000) provide improved sensitivity, higher conspicuity and reduced artifacts and thus improve the detectability of smallest infarcts than conventional DWI (b=1000). We propose a novel framework for accurately detecting stroke regions by combining information from multiple sources:b2000,b1000 data and the apparent diffusion coefficient map.The detected lesions are finally segmented using an active contour approach. The proposed method was tested on 41 datasets acquired with different protocols. A comparison of our method with a leading method [3] validates the effectiveness of our approach. The mediandice coefficient, sensitivity and specificity for stroke segmentation were 0.84, 87.07% and 99.90% respectively.The strength of the proposed method is its ability to capture (and accurately segment) the small (and large) lesions in the data which are often missed by segmentation methods operating on a single b-value data.

@inproceedings{bib_An_e_2012, AUTHOR = {GAUTAM, ROHIT and Sivaswamy, Jayanthi and Varma, Ravi }, TITLE = {An efficient, bolus-stage based method for motion correction in perfusion weighted MRI}, BOOKTITLE = {International conference on Pattern Recognition}. YEAR = {2012}}

This paper addresses the data corruption that occurs due to patient motion during a scan which is particularly a problem in perfusion weighted MRI due to long scan times. Motion correction is typically the rate-limiting step in processing as each volume has to be registered to a reference volume. This is compounded by the dynamically varying contrast in the volume series due to passage of an injected contrast agent. We propose an efficient two stage motion correction method, consisting of motion detection and a 2-pass registration method for aligning the motion-corrupted volumes. A 2D block-wise phase correlation in central slices is used for the first stage. Alignment employs a strategy which is sensitive to the status of the bolus in the volume and is based on gamma-variate function fitting for intensity correction to handle dynamic contrast in DSC-MRI. Evaluation of the approach shows that it is fast and accurate.

@inproceedings{bib_Asse_2012, AUTHOR = {JAMPANI, VARUN and UJJWAL, and Sivaswamy, Jayanthi and Vaidya, Vivek }, TITLE = {Assessment of computational visual attention models on medical images}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2012}}

Several computational visual saliency models have been pro-posed in the context of viewing natural scenes. We aim to investigate the relevance of computational saliency models in medical images in the context of abnormality detection.We report on two studies aimed at understanding the role of visual saliency in medical images. Diffuse lesions in ChestX-Ray images, which are characteristic of Pneumoconiosis and high contrast lesions such as ‘Hard Exudates’ in retinal images were chosen for the study. These approximately correspond to conjunctive and disjunctive targets in a visual search task. Saliency maps were computed using three popular models namely Itti-Koch [7], GBVS [3] and SR [4].The obtained maps were evaluated against gaze maps and ground truth from medical experts. Our results show that GBVS is seen to perform the best(Mdn. ROC area= 0.77) for chest X-Ray images while SRperforms the best (ROC area= 0.73) for retinal images,thus asserting that searching for conjunctive targets calls for a more local examination of an image while disjunctive targets call for a global examination. Based on the results of the above study, we propose extensions for the two best performing models. The first extension makes use of top down knowledge such as lung segmentation. This is shown to improve the performance of GBVS to some extent. Inthe second case the extension is by way of including multi-scale information. This is shown to significantly (by 28.76%)improve abnormality detection. The key insight from these studies is that bottom saliency continues to play a predominant role in examining medical images.

@inproceedings{bib_Moti_2012, AUTHOR = {DEEPAK, K SAI and JAIN, MADHULIKA and JOSHI, GOPAL DATT and Sivaswamy, Jayanthi }, TITLE = {Motion pattern-based image features for glaucoma detection from retinal images}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2012}}

Glaucoma is an eye disorder that causes irreversible loss of vision and is prevalent in the aging population. Glaucoma is indicated both by structural changes and presence of atrophy in retina. In retinal images, these appear in the form of subtle variation of local intensities. These variations are typically described using local shape based statistics which are prone to error. We propose an automated, global feature based approach to detect glaucoma from images. An image representation is devised to accentuate subtle indicators of the disease such that global image features can discriminate between normal and glaucoma cases effectively.The proposed method is demonstrated on a large image dataset annotated by 3 medical experts. The results show the method to be effective in detecting subtle glaucoma indi-cators. The classification performance on a dataset of 1186color retinal images containing a mixture of normal, suspect and confirmed cases of glaucoma is 97 percent sensitivity at 87 percent specificity. This improves further when the suspect cases are removed from the abnormal cases. Thus,the proposed method offers a good solution for glaucoma screening from retinal images.

@inproceedings{bib_A_me_2012, AUTHOR = {GAUTAM, ROHIT and Sivaswamy, Jayanthi and Varma, Ravi }, TITLE = {A method for motion detection and categorization in perfusion weighted MRI}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2012}}

The blood perfusion measurement is done by injecting a bolus of contrast agent in the brain followed by imaging over a period of time (scan). This process can extend into minutes and hence any patient motion mid-scan results in corrupted data. This is often observed in dynamic magnetic resonance(MR) imaging for both susceptibility (DSC) and contrast enhanced (DCE) scans. Motion correction done after scanning is typically the most time-intensive step in the entire measurement process since it involves registering each volume in the time-series to a reference volume. We argue that detecting the presence of motion prior to correction can mitigate this problem by reducing the number of volumes to be corrected. The challenge in motion detection is that the injected contrast alters the signal intensity as a function of time leading to false alarms. We present a robust multi-stage method: subdivision of the time series data into bolus and non bolus phases; clustering-based identification of bolus-affected pixels followed by correction of their intensity using a Gamma variate function fitting-based method and a 2Dblock-wise phase correlation for detecting motion between adjacent volumes in DSC-MRI data. The proposed method was tested on a DSC MR sequence with simulated motion of varying degrees. The experimental results show that the entropy of the derived motion fields is a good metric for detecting and categorizing the motion. The proposed scheme when applied prior to correction can achieve on average a37% reduction in the time required for motion correction

@inproceedings{bib_Dris_2011, AUTHOR = {JOSHI, GOPAL DATT and Sivaswamy, Jayanthi }, TITLE = {DrishtiCare: a telescreening platform for diabetic retinopathy powered with fundus image analysis}, BOOKTITLE = {Journal of diabetes science and technology}. YEAR = {2011}}

Diabetic retinopathy is the leading cause of blindness in urban populations. Early diagnosis through regular screening and timely treatment has been shown to prevent visual loss and blindness. It is very difficult to cater to this vast set of diabetes patients, primarily because of high costs in reaching out to patients and a scarcity of skilled personnel. Telescreening offers a cost-effective solution to reach out to patients but is still inadequate due to an insufficient number of experts who serve the diabetes population. Developments toward fundus image analysis have shown promise in addressing the scarcity of skilled personnel for large-scale screening. This article aims at addressing the underlying issues in traditional telescreening to develop a solution that leverages the developments carried out in fundus image analysis.

@inproceedings{bib_Unsu_2011, AUTHOR = {KAUSHIK, SANDEEP and Sivaswamy, Jayanthi }, TITLE = {Unsupervised 3D Segmentation of Hippocampus in Brain MR Images}, BOOKTITLE = {International Conference on Bio-inspired Systems and Signal Processing}. YEAR = {2011}}

The most widely followed procedure for diagnosis and prognosis of dementia is structural neuro imaging of hippocampus by means of MR. Hippocampus segmentation is of wide interest as it enables quantitative assessment of the structure. In this paper, we propose an algorithm for hippocampus segmentation that is un-supervised and image driven. It is based on a hybrid approach which combines a coarse segmentation and surface evolution. A coarse solution is derived using region growing which is further refined using a modified version of the physics based water flow model (Liu and Nixon, 2007). The proposed method has been tested on a publicly available dataset. The performance of this method is assessed using Dice coefficient against the ground truth provided for 25 volume images. It is consistent across volumes and the average Dice values are comparable to a multi-atlas based method reported on a subset of the same dataset.

@inproceedings{bib_Echo_2011, AUTHOR = {G, VIDHYADHARI and Sivaswamy, Jayanthi }, TITLE = {Echo-cardiographic segmentation: Via feature-space clustering}, BOOKTITLE = {National Conference on Communications}. YEAR = {2011}}

Segmentation in echo-cardiographic images is a difficult task due to the presence of speckle noise, low contrast and blurring. We present a novel method based on clustering performed in the feature space. A new feature-based image representation is proposed. It is obtained by computing a local feature descriptor at every pixel location. This descriptor is derived using the Radon-Transform to effectively characterise local image context. Next, an un-supervised clustering is performed in the feature space to segment regions in the image. The performance of the proposed method is tested on both synthetic and real images. A comparison against well established feature descriptors is carried out to demonstrate the strengths and applicability of the proposed representation. Overall, the results indicate promise in the strategy of doing segmentation of noisy data in image descriptor space.

@inproceedings{bib_Role_2011, AUTHOR = {JAMPANI, VARUN and Vivek, Vaidya and Sivaswamy, Jayanthi and Kishore, L. Tourani }, TITLE = {Role of expertise and contralateral symmetry in the diagnosis of pneumoconiosis: an experimental study}, BOOKTITLE = {Journal of Medical Imaging}. YEAR = {2011}}

Pneumoconiosis, a lung disease caused by the inhalation of dust, is mainly diagnosed using chest radiographs. The effects of using contralateral symmetric (CS) information present in chest radiographs in the diagnosis of pneumoconiosis are studied using an eye tracking experimental study. The role of expertise and the influence of CS information on the performance of readers with different expertise level are also of interest. Experimental subjects ranging from novices & medical students to staff radiologists were presented with 17 double and 16 single lung images, and were asked to give profusion ratings for each lung zone. Eye movements and the time for their diagnosis were also recorded. Kruskal-Wallis test (χ2(6) = 13.38, p = .038), showed that the observer error (average sum of absolute differences) in double lung images differed significantly across the different expertise categories when considering all the participants. Wilcoxon-signed rank test indicated that the observer error was significantly higher for single-lung images (Z = 3.13, p < .001) than for the double-lung images for all the participants. Mann-Whitney test (U = 28, p = .038) showed that the differential error between single and double lung images is significantly higher in doctors [staff & residents] than in non-doctors [others]. Thus, Expertise & CS information plays a significant role in the diagnosis of pneumoconiosis. CS information helps in diagnosing pneumoconiosis by reducing the general tendency of giving less profusion ratings. Training and experience appear to play important roles in learning to use the CS information present in the chest radiographs.

@inproceedings{bib_Opti_2011, AUTHOR = {JOSHI, GOPAL DATT and Sivaswamy, Jayanthi and Krishnadas, S. R. }, TITLE = {Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment}, BOOKTITLE = {IEEE Transactions on Medical Imaging}. YEAR = {2011}}

Automatic retinal image analysis is emerging as an important screening tool for early detection of eye diseases. Glaucoma is one of the most common causes of blindness. The manual examination of optic disk (OD) is a standard procedure used for detecting glaucoma. In this paper, we present an automatic OD parameterization technique based on segmented OD and cup regions obtained from monocular retinal images. A novel OD segmentation method is proposed which integrates the local image information around each point of interest in multidimensional feature space to provide robustness against variations found in and around the OD region. We also propose a novel cup segmentation method which is based on anatomical evidence such as vessel bends at the cup boundary, considered relevant by glaucoma experts. Bends in a vessel are robustly detected using a region of support concept, which automatically selects the right scale for analysis. A multi-stage strategy is employed to derive a reliable subset of vessel bends calledr-bends followed by a local spline fitting to derive the desired cup boundary. The method has been evaluated on 138 images comprising 33 normal and 105 glaucomatous images against three glaucoma experts. The obtained segmentation results show consistency in handling various geometric and photometric variations found across the dataset. The estimation error of the method or vertical cup-to-disk diameter ratio is 0.09/0.08 (mean/standard deviation) while for cup-to-disk area ratio it is 0.12/0.10. Overall,the obtained qualitative and quantitative results show effective-ness in both segmentation and subsequent OD parameterization for glaucoma assessment.

@inproceedings{bib_Auto_2011, AUTHOR = {DEEPAK, K SAI and Sivaswamy, Jayanthi }, TITLE = {Automatic assessment of macular edema from color retinal images}, BOOKTITLE = {IEEE Transactions on Medical Imaging}. YEAR = {2011}}

Diabetic macular edema (DME) is an advanced symptom of diabetic retinopathy and can lead to irreversible vision loss. In this paper, a two-stage methodology for the detection and classification of DME severity from color fundus images is proposed. DME detection is carried out via a supervised learning approach using the normal fundus images. A feature extraction technique is introduced to capture the global characteristics of the fundus images and discriminate the normal from DME images. Disease severity is assessed using a rotational asymmetry metric by examining the symmetry of macular region. The performance of the proposed methodology and features are evaluated against several publicly available datasets. The detection performance has a sensitivity of 100% with specificity between 74% and 90%. Cases needing immediate referral are detected with a sensitivity of 100% and specificity of 97%. The severity classification accuracy is 81% for the moderate case and 100% for severe cases. These results establish the effectiveness of the proposed solution.

@inproceedings{bib_A_no_2010, AUTHOR = {DIXIT, NEHA and Sivaswamy, Jayanthi }, TITLE = {A novel approach to generate up-sampled tomographic images using combination of rotated hexagonal lattices}, BOOKTITLE = {National Conference on Communications}. YEAR = {2010}}

Generation of upsampled tomographic images via combination of rotated lattices has been explored in [1]. In this paper, we evaluate the existing method using real phantom data. Up-sampled tomographic images are generated via combination of rotated hexagonal lattices. Sinogram data is filtered and back-projected on two hexagonal lattices which are rotated versions of each other. Samples from these lattices are interpolated to generate an up-sampled image defined on a square lattice. These results are compared with direct up-sampling method and image ISR-2 algorithm described in [10]. Two PET phantoms - NEMA and Hoffman brain phantom are used for purpose of evaluation. The results of the proposed method show considerable improvement over direct up-sampled image in terms of contrast, sharpness and imaging artifact; but when compared with ISR-2 generated image, the difference in image quality is not significant. A key advantage of the proposed method is that only two images are required for generating a high resolution image whereas ISR2 requires k low resolution images for an up-sampling factor of k.

@inproceedings{bib_Role_2010, AUTHOR = {S, HARINI A and Sivaswamy, Jayanthi and Indurkhya, Bipin }, TITLE = {Role of technology in assisting children with Developmental Disorders}, BOOKTITLE = {Workshop on Emerging Research Trends in Artificial Intelligence}. YEAR = {2010}}

Many fields of Artificial Intelligence including natural language processing, speech processing, robotics etc., have seen explosive growth in the last decade. In this paper, we discuss the application of these advances to aid children with autism and dyslexia. This paper describes two systems we are currently developing - an alternative and augmentative communication (AAC) system for children with autism and a speech modification system for children with dyslexia. We also present results of our initial evaluation.

@inproceedings{bib_Crea_2010, AUTHOR = {SINGH, JEETINDER and Sivaswamy, Jayanthi }, TITLE = {Creating User Interface for Interactive Simulations}, BOOKTITLE = {International Conference on Digital Game and Intelligent Toy Enhanced Learning}. YEAR = {2010}}

Interactive simulations encourage active/discovery learning in students. But developing simulations is a time consuming task. This along with the usability and scalability issues are the bottleneck in wide availability of such tools. The developer spends most of his/her time in tailoring the user interface (UI) to meet multiple constraints like pedagogy, teacher satisfaction and student learning styles. Providing an efficient way to develop UI can greatly speed up the development cycle and facilitate widespread access to high quality resources. In this paper, we describe how UI development can be separated from the simulation program to facilitate easy development of such visualization tool. We also discuss design and development of Graphical interface construction Kit (GicK) which helps in creating UI and combining it with simulation program for creating interactive simulations. A constructive physics simulation is developed as an exemplar of proposed framework. In the end we reported evaluation of constructive physics simulation by 43 higher school students and our conclusion.

@inproceedings{bib_Opti_2010, AUTHOR = {JOSHI, GOPAL DATT and Sivaswamy, Jayanthi and Karan, and Krishnadas, S. R. }, TITLE = {Optic disk and cup boundary detection using regional information}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2010}}

The shape deformation within the optic disk (OD) is an important indicator for the detection of glaucoma. In this paper, relevant disk parameters are estimated using the OD and cup boundaries. A deformable model guided by regional statistics is used to detect the OD boundary. A cup boundary detection scheme is presented based on the appearance of pallor in Lab colour space and the expected cup symmetry. The proposed scheme is tested on 170 images comprising 40 normal and 130 glaucomatous images. The proposed method gives a mean error 0.030 for normal and 0.121 for glaucomatous images in the estimation of cup-to-disk ratio which compares well with reported figures in literature.

@inproceedings{bib_Cont_2010, AUTHOR = {DEEPAK, K SAI and JOSHI, GOPAL DATT and Sivaswamy, Jayanthi }, TITLE = {Content-based retrieval of retinal images for maculopathy}, BOOKTITLE = {ACM International Health Informatics Symposium}. YEAR = {2010}}

A growing number of public initiatives for screening the population for retinal disorders along with widespread availability of digital fundus (retina) cameras is leading to large accumulation of color fundus images. The ability to retrieve images based on pathologic state is a powerful functionality that has wide applications in evidence-based medicine, automated computer assisted diagnosis and in training ophthalmologists. In this paper, we propose a new methodology for content-based retrieval of retinal images showing symptoms of maculopathy. Taking the view of a disease region as one which exhibits deviation from the normal image background, a model for the image background is learnt and used to extract disease-affected image regions. These are then analysed to assess the severity level of maculopathy. Symmetry-based descriptor is derived for the macula region and employed for retrieval of images according to severity of maculopathy. The proposed approach has been tested on a publicly available dataset. The results show that background learning is successful as images with or no maculopathy are detected with a mean precision of 0.98. An aggregate precision of 0.89 is achieved for retrieval of images at three severity-levels of macular edema, demonstrating the potential offered by the proposed disease-based retrieval system.

@inproceedings{bib_Robu_2010, AUTHOR = {B, YOGESH BABU and MEDATHATI, N V KARTHEEK and Sivaswamy, Jayanthi }, TITLE = {Robust matching of multi-modal retinal images using radon transform based local descriptor}, BOOKTITLE = {ACM International Health Informatics Symposium}. YEAR = {2010}}

Multi-Modal image registration is the primary step in fusing complementary information contained in different imaging modalities for diagnostic purposes. We focus on two specific retinal imaging modalities namely, Color Fundus Image(CFI) and Fluroscein Fundus Angiogram(FFA). In this paper we investigate a projection based method using Radon transform for accurate matching in multi-modal retinal images. A novel Radon Transform based descriptor is proposed, which is invariant to illumination, rotation and partially to scale. Our results show that our descriptor is well suited for retinal images as it is robust to lesions, and works well even in poor quality images. The descriptor has been tested on a dataset of 126 images and compared for matching application against gradient based descriptors. The results show that Radon based descriptor outperforms the gradient based ones in both being able to discriminate between true and false matches and under presence of lesions.

@inproceedings{bib_A_su_2010, AUTHOR = {RAM, S S KEERTHI and JOSHI, GOPAL DATT and Sivaswamy, Jayanthi }, TITLE = {A successive clutter-rejection-based approach for early detection of diabetic retinopathy}, BOOKTITLE = {IEEE Transactions on Biomedical Engineering}. YEAR = {2010}}

The presence of microaneurysms (MAs) is usually an early sign of diabetic retinopathy(DR) and their automatic detection from color retinal images is of clinical interest. In this paper, we present a new approach for automatic MA detection from digital colour fundus images. We formulate MA detection as a problem of target detection from clutter, where the probability of occurrence of target is considerably smaller compared to the clutter. A successive rejection-based strategy is proposed to progressively lower the number of clutter responses. The processing stages are designed to reject specific classes of clutter while passing majority of true MAs, using a set of specialized features. The true positives that remain after the final rejector are assigned a score which is based on its similarity to a true MA. Results of extensive evaluation of the proposed approach on three different retinal image datasets is reported, and are used to highlight the promise in the presented strategy.

@inproceedings{bib_Loca_2010, AUTHOR = {MEDATHATI, N V KARTHEEK and Sivaswamy, Jayanthi }, TITLE = {Local descriptor based on texture of projections}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2010}}

The aim of a local descriptor or a feature descriptor is to efficiently represent the region detected by an interest point operator in a compact format for use in various applications related to matching. The common design principle behind most of the mainstream descriptors like SIFT, GLOH, Shape context etc is to capture the spatial distribution of features using histograms computed over a grid around interest points. Histograms provide compact representation but typically loose the spatial distribution information. In this paper, we propose to use projection-based representation to improve a descriptor’s capacity to capture spatial distribution information while retaining the invariance required. Based on this proposal, two descriptors based on the CS-LBP are introduced. The descriptors have been evaluated against known descriptors on a standard dataset and found to outperform, in most cases, the existing descriptors. The obtained results demonstrate that proposed approach has the advantages of both the statistical robustness of histogram and the capability of the projection based representation to capture spatial information.

@inproceedings{bib_Robu_2010, AUTHOR = {JOSHI, GOPAL DATT and GAUTAM, ROHIT and Sivaswamy, Jayanthi and Krishnadas, S. R. }, TITLE = {Robust optic disk segmentation from colour retinal images}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2010}}

We present a novel segmentation method to better capture the boundary of a non-homogeneous object such as the optic disk(OD), defined locally by two similar characteristic regions. Existing active contour models which utilise gradient information [12] or global region intensity [2] fail to localise aforementioned boundaries. We propose a region-based active contour model that uses local image information around each point of interest in multi-dimensional feature space. This model uses a local energy functional and level-set representation to achieve desired OD segmentation. The local energy functional defined on each image point provides sufficient information to determine a desired OD segmentation which is robust to the variations found in and around the OD region. This method has been evaluated against the segmentation provided by three medical experts on 138 retinal images. Both region and boundary-based assessment performed against two well established active contour models show strengths of the proposed method.

@inproceedings{bib_Moti_2010, AUTHOR = {VEERAVASARAPU, V S RAO and Sivaswamy, Jayanthi }, TITLE = {Motion deblurring as optimisation}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2010}}

Motion blur is one of the most common causes of image degradation. It is of increasing interest due to the deep penetration of digital cameras into consumer applications. In this paper, we start with a hypothesis that there is sufficient information within a blurred image and approach the deblurring problem as an optimisation process where the deblurring is to be done by satisfying a set of conditions. These conditions are derived from first principles underlying the degradation process assuming noise-free environments. We propose a novel but effective method for removing motion blur from a single blurred image via an iterative algorithm. The strength of this method is that it enables deblurring without resorting to estimation of the blur kernel or blur depth. The proposed iterative method has been tested on several images with different degrees of blur. The obtained results have been compared with state of the art techniques including those that require more than one input image. The results are consistently of high quality and comparable or superior to the existing methods which demonstrates the effectiveness of the proposed technique.

@inproceedings{bib_Impu_2009, AUTHOR = {GHADIYARAM, PHANI DEEPTI and BORKER, MARUTI V and Sivaswamy, Jayanthi }, TITLE = {Impulse noise removal from color images with Hopfield neural network and improved vector median filter}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2009}}

In this paper, a novel and effective method for impulse noise removal in corrupted color images is discussed. The new method consists of two phases. The first phase is a noise detection phase where a modified Hopfield neural network is used to detect impulse noise pixels. The second is a noise filtering phase where the disadvantage of taking Vector Median in a single color space is addressed and a new algorithm based on performing Vector Median first in RGB space and then in HSI space is presented. The results of simulations performed on a set of standard test images on a wide range of noise corruption show that the proposed method is capable of detecting all the impulse noise pixels with almost zero false positive rates and removes noise while retaining finer image details. It outperforms the standard procedures and is yet simple and suitable for real time applications.

@inproceedings{bib_Synt_2009, AUTHOR = {DIXIT, NEHA and MEDATHATI, N V KARTHEEK and Sivaswamy, Jayanthi }, TITLE = {Synthetic Zooming of Tomographic Images by Combination of Lattices}, BOOKTITLE = {Symposium and Medical Imaging Conference)}. YEAR = {2009}}

We propose a method for synthetic zooming of tomographic images by applying super resolution technique on reconstructed data via a union of rotated lattices (URL). The proposed method consists of two steps: (i) sinogram data is filtered and back projected on to two lattices, which are rotated versions of each other and (ii) the samples from the two lattices are interpolated to generate the upsampled image. Square and hexagonal lattices have been investigated for URL. Results of subjective and objective evaluations of the proposed method on analytic phantoms are presented and compared with direct upsampling of data reconstructed on a single square lattice and upsampled image generated by union of low resolution shifted images (USL). The proposed method shows qualitative and quantitative improvement over direct up sampling but when compared with USL, generated up sampled images are of comparable quality.

@inproceedings{bib_Curv_2009, AUTHOR = {RAM, S S KEERTHI and B, YOGESH BABU and Sivaswamy, Jayanthi }, TITLE = {Curvature Orientation Histograms for Detection and Matching of Vascular Landmarks in Retinal Images}, BOOKTITLE = {Medical Imaging: Image Processing}. YEAR = {2009}}

Registration is a primary step in tracking pathological changes in medical images. Point-based registration requires a set of distinct, identifiable and comparable landmark points to be extracted from images. In this work, we illustrate a method for obtaining landmarks based on changes in a topographic descriptor of a retinal image. Building on the curvature primal sketch introduced by Asada and Brady1 for describing interest points on planar curves, we extend the notion to grayscale images. We view an image as a topographic surface and propose to identify interest points on the surface using the surface curvature as a descriptor. This is illustrated by modeling retinal vessels as trenches and identifying landmarks as points where the trench behaviour changes, such as it splits or bends sharply. Based on this model, we present a method which uses the surface curvature to characterise landmark points on retinal vessels as points of high dispersion in the curvature orientation histogram computed around the points. This approach yields junction/crossover points of retinal vessels and provides a means to derive additional information about the type of junction. A scheme is developed for using such information and determining the correspondence between sets of landmarks from two images related by a rigid transformation. In this paper we present the details of the proposed approach and results of testing on images from public domain datasets. Results include comparison of landmark detection with two other methods, and results of correspondence derivation. Results show the approach to be successful and fast.

@inproceedings{bib_An_O_2009, AUTHOR = {SINGH, JEETINDER and S, HARINI A and Sivaswamy, Jayanthi }, TITLE = {An Open Source Virtual Lab for School Physics Education}, BOOKTITLE = {National Conference on Open Source Software}. YEAR = {2009}}

There is a need to create quality open source educational resources to address the needs of Indian schools. In this paper,we describe a virtual physics lab which we built based on open source components. This is basically an authoring tool that lets user create their own experiments. We first discuss for the need for virtual labs. We then present the architecture of our tool and the technical challenges we faced in creating it. We also present the feedback we received from school students on this tool.

@inproceedings{bib_A_me_2009, AUTHOR = {CHAWLA, MAYANK and SHARMA, SAURABH and Sivaswamy, Jayanthi and Kishore.L.T, }, TITLE = {A method for automatic detection and classification of stroke from brain CT images}, BOOKTITLE = {International Conference of the IEEE Engineering in Medicine and Biology Society}. YEAR = {2009}}

Computed tomographic (CT) images are widely used in the diagnosis of stroke. In this paper, we present an automated method to detect and classify an abnormality into acute infarct, chronic infarct and hemorrhage at the slice level of non-contrast CT images. The proposed method consists of three main steps: image enhancement, detection of mid-line symmetry and classification of abnormal slices. A windowing operation is performed on the intensity distribution to enhance the region of interest. Domain knowledge about the anatomical structure of the skull and the brain is used to detect abnormalities in a rotation- and translation-invariant manner. A two-level classification scheme is used to detect abnormalities using features derived in the intensity and the wavelet domain. The proposed method has been evaluated on a dataset of 15 patients (347 image slices). The method gives 90% accuracy and 100% recall in detecting abnormality at patient level; and achieves an average precision of 91% and recall of 90% at the slice level.

@inproceedings{bib_Mult_2009, AUTHOR = {RAM, S S KEERTHI and Sivaswamy, Jayanthi }, TITLE = {Multi-space clustering for segmentation of exudates in retinal color photographs}, BOOKTITLE = {International Conference of the IEEE Engineering in Medicine and Biology Society}. YEAR = {2009}}

Exudates are a class of lipid retinal lesions visible through optical fundus imaging, and indicative of diabetic retinopathy. We propose a clustering-based method to segment exudates, using multi-space clustering, and colorspace features. The method was evaluated on a set of 89 images from a publicly available dataset, and achieves an accuracy of 89.7% and positive predictive value of 87%.

@inproceedings{bib_Lear_2009, AUTHOR = {SATHYA, S and S, HARINI A and Sivaswamy, Jayanthi }, TITLE = {Learning fractions by making patterns –An Ethnomathematics based approach}, BOOKTITLE = {International Conference on Computers in Education}. YEAR = {2009}}

Mathematics is one of the difficult subjects children encounter. This is attributed to the fact that mathematics is taught as an abstract set of symbols and rules. Many innovative approaches have been tried to clear this misconception and make children see the real applications of mathematics. One such approach is using ethnomathematics – the mathematics present in the cultural forms of an ethnic group. In this work, we explore the effectiveness of this approach to teach a difficult mathematics concept – fractions. Fractions have been chosen due to its complexity and the inherent difficulties they pose to children. A tool was developed to teach fractions by engaging the child in two activities – making a bead necklace and tiling an area. The evaluation results indicate that such an approach is very effective in teaching the concept.

@inproceedings{bib_Crea_2009, AUTHOR = {SINGH, JEETINDER and Sivaswamy, Jayanthi }, TITLE = {Creating Educational Game by Authoring Simulations}, BOOKTITLE = {International Conference on Computers in Education}. YEAR = {2009}}

The high level of engagement students have with games has motivated many researches to study various aspect of games-based learning. The approach taken in most of the studies is bringing instruction element implicitly in games. Adapting instructional content for creating games is a viable alternative approach to create interactive virtual learning environment development. Pedagogical support in the form of simulation exercises have been shown to be more effective in learning context. In this paper we argue the simulation exercises can be combined to produce games using an authoring tool. We illustrate our idea with an exemplar in the form of a 3D virtual physics game authoring tool. The results of evaluation of our exemplar indicate that use of subject-related terminology can help participants relate virtual game context with theoretical and real world phenomenon; however, games by themselves may not serve to be an effective way to learn new concepts.

@inproceedings{bib_Assi_2009, AUTHOR = {S, HARINI A and Sivaswamy, Jayanthi and Indurkhya, Bipin }, TITLE = {Assistive systems for children with dyslexia and autism}, BOOKTITLE = {ACM SIGACCESS Conference on Computers and Accessibility}. YEAR = {2009}}

Autism and dyslexia are both developmental disorders of neural origin. As we still do not understand the neural basis of these disorders fully, technology can take two approaches in helping those affected. The first is to compensate externally for a known difficulty and the other is to achieve the same function using a completely different means. To demonstrate the first option, we are developing a system to compensate for the auditory processing difficulties in case of dyslexia and to demonstrate the second option we propose a system for autism where we remove the need for traditional languages and instead use pictures for communication.

@inproceedings{bib_Movi_2009, AUTHOR = {KUNDU, ABHIJIT and Krishna, K Madhava and Sivaswamy, Jayanthi }, TITLE = {Moving object detection by multi-view geometric techniques from a single camera mounted robot}, BOOKTITLE = {International Conference on Intelligent Robots and Systems}. YEAR = {2009}}

The ability to detect, and track multiple moving objects like person and other robots, is an important prerequisite for mobile robots working in dynamic indoor environments. We approach this problem by detecting independently moving objects in image sequence from a monocular camera mounted on a robot. We use multi-view geometric constraints to classify a pixel as moving or static. The first constraint, we use, is the epipolar constraint which requires images of static points to lie on the corresponding epipolar lines in subsequent images. In the second constraint, we use the knowledge of the robot motion to estimate a bound in the position of image pixel along the epipolar line. This is capable of detecting moving objects followed by a moving camera in the same direction, a so-called degenerate configuration where the epipolar constraint fails. To classify the moving pixels robustly, a Bayesian framework is used to assign a probability that the pixel is stationary or dynamic based on the above geometric properties and the probabilities are updated when the pixels are tracked in subsequent images. The same framework also accounts for the error in estimation of camera motion. Successful and repeatable detection and pursuit of people and other moving objects in realtime with a monocular camera mounted on the Pioneer 3DX, in a cluttered environment confirms the efficacy of the method.

@inproceedings{bib_AUTO_2008, AUTHOR = {AGARWAL, AMIT and Sivaswamy, Jayanthi and Rani, Alka and Das, Taraprasad }, TITLE = {AUTOMATIC SEGMENTATION OF CAPILLARY NON-PERFUSION IN RETINAL ANGIOGRAMS}, BOOKTITLE = {International Conference on Bio-inspired Systems and Signal Processing}. YEAR = {2008}}

Capillary Non-Perfusion (CNP) is a condition in diabetic retinopathy where blood ceases to flow to certain parts of the retina, potentially leading to blindness. This paper presents a solution for automatically detecting and segmenting CNP regions from fundus fluorescein angiograms (FFAs). CNPs are modelled as valleys, and a novel multiresolution technique for trough-based valley detection is presented. The proposed algorithm has been tested on 40 images and validated against expert-marked ground truth. Obtained results are presented as a receiver operating characteristic (ROC) curve. The area under this curve is 0.842 and the distance of ROC from the ideal point (0,1) is 0.31.

@inproceedings{bib_Fund_2008, AUTHOR = {SINGH, JEETINDER and Sivaswamy, Jayanthi }, TITLE = {Fundus foveal localization based on image relative subtraction-IReS approach}, BOOKTITLE = {National Conference on Communications}. YEAR = {2008}}

In this paper we present a method for fovea localization which does not use organization information of other retinal structures like optic disk and arcades. The main advantage of this method is that it does not require segmentation/localization of other retinal structures which are required as prior knowledge in existing fovea localization methods. The key idea is to enhance the relative contrast between the fovea and its surrounding such that it is well-separated in a retinal image. The approach was tested on 520 retinal images which include normal and pathological color retinal images. An overall accuracy of 90.57% is reported independent of left eye, right eye, normal or pathological retinal images.

@inproceedings{bib_OPTI_2008, AUTHOR = {JOSHI, GOPAL DATT and G, VIDHYADHARI and Sivaswamy, Jayanthi }, TITLE = {OPTIC DISK DETECTION USING TOPOGRAPHICAL FEATURES}, BOOKTITLE = {International Conference on Bio-inspired Systems and Signal Processing}. YEAR = {2008}}

We present a new method for optic disk (OD) detection in a retinal image. It is an hybrid approach which uses properties of both appearance and model-based approaches which are mostly used for OD detection. An extrema pyramidal decomposition is employed and hill type topographical features are extracted at the lowest level of the image pyramid. The detected hill points are characterised as candidate OD locations. Later, a confidence measure is derived for each candidate using vessel structure information and candidate with the highest value is declared as final OD location. This method has been tested on different retinal image dataset and quantitative results are presented

@inproceedings{bib_Appe_2008, AUTHOR = {SINGH, JEETINDER and G.D, Joshi and Sivaswamy, Jayanthi }, TITLE = {Appearance-based object detection in colour retinal images}, BOOKTITLE = {International Conference on Image Processing}. YEAR = {2008}}

Extraction of anatomical structures (landmarks), such as optic disk (OD), fovea and blood vessels, from fundus images is useful in automatic diagnosis. Current approaches largely use spatial relationship among the landmarks’ position for detection. In this paper, we present an appearance-based method for detecting fovea and OD from colour images. The strategy used for detection is based on improving the local contrast which is achieved by combining information from two spectral channels of the given image. The proposed method has been successfully tested on different datasets and the results show 96% detection for fovea and 91% detection for OD (a total of 502 and 531 images for fovea and OD are taken respectively).

@inproceedings{bib_Colo_2008, AUTHOR = {JOSHI, GOPAL DATT and Sivaswamy, Jayanthi }, TITLE = {Colour retinal image enhancement based on domain knowledge}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2008}}

Retinal images are widely used to manually or automatically detect and diagnose many diseases. Due to the complex imaging setup, there is a large luminosity and contrast variability within and across images. Here, we use the knowledge of the imaging geometry and propose an enhancement method for colour retinal images, with a focus on contrast improvement with no introduction of artifacts. The method uses non-uniform sampling to estimate the degradation and derive a correction factor from a single plane. We also propose a scheme for applying the derived correction factor to enhance all the colour planes of a given image. The proposed enhancement method has been tested on a publicly available dataset [8]. Results show marked improvement over existing methods.

@inproceedings{bib_Imag_2008, AUTHOR = {KUMAR, PRAGADA SANJEEV and Sivaswamy, Jayanthi }, TITLE = {Image denoising using matched biorthogonal wavelets}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2008}}

Current denoising techniques use the classical orthonormal wavelets for decomposition of an image corrupted with additive white Gaussian noise, upon which various thresholding strategies are built. The use of available biorthogonal wavelets in image denoising is less common because of their poor performance. In this paper, we present a method to design image-matched biorthogonal wavelet bases and report on their potential for denoising. We have conducted experiments on various image datasets namely Natural, Satellite and Medical with the designed wavelets using two existing thresholding strategies. Test results from comparing the performance of matched and fixed biorthogonal wavelets show an average improvement of 35% in MSE for low SNR values (0 to 18db) in every dataset. This improvement was also seen in the PSNR and visual comparisons. This points to the importance of matching when using wavelet-based denoising

@inproceedings{bib_Pers_2008, AUTHOR = {HANDA, ANKUR and Sivaswamy, Jayanthi and Krishna, K Madhava and SINGH, SARTAJ and Menezes, Paulo }, TITLE = {Person following with a mobile robot using a modified optical flow}, BOOKTITLE = {Conference on Climbing and Walking Robots}. YEAR = {2008}}

This paper deals with the tracking and following of a person with a camera mounted mobile robot. A modified energy based optical flow approach is used for motion segmentation from a pair of images. Further a spatial relative veolcity based filering is used to extract prominently moving objects. Depth and color information are also used to robustly identify and follow a person.

@inproceedings{bib_MUDI_2007, AUTHOR = {SINGH, JEETINDER and Sivaswamy, Jayanthi and Naidu, Krishnarajulu }, TITLE = {MUDIS-A virtual learning environment}, BOOKTITLE = {International Workshop on Digital Game and Intelligent Toy Enhanced Learning}. YEAR = {2007}}

This paper presents a multi-component; distributed system (MuDiS) based solution for building a virtual learning environment which combines a wide range of technology, tools and digital gaming concepts to create an interactive tool for science education. MuDiS has been designed to be an extensible and easy-to-use system. The proposed environment is intended for designing and monitoring of educational content as well as creating a platform for exploring ideas. The system allows exchange of educational content and integrate different pedagogical approaches to learning and teaching under the same environment. We have developed a virtual physics lab that serves as an exemplar for the proposed virtual environment. We present the design details of the physics lab and discuss its performance.

@inproceedings{bib_Unsu_2007, AUTHOR = {GARG, SAURABH and Sivaswamy, Jayanthi and CHANDRA, B R SIVA }, TITLE = {Unsupervised curvature-based retinal vessel segmentation}, BOOKTITLE = {IEEE International Symposium on Biomedical Imaging}. YEAR = {2007}}

Unsupervised methods for automatic vessel segmentation from retinal images are attractive when only small datasets, with associated ground truth markings, are available. We present an unsupervised, curvature-based method for segmenting the complete vessel tree from colour retinal images. The vessels are modeled as trenches and the medial lines of the trenches are extracted using the curvature information derived from a novel curvature estimate. The complete vessel structure is then extracted using a modified region growing method. Testresults of the algorithm using the DRIVE dataset are superior to previously reported unsupervised methods and comparable to those obtained with the supervised methods.

@inproceedings{bib_A_ge_2007, AUTHOR = {JOSHI, GOPAL DATT and GARG, SAURABH and Sivaswamy, Jayanthi }, TITLE = {A generalised framework for script identification}, BOOKTITLE = {International Journal on Document Analysis and Recognition}. YEAR = {2007}}

Automatic identification of a script in a given document image facilitates many important applications such as automatic archiving of multilingual documents, searching online archives of document images and for the selection of script specific OCR in a multilingual environment. In this paper, we model script identification as a texture classification problem and examine a global approach inspired by human visual perception. A generalised, hierarchical framework is proposed for script identification. A set of energy and intensity space features for this task is also presented. The framework serves to establish the utility of a global approach to the classification of scripts. The framework has been tested on two datasets: 10 Indian and 13 world scripts. The obtained accuracy of identification across the two datasets is above 94%. The results demonstrate that the framework can be used to develop solutions for script identification from document images across a large set of script classes.

@inproceedings{bib_A_SI_2006, AUTHOR = {Joshi, Gopal Datt and Sivaswamy, Jayanthi }, TITLE = {A SIMPLE SCHEME FOR CONTOUR DETECTION}, BOOKTITLE = {International Conference on Computer Vision Theory and Applications}. YEAR = {2006}}

We present a computationally simple and general purpose scheme for the detection of all salient object contours in real images. The scheme is inspired by the mechanism of surround influence that is exhibited in 80% of neurons in the primary visual cortex of primates. It is based on the observation that the local context of a contour significantly affects the global saliency of the contour. The proposed scheme consists of two steps: first find the edge response at all points in an image using gradient computation and in the second step modulate the edge response at a point by the response in its surround. In this paper, we present the results of implementing this scheme using a Sobel edge operator followed by a mask operation for the surround influence. The proposed scheme has been tested successfully on a large set of images. The performance of the proposed detector compares favourably both computationally and qualitatively, in comparison with another contour detector which is also based on surround influence. Hence, the proposed scheme can serve as a low cost preprocessing step for high level tasks such shape based recognition and image retrieval.

@inproceedings{bib_A_co_2006, AUTHOR = {JOSHI, GOPAL DATT and Sivaswamy, Jayanthi }, TITLE = {A computational model for boundary detection}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2006}}

Boundary detection in natural images is a fundamental problem in many computer vision tasks. In this paper, we argue that early stages in primary visual cortex provide ample information to address the boundary detection problem. In other words, global visual primitives such as object and region boundaries can be extracted using local features captured by the receptive fields. The anatomy of visual cortex and psychological evidences are studied to identify some of the important underlying computational principles for the boundary detection task. A scheme for boundary detection based on these principles is developed and presented. Results of testing the scheme on a benchmark set of natural images, with associated human marked boundaries, show the performance to be quantitatively competitive with existing computer vision approaches.

@inproceedings{bib_An_a_2006, AUTHOR = {Sivaswamy, Jayanthi and JOSHI, GOPAL DATT and CHANDRA, B R SIVA }, TITLE = {An alternative curvature measure for topographic feature detection}, BOOKTITLE = {Indian Conference on Computer Vision, Graphics and Image Processing}. YEAR = {2006}}

The notion of topographic features like ridges, trenches, hills, etc. is formed by visualising the 2D image function as a surface in 3D space. Hence, properties of such a surface can be used to detect features from images. One such property, the curvature of the image surface, can be used to detect features characterised by a sharp bend in the surface. Curvature based feature detection requires an efficient technique to estimate/calculate the surface curvature. In this paper, we present an alternative measure for curvature and provide an analysis of the same to determine its scope. Feature detection algorithms using this measure are formulated and two applications are chosen to demonstrate their performance. The results show good potential of the proposed measure in terms of efficiency and scope.

@inproceedings{bib_Scri_2006, AUTHOR = {Joshi, Gopal Datt and Garg, Saurabh and Sivaswamy, Jayanthi }, TITLE = {Script identification from Indian documents}, BOOKTITLE = {International Workshop on Document Analysis Systems}. YEAR = {2006}}

Automatic identification of a script in a given document image facilitates many important applications such as automatic archiving of multilingual documents, searching online archives of document images and for the selection of script specific OCR in a multilingual environment. In this paper, we present a scheme to identify different Indian scripts from a document image. This scheme employs hierarchical classification which uses features consistent with human perception. Such features are extracted from the responses of a multi-channel log-Gabor filter bank, designed at an optimal scale and multiple orientations. In the first stage, the classifier groups the scripts into five major classes using global features. At the next stage, a sub-classification is performed based on script-specific features. All features are extracted globally from a given text block which does not require any complex and reliable segmentation of the document image into lines and characters. Thus the proposed scheme is efficient and can be used for many practical applications which require processing large volumes of data. The scheme has been tested on 10 Indian scripts and found to be robust to skew generated in the process of scanning and relatively insensitive to change in font size. This proposed system achieves an overall classification accuracy of 97.11% on a large testing data set. These results serve to establish the utility of global approach to classification of scripts.

@inproceedings{bib_An_a_2006, AUTHOR = {CHANDRA, B R SIVA and Sivaswamy, Jayanthi }, TITLE = {An analysis of curvature based ridge and valley detection}, BOOKTITLE = {International Conference on Acoustics, Speech, and Signal Processing}. YEAR = {2006}}

A 2D function, representing a digital image, is a surface in 3D space. Curvature of such a surface can be exploited to detect ridge and valley like features from images. In this paper, we present an analysis of such curvature based ridge and valley detection techniques and come up with a description for the different classes of ridge and valley profiles which can be detected by them. Such an analysis helps in understanding the scope and limitations of the curvature based techniques. As curvature is a measure of ‘bend’in the cross-section profile along a particular direction of the image intensities,the analysisis presented using 1D functions which represent cross-section profiles of ridges and valleys. The classes of profiles which can be detected by a curvature based technique are described in terms of the properties of the second-derivative of the 1D profile function.

@inproceedings{bib_Usef_2002, AUTHOR = {MOHAN, ADAPA SUNIL and Sivaswamy, Jayanthi }, TITLE = {Useful information embedding in images using watermarks}, BOOKTITLE = {International Conference on Multimedia and Design}. YEAR = {2002}}

Watermarking is being used in a wide variety of applications. Steganography, copyright protection, owner identification etc are some of them. But watermarking can also be used as means to store other kind of useful information in the image. This work discusses the advantages of putting such information into the image. A watermarking algorithm suitable for embedding large amount of information in the image, robust of jpeg compression is also presented.