Abstract

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.

Abstract

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.

Abstract

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.

Abstract

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

Abstract

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.

Abstract

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.

Abstract

As a form of visual representation, freehand line sketches are typically studied as an end product of the sketching process. However, from a recognition point of view, one can also study various orderings and properties of the primitive strokes that compose the sketch. Studying sketches in this manner has enabled us to create novel sparse yet discriminative sketch-based representations for object categories which we term category-epitomes. Concurrently, the epitome construction provides a natural measure for quantifying the sparseness underlying the original sketch, which we term epitome-score. We analyze category-epitomes and epitome-scores for hand-drawn sketches from a sketch dataset of 160 object categories commonly encountered in daily life. Our analysis provides a novel viewpoint for examining the complexity of representation for visual object categories.

Abstract

With a view to provide a user-friendly interface for designing, training and developing deep learning frameworks, we have developed Expresso, a GUI tool written in Python. Expresso is built atop Caffe, the open-source, prize-winning framework popularly used to develop Convolutional Neural Networks. Expresso provides a convenient wizard-like graphical interface which guides the user through various common scenarios--data import, construction and training of deep networks, performing various experiments, analyzing and visualizing the results of these experiments. The multi-threaded nature of Expresso enables concurrent execution and notification of events related to the aforementioned scenarios. The GUI sub-components and inter-component interfaces in Expresso have been designed with extensibility in mind. We believe Expresso's flexibility and ease of use will come in handy to researchers, newcomers and seasoned alike, in their explorations related to deep learning.

Abstract

Freehand line sketches are an interesting and unique form of visual representation. Typically, such sketches are studied and utilized as an end product of the sketching process. However, we have found it instructive to study the sketches as sequentially accumulated composition of drawing strokes added over time. Studying sketches in this manner has enabled us to create novel sparse yet discriminative sketch-based representations for object categories which we term category-epitomes. Our procedure for obtaining these epitomes concurrently provides a natural measure for quantifying the sparseness underlying the original sketch, which we term epitome-score. We construct and analyze category-epitomes and epitome-scores for freehand sketches belonging to various object categories. Our analysis provides a novel viewpoint for studying the semantic nature of object categories.

Abstract

here has been a profound interest of late in the digitization and reconstruction of historical monuments. Rendering massive monument models requires a cluster of work stations because of the computational in feasibility of rendering over a single machine. Moreover, interactive rendering of these massive models in an immersive environment is only possible over a cluster of machines. In this paper, we present a design of distributed rendering system to efficiently handle models with massive textures. A server holds the skeleton of the whole model and divides the screen space balancing the rendering load among multiple clients. Each client loads only the require geometry and textures to render its sub-scene. We present a virtual texturing method for handling massive textures over the distributed rendering system. These textures are combined into a texture atlas which is split into equally sized tiles. A virtual texture is built over this atlas with each pixel representing a tile in the atlas. An efficient caching module loads only the required tiles into the memory, that are identified using the virtual texture.A fragment shader uses the virtual texture as a mapping to the physical texture in memory to generate the fragments. We demonstrate the performance of our system over a 350M triangles and 500 gigapixel textured model of Vittala temple.