Abstract

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.

Abstract

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.

Abstract

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.

Abstract

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.

Abstract

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.

Abstract

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.

Abstract

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.

Abstract

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.

Abstract

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.

Abstract

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.