Discrimination of retinal images containing bright lesions using sparse coded features and SVM

Abstract

Diabetic Retinopathy (DR) is a chronic progressive disease of the retinal microvasculature which is among the major causes of vision loss in the world. The diagnosis of DR is based on the detection of retinal lesions such as microaneurysms, exudates and drusen in retinal images acquired by a fundus camera. However, bright lesions such as exudates and drusen share similar appearances while being signs of different diseases. Therefore, discriminating between different types of lesions is of interest for improving screening performances. In this paper, we propose to use sparse coding techniques for retinal images classification. In particular, we are interested in discriminating between retinal images containing either exudates or drusen, and normal images free of lesions. Extensive experiments show that dictionary learning techniques can capture strong structures of retinal images and produce discriminant descriptors for classification. In particular, using a linear SVM with the obtained sparse coded features, the proposed method achieves superior performance as compared with the popular Bag-of-Visual-Word approach for image classification. Experiments with a dataset of 828 retinal images collected from various sources show that the proposed approach provides excellent discrimination results for normal, drusen and exudates images. It achieves a sensitivity and a specificity of 96.50% and 97.70% for the normal class; 99.10% and 100% for the drusen class; and 97.40% and 98.20% for the exudates class with a medium size dictionary of 100 atoms.

Recent Development on Detection Methods for the Diagnosis of Diabetic Retinopathy

“…Morphological operations, like mean shift, normalized cut, and cannys, have presented better performance in EX extraction [103]. Several machine learning principles have shown better sensitivity results for EX segmentation [104][105][106][107][108][109][110][111]. Fraz et al in [104] applied morphological reconstruction and a Gabor filter for EX candidate extraction using 498 images.…”

“…Finally, the performance of the DCNN was combined with the disc and vessel results to segment true EX pixels, obtaining a 0.78 F-score. Similarly, SVM classifiers with sparse coded features, K-means, scale invariant feature transform, and visual dictionaries were exploited in [22,106,107] to distinguish non-EX from EX points. Logistic regression followed by multilayer perceptron and radial basis function classifiers successfully classified hard exudates using 130 images with a 96% sensitivity [108].…”

Automatic differentiation of color fundus images containing drusen or exudates using a contextual spatial pyramid approach

“…A method, making use of sparse coded features and a support vector machine achieved near perfect discrimination results [32]. However, it should be noted that a fair comparison between methods is hard to make since results are based on different datasets.…”

“…Based on a single lesion, it can be difficult or even impossible for an algorithm to make a differentiation. Reference criteria for data inclusion in the previous study [32] were not mentioned by the authors. Furthermore, no human observer was used in the previous study, which would allow to compare system performance to human level performance, giving a measure of overall performance.…”

Classification of melanoma lesions using sparse coded features and random forests

“…Sparse signal representation has become very popular in the past decades and lead to state-of-the-art results in various applications such as face recognition, 21 image denoising, image inpainting, 22 and image classification. 23 The main goal of sparse modeling is to efficiently represent the images as a linear combination of a few typical patterns, called atoms, selected from a dictionary. Here, we intend to use sparse representation of the low-level extracted features for melanoma classification.…”