Retinal Microaneurysms Detection Using Local Convergence Index Features

Abstract

Retinal microaneurysms (MAs) are the earliest clinical sign of diabetic retinopathy disease. Detection of MAs is crucial for the early diagnosis of diabetic retinopathy and prevention of blindness. In this paper, a novel and reliable method for automatic detection of MAs in retinal images is proposed. In the first stage of the proposed method, several preliminary microaneurysm candidates are extracted using a gradient weighting technique and an iterative thresholding approach. In the next stage, in addition to intensity and shape descriptors, a new set of features based on local convergence index filters is extracted for each candidate. Finally, the collective set of features is fed to a hybrid sampling/boosting classifier to discriminate the MAs from non-MAs candidates. The method is evaluated on images with different resolutions and modalities (color and scanning laser ophthalmoscope) using six publicly available data sets including the retinopathy online challenges (ROC) data set. The proposed method achieves an average sensitivity score of 0.471 on the ROC data set outperforming state-of-the-art approaches in an extensive comparison. The experimental results on the other five data sets demonstrate the effectiveness and robustness of the proposed MAs detection method regardless of different image resolutions and modalities.

Automated retinal lesion detection via image saliency analysis

“…For brevity, we provide readers with the performance only from the three most recent MA detection methods (note, only Ref. [4] reports the detection performance on the RC‐RGB‐MA dataset): this is not intended to be taken as exhaustive. As observed, the proposed method outperforms the existing state‐of‐the‐art ones on all the four datasets in terms of final score.…”

“…Seoud et al generated a new set of shape features called dynamic shape features to detect dark lesions from retinal images. Dashtbozorg et al used a gradient weighting‐based iterative thresholding approach and a boosting classifier to locate MA.…”

“…To evaluate its effectiveness, we have evaluated the proposed method on seven publicly available retinal image datasets showing diabetic or malarial pathogenesis. These were: the Retina Check project managed by Eindhoven University of Technology (RC‐RGB‐MA); the DiaretDB1; the Retinopathy Online Challenge training set (ROC); the e‐ophtha; the Messidor; the Diabetic Macular Edema (DME‐DUKE) dataset collected by Duke University; and the Malarial Retinopathy dataset collected by the University of Liverpool (LIMA) . Table summarizes the key information of these datasets.…”

“…Current practical approaches for the quantitative analysis of retinal abnormalities require extensive manual annotation by experienced graders . Manual grading is often time‐consuming, expensive, and subject to human errors, thus will be impractical for routine clinical applications.…”

Bayesian inference framework for bounded generalized Gaussian‐based mixture model and its application to biomedical images classification

“…An accurate analysis of biomedical data (eg, segmentation, categorization, classification, detection, denoising, and quantification) is a highly required task for several clinical applications in order to improve health care. 3,25,36,55 Breast cancer detection is another challenging biomedical application that has become the major frequent cancers among females and the most common threat to women's health. Nevertheless, performing a precise analysis is a challenging problem due to the big size of the datasets coupled with the complexity and inter-and intra-class variability of the anatomic organs such as the shape and appearance properties.…”