Effective Fundus Image Decomposition for the Detection of Red Lesions and Hard Exudates to Aid in the Diagnosis of Diabetic Retinopathy

Abstract

Diabetic retinopathy (DR) is characterized by the presence of red lesions (RLs), such as microaneurysms and hemorrhages, and bright lesions, such as exudates (EXs). Early DR diagnosis is paramount to prevent serious sight damage. Computer-assisted diagnostic systems are based on the detection of those lesions through the analysis of fundus images. In this paper, a novel method is proposed for the automatic detection of RLs and EXs. As the main contribution, the fundus image was decomposed into various layers, including the lesion candidates, the reflective features of the retina, and the choroidal vasculature visible in tigroid retinas. We used a proprietary database containing 564 images, randomly divided into a training set and a test set, and the public database DiaretDB1 to verify the robustness of the algorithm. Lesion detection results were computed per pixel and per image. Using the proprietary database, 88.34% per-image accuracy (ACCi), 91.07% per-pixel positive predictive value (PPVp), and 85.25% per-pixel sensitivity (SEp) were reached for the detection of RLs. Using the public database, 90.16% ACCi, 96.26% PPV_p, and 84.79% SEp were obtained. As for the detection of EXs, 95.41% ACCi, 96.01% PPV_p, and 89.42% SE_p were reached with the proprietary database. Using the public database, 91.80% ACCi, 98.59% PPVp, and 91.65% SEp were obtained. The proposed method could be useful to aid in the diagnosis of DR, reducing the workload of specialists and improving the attention to diabetic patients.

Red-lesion extraction in retinal fundus images by directional intensity changes’ analysis

“…The research works chosen for comparison for Diaretdb1 dataset are the research works of Refs. 35 , 53 . Dark and bright abnormal lesions are detected with the method of Ref.…”

“…It is possible to categorize the existing methods for abnormality detection in retinal fundus images into mathematical morphology-based 26 – 29 , region growing-based 30 , 31 , wavelet-based 32 – 34 , pixel classification 17 , artificial intelligence and deep learning 35 , 36 , knowledge-based 37 and hybrid approaches 38 – 41 .…”

“…A method for detecting red-lesions and exudates is proposed in Ref. 35 . This method includes several steps.…”

“…Then, several features are extracted from the obtained layers. Finally, a Multi-Perceptron Layer is utilized to discriminate the true lesions from falsely detected candidates 35 . However, the segmentation of blood vasculature and decomposition of image into several layers inflict a significant volume of computations.…”

“…The methods focused on detecting abnormalities in retinal fundus images can be categorized into mathematical morphology-based 26 – 29 , region growing-based 30 , 31 , wavelet-based 32 – 34 , pixel classification 17 , artificial intelligence and deep learning 35 , 36 , knowledge-based 37 and hybrid approaches 38 – 41 . In the next section, each class is described by explaining sample related research works.…”