A novel method for retinal exudate segmentation using signal separation algorithm. Issue 133 (September 2016)

• Record Type: Journal Article
• Authors: Imani, Elaheh; Pourreza, Hamid-Reza
• Is Part Of: Computer methods and programs in biomedicine. Issue 133(2016)
• Page Start: 195
• Page End: 205
• Publication Date: 2016-09
• Subjects: Exudate detection -- Morphological component analysis (MCA) algorithm -- Dynamic thresholding -- Mathematical morphology -- Diabetic retinopathy -- Macula edema; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2016.05.016
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A novel scheme for extracting retinal exudates based on morphological component analysis algorithm is presented in this paper. We separate vessels from retinal images to facilitate exudate detection process. A dynamic thresholding algorithm is used to create initial exudates map. Morphological operators are used to detect exact exudates border. The Kirsch edge detection is employed to remove false positive regions. Abstract: Diabetic retinopathy is one of the major causes of blindness in the world. Early diagnosis of this disease is vital to the prevention of visual loss. The analysis of retinal lesions such as exudates, microaneurysms and hemorrhages is a prerequisite to detect diabetic disorders such as diabetic retinopathy and macular edema in fundus images. This paper presents an automatic method for the detection of retinal exudates. The novelty of this method lies in the use of Morphological Component Analysis (MCA) algorithm to separate lesions from normal retinal structures to facilitate the detection process. In the first stage, vessels are separated from lesions using the MCA algorithm with appropriate dictionaries. Then, the lesion part of retinal image is prepared for the detection of exudate regions. The final exudate map is created using dynamic thresholding and mathematical morphologies. Performance of the proposed method is measured on the three publicly available DiaretDB, HEI-MED and e-ophtha datasets. Accordingly, the AUC of 0.961 and 0.948 and 0.937 is achieved respectively, which are greater than most of the state-of-the-art methods.