Multiscale segmentation of exudates in retinal images using contextual cues and ensemble classification. (May 2017)

• Record Type: Journal Article
• Authors: Fraz, M. Moazam; Jahangir, Waqas; Zahid, Saqib; Hamayun, Mian M.; Barman, Sarah A.
• Is Part Of: Biomedical signal processing and control. Volume 35(2017)
• Page Start: 50
• Page End: 62
• Publication Date: 2017-05
• Subjects: Medical image analysis -- Feature extraction -- Ensemble classification -- Exudate segmentation -- Machine learning -- Diabetic retinopathy; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2017.02.012
• Languages: English
• ISSNs: 1746-8094

Abstract

Graphical abstract: Highlights: Exudates in retinal images are the early sign of diabetic retinopathy. Automated multiscale segmentation of exudates using ensemble classifier. Morphological reconstruction for fine grain candidate exudate detection. Gabor filter for coarse grain candidate exudate identification. Extensive evaluation shows significant performance gain on other methods. Abstract: Diabetic Retinopathy (DR) is the one among other main reasons of blindness in the adult population. Early discovery of DR through screening programs and successive treatment is critical in order to avoid visual blindness. The early signs of DR as manifested in retinal images include micro-aneurysms, hemorrhages and exudates. In this paper, we have presented an ensemble classifier of bootstrapped decision trees for multiscale localization and segmentation of exudates in retinal fundus images. The candidate exudates are extracted at fine grain and coarse grain levels using morphological reconstruction and Gabor filter respectively. The contextual cues are applied to the candidate exudates, which greatly reduces false positives in exudate segmentation. Several region based features are computed from candidate regions to train the ensemble classifier for classification of pixel as exudate and non-exudate region. The method has been evaluated on four publically available databases; DIARETDB1, e-Ophtha EX, HEI-MED and Messidor. The method has achieved the segmentation accuracy as (0.8772, 0.8925, 0.9577, and 0.9836) and area under ROC as (0.9310, 0.9403, 0.9842, and 0.9961) for each of the dataset respectively. The algorithm appears to be an efficient tool for automated detection of exudates in large population based DR screening programs, due to the attained accuracy, robustness, simplicity and speed.