Automated identification of diabetic retinal exudates in digital colour images. Issue 10 (23rd September 2003)

• Record Type: Journal Article
• Authors: Osareh, A; Mirmehdi, M; Thomas, B; Markham, R
• Is Part Of: British journal of ophthalmology. Volume 87:Issue 10(2003)
• Page Start: 1220
• Page End: 1223
• Publication Date: 2003-09-23
• Subjects: diabetic retinopathy -- exudates -- segmentation -- neural networks; Ophthalmology -- Periodicals; 617.7
• DOI: 10.1136/bjo.87.10.1220
• Languages: English
• ISSNs: 0007-1161

Abstract

Abstract : Aim: To identify retinal exudates automatically from colour retinal images. Methods: The colour retinal images were segmented using fuzzy C-means clustering following some key preprocessing steps. To classify the segmented regions into exudates and non-exudates, an artificial neural network classifier was investigated. Results: The proposed system can achieve a diagnostic accuracy with 95.0% sensitivity and 88.9% specificity for the identification of images containing any evidence of retinopathy, where the trade off between sensitivity and specificity was appropriately balanced for this particular problem. Furthermore, it demonstrates 93.0% sensitivity and 94.1% specificity in terms of exudate based classification. Conclusions: This study indicates that automated evaluation of digital retinal images could be used to screen for exudative diabetic retinopathy.