Detection of exudates in fundus photographs using deep neural networks and anatomical landmark detection fusion. (December 2016)

• Record Type: Journal Article
• Authors: Prentašić, Pavle; Lončarić, Sven
• Is Part Of: Computer methods and programs in biomedicine. Volume 137(2016)
• Page Start: 281
• Page End: 292
• Publication Date: 2016-12
• Subjects: Diabetic retinopathy -- Exudates -- Machine learning -- Convolutional neural networks -- Fundus photographs; 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.2016.09.018
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Detection of exudates is important for detection of diabetic retinopathy. Method based on landmark detection and convolutional network fusion is presented. F1 measure of 0.78 was achieved. Easily incorporated in a screening system. Abstract: Background and objective: Diabetic retinopathy is one of the leading disabling chronic diseases and one of the leading causes of preventable blindness in developed world. Early diagnosis of diabetic retinopathy enables timely treatment and in order to achieve it a major effort will have to be invested into automated population screening programs. Detection of exudates in color fundus photographs is very important for early diagnosis of diabetic retinopathy. Methods: We use deep convolutional neural networks for exudate detection. In order to incorporate high level anatomical knowledge about potential exudate locations, output of the convolutional neural network is combined with the output of the optic disc detection and vessel detection procedures. Results: In the validation step using a manually segmented image database we obtain a maximum F 1 measure of 0.78. Conclusions: As manually segmenting and counting exudate areas is a tedious task, having a reliable automated output, such as automated segmentation using convolutional neural networks in combination with other landmark detectors, is an important step in creating automated screening programs for early detection of diabetic retinopathy.