An exclusive‐disjunction‐based detection of neovascularisation using multi‐scale CNN. Issue 7 (3rd January 2021)

• Record Type: Journal Article
• Authors: Pavani P, Geetha; Biswal, Birendra; Sairam, M V S; Biswal, Pradyut Kumar
• Is Part Of: IET image processing. Volume 15:Issue 7(2021)
• Page Start: 1518
• Page End: 1529
• Publication Date: 2021-01-03
• Subjects: Haemodynamics, pneumodynamics -- Optical and laser radiation (medical uses) -- Patient diagnostic methods and instrumentation -- Image recognition -- Optical and laser radiation (biomedical imaging/measurement) -- Computer vision and image processing techniques -- Biology and medical computing -- Neural nets; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/ipr2.12122
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract: In this article, an exclusive‐disjunction‐based detection of neovascularisation (NV), which is the formation of new blood vessels on the retinal surfaces, is presented. These vessels, being thin and fragile, get ruptured easily leading to permanent blindness. The proposed algorithm consists of two stages. In the first stage, the retinal images are classified into non‐NV and NV using multi‐scale convolutional neural network, while in the second stage, 13 relevant features are extracted from the vascular map of NV images to achieve the pixel locations of new blood vessels using a directional matched filter along with the Difference of Laplacian of Gaussian operator followed by an exclusive disjunction function with adaptive thresholding of the vascular map. At the same time, the pixel locations of optic disc (OD) are detected using intensity distribution and variations on the retinal images. Finally, the pixel locations of both new blood vessels and OD are compared for classification. If the pixel locations of new blood vessels fall inside the OD, they are labelled as NV on OD, else they are labelled as NV elsewhere. The proposed algorithm has achieved an accuracy of 99.5%, specificity of 97.5%, sensitivity of 98.9%, and area under the curve of 94.2% when tested on 155 non‐NV and 115 NV images.