Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network

Bhandary, Sulatha V (2017) Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network. Journal of Computational Science, 20. pp. 70-79. ISSN 18777503

[img] PDF
4480 DisplayPdf.pdf - Published Version
Restricted to Registered users only

Download (945kB) | Request a copy

Abstract

We have developed and trained a convolutional neural network to automatically and simultaneously segment optic disc, fovea and blood vessels. Fundus images were normalized before segmentation was performed to enforce consistency in background lighting and contrast. For every effective point in the fundus image, our algorithm extracted three channels of input from the point’s neighbourhood and forwarded the response across the 7-layer network. The output layer consists of four neurons, representing background, optic disc, fovea and blood vessels. In average, our segmentation correctly classified 92.68% of the ground truths (on the testing set from Drive database). The highest accuracy achieved on a single image was 94.54%, the lowest 88.85%. A single convolutional neural network can be used not just to segment blood vessels, but also optic disc and fovea with good accuracy.

Item Type: Article
Uncontrolled Keywords: Optic disc segmentation; Blood vessels segmentation; Fovea segmentation; Convolutional neural network; Fundus image
Subjects: Medicine > KMC Manipal > Ophthalmology
Depositing User: KMC Library
Date Deposited: 05 Jun 2018 04:01
Last Modified: 05 Jun 2018 04:01
URI: http://eprints.manipal.edu/id/eprint/151227

Actions (login required)

View Item View Item