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

TL;DR

This paper presents a convolutional neural network that automatically segments the optic disc, fovea, and retinal blood vessels in fundus images with high accuracy, aiding ophthalmic diagnostics.

Contribution

A novel CNN architecture capable of simultaneous segmentation of multiple retinal structures in fundus images, improving efficiency and accuracy over existing methods.

Findings

Achieved 92.68% accuracy on Drive database

Successfully segmented multiple structures with a single network

Enhanced consistency through image normalization

Abstract

We have developed and trained a convolutional neural network to automatically and simultaneously segment optic disc, fovea and blood vessels. Fundus images were normalised 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 neighbourhood of the point and forward the response across the 7 layer network. In average, our segmentation achieved an accuracy of 92.68 percent on the testing set from Drive database.