An Inception Inspired Deep Network to Analyse Fundus Images

TL;DR

This paper introduces a novel deep neural network inspired by inception modules for vessel segmentation in fundus images, demonstrating improved or comparable performance on DRIVE and IOSTAR datasets.

Contribution

The study presents a new inception-inspired deep network with three sub-networks for vessel segmentation, highlighting its architecture and competitive results.

Findings

Outperforms previous methods on DRIVE and IOSTAR datasets.

Sub-networks focus on different image regions, enhancing segmentation.

Network achieves comparable or better accuracy than existing approaches.

Abstract

A fundus image usually contains the optic disc, pathologies and other structures in addition to vessels to be segmented. This study proposes a deep network for vessel segmentation, whose architecture is inspired by inception modules. The network contains three sub-networks, each with a different filter size, which are connected in the last layer of the proposed network. According to experiments conducted in the DRIVE and IOSTAR, the performance of our network is found to be better than or comparable to that of the previous methods. We also observe that the sub-networks pay attention to different parts of an input image when producing an output map in the last layer of the proposed network; though, training of the proposed network is not constrained for this purpose.