REFUGE CHALLENGE 2018-Task 2:Deep Optic Disc and Cup Segmentation in Fundus Images Using U-Net and Multi-scale Feature Matching Networks

TL;DR

This paper presents a novel optic disc and cup segmentation method using U-Net with multi-scale feature matching, achieving improved accuracy in fundus image analysis for the REFUGE challenge 2018.

Contribution

It introduces a multi-scale feature matching network combined with U-Net for more accurate segmentation without increasing model complexity.

Findings

Achieved improved segmentation accuracy on REFUGE 2018 dataset.

Utilized multi-scale feature matching to enhance generator performance.

Integrated SSD for effective image cropping.

Abstract

In this paper, an optic disc and cup segmentation method is proposed using U-Net followed by a multi-scale feature matching network. The proposed method targets task 2 of the REFUGE challenge 2018. In order to solve the segmentation problem of task 2, we firstly crop the input image using single shot multibox detector (SSD). The cropped image is then passed to an encoder-decoder network with skip connections also known as generator. Afterwards, both the ground truth and generated images are fed to a convolution neural network (CNN) to extract their multi-level features. A dice loss function is then used to match the features of the two images by minimizing the error at each layer. The aggregation of error from each layer is back-propagated through the generator network to enforce it to generate a segmented image closer to the ground truth. The CNN network improves the performance of the generator network without increasing the complexity of the model.