Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image

TL;DR

This paper presents a novel deep learning ensemble network that directly screens for glaucoma from fundus images by integrating global and local features, outperforming existing methods that rely heavily on segmentation accuracy.

Contribution

Introduction of the Disc-aware Ensemble Network (DENet), a multi-stream deep learning model that combines global and local features for improved glaucoma screening from fundus images.

Findings

Outperforms state-of-the-art algorithms on two datasets

Effectively integrates global and local image features

Reduces reliance on segmentation accuracy

Abstract

Glaucoma is a chronic eye disease that leads to irreversible vision loss. Most of the existing automatic screening methods firstly segment the main structure, and subsequently calculate the clinical measurement for detection and screening of glaucoma. However, these measurement-based methods rely heavily on the segmentation accuracy, and ignore various visual features. In this paper, we introduce a deep learning technique to gain additional image-relevant information, and screen glaucoma from the fundus image directly. Specifically, a novel Disc-aware Ensemble Network (DENet) for automatic glaucoma screening is proposed, which integrates the deep hierarchical context of the global fundus image and the local optic disc region. Four deep streams on different levels and modules are respectively considered as global image stream, segmentation-guided network, local disc region stream, and disc polar transformation stream. Finally, the output probabilities of different streams are fused as the final screening result. The experiments on two glaucoma datasets (SCES and new SINDI datasets) show our method outperforms other state-of-the-art algorithms.