ODFormer: Semantic Fundus Image Segmentation Using Transformer for Optic Nerve Head Detection

TL;DR

This paper introduces ODFormer, a transformer-based network for optic nerve head detection in fundus images, along with a new dataset and benchmark to improve generalizability across diverse datasets and camera types.

Contribution

The paper presents a novel transformer-based network, ODFormer, a large-scale multi-camera dataset TongjiU-DROD, and a comprehensive benchmark for ONH detection, addressing dataset discrepancy issues.

Findings

ODFormer outperforms existing models in accuracy and generalizability.

The TongjiU-DROD dataset enhances diversity in fundus imaging data.

The benchmark facilitates evaluation across multiple datasets and camera types.

Abstract

Optic nerve head (ONH) detection has been a crucial area of study in ophthalmology for years. However, the significant discrepancy between fundus image datasets, each generated using a single type of fundus camera, poses challenges to the generalizability of ONH detection approaches developed based on semantic segmentation networks. Despite the numerous recent advancements in general-purpose semantic segmentation methods using convolutional neural networks (CNNs) and Transformers, there is currently a lack of benchmarks for these state-of-the-art (SoTA) networks specifically trained for ONH detection. Therefore, in this article, we make contributions from three key aspects: network design, the publication of a dataset, and the establishment of a comprehensive benchmark. Our newly developed ONH detection network, referred to as ODFormer, is based upon the Swin Transformer architecture and incorporates two novel components: a multi-scale context aggregator and a lightweight bidirectional feature recalibrator. Our published large-scale dataset, known as TongjiU-DROD, provides multi-resolution fundus images for each participant, captured using two distinct types of cameras. Our established benchmark involves three datasets: DRIONS-DB, DRISHTI-GS1, and TongjiU-DROD, created by researchers from different countries and containing fundus images captured from participants of diverse races and ages. Extensive experimental results demonstrate that our proposed ODFormer outperforms other state-of-the-art (SoTA) networks in terms of performance and generalizability. Our dataset and source code are publicly available at mias.group/ODFormer.