Diabetic retinopathy identification based on multi-source-free domain adaptation

To address the challenges of data labeling difficulties, data privacy, and necessary large amount of labeled data for deep learning methods in diabetic retinopathy (DR) identification, the aim of this study is to develop a source-free domain adaptation (SFDA) method for efficient and effective DR id...

Full description

Saved in:
Bibliographic Details
Published in:International journal of ophthalmology 2024-07, Vol.17 (7), p.1193-1204
Main Authors: Zhang, Guang-Hua, Zhuo, Guang-Ping, Zhang, Zhao-Xia, Sun, Bin, Yang, Wei-Hua, Zhang, Shao-Chong
Format: Article
Language:English
Subjects:
diabetic retinopathy
domain adaptation
Intelligent Ophthalmology
multisource-free
pseudo-label generation
softmax-consistence minimization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To address the challenges of data labeling difficulties, data privacy, and necessary large amount of labeled data for deep learning methods in diabetic retinopathy (DR) identification, the aim of this study is to develop a source-free domain adaptation (SFDA) method for efficient and effective DR identification from unlabeled data. A multi-SFDA method was proposed for DR identification. This method integrates multiple source models, which are trained from the same source domain, to generate synthetic pseudo labels for the unlabeled target domain. Besides, a softmax-consistence minimization term is utilized to minimize the intra-class distances between the source and target domains and maximize the inter-class distances. Validation is performed using three color fundus photograph datasets (APTOS2019, DDR, and EyePACS). The proposed model was evaluated and provided promising results with respectively 0.8917 and 0.9795 F1-scores on referable and normal/abnormal DR identification tasks. It demonstrated effective DR identification through minimizing intra-class distances and maximizing inter-class distances between source and target domains. The multi-SFDA method provides an effective approach to overcome the challenges in DR identification. The method not only addresses difficulties in data labeling and privacy issues, but also reduces the need for large amounts of labeled data required by deep learning methods, making it a practical tool for early detection and preservation of vision in diabetic patients.
ISSN:2222-3959
2227-4898
DOI:10.18240/ijo.2024.07.03