Collaborative learning of weakly-supervised domain adaptation for diabetic retinopathy grading on retinal images

• Published in: Computers in biology and medicine 2022-05, Vol.144, p.105341-105341, Article 105341
• Main Authors: Cao, Peng, Hou, Qingshan, Song, Ruoxian, Wang, Haonan, Zaiane, Osmar
• Format: Article
• Language: English
• Subjects: Adaptation; Algorithms; Annotations; Classification; Collaborative learning; Computer-aided diagnosis; Datasets; Decision making; Deep learning; Diabetes; Diabetes Mellitus; Diabetic retinopathy; Diabetic Retinopathy - diagnostic imaging; Domain adaption; Domains; Hemorrhage; Humans; Interdisciplinary Placement; Interpretability; Learning; Medical diagnosis; Methods; Multi-instance learning; Neural networks; Retinal images; Retinopathy; Source code; Supervision; Training
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.105341

Early detection and treatment of diabetic retinopathy (DR) can significantly reduce the risk of vision loss in patients. In essence, we are faced with two challenges: (i) how to simultaneously achieve domain adaptation from the different domains and (ii) how to build an interpretable multi-instance learning (MIL) on the target domain in an end-to-end framework. In this paper, we address these issues and propose a unified weakly-supervised domain adaptation framework, which consists of three components: domain adaptation, instance progressive discriminator and multi-instance learning with attention. The method models the relationship between the patches and images in the target domain with a multi-instance learning scheme and an attention mechanism. Meanwhile, it incorporates all available information from both source and target domains for a jointly learning strategy. We validate the performance of the proposed framework for DR grading on the Messidor dataset and the large-scale Eyepacs dataset. The experimental results demonstrate that it achieves an average accuracy of 0.949 (95% CI 0.931–0.958)/0.764 (95% CI 0.755–0.772) and an average AUC value of 0.958 (95% CI 0.945–0.962)/0.749 (95% CI 0.732–0.761) for binary-class/multi-class classification tasks on the Messidor dataset. Moreover, the proposed method achieves an accuracy of 0.887 and a quadratic weighted kappa score value of 0.860 on the Eyepacs dataset, outperforming the state-of-the-art approaches. Comprehensive experiments confirm the effectiveness of the approach in terms of both grading performance and interpretability. The source code is available at https://github.com/HouQingshan/WAD-Net.