Multi-point attention-based semi-supervised learning for diabetic retinopathy classification. (February 2023)

• Record Type: Journal Article
• Authors: Zhang, Chenrui; Chen, Ping; Lei, Tao
• Is Part Of: Biomedical signal processing and control. Volume 80:Part 2(2023)
• Publication Date: 2023-02
• Subjects: Diabetic retinopathy classification -- Multi-point attention -- Semi-supervised learning -- Self supervision -- Retinal image classification; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104412
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: In recent years, the severity classification of some well-known diseases has gradually become a focus of researchers, especially diabetic retinopathy (DR) recognition caused by diabetes. Existing diagnostic methods usually require many annotated fundus images for training. However, in practical situations, the high time and economic cost of annotating images make it unaffordable for many researchers. In this paper, we design a semi-supervised learning framework to explore the associations between unlabeled data, with the help of a small number of labeled samples, for accurate fundus image classification of DR. Through the analysis of semi-supervised tasks, it can be observed that: (1) an attention mechanism that fits the data can improve the network's potential to extract critical features; (2) unlabeled data is as potentially valuable as labeled ones, and the association between these unknown samples can further improve the model's performance. Therefore, we propose a Multi-point Attention-based Semi-supervised Learning (MASL) framework that efficiently utilizes the massive unlabeled data for accurate DR classification. Specifically, we propose a multi-point attention mechanism that enables the model to extract subtle features from multiple perspectives of fundus images and discard invalid regions. In addition, we design a new self-supervision mechanism to force the model to perform mandatory similarity mining on unknown samples, maximizing the potential of squeezing unlabeled data based on the confidence of the selected unannotated samples. Sufficient experimental results demonstrate that our MASL method significantly outperforms other methods on two public datasets.