Suppressing label noise in medical image classification using mixup attention and self-supervised learning

Gao，Mengdi1,2; Jiang，Hongyang3,4,5; Hu，Yan3,4; Ren，Qiushi6; Xie，Zhaoheng7; Liu，Jiang3,4

2024-05-21

10.1088/1361-6560/ad4083

Physics in Medicine and Biology   影响因子和分区

0031-9155

1361-6560

Deep neural networks (DNNs) have been widely applied in medical image classification and achieve remarkable classification performance. These achievements heavily depend on large-scale accurately annotated training data. However, label noise is inevitably introduced in the medical image annotation, as the labeling process heavily relies on the expertise and experience of annotators. Meanwhile, DNNs suffer from overfitting noisy labels, degrading the performance of models. Therefore, in this work, we innovatively devise a noise-robust training approach to mitigate the adverse effects of noisy labels in medical image classification. Specifically, we incorporate contrastive learning and intra-group mixup attention strategies into vanilla supervised learning. The contrastive learning for feature extractor helps to enhance visual representation of DNNs. The intra-group mixup attention module constructs groups and assigns self-attention weights for group-wise samples, and subsequently interpolates massive noisy-suppressed samples through weighted mixup operation. We conduct comparative experiments on both synthetic and real-world noisy medical datasets under various noise levels. Rigorous experiments validate that our noise-robust method with contrastive learning and mixup attention can effectively handle with label noise, and is superior to state-of-the-art methods. An ablation study also shows that both components contribute to boost model performance. The proposed method demonstrates its capability of curb label noise and has certain potential toward real-world clinic applications.

deep learning medical imaging mixup attention noisy label self-supervised learning

SCI ; EI

英语

其他

MOLECULAR BIOLOGY & GENETICS

2-s2.0-85193094655

Scopus

1.College of Chemistry and Life Science,Beijing University of Technology,Beijing,China
2.Beijing International Science and Technology Cooperation Base for Intelligent Physiological Measurement and Clinical Transformation,Beijing,China
3.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
4.Research Institute of Trustworthy Autonomous Systems,Southern University of Science and Technology,Shenzhen,518055,China
5.Department of Ophthalmology and Visual Sciences,The Chinese University of Hong Kong,Hong Kong,Hong Kong
6.Department of Biomedical Engineering,College of Future Technology,Peking University,Beijing,100871,China
7.Institute of Medical Technology,Peking University Health Science Center,Peking University,Beijing,100191,China

Gao，Mengdi,Jiang，Hongyang,Hu，Yan,et al. Suppressing label noise in medical image classification using mixup attention and self-supervised learning[J]. Physics in Medicine and Biology,2024,69(10).

Gao，Mengdi,Jiang，Hongyang,Hu，Yan,Ren，Qiushi,Xie，Zhaoheng,&Liu，Jiang.(2024).Suppressing label noise in medical image classification using mixup attention and self-supervised learning.Physics in Medicine and Biology,69(10).

Gao，Mengdi,et al."Suppressing label noise in medical image classification using mixup attention and self-supervised learning".Physics in Medicine and Biology 69.10(2024).