Learning with less supervision: A survey of label-efficient learning for medical image analysis.
Authors
Affiliations (4)
Affiliations (4)
- Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon Hong Kong SAR, China.
- Department of Population Health Sciences, Weill Cornell Medicine, New York, NY, USA.
- Department of Biomedical Informatics, Harvard University, Cambridge, MA, USA.
- Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon Hong Kong SAR, China; Department of Chemical and Biological Engineering, The Hong Kong University of Science and Technology, Kowloon Hong Kong SAR, China; Division of Life Science, The Hong Kong University of Science and Technology, Hong Kong SAR, China; HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute, Futian Shenzhen, China; State Key Laboratory of Nervous System Disorders, The Hong Kong University of Science and Technology, Hong Kong SAR, China. Electronic address: [email protected].
Abstract
Deep learning has significantly advanced medical imaging analysis (MIA), achieving state-of-the-art performance across diverse clinical tasks. However, its success largely depends on large-scale, high-quality labeled datasets, which are costly and time-consuming to obtain due to the need for expert annotation. To mitigate this limitation, label-efficient deep learning methods have emerged to improve model performance under limited supervision by leveraging labeled, unlabeled, and weakly labeled data. In this survey, we systematically review relevant peer-reviewed studies as well as influential preprints and present a comprehensive taxonomy of label-efficient learning methods in MIA. These methods are categorized into four labeling paradigms: no label, insufficient label, inexact label, and label refinement. For each scenario, we analyze representative techniques across imaging modalities and clinical tasks, and highlight shared methodological principles as well as adaptations. Crucially, we emphasize how the advent of health foundation models (HFMs) has fundamentally transformed label-efficient learning in medical imaging. Finally, we discuss ongoing challenges and outline future research directions spanning the research-to-deployment continuum. By synthesizing recent advances and open questions, this survey aims to provide a unified perspective to guide the development and clinical translation of robust, label-efficient solutions for medical image analysis.