Learning with less supervision: A survey of label-efficient learning for medical image analysis

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.