Authors
Yang Hu, Yuanyuan Chen, Qingjie Zeng, Yong Xia
Published in
Medical image analysis. Volume 116. Pages 104355. Oct 17, 2026. Epub Oct 17, 2026.
Abstract
The automatic diagnosis of rare diseases via few-shot class-incremental learning (FSCIL) is critically hindered by severe data scarcity and the prevailing treatment of disease labels as a flat, unstructured space. This oversimplification neglects the rich taxonomic structures inherent in medical ontologies, leading to poor generalization on fine-grained subtypes. To bridge this gap, we propose Hierarchical Visual Prompt Disentanglement (HVPD), a hierarchy-guided framework for continual rare disease diagnosis. Unlike methods that use textual cues for flat semantic alignment, HVPD uses superclass and subclass category names to elicit visual-attribute semantics from a medical large language model (LLM) and converts the LLM's pre-decoding representations into hierarchical semantic anchors that guide image-conditioned visual prompt generation. We design a hierarchy-aware disentanglement mechanism that synthesizes instance-adaptive visual prompts while reducing the overlap between superclass-common patterns and subclass-specific diagnostic cues through an orthogonality-based cross-level constraint. This design alleviates the stability-plasticity dilemma by injecting structured medical priors into the visual feature space. Extensive experiments on the SD-198 (dermatology) and RFMiD (ophthalmology) datasets demonstrate that HVPD consistently improves over existing FSCIL approaches, delivering stronger fine-grained discrimination and knowledge retention under extreme few-shot regimes.
PMID:
42893626
Bibliographic data and abstract were imported from PubMed on 19 Oct 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 10
- Comments 0