Hierarchical visual prompt disentanglement for continual rare disease diagnosis.
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. 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.
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. 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.
What the study was
- Study design
- Observational or experimental study
- Category
- Genomics/Precision Medicine
- Maturity
- Exploratory
- Journal
- Medical image analysis
Why it surfaced
Retained as a 8/10 high-priority candidate for Rare diseases with high unmet need; PubMed metadata and abstract were assessed conservatively.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.