Boosting Pathology Foundation Models via Few-shot Prompt-tuning for Rare Cancer Subtyping

TL;DR

This paper introduces PathPT, a novel framework that enhances rare cancer subtyping by leveraging vision-language models with spatially-aware visual aggregation and prompt tuning, significantly improving accuracy and interpretability in limited data scenarios.

Contribution

PathPT is the first to fully exploit vision-language foundation models for rare cancer subtyping through spatial aggregation and prompt tuning, converting weak supervision into fine-grained guidance.

Findings

PathPT outperforms existing methods across multiple datasets.

It improves localization of cancerous regions in WSIs.

PathPT shows robustness in few-shot learning settings.

Abstract

Rare cancers comprise 20-25% of all malignancies but face major diagnostic challenges due to limited expert availability-especially in pediatric oncology, where they represent over 70% of cases. While pathology vision-language (VL) foundation models show promising zero-shot capabilities for common cancer subtyping, their clinical performance for rare cancers remains limited. Existing multi-instance learning (MIL) methods rely only on visual features, overlooking cross-modal knowledge and compromising interpretability critical for rare cancer diagnosis. To address this limitation, we propose PathPT, a novel framework that fully exploits the potential of vision-language pathology foundation models through spatially-aware visual aggregation and task-specific prompt tuning. Unlike conventional MIL, PathPT converts WSI-level supervision into fine-grained tile-level guidance by leveraging the zero-shot capabilities of VL models, thereby preserving localization on cancerous regions and enabling cross-modal reasoning through prompts aligned with histopathological semantics. We benchmark PathPT on eight rare cancer datasets(four adult and four pediatric) spanning 56 subtypes and 2,910 WSIs, as well as three common cancer datasets, evaluating four state-of-the-art VL models and four MIL frameworks under three few-shot settings. Results show that PathPT consistently delivers superior performance, achieving substantial gains in subtyping accuracy and cancerous region grounding ability. This work advances AI-assisted diagnosis for rare cancers, offering a scalable solution for improving subtyping accuracy in settings with limited access to specialized expertise.