Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement

TL;DR

This paper introduces CATE, a novel method that enhances pathology foundation models for specific tasks by integrating concept-guided modules, leading to improved performance, interpretability, and generalizability in WSI analysis.

Contribution

The paper proposes a new adaptable paradigm, CATE, that dynamically calibrates foundation model features for specific pathology tasks using concept-guided modules.

Findings

CATE significantly improves model performance on public WSI datasets.

CATE enhances the interpretability of pathology models through visualization.

The method demonstrates strong generalizability across different cancer types.

Abstract

Whole slide image (WSI) analysis is gaining prominence within the medical imaging field. Recent advances in pathology foundation models have shown the potential to extract powerful feature representations from WSIs for downstream tasks. However, these foundation models are usually designed for general-purpose pathology image analysis and may not be optimal for specific downstream tasks or cancer types. In this work, we present Concept Anchor-guided Task-specific Feature Enhancement (CATE), an adaptable paradigm that can boost the expressivity and discriminativeness of pathology foundation models for specific downstream tasks. Based on a set of task-specific concepts derived from the pathology vision-language model with expert-designed prompts, we introduce two interconnected modules to dynamically calibrate the generic image features extracted by foundation models for certain tasks or cancer types. Specifically, we design a Concept-guided Information Bottleneck module to enhance task-relevant characteristics by maximizing the mutual information between image features and concept anchors while suppressing superfluous information. Moreover, a Concept-Feature Interference module is proposed to utilize the similarity between calibrated features and concept anchors to further generate discriminative task-specific features. The extensive experiments on public WSI datasets demonstrate that CATE significantly enhances the performance and generalizability of MIL models. Additionally, heatmap and umap visualization results also reveal the effectiveness and interpretability of CATE. The source code is available at https://github.com/HKU-MedAI/CATE.