Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement
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.
Code (1)
Tasks
modelMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Free Lunch in Medical Image Foundation Model Pre-training via Randomized Synthesis and Disentanglement
Medical image foundation models (MIFMs) have demonstrated remarkable potential for a wide range of clinical tasks, yet their development is constrained by the scarcity, heterogeneity, and high cost of large-scale annotat…
Representation LearningThere are free lunches
No-Free-Lunch Theorems state that the performance of all algorithms is the same when averaged over all possible tasks. It has been argued that the necessary conditions for NFL are too restrictive to be found in practice.…
AllVisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
Foundation models have emerged as a promising approach in time series forecasting (TSF). Existing approaches either repurpose large language models (LLMs) or build large-scale time series datasets to develop TSF foundati…
Image ReconstructionTime SeriesTime Series ForecastingThe Butterfly Effect in Pathology: Exploring Security in Pathology Foundation Models
With the widespread adoption of pathology foundation models in both research and clinical decision support systems, exploring their security has become a critical concern. However, despite their growing impact, the vulne…
Adversarial RobustnessFree Lunch for Optimisation under the Universal Distribution
Function optimisation is a major challenge in computer science. The No Free Lunch theorems state that if all functions with the same histogram are assumed to be equally probable then no algorithm outperforms any other in…