MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI Classification

TL;DR

This paper presents MGPATH, a novel vision-language model with multi-granular prompt learning designed for few-shot whole slide image classification, effectively capturing detailed and contextual features to improve accuracy in pathology analysis.

Contribution

The paper introduces a multi-granular attention mechanism and a contrastive learning framework to adapt large vision-language models for few-shot pathology classification, enhancing feature interaction and robustness.

Findings

Outperforms recent competitors on multiple pathology datasets.

Improves recognition of complex patterns across sub-regions.

Enhances model robustness with optimal transport-based distance.

Abstract

Whole slide pathology image classification presents challenges due to gigapixel image sizes and limited annotation labels, hindering model generalization. This paper introduces a prompt learning method to adapt large vision-language models for few-shot pathology classification. We first extend the Prov-GigaPath vision foundation model, pre-trained on 1.3 billion pathology image tiles, into a vision-language model by adding adaptors and aligning it with medical text encoders via contrastive learning on 923K image-text pairs. The model is then used to extract visual features and text embeddings from few-shot annotations and fine-tunes with learnable prompt embeddings. Unlike prior methods that combine prompts with frozen features using prefix embeddings or self-attention, we propose multi-granular attention that compares interactions between learnable prompts with individual image patches and groups of them. This approach improves the model's ability to capture both fine-grained details and broader context, enhancing its recognition of complex patterns across sub-regions. To further improve accuracy, we leverage (unbalanced) optimal transport-based visual-text distance to secure model robustness by mitigating perturbations that might occur during the data augmentation process. Empirical experiments on lung, kidney, and breast pathology modalities validate the effectiveness of our approach; thereby, we surpass several of the latest competitors and consistently improve performance across diverse architectures, including CLIP, PLIP, and Prov-GigaPath integrated PLIP.