MSCPT: Few-shot Whole Slide Image Classification with Multi-scale and Context-focused Prompt Tuning

TL;DR

MSCPT introduces a novel multi-scale, context-aware prompt tuning approach leveraging vision-language models for effective few-shot whole slide image classification, addressing data scarcity and rare disease challenges.

Contribution

The paper proposes MSCPT, a multi-scale, context-focused prompt tuning method that fully utilizes VLMs' prior knowledge and instance aggregation for WSI classification in few-shot settings.

Findings

MSCPT outperforms existing methods on five datasets.

It effectively leverages multi-scale and contextual information.

The approach demonstrates strong interpretability and generalization.

Abstract

Multiple instance learning (MIL) has become a standard paradigm for the weakly supervised classification of whole slide images (WSIs). However, this paradigm relies on using a large number of labeled WSIs for training. The lack of training data and the presence of rare diseases pose significant challenges for these methods. Prompt tuning combined with pre-trained Vision-Language models (VLMs) is an effective solution to the Few-shot Weakly Supervised WSI Classification (FSWC) task. Nevertheless, applying prompt tuning methods designed for natural images to WSIs presents three significant challenges: 1) These methods fail to fully leverage the prior knowledge from the VLM's text modality; 2) They overlook the essential multi-scale and contextual information in WSIs, leading to suboptimal results; and 3) They lack exploration of instance aggregation methods. To address these problems, we propose a Multi-Scale and Context-focused Prompt Tuning (MSCPT) method for FSWC task. Specifically, MSCPT employs the frozen large language model to generate pathological visual language prior knowledge at multiple scales, guiding hierarchical prompt tuning. Additionally, we design a graph prompt tuning module to learn essential contextual information within WSI, and finally, a non-parametric cross-guided instance aggregation module has been introduced to derive the WSI-level features. Extensive experiments, visualizations, and interpretability analyses were conducted on five datasets and three downstream tasks using three VLMs, demonstrating the strong performance of our MSCPT. All codes have been made publicly accessible at https://github.com/Hanminghao/MSCPT.