Parameter-efficient Prompt Tuning and Hierarchical Textual Guidance for Few-shot Whole Slide Image Classification

TL;DR

This paper introduces a parameter-efficient prompt tuning method and hierarchical textual guidance for few-shot whole slide image classification, improving accuracy and reducing computational costs.

Contribution

It proposes a novel prompt tuning approach that scales and shifts text encoder features, and a hierarchical textual guidance strategy leveraging WSI structure without hard instance filtering.

Findings

Achieves up to 13.8% accuracy improvement over state-of-the-art methods.

Reduces trainable parameters by up to 18.1%.

Enhances weakly-supervised tumor localization.

Abstract

Whole Slide Images (WSIs) are giga-pixel in scale and are typically partitioned into small instances in WSI classification pipelines for computational feasibility. However, obtaining extensive instance level annotations is costly, making few-shot weakly supervised WSI classification (FSWC) crucial for learning from limited slide-level labels. Recently, pre-trained vision-language models (VLMs) have been adopted in FSWC, yet they exhibit several limitations. Existing prompt tuning methods in FSWC substantially increase both the number of trainable parameters and inference overhead. Moreover, current methods discard instances with low alignment to text embeddings from VLMs, potentially leading to information loss. To address these challenges, we propose two key contributions. First, we introduce a new parameter efficient prompt tuning method by scaling and shifting features in text encoder, which significantly reduces the computational cost. Second, to leverage not only the pre-trained knowledge of VLMs, but also the inherent hierarchical structure of WSIs, we introduce a WSI representation learning approach with a soft hierarchical textual guidance strategy without utilizing hard instance filtering. Comprehensive evaluations on pathology datasets covering breast, lung, and ovarian cancer types demonstrate consistent improvements up-to 10.9%, 7.8%, and 13.8% respectively, over the state-of-the-art methods in FSWC. Our method reduces the number of trainable parameters by 18.1% on both breast and lung cancer datasets, and 5.8% on the ovarian cancer dataset, while also excelling at weakly-supervised tumor localization. Code at https://github.com/Jayanie/HIPSS.