Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction

TL;DR

This paper introduces the FiVE framework, which enhances whole slide image classification by leveraging fine-grained visual-semantic interactions and localized pathological descriptions, improving generalization and transferability across diverse tasks.

Contribution

The paper proposes a novel FiVE framework that uses fine-grained visual-semantic interaction and language-driven descriptions to improve WSI classification generalization.

Findings

Outperforms existing methods on TCGA Lung Cancer dataset with at least 9.19% higher accuracy.

Utilizes language models to extract detailed pathological descriptions from reports.

Sampling of visual instances improves training efficiency and robustness.

Abstract

Whole Slide Image (WSI) classification is often formulated as a Multiple Instance Learning (MIL) problem. Recently, Vision-Language Models (VLMs) have demonstrated remarkable performance in WSI classification. However, existing methods leverage coarse-grained pathogenetic descriptions for visual representation supervision, which are insufficient to capture the complex visual appearance of pathogenetic images, hindering the generalizability of models on diverse downstream tasks. Additionally, processing high-resolution WSIs can be computationally expensive. In this paper, we propose a novel "Fine-grained Visual-Semantic Interaction" (FiVE) framework for WSI classification. It is designed to enhance the model's generalizability by leveraging the interaction between localized visual patterns and fine-grained pathological semantics. Specifically, with meticulously designed queries, we start by utilizing a large language model to extract fine-grained pathological descriptions from various non-standardized raw reports. The output descriptions are then reconstructed into fine-grained labels used for training. By introducing a Task-specific Fine-grained Semantics (TFS) module, we enable prompts to capture crucial visual information in WSIs, which enhances representation learning and augments generalization capabilities significantly. Furthermore, given that pathological visual patterns are redundantly distributed across tissue slices, we sample a subset of visual instances during training. Our method demonstrates robust generalizability and strong transferability, dominantly outperforming the counterparts on the TCGA Lung Cancer dataset with at least 9.19% higher accuracy in few-shot experiments. The code is available at: https://github.com/ls1rius/WSI_FiVE.