Knowledge-enhanced Visual-Language Pretraining for Computational Pathology

TL;DR

This paper introduces a novel knowledge-enhanced visual-language pretraining method for computational pathology, leveraging a large structured pathology knowledge base to improve visual representation learning and downstream task performance.

Contribution

It creates the first comprehensive pathology knowledge base and integrates it into a pretraining framework to enhance visual representations in pathology analysis.

Findings

Significant improvements in cross-modal retrieval accuracy.

Effective zero-shot classification on pathology patches.

Enhanced zero-shot tumor subtyping on whole slide images.

Abstract

In this paper, we consider the problem of visual representation learning for computational pathology, by exploiting large-scale image-text pairs gathered from public resources, along with the domain-specific knowledge in pathology. Specifically, we make the following contributions: (i) We curate a pathology knowledge tree that consists of 50,470 informative attributes for 4,718 diseases requiring pathology diagnosis from 32 human tissues. To our knowledge, this is the first comprehensive structured pathology knowledge base; (ii) We develop a knowledge-enhanced visual-language pretraining approach, where we first project pathology-specific knowledge into latent embedding space via a language model, and use it to guide the visual representation learning; (iii) We conduct thorough experiments to validate the effectiveness of our proposed components, demonstrating significant performance improvement on various downstream tasks, including cross-modal retrieval, zero-shot classification on pathology patches, and zero-shot tumor subtyping on whole slide images (WSIs).