Towards a text-based quantitative and explainable histopathology image analysis

TL;DR

This paper introduces TQx, a novel approach using pre-trained vision-language models for quantitative and explainable analysis of histopathology images through image-to-text retrieval, enabling effective clustering and classification.

Contribution

The paper presents TQx, a new method that leverages pre-trained vision-language models for direct, text-based quantification and analysis of histopathology images, enhancing interpretability.

Findings

TQx achieves comparable performance to visual models in clustering tasks.

TQx enables explainable analysis via text-based feature embeddings.

The method effectively quantifies histopathology images using image-to-text retrieval.

Abstract

Recently, vision-language pre-trained models have emerged in computational pathology. Previous works generally focused on the alignment of image-text pairs via the contrastive pre-training paradigm. Such pre-trained models have been applied to pathology image classification in zero-shot learning or transfer learning fashion. Herein, we hypothesize that the pre-trained vision-language models can be utilized for quantitative histopathology image analysis through a simple image-to-text retrieval. To this end, we propose a Text-based Quantitative and Explainable histopathology image analysis, which we call TQx. Given a set of histopathology images, we adopt a pre-trained vision-language model to retrieve a word-of-interest pool. The retrieved words are then used to quantify the histopathology images and generate understandable feature embeddings due to the direct mapping to the text description. To evaluate the proposed method, the text-based embeddings of four histopathology image datasets are utilized to perform clustering and classification tasks. The results demonstrate that TQx is able to quantify and analyze histopathology images that are comparable to the prevalent visual models in computational pathology.