Spatially Resolved Gene Expression Prediction from H&E Histology Images via Bi-modal Contrastive Learning

TL;DR

This paper introduces BLEEP, a bi-modal contrastive learning framework that predicts spatial gene expression from histology images, significantly reducing time and cost while providing molecular insights into tissue architecture.

Contribution

BLEEP is the first framework to generate spatially resolved gene expression profiles from H&E images using contrastive learning, improving accuracy over existing methods.

Findings

BLEEP outperforms existing gene expression prediction methods on liver tissue data.

The framework effectively imputes gene expression for image patches.

It offers a cost-effective alternative for molecular analysis in histology.

Abstract

Histology imaging is an important tool in medical diagnosis and research, enabling the examination of tissue structure and composition at the microscopic level. Understanding the underlying molecular mechanisms of tissue architecture is critical in uncovering disease mechanisms and developing effective treatments. Gene expression profiling provides insight into the molecular processes underlying tissue architecture, but the process can be time-consuming and expensive. We present BLEEP (Bi-modaL Embedding for Expression Prediction), a bi-modal embedding framework capable of generating spatially resolved gene expression profiles of whole-slide Hematoxylin and eosin (H&E) stained histology images. BLEEP uses contrastive learning to construct a low-dimensional joint embedding space from a reference dataset using paired image and expression profiles at micrometer resolution. With this approach, the gene expression of any query image patch can be imputed using the expression profiles from the reference dataset. We demonstrate BLEEP's effectiveness in gene expression prediction by benchmarking its performance on a human liver tissue dataset captured using the 10x Visium platform, where it achieves significant improvements over existing methods. Our results demonstrate the potential of BLEEP to provide insights into the molecular mechanisms underlying tissue architecture, with important implications in diagnosis and research of various diseases. The proposed approach can significantly reduce the time and cost associated with gene expression profiling, opening up new avenues for high-throughput analysis of histology images for both research and clinical applications.