Spatial Transcriptomics Expression Prediction from Histopathology Based on Cross-Modal Mask Reconstruction and Contrastive Learning

TL;DR

This paper introduces a contrastive learning-based deep learning approach to predict spatial gene expression from histopathology images, improving accuracy and applicability in cancer analysis with limited data.

Contribution

The study presents a novel cross-modal mask reconstruction and contrastive learning method for spatial transcriptomics prediction from histopathology images, outperforming existing methods.

Findings

Improves PCC in predicting highly expressed, variable, and marker genes by over 6-11%.

Preserves gene-gene correlations in predictions.

Effective in cancer tissue localization based on biomarkers.

Abstract

Spatial transcriptomics is a technology that captures gene expression levels at different spatial locations, widely used in tumor microenvironment analysis and molecular profiling of histopathology, providing valuable insights into resolving gene expression and clinical diagnosis of cancer. Due to the high cost of data acquisition, large-scale spatial transcriptomics data remain challenging to obtain. In this study, we develop a contrastive learning-based deep learning method to predict spatially resolved gene expression from whole-slide images. Evaluation across six different disease datasets demonstrates that, compared to existing studies, our method improves Pearson Correlation Coefficient (PCC) in the prediction of highly expressed genes, highly variable genes, and marker genes by 6.27%, 6.11%, and 11.26% respectively. Further analysis indicates that our method preserves gene-gene correlations and applies to datasets with limited samples. Additionally, our method exhibits potential in cancer tissue localization based on biomarker expression.