High-Resolution Spatial Transcriptomics from Histology Images using HisToSGE

TL;DR

HisToSGE is a deep learning method that leverages a large pathology image model to accurately predict high-resolution spatial gene expression profiles from histology images, improving spatial transcriptomics analysis.

Contribution

We introduce HisToSGE, a novel approach combining a Pathology Image Large Model with feature learning to enhance high-resolution gene expression prediction from histological images.

Findings

Outperforms five baseline methods in high-resolution gene expression prediction.

Excels in downstream tasks like spatial domain identification.

Validated on four spatial transcriptomics datasets.

Abstract

Spatial transcriptomics (ST) is a groundbreaking genomic technology that enables spatial localization analysis of gene expression within tissue sections. However, it is significantly limited by high costs and sparse spatial resolution. An alternative, more cost-effective strategy is to use deep learning methods to predict high-density gene expression profiles from histological images. However, existing methods struggle to capture rich image features effectively or rely on low-dimensional positional coordinates, making it difficult to accurately predict high-resolution gene expression profiles. To address these limitations, we developed HisToSGE, a method that employs a Pathology Image Large Model (PILM) to extract rich image features from histological images and utilizes a feature learning module to robustly generate high-resolution gene expression profiles. We evaluated HisToSGE on four ST datasets, comparing its performance with five state-of-the-art baseline methods. The results demonstrate that HisToSGE excels in generating high-resolution gene expression profiles and performing downstream tasks such as spatial domain identification. All code and public datasets used in this paper are available at https://github.com/wenwenmin/HisToSGE and https://zenodo.org/records/12792163.