All You Need is Color: Image based Spatial Gene Expression Prediction using Neural Stain Learning

TL;DR

This paper introduces Neural Stain Learning, a novel stain-aware machine learning method that predicts spatial gene expression from routine histology images by modeling stain absorption, outperforming existing models with minimal parameters.

Contribution

The paper presents a new stain-aware approach that explicitly models stain absorption characteristics for gene expression prediction, using an end-to-end trainable model with only 11 parameters.

Findings

Outperforms classical regression and deep learning methods.

Shows higher correlation with true gene expression values.

Requires only 11 trainable parameters.

Abstract

"Is it possible to predict expression levels of different genes at a given spatial location in the routine histology image of a tumor section by modeling its stain absorption characteristics?" In this work, we propose a "stain-aware" machine learning approach for prediction of spatial transcriptomic gene expression profiles using digital pathology image of a routine Hematoxylin & Eosin (H&E) histology section. Unlike recent deep learning methods which are used for gene expression prediction, our proposed approach termed Neural Stain Learning (NSL) explicitly models the association of stain absorption characteristics of the tissue with gene expression patterns in spatial transcriptomics by learning a problem-specific stain deconvolution matrix in an end-to-end manner. The proposed method with only 11 trainable weight parameters outperforms both classical regression models with cellular composition and morphological features as well as deep learning methods. We have found that the gene expression predictions from the proposed approach show higher correlations with true expression values obtained through sequencing for a larger set of genes in comparison to other approaches.