Spatial Transcriptomics Inferred from Pathology Whole-Slide Images Links Tumor Heterogeneity to Survival in Breast and Lung Cancer

Abstract

<jats:title>A<jats:sc>bstract</jats:sc></jats:title><jats:p>Digital analysis of pathology whole-slide images is fast becoming a game changer in cancer diagnosis and treatment. Specifically, deep learning methods have shown great potential to support pathology analysis, with recent studies identifying molecular traits that were not previously recognized on pathology H&amp;E whole-slide images. Simultaneous to these developments, it is becoming increasingly evident that tumor heterogeneity is an important determinant of cancer prognosis and susceptibility to treatment, and should therefore play a role in the evolving practices of matching treatment protocols to patients. State of the art diagnostic procedures, however, do not provide scalable methods for characterizing and/or quantifying tumor heterogeneity, certainly not in a spatial context. In this paper, we present a scalable approach that accurately and automatically spatially resolves mRNA and miRNA expression levels on pathology whole-slide images. This is the first demonstration of this type of inference from H&amp;E images. We use this method to produce tumor molecular cartographies and to characterize certain aspects of tumor spatial transcriptomics. Specifically, we develop a heterogeneity index (HTI), derived from the molecular cartographies. Applying our methods to breast and lung cancer slides, we show a significant statistical link between heterogeneity and survival. Our results highlight the value of automated analysis of pathology whole slide images. Our methods potentially open a new approach to investigating tumor heterogeneity and other spatial molecular properties and their link to clinical characteristics, including treatment susceptibility and survival.</jats:p>

Exploring tissue architecture using spatial transcriptomics

“…Deep learning has also been used to predict cell type annotations from gene expression and histology, outperforming annotations predicted from either modality alone 149 . With the increase in transcriptomic data available for training, machine learning algorithms have also been used to predict gene expression from histopathology images 150,151 . Rather than relying on pre-defined morphological features, these algorithms improve their performance by decomposing the full image into "tiles".…”

Integration of deep learning-based image analysis and genomic data in cancer pathology: A systematic review

“…Integration of spatial transcriptomics data was mostly performed with small numbers of patients/slides [27e29] because of the novelty, required effort and cost of the method, as spatial omics require the analysis of several thousand spots per slide [47]. However, the advantage of this method is a high spatial molecular resolution of the tumour on patch-level [48]. Even with a small dataset [30,35], this technique may, therefore, be useful to resolve tumour heterogeneity.…”

Spatial omics: Navigating to the golden era of cancer research

“…In the clinical practice, spatial omics technology may pave the way for precision pathology. It is now possible to link the pathological images with spatial gene expression profile by using machine learning or deep learning algorithms 130,131 . These studies may enable the prediction of the transcriptomics profile based on existed H&E staining slides which may perform better than existed biomarkers.…”