English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Molecular phenotyping is central in cancer precision medicine, but remainscostly and standard methods only provide a tumour average profile. Microscopicmorphological patterns observable in histopathology sections from tumours aredetermined by the underlying molecular phenotype and associated with clinicalfactors. The relationship between morphology and molecular phenotype has apotential to be exploited for prediction of the molecular phenotype from themorphology visible in histopathology images.  We report the first transcriptome-wide Expression-MOrphology (EMO) analysisin breast cancer, where gene-specific models were optimised and validated forprediction of mRNA expression both as a tumour average and in spatiallyresolved manner. Individual deep convolutional neural networks (CNNs) wereoptimised to predict the expression of 17,695 genes from hematoxylin and eosin(HE) stained whole slide images (WSIs). Predictions for 9,334 (52.75%) geneswere significantly associated with RNA-sequencing estimates (FDR adjustedp-value < 0.05). 1,011 of the genes were brought forward for validation, with876 (87%) and 908 (90%) successfully replicated in internal and external testdata, respectively. Predicted spatial intra-tumour variabilities in expressionwere validated in 76 genes, out of which 59 (77.6%) had a significantassociation (FDR adjusted p-value < 0.05) with spatial transcriptomicsestimates. These results suggest that the proposed methodology can be appliedto predict both tumour average gene expression and intra-tumour spatialexpression directly from morphology, thus providing a scalable approach tocharacterise intra-tumour heterogeneity.

Predicting molecular phenotypes from histopathology images: a transcriptome-wide expression-morphology analysis in breast cancer