biostudies-literatureKather JNNIDCR NIH HHSEuropean Research CouncilNCI NIH HHS789-799https://www.ebi.ac.uk/biostudies/studies/S-EPMC7610412biostudies-literatureUnknown1(8)Molecular alterations in cancer can cause phenotypic changes in tumor cells and their micro-environment. Routine histopathology tissue slides - which are ubiquitously available - can reflect such morphological changes. Here, we show that deep learning can consistently infer a wide range of genetic mutations, molecular tumor subtypes, gene expression signatures and standard pathology biomarkers directly from routine histology. We developed, optimized, validated and publicly released a one-stop-shop workflow and applied it to tissue slides of more than 5000 patients across multiple solid tumors. Our findings show that a single deep learning algorithm can be trained to predict a wide range of molecular alterations from routine, paraffin-embedded histology slides stained with hematoxylin and eNature cancerPan-cancer image-based detection of clinically actionable genetic alterations.PMC7610412771083K08 DE026500208237P30 CA014599Kochanny SKather JNTrautwein CSpeirs VOrtiz-Bruchle NNSommer KAJPearson ATBuelow RDSrisuwananukorn AGrabsch HIKrause JLoeffler CLuedde TBankhead PHanby AMNiehues JMvan den Brandt PAEchle AJager DBoor PSchulte JJMuti HSBrenner HHeij LRCipriani NAKooreman LFSPatnaik AHoffmeister MfalsePan-cancer image-based detection of clinically actionable genetic alterations.Molecular alterations in cancer can cause phenotypic changes in tumor cells and their micro-environment. Routine histopathology tissue slides - which are ubiquitously available - can reflect such morphological changes. Here, we show that deep learning can consistently infer a wide range of genetic mutations, molecular tumor subtypes, gene expression signatures and standard pathology biomarkers directly from routine histology. We developed, optimized, validated and publicly released a one-stop-shop workflow and applied it to tissue slides of more than 5000 patients across multiple solid tumors. Our findings show that a single deep learning algorithm can be trained to predict a wide range of molecular alterations from routine, paraffin-embedded histology slides stained with hematoxylin and e2020-01-01T00:00:00Z2020 Aug2026-06-02T18:32:49.806Z2025-04-06T18:04:44.579ZS-EPMC76104123376365110.1038/s43018-020-0087-6