Pan-cancer image-based detection of clinically actionable genetic alterations

Jakob Nikolas Kather ,Hannah Sophie Muti ,Nicole A Cipriani ,Jeremias Krause ,Hermann Brenner ,Nadina Ortiz-Brüchle ,Jan Moritz Niehues ,Kai Sommer ,Andrew M Hanby ,Jefree J Schulte ,Sara Kochanny ,Andrew Srisuwananukorn ,Piet A Van Den Brandt ,Amelie Echle ,Loes Kooreman ,Heike Grabsch ,Christian Trautwein ,Dirk Jäger ,Michael Hoffmeister ,Akash Patnaik ,Alexander T Pearson ,Peter Boor ,Chiara Maria Lavinia Loeffler ,Valerie Speirs ,Lara Heij ,Peter Bankhead ,Roman D Buelow ,Tom Luedde

doi:10.1038/s43018-020-0087-6

Abstract

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 eosin. These predictions generalize to other populations and are spatially resolved. Our method can be implemented on mobile hardware, potentially enabling point-of-care diagnostics for personalized cancer treatment. More generally, this approach could elucidate and quantify genotype-phenotype links in cancer.

Highlights

Precision treatment of cancer relies on detection of genetic alterations which are diagnosed by molecular biology assays.[1]
We hypothesized that deep learning can infer molecular alterations directly from routine histology images across multiple common solid tumor types
We found that our method could detect TCGA molecular subtypes[37] with up to area under the ROC curve (AUROC) 0.74 in lung adenocarcinoma (Fig. 4e), pan-gastrointestinal subtypes[36] with up to AUROC 0.76 in colorectal cancer (Fig. 4f) and PAM50 subtypes with up to AUROC 0.78 in breast cancer (Fig. 4g), among other molecular subtypes

Summary

Introduction

Precision treatment of cancer relies on detection of genetic alterations which are diagnosed by molecular biology assays.[1]. In most tumor types, routine testing includes only a handful of alterations, such as KRAS, NRAS, BRAF mutations and microsatellite instability (MSI) in colorectal cancer.[3] While new studies identify more and more molecular features of potential clinical relevance, current diagnostic workflows are not designed to incorporate an exponentially rising load of tests. In colorectal cancer, previous studies have identified consensus molecular subtypes (CMS)[4] as a candidate biomarker, but sequencing costs and method complexity preclude widespread testing in clinical routine and clinical trials.[5] there is a growing need to identify new, inexpensive and scalable biomarkers in medical oncology

Objectives

Methods

Results

Conclusion