TY - JOUR
T1 - Pan-cancer image-based detection of clinically actionable genetic alterations
AU - Kather, Jakob Nikolas
AU - Heij, Lara R.
AU - Grabsch, Heike I.
AU - Loeffler, Chiara
AU - Echle, Amelie
AU - Muti, Hannah Sophie
AU - Krause, Jeremias
AU - Niehues, Jan M.
AU - Sommer, Kai A. J.
AU - Bankhead, Peter
AU - Kooreman, Loes F. S.
AU - Schulte, Jefree J.
AU - Cipriani, Nicole A.
AU - Buelow, Roman D.
AU - Boor, Peter
AU - Ortiz-Brüchle, Nadina
AU - Hanby, Andrew M.
AU - Speirs, Valerie
AU - Kochanny, Sara
AU - Patnaik, Akash
AU - Srisuwananukorn, Andrew
AU - Brenner, Hermann
AU - Hoffmeister, Michael
AU - van den Brandt, Piet A.
AU - Jäger, Dirk
AU - Trautwein, Christian
AU - Pearson, Alexander T.
AU - Luedde, Tom
N1 - Funding
The results are in part based upon data generated by the TCGA Research Network: http://cancergenome.nih.gov/. Our funding sources are as follows. J.N.K.: RWTH University Aachen (START 2018-691906). V.S.: Breast Cancer Now, P.Bo: DFG: (SFB/TRR57, SFB/TRR219, BO3755/3-1, and BO3755/6-1), the German Ministry of Education and Research (BMBF: STOP-FSGS-01GM1901A) and the German Ministry of Economic Affairs and Energy (BMWi: EMPAIA project). A.T.P.: NIH/NIDCR (#K08-DE026500), Institutional Research Grant (#IRG-16-222-56) from the American Cancer Society, Cancer Research Foundation Research Grant, and the University of Chicago Med470 icine Comprehensive Cancer Center Support Grant (#P30-CA14599). T.L.: Horizon 2020 through the European Research Council (ERC) Consolidator Grant PhaseControl (771083), a Mildred Scheel-Endowed Professorship from the German Cancer Aid (Deutsche Krebshilfe), the German Research Foundation (DFG) (SFB CRC1382/P01, SFB-TRR57/P06, LU 1360/3-1), the Ernst-Jung Foundation Hamburg and the IZKF (interdisciplinary center of clinical research) at RWTH Aachen.
Correction to: Nature Cancer https://doi.org/10.1038/s43018-020-0087-6, published online 27 July 2020. https://doi.org/10.1038/s43018-020-00149-6
PY - 2020/8
Y1 - 2020/8
N2 - Molecular alterations in malignant tumors can cause phenotypic changes in tumor cells and their microenvironment. Routine histopathology tissue slides – which are ubiquitously available for patients with solid tumors – 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 images of cancer. We developed, systematically optimized, validated and publicly released a one-stop-shop workflow and applied it to routine tissue slides of more than 5000 patients across a broad spectrum of common solid tumors including lung, colorectal, breast and gastric cancer. 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 yield spatially resolved predictions. Our method can be implemented on mobile hardware, potentially enabling point-of-care diagnostics for personalized cancer treatment. More generally, this approach can be used to elucidate and quantify genotype-phenotype links in cancer.
AB - Molecular alterations in malignant tumors can cause phenotypic changes in tumor cells and their microenvironment. Routine histopathology tissue slides – which are ubiquitously available for patients with solid tumors – 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 images of cancer. We developed, systematically optimized, validated and publicly released a one-stop-shop workflow and applied it to routine tissue slides of more than 5000 patients across a broad spectrum of common solid tumors including lung, colorectal, breast and gastric cancer. 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 yield spatially resolved predictions. Our method can be implemented on mobile hardware, potentially enabling point-of-care diagnostics for personalized cancer treatment. More generally, this approach can be used to elucidate and quantify genotype-phenotype links in cancer.
UR - https://doi.org/10.1038/s43018-020-00149-6
UR - http://www.scopus.com/inward/record.url?scp=85087510208&partnerID=8YFLogxK
U2 - 10.1101/833756
DO - 10.1101/833756
M3 - Article
C2 - 33763651
VL - 1
SP - 789
EP - 799
JO - Nature Cancer
JF - Nature Cancer
SN - 2662-1347
IS - 8
ER -