Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer

Jakob Nikolas Kather; Alexander T. Pearson; Niels Halama; Dirk Jaeger; Jeremias Krause; Sven H. Loosen; Alexander Marx; Peter Boor; Frank Tacke; Ulf Peter Neumann; Heike I. Grabsch; Takaki Yoshikawa; Hermann Brenner; Jenny Chang-Claude; Michael Hoffmeister; Christian Trautwein; Tom Luedde

doi:10.1038/s41591-019-0462-y

Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer

Jakob Nikolas Kather^*
, Alexander T. Pearson
, Niels Halama
, Dirk Jaeger
, Jeremias Krause
, Sven H. Loosen
, Alexander Marx
, Peter Boor
, Frank Tacke
, Ulf Peter Neumann
, Heike I. Grabsch
, Takaki Yoshikawa
, Hermann Brenner
, Jenny Chang-Claude
, Michael Hoffmeister
, Christian Trautwein
, Tom Luedde^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Microsatellite instability determines whether patients with gastrointestinal cancer respond exceptionally well to immunotherapy. However, in clinical practice, not every patient is tested for MSI, because this requires additional genetic or immunohistochemical tests. Here we show that deep residual learning can predict MSI directly from H&E histology, which is ubiquitously available. This approach has the potential to provide immunotherapy to a much broader subset of patients with gastrointestinal cancer.

Original language	English
Pages (from-to)	1054-1056
Number of pages	8
Journal	Nature Medicine
Volume	25
Issue number	7
DOIs	https://doi.org/10.1038/s41591-019-0462-y
Publication status	Published - Jul 2019

Keywords

COMPREHENSIVE MOLECULAR CHARACTERIZATION
GASTRIC-CANCER
TUMORS

Access to Document

10.1038/s41591-019-0462-yLicence: CC BY

Cite this

Kather, J. N., Pearson, A. T., Halama, N., Jaeger, D., Krause, J., Loosen, S. H., Marx, A., Boor, P., Tacke, F., Neumann, U. P., Grabsch, H. I., Yoshikawa, T., Brenner, H., Chang-Claude, J., Hoffmeister, M., Trautwein, C., & Luedde, T. (2019). Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nature Medicine, 25(7), 1054-1056. https://doi.org/10.1038/s41591-019-0462-y

@article{a9ff33c32fa34da18a76e205f9803b99,

title = "Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer",

abstract = "Microsatellite instability determines whether patients with gastrointestinal cancer respond exceptionally well to immunotherapy. However, in clinical practice, not every patient is tested for MSI, because this requires additional genetic or immunohistochemical tests. Here we show that deep residual learning can predict MSI directly from H\&E histology, which is ubiquitously available. This approach has the potential to provide immunotherapy to a much broader subset of patients with gastrointestinal cancer.",

keywords = "COMPREHENSIVE MOLECULAR CHARACTERIZATION, GASTRIC-CANCER, TUMORS",

author = "Kather, \{Jakob Nikolas\} and Pearson, \{Alexander T.\} and Niels Halama and Dirk Jaeger and Jeremias Krause and Loosen, \{Sven H.\} and Alexander Marx and Peter Boor and Frank Tacke and Neumann, \{Ulf Peter\} and Grabsch, \{Heike I.\} and Takaki Yoshikawa and Hermann Brenner and Jenny Chang-Claude and Michael Hoffmeister and Christian Trautwein and Tom Luedde",

note = "Funding Information: The results are in part based on data generated by the TCGA Research Network (http://cancergenome.nih.gov/). J.N.K. was funded by RWTH University Aachen (START 2018-691906). A.T.P. was funded by NIH/NIDCR (K08-DE026500). A.M. was funded by the German Federal Ministry of Education and Research (BMBF) (M2oBITE/13GW0091E). The DACHS study was funded by the Interdisciplinary Research Program of the National Center for Tumor Diseases (NCT), Germany and German Research Council DFG (BR 1704/6-1, BR 1704/6-3, BR 1704/6-4, BR 1704/17-1, CH 117/1-1 and HO 5117/2-1), BMBF (01ER0814, 01ER0815, 01ER1505A and 01ER1505B). P.B. was funded by the DFG (BO 3755/6-1, SFB-TRR57 and SFB-TRR219). T.L. was funded by Horizon 2020 through the European Research Council (ERC) Consolidator Grant PhaseControl (771083), Mildred-Scheel-Endowed Professorship from the German Cancer Aid, DFG (SFB-TRR57/P06 and LU 1360/3-1), Ernst-Jung-Foundation Hamburg and IZKF (Interdisciplinary Center of Clinical Research) at RWTH Aachen. Publisher Copyright: {\textcopyright} 2019, The Author(s), under exclusive licence to Springer Nature America, Inc.",

year = "2019",

month = jul,

doi = "10.1038/s41591-019-0462-y",

language = "English",

volume = "25",

pages = "1054--1056",

journal = "Nature Medicine",

issn = "1078-8956",

publisher = "Nature Research",

number = "7",

}

Kather, JN, Pearson, AT, Halama, N, Jaeger, D, Krause, J, Loosen, SH, Marx, A, Boor, P, Tacke, F, Neumann, UP , Grabsch, HI, Yoshikawa, T, Brenner, H, Chang-Claude, J, Hoffmeister, M, Trautwein, C & Luedde, T 2019, 'Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer', Nature Medicine, vol. 25, no. 7, pp. 1054-1056. https://doi.org/10.1038/s41591-019-0462-y

TY - JOUR

T1 - Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer

AU - Kather, Jakob Nikolas

AU - Pearson, Alexander T.

AU - Halama, Niels

AU - Jaeger, Dirk

AU - Krause, Jeremias

AU - Loosen, Sven H.

AU - Marx, Alexander

AU - Boor, Peter

AU - Tacke, Frank

AU - Neumann, Ulf Peter

AU - Grabsch, Heike I.

AU - Yoshikawa, Takaki

AU - Brenner, Hermann

AU - Chang-Claude, Jenny

AU - Hoffmeister, Michael

AU - Trautwein, Christian

AU - Luedde, Tom

N1 - Funding Information: The results are in part based on data generated by the TCGA Research Network (http://cancergenome.nih.gov/). J.N.K. was funded by RWTH University Aachen (START 2018-691906). A.T.P. was funded by NIH/NIDCR (K08-DE026500). A.M. was funded by the German Federal Ministry of Education and Research (BMBF) (M2oBITE/13GW0091E). The DACHS study was funded by the Interdisciplinary Research Program of the National Center for Tumor Diseases (NCT), Germany and German Research Council DFG (BR 1704/6-1, BR 1704/6-3, BR 1704/6-4, BR 1704/17-1, CH 117/1-1 and HO 5117/2-1), BMBF (01ER0814, 01ER0815, 01ER1505A and 01ER1505B). P.B. was funded by the DFG (BO 3755/6-1, SFB-TRR57 and SFB-TRR219). T.L. was funded by Horizon 2020 through the European Research Council (ERC) Consolidator Grant PhaseControl (771083), Mildred-Scheel-Endowed Professorship from the German Cancer Aid, DFG (SFB-TRR57/P06 and LU 1360/3-1), Ernst-Jung-Foundation Hamburg and IZKF (Interdisciplinary Center of Clinical Research) at RWTH Aachen. Publisher Copyright: © 2019, The Author(s), under exclusive licence to Springer Nature America, Inc.

PY - 2019/7

Y1 - 2019/7

N2 - Microsatellite instability determines whether patients with gastrointestinal cancer respond exceptionally well to immunotherapy. However, in clinical practice, not every patient is tested for MSI, because this requires additional genetic or immunohistochemical tests. Here we show that deep residual learning can predict MSI directly from H&E histology, which is ubiquitously available. This approach has the potential to provide immunotherapy to a much broader subset of patients with gastrointestinal cancer.

AB - Microsatellite instability determines whether patients with gastrointestinal cancer respond exceptionally well to immunotherapy. However, in clinical practice, not every patient is tested for MSI, because this requires additional genetic or immunohistochemical tests. Here we show that deep residual learning can predict MSI directly from H&E histology, which is ubiquitously available. This approach has the potential to provide immunotherapy to a much broader subset of patients with gastrointestinal cancer.

KW - COMPREHENSIVE MOLECULAR CHARACTERIZATION

KW - GASTRIC-CANCER

KW - TUMORS

U2 - 10.1038/s41591-019-0462-y

DO - 10.1038/s41591-019-0462-y

M3 - Article

C2 - 31160815

SN - 1078-8956

VL - 25

SP - 1054

EP - 1056

JO - Nature Medicine

JF - Nature Medicine

IS - 7

ER -

Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer

Abstract

Keywords

Access to Document

Fingerprint

Cite this