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

352 Citations (Web of Science)

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-+
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-y

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-+. 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",

year = "2019",

month = jul,

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

language = "English",

volume = "25",

pages = "1054--+",

journal = "Nature Medicine",

issn = "1078-8956",

publisher = "Nature Publishing Group",

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-+. 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

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

VL - 25

SP - 1054-+

JO - Nature Medicine

JF - Nature Medicine

SN - 1078-8956

IS - 7

ER -