Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer
Jakob Nikolas Kather, Alexander T. Pearson, Niels Halama et al. · Nature Medicine · 2019
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. A deep residual learning framework identifies microsatellite instability in histology slides from patients with cancer and can be used to guide immunotherapy.
Cited by 1,442 works. doi:10.1038/s41591-019-0462-y
Authors
- Jakob Nikolas Kather
- Alexander T. Pearson
- Niels Halama
- Dirk Jäger
- Jeremias Krause
- Sven Heiko Loosen
- Alexander Marx
- Peter Boor
- Frank Tacke
- Ulf P. Neumann
- Heike Irmgard Grabsch
- Takaki Yoshikawa
- Hermann Brenner
- Jenny C. Chang-Claude
- Michael Hoffmeister
- Christian Trautwein
- Tom Luedde
References
- Advances in neural information processing systems 7
- PD-1 Blockade in Tumors with Mismatch-Repair Deficiency
- Comprehensive molecular characterization of human colon and rectal cancer
- Integrated genomic characterization of endometrial carcinoma
- Mismatch repair deficiency predicts response of solid tumors to PD-1 blockade
- Comprehensive molecular characterization of gastric adenocarcinoma
- Bootstrap confidence intervals
- Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning
- 2012 IEEE Conference on Computer Vision and Pattern Recognition
- Comprehensive Characterization of Cancer Driver Genes and Mutations