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

By Jakob Nikolas Kather, A. Pearson, N. Halama, D. Jäger, Jeremias Krause, S. Loosen, A. Marx, P. Boor, F. Tacke, U. Neumann and 7 more. Nature Medicine, 2019

1,260 citations recorded by the source corpus.

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.

Subfields: Oncology, Pathology and Forensic Medicine, Surgery

View Paper: https://www.semanticscholar.org/paper/0ff8b16931a5fb1141a866e04941f8e9409e00e1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Oncology

In Pathology and Forensic Medicine

Anant Madabhushi

In Surgery

Pranav Rajpurkar

Citations in the corpus

Harnessing multimodal data integration to advance precision oncology (2021, background): “One notable multicentre example in colorectal cancer showed that H&E WSIs contain information predictive of microsatellite instability (MSI) status as a biomarker for response to ICB 34,35 .”
Algorithm fairness in artificial intelligence for medicine and healthcare (2023, background): “It could be used to predict biomarkers (such as microsatellite instability) that guide the use of immune-checkpoint inhibition therapy 166 , or of EGFR status to guide the selection of a tyrosine kinase inhibitor in the treatment of lung cancer 167 .”
Artificial intelligence in histopathology: enhancing cancer research and clinical oncology (2022, background): “In particular, AI was shown to predict MSI status from histology 57 in colorectal, gastric and endometrial cancer, which was subsequently validated in multiple larger follow-up studies 58,59,62,63,77–81 .”
From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment. (2023, background): “Besides tumor subtype, another goal is to predict the genetic characteristics of a tumor, such as microsatellite instability, 46 tumor mutational burden, 47 or whole-genome duplication.”
Identification of antimicrobial peptides from the human gut microbiome using deep learning (2022, background): “The recent surge in applying artificial intelligence approaches in bio-medical research has brought up many new opportunities, including image-processing-related tools for clinical diagnostics of eye 39 , lung 40 , cancer tissue pathologies 41 and antibiotics 19,42 .”
Clinical-grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning. (2020, methodology): “following 4 previous studies with the intent of retraining a previously described deep learning system.(16,17) First, we used the publicly available Cancer Genome Atlas (TCGA) (n 1⁄4 616”
AI in health and medicine (2022, background): “In the field of pathology, AI has made major strides in diagnosing cancers and providing new disease insights 28–33 , largely through the use of whole-slide imaging.”
Artificial Intelligence in Cancer Research and Precision Medicine (2021, methodology): “This method was applied to 1,600 TCGA tumors focused on gastric, colorectal, and endometrial cancers (40).”
A deep learning model to predict RNA-Seq expression of tumours from whole slide images (2020, positive): “…correlation above significance threshold (BH correction) d b c e –log(p-value) 0 2 4 6 8 10 80 20 40 60 80 100 60 WSI Transcriptomic representation Kather et al. 2019 Adapted from Kather et al. 2019 Adapted from Kather et al. 2019 40 20 0 FFPE slides: No. patients = 465 (No. slides = 483) No.”
AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020, positive): “Thesemethodshavebeenappliedto studiesoncancers,includingbreast[250],lung[252],andcol-orectal [253].”