Deep learning for the detection of microsatellite instability from histology images in colorectal cancer: A systematic literature review

Microsatellite instability (MSI) or deficient mismatch repair (dMMR) is a clinically important genetic feature affecting 10–15% of colorectal cancer (CRC) patients. Patients with metastatic MSI/dMMR CRC are eligible for therapy with immune checkpoint inhibitors, making MSI/dMMR the most important im...

Full description

Saved in:
Bibliographic Details
Main Authors: Amelie Echle, Narmin Ghaffari Laleh, Peter L. Schrammen, Nicholas P. West, Christian Trautwein, Titus J. Brinker, Stephen B. Gruber, Roman D. Buelow, Peter Boor, Heike I. Grabsch, Philip Quirke, Jakob N. Kather
Format: Article
Language:English
Published: Elsevier 2021-12-01
Series:ImmunoInformatics
Online Access:http://www.sciencedirect.com/science/article/pii/S2667119021000082
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850073579509514240
author Amelie Echle
Narmin Ghaffari Laleh
Peter L. Schrammen
Nicholas P. West
Christian Trautwein
Titus J. Brinker
Stephen B. Gruber
Roman D. Buelow
Peter Boor
Heike I. Grabsch
Philip Quirke
Jakob N. Kather
author_facet Amelie Echle
Narmin Ghaffari Laleh
Peter L. Schrammen
Nicholas P. West
Christian Trautwein
Titus J. Brinker
Stephen B. Gruber
Roman D. Buelow
Peter Boor
Heike I. Grabsch
Philip Quirke
Jakob N. Kather
author_sort Amelie Echle
collection DOAJ
description Microsatellite instability (MSI) or deficient mismatch repair (dMMR) is a clinically important genetic feature affecting 10–15% of colorectal cancer (CRC) patients. Patients with metastatic MSI/dMMR CRC are eligible for therapy with immune checkpoint inhibitors, making MSI/dMMR the most important immuno-oncological biomarker in CRC. Gold standard tests for detection of MSI/dMMR in CRC are based on wet laboratory tests such as immunohistochemistry (IHC) or DNA extraction with subsequent polymerase chain reaction (PCR). However, since 2019, advances in Deep Learning (DL), an Artificial Intelligence (AI) technology, have enabled the prediction of MSI/dMMR directly from digitized routine haematoxylin and eosin (H&E) histopathology slides with high accuracy. In addition to the initial proof-of-concept publication in 2019, twelve subsequent studies have refined, improved, and further validated this approach. At this moment, MSI/dMMR prediction using Deep Learning has become a widely used benchmark task for academic studies in the field of computational pathology. Beyond academic use, this assay has attracted commercial interest from companies with the possibility of approval as a diagnostic device in the near future. In this review, we summarize and quantitatively compare the existing evidence on Deep-Learning-based detection of MSI/dMMR in CRC and discuss the need for further improvement and potential for integration into routine pathological workflows. Ultimately, this DL-based method could facilitate the identification of patients eligible for treatment with immune checkpoint inhibitors by pre-screening or replacement of current methods.
format Article
id doaj-art-ee9727f317444a1ca55efe1dcf4304e9
institution DOAJ
issn 2667-1190
language English
publishDate 2021-12-01
publisher Elsevier
record_format Article
series ImmunoInformatics
spelling doaj-art-ee9727f317444a1ca55efe1dcf4304e92025-08-20T02:46:47ZengElsevierImmunoInformatics2667-11902021-12-01310000810.1016/j.immuno.2021.100008Deep learning for the detection of microsatellite instability from histology images in colorectal cancer: A systematic literature reviewAmelie Echle0Narmin Ghaffari Laleh1Peter L. Schrammen2Nicholas P. West3Christian Trautwein4Titus J. Brinker5Stephen B. Gruber6Roman D. Buelow7Peter Boor8Heike I. Grabsch9Philip Quirke10Jakob N. Kather11Department of Medicine III, University Hospital RWTH Aachen, Pauwelsstr. 30, Aachen 52074, GermanyDepartment of Medicine III, University Hospital RWTH Aachen, Pauwelsstr. 30, Aachen 52074, GermanyDepartment of Medicine III, University Hospital RWTH Aachen, Pauwelsstr. 30, Aachen 52074, GermanyPathology & Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, United KingdomDepartment of Medicine III, University Hospital RWTH Aachen, Pauwelsstr. 30, Aachen 52074, GermanyDigital Biomarkers for Oncology Group, National Center for Tumor Diseases (NCT), German Cancer Research Center (DKFZ), Heidelberg, GermanyCenter for Precision Medicine and Department of Medical Oncology, City of Hope National Medical Center, Duarte, CA, United StatesInstitute of Pathology, University Hospital RWTH Aachen, Aachen, GermanyInstitute of Pathology, University Hospital RWTH Aachen, Aachen, GermanyPathology & Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, United Kingdom; Department of Pathology, GROW School for Oncology and Developmental Biology, Maastricht University Medical Center+, Maastricht, NetherlandsPathology & Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, United KingdomDepartment of Medicine III, University Hospital RWTH Aachen, Pauwelsstr. 30, Aachen 52074, Germany; Pathology & Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, United Kingdom; Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany; Corresponding author.Microsatellite instability (MSI) or deficient mismatch repair (dMMR) is a clinically important genetic feature affecting 10–15% of colorectal cancer (CRC) patients. Patients with metastatic MSI/dMMR CRC are eligible for therapy with immune checkpoint inhibitors, making MSI/dMMR the most important immuno-oncological biomarker in CRC. Gold standard tests for detection of MSI/dMMR in CRC are based on wet laboratory tests such as immunohistochemistry (IHC) or DNA extraction with subsequent polymerase chain reaction (PCR). However, since 2019, advances in Deep Learning (DL), an Artificial Intelligence (AI) technology, have enabled the prediction of MSI/dMMR directly from digitized routine haematoxylin and eosin (H&E) histopathology slides with high accuracy. In addition to the initial proof-of-concept publication in 2019, twelve subsequent studies have refined, improved, and further validated this approach. At this moment, MSI/dMMR prediction using Deep Learning has become a widely used benchmark task for academic studies in the field of computational pathology. Beyond academic use, this assay has attracted commercial interest from companies with the possibility of approval as a diagnostic device in the near future. In this review, we summarize and quantitatively compare the existing evidence on Deep-Learning-based detection of MSI/dMMR in CRC and discuss the need for further improvement and potential for integration into routine pathological workflows. Ultimately, this DL-based method could facilitate the identification of patients eligible for treatment with immune checkpoint inhibitors by pre-screening or replacement of current methods.http://www.sciencedirect.com/science/article/pii/S2667119021000082
spellingShingle Amelie Echle
Narmin Ghaffari Laleh
Peter L. Schrammen
Nicholas P. West
Christian Trautwein
Titus J. Brinker
Stephen B. Gruber
Roman D. Buelow
Peter Boor
Heike I. Grabsch
Philip Quirke
Jakob N. Kather
Deep learning for the detection of microsatellite instability from histology images in colorectal cancer: A systematic literature review
ImmunoInformatics
title Deep learning for the detection of microsatellite instability from histology images in colorectal cancer: A systematic literature review
title_full Deep learning for the detection of microsatellite instability from histology images in colorectal cancer: A systematic literature review
title_fullStr Deep learning for the detection of microsatellite instability from histology images in colorectal cancer: A systematic literature review
title_full_unstemmed Deep learning for the detection of microsatellite instability from histology images in colorectal cancer: A systematic literature review
title_short Deep learning for the detection of microsatellite instability from histology images in colorectal cancer: A systematic literature review
title_sort deep learning for the detection of microsatellite instability from histology images in colorectal cancer a systematic literature review
url http://www.sciencedirect.com/science/article/pii/S2667119021000082
work_keys_str_mv AT amelieechle deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview
AT narminghaffarilaleh deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview
AT peterlschrammen deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview
AT nicholaspwest deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview
AT christiantrautwein deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview
AT titusjbrinker deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview
AT stephenbgruber deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview
AT romandbuelow deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview
AT peterboor deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview
AT heikeigrabsch deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview
AT philipquirke deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview
AT jakobnkather deeplearningforthedetectionofmicrosatelliteinstabilityfromhistologyimagesincolorectalcancerasystematicliteraturereview