Artificial Intelligence in Predicting Microsatellite Instability and KRAS, BRAF Mutations from Whole-Slide Images in Colorectal Cancer: A Systematic Review
Mismatch repair deficiency (d-MMR)/microsatellite instability (MSI), <i>KRAS</i>, and <i>BRAF</i> mutational status are crucial for treating advanced colorectal cancer patients. Traditional methods like immunohistochemistry or polymerase chain reaction (PCR) can be challenged...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-12-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/14/1/99 |
_version_ | 1797358954545676288 |
---|---|
author | Theo Guitton Pierre Allaume Noémie Rabilloud Nathalie Rioux-Leclercq Sébastien Henno Bruno Turlin Marie-Dominique Galibert-Anne Astrid Lièvre Alexandra Lespagnol Thierry Pécot Solène-Florence Kammerer-Jacquet |
author_facet | Theo Guitton Pierre Allaume Noémie Rabilloud Nathalie Rioux-Leclercq Sébastien Henno Bruno Turlin Marie-Dominique Galibert-Anne Astrid Lièvre Alexandra Lespagnol Thierry Pécot Solène-Florence Kammerer-Jacquet |
author_sort | Theo Guitton |
collection | DOAJ |
description | Mismatch repair deficiency (d-MMR)/microsatellite instability (MSI), <i>KRAS</i>, and <i>BRAF</i> mutational status are crucial for treating advanced colorectal cancer patients. Traditional methods like immunohistochemistry or polymerase chain reaction (PCR) can be challenged by artificial intelligence (AI) based on whole slide images (WSI) to predict tumor status. In this systematic review, we evaluated the role of AI in predicting MSI status, <i>KRAS</i>, and <i>BRAF</i> mutations in colorectal cancer. Studies published in PubMed up to June 2023 were included (<i>n</i> = 17), and we reported the risk of bias and the performance for each study. Some studies were impacted by the reduced number of slides included in the data set and the lack of external validation cohorts. Deep learning models for the d-MMR/MSI status showed a good performance in training cohorts (mean AUC = 0.89, [0.74–0.97]) but slightly less than expected in the validation cohort when available (mean AUC = 0.82, [0.63–0.98]). Contrary to the MSI status, the prediction of <i>KRAS</i> and <i>BRAF</i> mutations was less explored with a less robust methodology. The performance was lower, with a maximum of 0.77 in the training cohort, 0.58 in the validation cohort for <i>KRAS</i>, and 0.82 AUC in the training cohort for <i>BRAF</i>. |
first_indexed | 2024-03-08T15:09:37Z |
format | Article |
id | doaj.art-ab2a4a0f2d7c4d5bbc3313fcf2072155 |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-03-08T15:09:37Z |
publishDate | 2023-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-ab2a4a0f2d7c4d5bbc3313fcf20721552024-01-10T14:53:59ZengMDPI AGDiagnostics2075-44182023-12-011419910.3390/diagnostics14010099Artificial Intelligence in Predicting Microsatellite Instability and KRAS, BRAF Mutations from Whole-Slide Images in Colorectal Cancer: A Systematic ReviewTheo Guitton0Pierre Allaume1Noémie Rabilloud2Nathalie Rioux-Leclercq3Sébastien Henno4Bruno Turlin5Marie-Dominique Galibert-Anne6Astrid Lièvre7Alexandra Lespagnol8Thierry Pécot9Solène-Florence Kammerer-Jacquet10Department of Pathology CHU de Rennes, Rennes 1 University, Pontchaillou Hospital, 2 Rue Henri Le Guilloux, CEDEX 09, 35033 Rennes, FranceDepartment of Pathology CHU de Rennes, Rennes 1 University, Pontchaillou Hospital, 2 Rue Henri Le Guilloux, CEDEX 09, 35033 Rennes, FranceImpact TEAM, Laboratoire Traitement du Signal et de l’Image (LTSI) INSERM, Rennes 1 University, Pontchaillou Hospital, CEDEX 09, 35033 Rennes, FranceDepartment of Pathology CHU de Rennes, Rennes 1 University, Pontchaillou Hospital, 2 Rue Henri Le Guilloux, CEDEX 09, 35033 Rennes, FranceDepartment of Pathology CHU de Rennes, Rennes 1 University, Pontchaillou Hospital, 2 Rue Henri Le Guilloux, CEDEX 09, 35033 Rennes, FranceDepartment of Pathology CHU de Rennes, Rennes 1 University, Pontchaillou Hospital, 2 Rue Henri Le Guilloux, CEDEX 09, 35033 Rennes, FranceDepartment of Molecular Genetics and Medical Genomics CHU de Rennes, Rennes 1 University, Pontchaillou Hospital, 2 Rue Henri Le Guilloux, CEDEX 09, 35033 Rennes, FranceDepartment of Gastro-Entrology CHU de Rennes, Rennes 1 University, Pontchaillou Hospital, 2 Rue Henri Le Guilloux, CEDEX 09, 35033 Rennes, FranceDepartment of Molecular Genetics and Medical Genomics CHU de Rennes, Rennes 1 University, Pontchaillou Hospital, 2 Rue Henri Le Guilloux, CEDEX 09, 35033 Rennes, FranceFacility for Artificial Intelligence and Image Analysis (FAIIA), Biosit UAR 3480 CNRS-US18 INSERM, Rennes University, 2 Avenue du Professeur Léon Bernard, 35042 Rennes, FranceDepartment of Pathology CHU de Rennes, Rennes 1 University, Pontchaillou Hospital, 2 Rue Henri Le Guilloux, CEDEX 09, 35033 Rennes, FranceMismatch repair deficiency (d-MMR)/microsatellite instability (MSI), <i>KRAS</i>, and <i>BRAF</i> mutational status are crucial for treating advanced colorectal cancer patients. Traditional methods like immunohistochemistry or polymerase chain reaction (PCR) can be challenged by artificial intelligence (AI) based on whole slide images (WSI) to predict tumor status. In this systematic review, we evaluated the role of AI in predicting MSI status, <i>KRAS</i>, and <i>BRAF</i> mutations in colorectal cancer. Studies published in PubMed up to June 2023 were included (<i>n</i> = 17), and we reported the risk of bias and the performance for each study. Some studies were impacted by the reduced number of slides included in the data set and the lack of external validation cohorts. Deep learning models for the d-MMR/MSI status showed a good performance in training cohorts (mean AUC = 0.89, [0.74–0.97]) but slightly less than expected in the validation cohort when available (mean AUC = 0.82, [0.63–0.98]). Contrary to the MSI status, the prediction of <i>KRAS</i> and <i>BRAF</i> mutations was less explored with a less robust methodology. The performance was lower, with a maximum of 0.77 in the training cohort, 0.58 in the validation cohort for <i>KRAS</i>, and 0.82 AUC in the training cohort for <i>BRAF</i>.https://www.mdpi.com/2075-4418/14/1/99digital pathologyartificial intelligencecolorectal cancerdeep learningmicrosatellite instabilitymismatch repair deficiency |
spellingShingle | Theo Guitton Pierre Allaume Noémie Rabilloud Nathalie Rioux-Leclercq Sébastien Henno Bruno Turlin Marie-Dominique Galibert-Anne Astrid Lièvre Alexandra Lespagnol Thierry Pécot Solène-Florence Kammerer-Jacquet Artificial Intelligence in Predicting Microsatellite Instability and KRAS, BRAF Mutations from Whole-Slide Images in Colorectal Cancer: A Systematic Review Diagnostics digital pathology artificial intelligence colorectal cancer deep learning microsatellite instability mismatch repair deficiency |
title | Artificial Intelligence in Predicting Microsatellite Instability and KRAS, BRAF Mutations from Whole-Slide Images in Colorectal Cancer: A Systematic Review |
title_full | Artificial Intelligence in Predicting Microsatellite Instability and KRAS, BRAF Mutations from Whole-Slide Images in Colorectal Cancer: A Systematic Review |
title_fullStr | Artificial Intelligence in Predicting Microsatellite Instability and KRAS, BRAF Mutations from Whole-Slide Images in Colorectal Cancer: A Systematic Review |
title_full_unstemmed | Artificial Intelligence in Predicting Microsatellite Instability and KRAS, BRAF Mutations from Whole-Slide Images in Colorectal Cancer: A Systematic Review |
title_short | Artificial Intelligence in Predicting Microsatellite Instability and KRAS, BRAF Mutations from Whole-Slide Images in Colorectal Cancer: A Systematic Review |
title_sort | artificial intelligence in predicting microsatellite instability and kras braf mutations from whole slide images in colorectal cancer a systematic review |
topic | digital pathology artificial intelligence colorectal cancer deep learning microsatellite instability mismatch repair deficiency |
url | https://www.mdpi.com/2075-4418/14/1/99 |
work_keys_str_mv | AT theoguitton artificialintelligenceinpredictingmicrosatelliteinstabilityandkrasbrafmutationsfromwholeslideimagesincolorectalcancerasystematicreview AT pierreallaume artificialintelligenceinpredictingmicrosatelliteinstabilityandkrasbrafmutationsfromwholeslideimagesincolorectalcancerasystematicreview AT noemierabilloud artificialintelligenceinpredictingmicrosatelliteinstabilityandkrasbrafmutationsfromwholeslideimagesincolorectalcancerasystematicreview AT nathalieriouxleclercq artificialintelligenceinpredictingmicrosatelliteinstabilityandkrasbrafmutationsfromwholeslideimagesincolorectalcancerasystematicreview AT sebastienhenno artificialintelligenceinpredictingmicrosatelliteinstabilityandkrasbrafmutationsfromwholeslideimagesincolorectalcancerasystematicreview AT brunoturlin artificialintelligenceinpredictingmicrosatelliteinstabilityandkrasbrafmutationsfromwholeslideimagesincolorectalcancerasystematicreview AT mariedominiquegalibertanne artificialintelligenceinpredictingmicrosatelliteinstabilityandkrasbrafmutationsfromwholeslideimagesincolorectalcancerasystematicreview AT astridlievre artificialintelligenceinpredictingmicrosatelliteinstabilityandkrasbrafmutationsfromwholeslideimagesincolorectalcancerasystematicreview AT alexandralespagnol artificialintelligenceinpredictingmicrosatelliteinstabilityandkrasbrafmutationsfromwholeslideimagesincolorectalcancerasystematicreview AT thierrypecot artificialintelligenceinpredictingmicrosatelliteinstabilityandkrasbrafmutationsfromwholeslideimagesincolorectalcancerasystematicreview AT soleneflorencekammererjacquet artificialintelligenceinpredictingmicrosatelliteinstabilityandkrasbrafmutationsfromwholeslideimagesincolorectalcancerasystematicreview |