Validation of MSIntuit as an AI-based pre-screening tool for MSI detection from colorectal cancer histology slides

Charlie Saillard (), Rémy Dubois, Oussama Tchita, Nicolas Loiseau, Thierry Garcia, Aurélie Adriansen, Séverine Carpentier, Joelle Reyre, Diana Enea, Katharina Loga, Aurélie Kamoun, Stéphane Rossat, Corentin Wiscart, Meriem Sefta, Michaël Auffret, Lionel Guillou, Arnaud Fouillet, Jakob Nikolas Kather and Magali Svrcek
Additional contact information
Charlie Saillard: Owkin France
Rémy Dubois: Owkin France
Oussama Tchita: Owkin France
Nicolas Loiseau: Owkin France
Thierry Garcia: Medipath
Aurélie Adriansen: Medipath
Séverine Carpentier: Medipath
Joelle Reyre: Medipath
Diana Enea: Saint-Antoine Hospital - Sorbonne Université, AP-HP
Katharina Loga: Owkin France
Aurélie Kamoun: Owkin France
Stéphane Rossat: Medipath
Corentin Wiscart: Owkin France
Meriem Sefta: Owkin France
Michaël Auffret: Owkin France
Lionel Guillou: Owkin France
Arnaud Fouillet: Owkin France
Jakob Nikolas Kather: Technical University Dresden
Magali Svrcek: Saint-Antoine Hospital - Sorbonne Université, AP-HP

Nature Communications, 2023, vol. 14, issue 1, 1-11

Abstract: Abstract Mismatch Repair Deficiency (dMMR)/Microsatellite Instability (MSI) is a key biomarker in colorectal cancer (CRC). Universal screening of CRC patients for MSI status is now recommended, but contributes to increased workload for pathologists and delayed therapeutic decisions. Deep learning has the potential to ease dMMR/MSI testing and accelerate oncologist decision making in clinical practice, yet no comprehensive validation of a clinically approved tool has been conducted. We developed MSIntuit, a clinically approved artificial intelligence (AI) based pre-screening tool for MSI detection from haematoxylin-eosin (H&E) stained slides. After training on samples from The Cancer Genome Atlas (TCGA), a blind validation is performed on an independent dataset of 600 consecutive CRC patients. Inter-scanner reliability is studied by digitising each slide using two different scanners. MSIntuit yields a sensitivity of 0.96–0.98, a specificity of 0.47-0.46, and an excellent inter-scanner agreement (Cohen’s κ: 0.82). By reaching high sensitivity comparable to gold standard methods while ruling out almost half of the non-MSI population, we show that MSIntuit can effectively serve as a pre-screening tool to alleviate MSI testing burden in clinical practice.

Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-023-42453-6 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:14:y:2023:i:1:d:10.1038_s41467-023-42453-6

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-023-42453-6

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().