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

Research output: Contribution to journalResearch articleContributedpeer-review


  • Charlie Saillard - , Owkin France (Author)
  • Rémy Dubois - , Owkin France (Author)
  • Oussama Tchita - , Owkin France (Author)
  • Nicolas Loiseau - , Owkin France (Author)
  • Thierry Garcia - , Medipath (Author)
  • Aurélie Adriansen - , Medipath (Author)
  • Séverine Carpentier - , Medipath (Author)
  • Joelle Reyre - , Medipath (Author)
  • Diana Enea - , Saint-Antoine Hospital - Sorbonne Université (Author)
  • Katharina von Loga - , Owkin France (Author)
  • Aurélie Kamoun - , Owkin France (Author)
  • Stéphane Rossat - , Medipath (Author)
  • Corentin Wiscart - , Owkin France (Author)
  • Meriem Sefta - , Owkin France (Author)
  • Michaël Auffret - , Owkin France (Author)
  • Lionel Guillou - , Owkin France (Author)
  • Arnaud Fouillet - , Owkin France (Author)
  • Jakob Nikolas Kather - , Else Kröner Fresenius Center for Digital Health, Department of internal Medicine I (Author)
  • Magali Svrcek - , Saint-Antoine Hospital - Sorbonne Université (Author)


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.


Original languageEnglish
Article number6695
Pages (from-to)6695
JournalNature communications
Issue number1
Publication statusPublished - 6 Nov 2023

External IDs

PubMedCentral PMC10628260
Scopus 85175841046


Sustainable Development Goals


  • Humans, Microsatellite Instability, Artificial Intelligence, Reproducibility of Results, Early Detection of Cancer, Colorectal Neoplasms/genetics, DNA Mismatch Repair