MSIntuit® CRC

Optimize MSI testing for colorectal cancer

MSIntuit® CRC is a CE-marked AI diagnostic that provides a prescreen approach with digital pathology

Clinical context

Facilitate better access to immunotherapy with microsatellite instability (MSI) testing

In 2019 CRC was the second most common cause of death by cancer world-wide. 2
MSI, a genomic biomarker, represents ~15% of overall CRC population; 3 playing an important role in determining treatment.
MSI patients show better prognoses and don’t benefit from chemotherapy in stage II. 4
ICI has been approved for MSI patients, independent of the cancer type.
Lynch Syndrome (HNPCC) represent 20% of MSI patients. 5
Current MSI screening techniques are MMR-IHC staining, MSI-PCR test, or Next-Generation Sequencing (NGS).

Immunotherapy has been approved for this subset of patients—prompting guidelines for universal screening. Furthermore, MSI status is reported to be predictive of response to immunotherapy across all solid tumors.

MSI tumors can also arise from a hereditary condition which increases the risk of developing cancers in multiple organs (Lynch syndrome). It is key to identify these patients and provide them with closer follow-up.

As demand for MSI screening for CRC patients (and beyond) increases, so too does the testing burden for pathologists and labs—creating bottlenecks and resource pressures.

MSIntuit CRC

Rule out patients with MSS phenotypes


Suitable for adults with primary colorectal cancer

Digital pathology

Works with surgically resected tissue on digitized H&E slides

Sensitivity 1

Equivalent when compared to standard testing techniques

Workflow agnostic

Deployment is feasible across IMS systems or shared directory

PDF report

Delivered as a PDF report with user-friendly design


Provides high confidence in MSS prediction by AI

MSIntuit TabletMSIntuit Screen
Integrating MSIntuit® CRC into pathology workflow


40% of CRC patients can be ruled-out from automatic IHC/PCR screening for MMR/MSI thanks to a sensitivity of 95% 1

MSS-AI patients can avoid additional testing thanks to a high diagnosis precision that enables a very low rate of false negative patients.



“Considering the global shortage of pathologists, an obvious step is to use AI to automate such tasks— a move that could also mitigate problems of intra- and inter-observer variability in histopathology. This diagnostic solution could make dMMR/MSI screening faster and more efficient.”
Jakob Nikolas Kather, MD, MSc
Professor of Clinical Artificial Intelligence, Else Kröner Fresenius Center for Digital Health, Technical University Dresden

In clinical routine

A step towards increased lab capacity

Due to variability across pathology labs, workflows may vary by institutions and disease indications.


Tissue sample is taken and prepared as H&E slide


H&E slide digitized

AI solution diagram
AI solution

MSIntuit CRC deep neural networks extract and analyze features from the digitized slide

MSIntuit CRC

PDF report



Patient recommended for a confirmatory MSI test


Pathologist determines there is no need for additional testing

Confirmatory test

An IHC, PCR or NGS test is performed

Research and development

Timeline of milestones

First proof of concept trained
Peer reviewed research in Nature Communications publication
MICCAI science presented at COMPAY workshop
Product CE marked
Abstract presented at ESMO


  1. Svrcek M, Saillard C, Dubois R, et al. Blind validation of MSIntuit, an AI-based pre-screening tool for MSI detection from colorectal cancer H&E slides. Poster presented at: European Society for Medical Oncology (ESMO);  May 9th - 13th 2022; Paris France.
  2. Mayur Amonkar et al. Journal of Clinical Oncology 2019
  3. factsheets/cancers/10_8_9- Colorectum-fact-sheet.pdf
  4. Kawakami H et al. - Microsatellite instability testing and its role in the management of colorectal cancer. - Curr Treat Options Oncol. 2015
  5. Abu-Ghazaleh N et al. - Worldwide prevalence of Lynch syndrome in patients with colorectal cancer: Systematic review and meta-analysis. Genet Med. 2022
MSIntuit® CRC is a medical device for use by healthcare professionals only. This deep learning software is intended for assisting pathologists in the pre-selection of patients with a stable microsatellite phenotype (MSS) / proficient mismatch repair system (pMMR) associated with primary colorectal cancer. It identifies MSS patients from a digitized histology slide image file of hematoxylin and eosin (H&E) stained colorectal tissue resection for patients with primary colorectal cancer. MSIntuit® CRC is intended to be used as an additional source of information and its results should not be used as the primary diagnosis for MSI. Pathologists should only use MSIntuit® CRC in conjunction with their usual diagnostic criteria.
MSIntuit® CRC is CE-IVD marked for diagnostic use in Europe and registered with the MHRA in the United Kingdom. In all other countries, including the United States, the use of the product is limited to research, not for use in diagnostic procedures. For detailed information on proper use and precautions, please read carefully the instructions for use provided with the product or contact Owkin.
Images shown may represent the range of products, or be for illustration purposes only, and may not be an exact representation of the product.
Manufacturer: Owkin France. MSIntuit® CRC is a trademark of Owkin Inc
Information updated on 27th November 2023