Related Experiment Video
Updated: Jul 11, 2025
Automated Multiplex Immunofluorescence Panel for Immuno-oncology Studies on Formalin-fixed Carcinoma Tissue Specimens
Published on: January 21, 2019
Validation of MSIntuit as an AI-based pre-screening tool for MSI detection from colorectal cancer histology slides
Charlie Saillard1, Rémy Dubois2, Oussama Tchita2
1Owkin France, Paris, France. charlie.saillard@owkin.com.
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.
Insights
An AI tool, MSIntuit, effectively pre-screens colorectal cancer (CRC) for mismatch repair deficiency (dMMR)/microsatellite instability (MSI). This deep learning approach aids pathologists by significantly reducing the workload associated with MSI testing.
Area of Science:
- Oncology
- Computational Pathology
- Artificial Intelligence in Medicine
Background:
- Mismatch Repair Deficiency (dMMR)/Microsatellite Instability (MSI) is a critical biomarker in colorectal cancer (CRC).
- Universal screening for MSI status in CRC patients is recommended, increasing pathologist workload and potentially delaying treatment decisions.
- Deep learning offers a promising avenue for streamlining MSI testing and accelerating clinical decision-making.
Purpose of the Study:
- To develop and validate MSIntuit, a clinically approved artificial intelligence (AI) tool for pre-screening MSI status in CRC using H&E stained slides.
- To assess the performance of MSIntuit on an independent cohort of CRC patients.
- To evaluate the inter-scanner reliability of the AI tool.
Main Methods:
- MSIntuit was trained on The Cancer Genome Atlas (TCGA) dataset.
- A blind validation was conducted on 600 independent CRC patient samples.
- Slides were digitized using two different scanners to assess inter-scanner reliability.
Main Results:
- MSIntuit achieved a sensitivity of 0.96-0.98 and a specificity of 0.47-0.46.
- Excellent inter-scanner agreement was observed (Cohen's κ: 0.82).
- The tool effectively identified a high proportion of MSI cases while ruling out nearly half of the non-MSI cases.
Conclusions:
- MSIntuit demonstrates high sensitivity comparable to gold-standard methods for MSI detection.
- The AI tool can significantly alleviate the burden of MSI testing in clinical practice.
- MSIntuit shows potential as an effective pre-screening tool for colorectal cancer patients.
