EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSAI-Path: Predicting Microsatellite Instability From Routine Histology Slides Without Reinventing the Wheel

Elias Baumann, Luca E M Schäfer, Frédérique Meeuwsen, Richard Kirsch, Iris D Nagtegaal, Martin D Berger, Heather Dawson, Inti Zlobec

Modern Pathology · 2026-01 · 39 (1) · 100932

DOI: 10.1016/j.modpat.2025.100932 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Modern Pathology, 2026-01. Verfasst von Elias Baumann und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Tissue Medicine and Pathology, University of Bern, Bern, Switzerland; Graduate School for Cellular and Biomedical Sciences, University o…. Hauptthemen laut MEDLINE: Microsatellite Instability, Colorectal Neoplasms, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Bern, Swiss National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Microsatellite instability (MSI) is an important biomarker in colorectal cancer, influencing both patient prognosis and treatment decisions. Current approaches for MSI prediction from hematoxylin and eosin--stained whole-slide images (WSI) rely on end-to-end deep learning ("black-box") models with limited interpretability, often relying on heatmaps for visualization. However, experienced pathologists can intuitively identify MSI through specific histologic features and have developed manual classification systems such as MS-Path for Lynch syndrome screening. We present a novel hybrid approach that combines computational and pathologist expertise to create an explainable and verifiable method for MSI prediction in colorectal cancer, applicable to resection and biopsy WSI. Our proposed method uses nuclei and tissue segmentation models to automatically quantify MSI-associated histologic features outlined in the Bethesda guidelines, including intraepithelial lymphocytes, grade of differentiation, mucinous components, and tertiary lymphoid structures. After validation on annotated data sets, these features are integrated with clinical data and used in logistic regression and random forest models to predict MSI status. We validated our approach using 3256 WSI from 2267 patients across 7 cohorts from 5 centers. The method achieved an area under the curve of up to 0.88 across all resection cohorts, and 0.90 on biopsies, performing on par with published black-box deep learning models. Importantly, the learned variable importances strongly correlated with manual scoring systems and aligned with manual pathologist assessments. We observed significant intrapatient heterogeneity in predicted scores, emphasizing the importance of whole-case analysis. Our approach also shows potential as a screening tool that could exclude 41% of patients from gold-standard MSI testing while maintaining 95% sensitivity. This study demonstrates that classifiers based on clinical and validated histologic information can predict MSI status as effectively as black-box models while providing complete interpretability. Our method offers an alternative pathway for understandable, explainable, and trustworthy biomarker prediction in computational pathology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Microsatellite InstabilityColorectal NeoplasmsImage Interpretation, Computer-AssistedHumansPredictive Value of TestsDeep Learning

Stichwörter der Autor:innen

colorectal cancerdeep learningexplainabilityinterpretabilitymicrosatellite instability

Autor:innen und Institutionen

  • Institute of Tissue Medicine and Pathology, University of Bern, Bern, Switzerland; Graduate School for Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland.
  • Institute of Tissue Medicine and Pathology, University of Bern, Bern, Switzerland.
  • Department of Pathology, Radboud University Medical Centre, Nijmegen, The Netherlands.
  • Pathology and Laboratory Medicine, Mount Sinai Hospital, University of Toronto, Toronto, Ontario, Canada.
  • Department of Medical Oncology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland.
  • Institute of Tissue Medicine and Pathology, University of Bern, Bern, Switzerland; Department of Digital Medicine, University of Bern, Bern, Switzerland. Electronic address: inti.zlobec@unibe.ch.

Förderung

  • University of Bern
  • Swiss National Science Foundation

Zitieren

APA

Baumann, E., Schäfer, L. E. M., Meeuwsen, F., Kirsch, R., Nagtegaal, I. D., Berger, M. D., Dawson, H., & Zlobec, I. (2026). MSAI-Path: Predicting Microsatellite Instability From Routine Histology Slides Without Reinventing the Wheel. Modern Pathology, 39(1), 100932. https://doi.org/10.1016/j.modpat.2025.100932

Vancouver

Baumann E, Schäfer LEM, Meeuwsen F, Kirsch R, Nagtegaal ID, Berger MD, et al. MSAI-Path: Predicting Microsatellite Instability From Routine Histology Slides Without Reinventing the Wheel. Modern Pathology. 2026;39(1):100932. doi:10.1016/j.modpat.2025.100932

BibTeX
@article{Baumann2026,
  author = {Baumann, Elias and Schäfer, Luca E M and Meeuwsen, Frédérique and Kirsch, Richard and Nagtegaal, Iris D and Berger, Martin D and Dawson, Heather and Zlobec, Inti},
  title = {MSAI-Path: Predicting Microsatellite Instability From Routine Histology Slides Without Reinventing the Wheel},
  journal = {Modern Pathology},
  year = {2026},
  volume = {39},
  number = {1},
  pages = {100932},
  doi = {10.1016/j.modpat.2025.100932}
}
Kostenlos starten →