H&E-based MSI/MMR testing with AI in colorectal cancer: a multi-centred blinded evaluation - Summary - MDSpire

H&E-based MSI/MMR testing with AI in colorectal cancer: a multi-centred blinded evaluation

  • By

  • Cher Bass

  • Foivos Ntelemis

  • Julian Schmidt

  • Steffen Wolf

  • André Geraldes

  • Debapriya Mehrotra

  • Shikha Singhal

  • Narender Kumar

  • Angelica Marcia

  • Nicholas Bennett

  • Oscar Maiques

  • Mitchell Hyde

  • Bejal Mistry

  • Grace Rogerson

  • Michele Cummings

  • Clare Freer

  • Elizabeth Walsh

  • Manuel Salto-Tellez

  • Maurice Loughrey

  • In Hwa Um

  • David J. Harrison

  • Richard Clarkson

  • James Blackwood

  • J. Carl Barrett

  • Jakob Nikolas Kather

  • Nicolas M. Orsi

  • Pahini Pandya

  • Salim Arslan

  • December 15, 2025

  • 0 min

Share

Objective:

To assess the performance of the PANProfiler Colorectal (PPC), an AI-based biomarker test, in determining MSI/MMR status from H&E-stained slides in colorectal cancer patients.

Key Findings:
  • PPC produced definitive results for 86.55% of slides.
  • Achieved an overall agreement of 93.83%, positive agreement of 92.54%, and negative agreement of 94.02%.
  • Demonstrated robust performance across diverse cohorts and clinical settings.
Interpretation:

PPC accurately determines MSI/MMR status from routine H&E slides, providing a rapid and scalable alternative to conventional diagnostic methods.

Limitations:
  • The study may not fully represent all CRC subpopulations due to its specific cohort.
  • Variability in scanning equipment and image formats could affect generalizability.
Conclusion:

PPC shows promise as a reliable, cost-effective tool for MSI/MMR testing in colorectal cancer, potentially improving patient management and treatment outcomes.

Original Source(s)

H&E-based MSI/MMR testing with AI in colorectal cancer: a multi-centred blinded evaluation

  • by Cher Bass, Foivos Ntelemis, Julian Schmidt, Steffen Wolf, André Geraldes, Debapriya Mehrotra, Shikha Singhal, Narender Kumar, Angelica Marcia, Nicholas Bennett, Oscar Maiques, Mitchell Hyde, Bejal Mistry, Grace Rogerson, Michele Cummings, Clare Freer, Elizabeth Walsh, Manuel Salto-Tellez, Maurice Loughrey, In Hwa Um, David J. Harrison, Richard Clarkson, James Blackwood, J. Carl Barrett, Jakob Nikolas Kather, Nicolas M. Orsi, Pahini Pandya, Salim Arslan

  • December 15, 2025

Related Content

Uncertainty-aware and causal test-time adaptive foundation model for robust colorectal cancer pathology diagnosis

Barriers and Variations in Cancer Diagnosis: A Cross-Sectional Analysis of Patient Journeys and Healthcare Provider Timelines in Public Health Systems of Chile, Colombia, and Ecuador

Preoperative HALP and LMR as Predictors of Disease-Free Survival in Stage III Colon Cancer: Implications for Nomogram-Based Risk Assessment