dMMR prediction from colorectal cancer histopathology: Leveraging non-tumor and low-magnification regions

This study demonstrates that dMMR status in colorectal cancer can be effectively predicted from histopathological WSIs using MIL-based models, with moderate generalizability across independent cohorts. In addition to confirming the predictive value of tumor regions, the results reveal that non-tumorous tissue also contains detectable predictive signals, suggesting that microenvironmental features may contribute to dMMR-associated histological patterns. Furthermore, the use of foundation model-derived embeddings improved generalizability across datasets. Future work should explore integrating non-tumor tissue features and clinical data to further improve predictive performance.

Authors

Institutions

Publication Details

Journal
Computer Methods and Programs in Biomedicine
Published
2026-03-17
DOI
https://doi.org/10.1016/j.cmpb.2026.109317
Primary Topic
Genetic factors in colorectal cancer
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

dMMR prediction from colorectal cancer histopathology: Leveraging non-tumor and low-magnification regions

Maarit Ahtiainen, Hanna Elomaa, Ville K. Äijälä, Ilkka Pölönen et al.
Computer Methods and Programs in Biomedicine
Genetic factors in colorectal cancer
article

dMMR prediction from colorectal cancer histopathology: Leveraging non-tumor and low-magnification regions

Maarit Ahtiainen, Hanna Elomaa, Ville K. Äijälä, Ilkka Pölönen, Meeri Kastinen, Markus J. Mäkinen, Päivi Sirniö, Liisa Petäinen, Henna Karjalainen, Juha P. Väyrynen, Sami Äyrämö, Vilja V. Tapiainen, Pekka Ruusuvuori, Jukka-Pekka Mecklin, Jan Böhm, Anne Tuomisto
article en

Abstract

This study demonstrates that dMMR status in colorectal cancer can be effectively predicted from histopathological WSIs using MIL-based models, with moderate generalizability across independent cohorts. In addition to confirming the predictive value of tumor regions, the results reveal that non-tumorous tissue also contains detectable predictive signals, suggesting that microenvironmental features may contribute to dMMR-associated histological patterns. Furthermore, the use of foundation model-derived embeddings improved generalizability across datasets. Future work should explore integrating non-tumor tissue features and clinical data to further improve predictive performance.

Computer Methods and Programs in BiomedicineVol. 280
Tampere University of Applied Sciences (FI), University of Turku (FI), JAMK University of Applied Sciences (FI), Oulu University Hospital (FI), Tampere University (FI), Central Finland Health Care District (FI), University of Jyväskylä (FI)
Good health and well-being
Openalex Percentile: Top 20%
Genetic factors in colorectal cancer
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.