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

Colorectal cancer (CRC) is a leading malignancy worldwide, where histopathological assessment of hematoxylin and eosin (H&E) stained whole-slide images remains the diagnostic gold standard. However, current computational pathology models suffer from domain shifts, unreliable uncertainty estimation, and spurious correlations, limiting clinical reliability. We present UAD-FM, an Uncertainty-Aware and Causally Adaptive Foundation Model that integrates epistemic-aleatoric uncertainty decomposition, causal test-time adaptation using do-interventions, and post-hoc calibration for trustworthy inference. Across five public CRC datasets (TCGA-COAD/READ, CRAG, DigestPath 2019, NCT-CRC-HE-100K, and LC25000), UAD-FM achieves superior accuracy, calibration, and domain robustness compared with existing foundation models and adaptation baselines. The model also produces interpretable uncertainty maps to support human-AI collaboration. UAD-FM provides a unified, transparent framework for reliable and generalizable CRC pathology diagnosis across heterogeneous clinical settings.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2025-12-06
DOI
https://doi.org/10.1038/s41746-025-02149-1
Primary Topic
AI in cancer detection
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

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

Hongxue Meng, Xinyue Zhang, Meihong Yan, Siyuan Ma et al.
npj Digital Medicine
AI in cancer detection
article

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

Hongxue Meng, Xinyue Zhang, Meihong Yan, Siyuan Ma, Lei Cao, Shenghan Lou, Xiao Zhang, Gary Mo, Keru Ma, C. Li, Yuze Huang, Hao Li, Hao Wang, Huiying Li, Peng Han, Haonan Xie
article en

Abstract

Colorectal cancer (CRC) is a leading malignancy worldwide, where histopathological assessment of hematoxylin and eosin (H&E) stained whole-slide images remains the diagnostic gold standard. However, current computational pathology models suffer from domain shifts, unreliable uncertainty estimation, and spurious correlations, limiting clinical reliability. We present UAD-FM, an Uncertainty-Aware and Causally Adaptive Foundation Model that integrates epistemic-aleatoric uncertainty decomposition, causal test-time adaptation using do-interventions, and post-hoc calibration for trustworthy inference. Across five public CRC datasets (TCGA-COAD/READ, CRAG, DigestPath 2019, NCT-CRC-HE-100K, and LC25000), UAD-FM achieves superior accuracy, calibration, and domain robustness compared with existing foundation models and adaptation baselines. The model also produces interpretable uncertainty maps to support human-AI collaboration. UAD-FM provides a unified, transparent framework for reliable and generalizable CRC pathology diagnosis across heterogeneous clinical settings.

npj Digital MedicineVol. 8(1)
Harbin Medical University (CN), Nanyang Technological University (SG), Third Affiliated Hospital of Harbin Medical University (CN), China Rural Technology Development Center (CN), Education Department of Heilongjiang Province (CN), Heilongjiang Institute of Wood Science (CN), Heilongjiang Institute of Technology (CN), Heilongjiang University (CN)
Harbin Medical University, Health Commission of Heilongjiang Province, National Natural Science Foundation of China, China Postdoctoral Science Foundation
Openalex Percentile: Top 79%
AI in cancer detection
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.