Deep Pathomic Learning Defines Prognostic Subtypes and Molecular Drivers in Colorectal Cancer

2025-11-19

AI Summary

Colorectal cancer (CRC) exhibits high intertumoral heterogeneity, rendering conventional TNM staging insufficient for precise prognostication. To address this, we propose TDAM-CRC, a deep histopathomic model that jointly analyzes whole-slide images and multi-omics data via multi-instance learning, cross-modal fusion, and interaction network modeling to enable interpretable risk stratification. TDAM-CRC identifies MRPL37 as a key hub gene—its promoter hypomethylation drives overexpression, and MRPL37 is validated as an independent prognostic biomarker. In multiple independent cohorts, TDAM-CRC significantly outperforms TNM staging (C-index improvement ≥0.12); its risk score serves as a robust independent prognostic factor (HR=2.84, p<0.001). Furthermore, the model is integrated into a clinical nomogram to support personalized therapeutic decision-making.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Precise prognostic stratification of colorectal cancer (CRC) remains a major clinical challenge due to its high heterogeneity. The conventional TNM staging system is inadequate for personalized medicine. We aimed to develop and validate a novel multiple instance learning model TDAM-CRC using histopathological whole-slide images for accurate prognostic prediction and to uncover its underlying molecular mechanisms. We trained the model on the TCGA discovery cohort (n=581), validated it in an independent external cohort (n=1031), and further we integrated multi-omics data to improve model interpretability and identify novel prognostic biomarkers. The results demonstrated that the TDAM-CRC achieved robust risk stratification in both cohorts. Its predictive performance significantly outperformed the conventional clinical staging system and multiple state-of-the-art models. The TDAM-CRC risk score was confirmed as an independent prognostic factor in multivariable analysis. Multi-omics analysis revealed that the high-risk subtype is closely associated with metabolic reprogramming and an immunosuppressive tumor microenvironment. Through interaction network analysis, we identified and validated Mitochondrial Ribosomal Protein L37 (MRPL37) as a key hub gene linking deep pathomic features to clinical prognosis. We found that high expression of MRPL37, driven by promoter hypomethylation, serves as an independent biomarker of favorable prognosis. Finally, we constructed a nomogram incorporating the TDAM-CRC risk score and clinical factors to provide a precise and interpretable clinical decision-making tool for CRC patients. Our AI-driven pathological model TDAM-CRC provides a robust tool for improved CRC risk stratification, reveals new molecular targets, and facilitates personalized clinical decision-making.

Problem

• Develops AI model for colorectal cancer prognosis using histopathology images
• Identifies molecular mechanisms linking pathology features to clinical outcomes
• Creates clinical tool for personalized risk stratification and treatment decisions

Innovation

• Multiple instance learning model for cancer prognosis
• Integration of multi-omics data for biomarker discovery
• AI-driven pathological analysis with clinical nomogram