Morphology-Aware Prognostic model for Five-Year Survival Prediction in Colorectal Cancer from H&E Whole Slide Images

2025-10-16

AI Summary

This study addresses the limitation in colorectal cancer (CRC) prognosis prediction—namely, the neglect of morphological continuum variation and progressive neoplastic evolution. We propose PRISM, an interpretable AI model trained on 8.74 million H&E-stained whole-slide images. PRISM integrates deep learning, spatial morphological modeling, and survival analysis to explicitly encode organ-specific morphological continuum spectra into prognostic modeling, thereby capturing the biological graduality of malignant transformation. In five-year overall survival prediction, PRISM achieves an AUC of 0.70, accuracy of 68.37%, and a hazard ratio (HR) of 3.34—outperforming existing CRC-specific methods by 15% and general-purpose AI baselines by 23%. Moreover, PRISM demonstrates robust generalization across gender and treatment subgroups, significantly enhancing clinical interpretability and model robustness.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: Explainable AI (XAI) for Human Understanding

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
• Security and Privacy: Data transparency and provenance

Abstract

Colorectal cancer (CRC) remains the third most prevalent malignancy globally, with approximately 154,000 new cases and 54,000 projected deaths anticipated for 2025. The recent advancement of foundation models in computational pathology has been largely propelled by task agnostic methodologies that can overlook organ-specific crucial morphological patterns that represent distinct biological processes that can fundamentally influence tumor behavior, therapeutic response, and patient outcomes. The aim of this study is to develop a novel, interpretable AI model, PRISM (Prognostic Representation of Integrated Spatial Morphology), that incorporates a continuous variability spectrum within each distinct morphology to characterize phenotypic diversity and reflecting the principle that malignant transformation occurs through incremental evolutionary processes rather than abrupt phenotypic shifts. PRISM is trained on 8.74 million histological images extracted from surgical resection specimens of 424 patients with stage III CRC. PRISM achieved superior prognostic performance for five-year OS (AUC = 0.70 +- 0.04; accuracy = 68.37% +- 4.75%; HR = 3.34, 95% CI = 2.28-4.90; p<0.0001), outperforming existing CRC-specific methods by 15% and AI foundation models by ~23% accuracy. It showed sex-agnostic robustness (AUC delta = 0.02; accuracy delta = 0.15%) and stable performance across clinicopathological subgroups, with minimal accuracy fluctuation (delta = 1.44%) between 5FU/LV and CPT-11/5FU/LV regimens, replicating the Alliance cohort finding of no survival difference between treatments.

Problem

• Predicting five-year survival for colorectal cancer patients
• Incorporating morphological diversity into prognostic AI models
• Addressing limitations of organ-agnostic computational pathology methods

Innovation

• AI model integrates continuous morphological variability spectrum
• Interprets incremental evolutionary processes in cancer progression
• Outperforms existing methods by 15-23% accuracy