Whole-body Representation Learning For Competing Preclinical Disease Risk Assessment

2025-08-04

AI Summary

Current disease-risk assessment approaches are predominantly single-disease–oriented and rely on manual feature segmentation, limiting generalizability and reliability. To address this, we propose an end-to-end, whole-body voxel-level self-supervised representation learning framework that jointly leverages routine whole-body CT and cardiac MRI. Our method employs a 3D convolutional neural network with contrastive learning—requiring no manual annotations or organ segmentation—to simultaneously predict the risk of four major chronic diseases under a competing-risks survival modeling framework: cardiovascular disease, type 2 diabetes, chronic obstructive pulmonary disease, and chronic kidney disease. Experimental results demonstrate substantial improvements over conventional radiomics, particularly in early identification of ischemic heart disease, hypertension, and stroke. The framework achieves robust standalone screening performance and exhibits strong potential for integration into multimodal clinical workflows.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Representation Learning
• 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: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Reliable preclinical disease risk assessment is essential to move public healthcare from reactive treatment to proactive identification and prevention. However, image-based risk prediction algorithms often consider one condition at a time and depend on hand-crafted features obtained through segmentation tools. We propose a whole-body self-supervised representation learning method for the preclinical disease risk assessment under a competing risk modeling. This approach outperforms whole-body radiomics in multiple diseases, including cardiovascular disease (CVD), type 2 diabetes (T2D), chronic obstructive pulmonary disease (COPD), and chronic kidney disease (CKD). Simulating a preclinical screening scenario and subsequently combining with cardiac MRI, it sharpens further the prediction for CVD subgroups: ischemic heart disease (IHD), hypertensive diseases (HD), and stroke. The results indicate the translational potential of whole-body representations as a standalone screening modality and as part of a multi-modal framework within clinical workflows for early personalized risk stratification. The code is available at https://github.com/yayapa/WBRLforCR/

Problem

• Develops self-supervised whole-body representation learning for disease risk
• Improves multi-disease prediction over traditional radiomics methods
• Enables early personalized risk stratification in clinical workflows

Innovation

• Self-supervised whole-body representation learning method
• Competing risk modeling for disease assessment
• Multi-modal integration with cardiac MRI