Whole-body Representation Learning For Competing Preclinical Disease Risk Assessment

TL;DR

This paper introduces a self-supervised whole-body representation learning method for preclinical disease risk assessment, outperforming traditional radiomics across multiple diseases and enhancing subgroup predictions, with potential for clinical screening.

Contribution

It presents a novel self-supervised learning approach for whole-body imaging that improves early disease risk prediction over existing radiomics methods.

Findings

Outperforms whole-body radiomics in multiple diseases.

Enhances prediction for CVD subgroups using combined MRI data.

Demonstrates potential for clinical early screening and personalized risk stratification.

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/