Cardiac Digital Twins at Scale from MRI: Open Tools and Representative Models from ~55000 UK Biobank Participants

2025-05-27

AI Summary

Scalable construction and sharing of cardiac digital twins remain hindered by labor-intensive, non-standardized mesh generation. Method: We propose a fully automated, anatomically accurate 3D biventricular meshing framework integrating deep learning–based segmentation, anisotropic myocardial fiber modeling, and universal virtual coordinate (UVC) parameterization. Leveraging ~55,000 cardiovascular MRI scans from UK Biobank, we generate high-fidelity meshes across diverse demographics. Contribution/Results: We establish the largest open-source adult cardiac digital twin repository to date—comprising 1,423 representative models stratified by sex, age (49–80 years), and BMI (16–42 kg/m²)—with optimal demographic balance. The repository includes standardized geometric and fiber-orientation data. We publicly release end-to-end open-source code and pre-trained models, enabling reproducible electro-mechanical coupling simulations and cross-population pathophysiological investigations. This resource substantially enhances reproducibility, generalizability, and accessibility in computational cardiac modeling.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Medical and Biological Imaging
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

A cardiac digital twin is a virtual replica of a patient's heart for screening, diagnosis, prognosis, risk assessment, and treatment planning of cardiovascular diseases. This requires an anatomically accurate patient-specific 3D structural representation of the heart, suitable for electro-mechanical simulations or study of disease mechanisms. However, generation of cardiac digital twins at scale is demanding and there are no public repositories of models across demographic groups. We describe an automatic open-source pipeline for creating patient-specific left and right ventricular meshes from cardiovascular magnetic resonance images, its application to a large cohort of ~55000 participants from UK Biobank, and the construction of the most comprehensive cohort of adult heart models to date, comprising 1423 representative meshes across sex (male, female), body mass index (range: 16 - 42 kg/m$^2$) and age (range: 49 - 80 years). Our code is available at https://github.com/cdttk/biv-volumetric-meshing/tree/plos2025 , and pre-trained networks, representative volumetric meshes with fibers and UVCs will be made available soon.

Problem

• Creating scalable cardiac digital twins from MRI data
• Lack of public 3D heart models across demographics
• Automated pipeline for patient-specific ventricular mesh generation

Innovation

• Automatic open-source pipeline for ventricular meshes
• Large-scale application to 55000 UK Biobank participants
• Comprehensive cohort of 1423 representative heart models