Personalized 4D Whole Heart Geometry Reconstruction from Cine MRI for Cardiac Digital Twins

2025-07-20

AI Summary

Reconstructing personalized, high-fidelity 4D (3D + time) whole-heart geometric models from routine clinical multi-view 2D cine MRI for cardiac digital twin (CDT) construction remains challenging due to limited spatiotemporal resolution and lack of dense ground-truth annotations. Method: We propose a weakly supervised end-to-end deep learning framework that jointly leverages self-supervised mapping learning and multi-view MRI spatiotemporal feature alignment—requiring only standard cine MRI sequences, without manual segmentation or auxiliary imaging modalities. Contribution/Results: Our method automatically generates high-resolution, dynamic 4D myocardial meshes of the four-chamber heart. Quantitative evaluation demonstrates accurate estimation of ejection fraction and dynamic chamber volumes, with errors below clinically acceptable thresholds. To our knowledge, this is the first work enabling fully automated reconstruction of electrophysio-mechanically ready 4D whole-heart meshes directly from routine cine MRI—providing a critical technical foundation for functional CDT deployment in clinical practice.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: State Estimation

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Cardiac digital twins (CDTs) provide personalized in-silico cardiac representations and hold great potential for precision medicine in cardiology. However, whole-heart CDT models that simulate the full organ-scale electromechanics of all four heart chambers remain limited. In this work, we propose a weakly supervised learning model to reconstruct 4D (3D+t) heart mesh directly from multi-view 2D cardiac cine MRIs. This is achieved by learning a self-supervised mapping between cine MRIs and 4D cardiac meshes, enabling the generation of personalized heart models that closely correspond to input cine MRIs. The resulting 4D heart meshes can facilitate the automatic extraction of key cardiac variables, including ejection fraction and dynamic chamber volume changes with high temporal resolution. It demonstrates the feasibility of inferring personalized 4D heart models from cardiac MRIs, paving the way for an efficient CDT platform for precision medicine. The code will be publicly released once the manuscript is accepted.

Problem

• Reconstruct 4D heart geometry from 2D MRI for digital twins
• Enable personalized cardiac modeling with weak supervision
• Automate extraction of key cardiac variables from meshes

Innovation

• Weakly supervised learning for 4D heart reconstruction
• Self-supervised MRI to 4D mesh mapping
• Automatic extraction of cardiac variables