Chain of Flow: A Foundational Generative Framework for ECG-to-4D Cardiac Digital Twins

2026-02-26

AI Summary

This work proposes the Chain of Flow (COF) framework, a novel approach that enables end-to-end reconstruction of a 4D cardiac digital twin driven solely by a single-cycle 12-lead electrocardiogram (ECG). In contrast to existing methods limited to task-specific predictions, COF integrates cine cardiovascular magnetic resonance (CMR) and ECG data to jointly learn a unified generative representation encompassing cardiac geometry, electrophysiology, and kinematic dynamics. The framework accurately recapitulates anatomical structures, chamber function, and dynamic motion across multiple cohorts, supporting downstream applications such as volumetric quantification, regional functional analysis, and synthetic cine generation. By transforming the digital twin from a predictive model into an interactive, patient-specific generative virtual organ, COF establishes a new paradigm for actionable cardiac simulation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Multi-modal Vision

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

A clinically actionable Cardiac Digital Twin (CDT) should reconstruct individualised cardiac anatomy and physiology, update its internal state from multimodal signals, and enable a broad range of downstream simulations beyond isolated tasks. However, existing CDT frameworks remain limited to task-specific predictors rather than building a patient-specific, manipulable virtual heart. In this work, we introduce Chain of Flow (COF), a foundational ECG-driven generative framework that reconstructs full 4D cardiac structure and motion from a single cardiac cycle. The method integrates cine-CMR and 12-lead ECG during training to learn a unified representation of cardiac geometry, electrophysiology, and motion dynamics. We evaluate Chain of Flow on diverse cohorts and demonstrate accurate recovery of cardiac anatomy, chamber-wise function, and dynamic motion patterns. The reconstructed 4D hearts further support downstream CDT tasks such as volumetry, regional function analysis, and virtual cine synthesis. By enabling full 4D organ reconstruction directly from ECG, COF transforms cardiac digital twins from narrow predictive models into fully generative, patient-specific virtual hearts. Code will be released after review.

Problem

• Cardiac Digital Twin
• 4D cardiac reconstruction
• ECG-driven modeling
• patient-specific virtual heart
• multimodal signal integration

Innovation

• Chain of Flow
• ECG-to-4D
• Cardiac Digital Twin
• Generative Framework
• Multimodal Integration