mlsanityData to 7 Oct 2026

Chain of Flow: ECG-Conditioned 4D Cardiac Cine Generation from Patient-Specific Anatomical Anchor

arXiv 2602.22919 ↗First posted 26 Feb 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Cardiac cine magnetic resonance imaging (MRI) is central to functional cardiac assessment, yet a full current cine sequence may not always be directly available at the point of analysis. We introduce Chain of Flow (COF), an electrocardiography (ECG)-conditioned framework that combines patient-specific MRI and current ECG for subject-specific 4D cardiac cine generation. On the UK Biobank dataset, COF achieves strong image-level fidelity and downstream function-oriented performance on a shared same-visit evaluable benchmark. Multi-slice and multi-resolution analyses indicate stable structural generation quality across the short-axis stack and heterogeneous acquisition resolutions. Controlled phase-robustness analyses across resampled input MRI phases further provide same-visit proxy support for patient-specific MRI plus current ECG when a target MRI phase is not directly observed. A cross-visit route provides exploratory serial evidence, with the clearest gains in current-facing region-of-interest readout. Disease-category functional audits, case-level volume-trajectory evidence review further delineate where the current patient-specific MRI plus ECG formulation remains stable for anatomy-aware downstream cardiac analysis. Code is available at https://anonymous.4open.science/r/COF-paper-release-C88B.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 66 references that are in the map. First posted on arXiv 26 Feb 2026.

Builds on

17 of 66 references.

References · 17

  1. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
  2. 2022MONAI: An open-source framework for deep learning in healthcarecited by 438
  3. 2018Generative Adversarial Network in Medical Imaging: A Reviewcited by 257
  4. 2024Improving the Training of Rectified Flowscited by 106
  5. 2024Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogramcited by 84
  6. 2022SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generationcited by 56
  7. 2018Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequencescited by 47
  8. 2023Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesiscited by 32
  9. 2023Towards Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inferencecited by 18
  10. 2024EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharingcited by 17
  11. 2023Unlocking the diagnostic potential of electrocardiograms through information transfer from cardiac magnetic resonance imagingcited by 14
  12. 2024Solving the Inverse Problem of Electrocardiography for Cardiac Digital Twins: A Surveycited by 14
5 more
  1. 2021Physics-constrained Deep Learning for Robust Inverse ECG Modelingcited by 12
  2. 2018Factorised spatial representation learning: application in semi-supervised myocardial segmentationcited by 11
  3. 2024ECHOPulse: ECG controlled echocardio-grams video generationcited by 8
  4. 2025CardiacFlow: 3D+t Four-Chamber Cardiac Shape Completion and Generation via Flow Matchingcited by 8
  5. 2019Bayesian Optimization on Large Graphs via a Graph Convolutional Generative Model: Application in Cardiac Model Personalizationcited by 6

Built on by

Not cited yet.