A Latent ODE Approach to Spatiotemporal Modeling of Cine Cardiac MRI

2026-06-25

AI Summary

This study addresses the limitation of conventional cardiovascular risk models that rely solely on derived metrics from limited phases of cardiac magnetic resonance (CMR) imaging, thereby neglecting the rich spatiotemporal dynamics across the entire cardiac cycle. To overcome this, the authors propose a latent dynamical model integrating a heart-rate-aware neural ordinary differential equation with a graph-structured mesh autoencoder to continuously model 3D+t biventricular motion. The model incorporates a covariate-conditioned prior to characterize end-diastolic states for heart failure risk prediction. It achieves, for the first time, continuous latent trajectory encoding of full-cycle ventricular motion and introduces latent trajectory deviation as a novel prognostic biomarker. Evaluated on 72,386 UK Biobank participants, the proposed latent score improved the C-index from 0.704 to 0.785—significantly outperforming conventional metrics (C-index: 0.764)—while achieving an optimal balance among reconstruction fidelity, generative realism, and prognostic performance.

Abstract

Cardiac magnetic resonance imaging (CMR) captures rich spatiotemporal information about ventricular structure and motion, but conventional risk models use only a few image-derived indices from selected cardiac phases. We present a latent dynamical model that encodes bi-ventricular anatomy and full-cycle cine motion as a continuous latent trajectory, using heart-rate-aware neural ordinary differential equation (ODE) dynamics and a graph-based mesh autoencoder to reconstruct anatomically consistent 3D+t ventricular motion. A covariate-conditioned prior defines the expected end-diastolic latent state, and a Cox proportional hazards model tests whether deviations from this prior predict incident heart failure. We studied 72,386 UK Biobank participants without baseline cardiovascular disease, including 367 incident heart failure events. In a held-out evaluation subset, adding the latent score to refitted pooled cohort equations improved the stratified C-index from 0.704 to 0.785, compared with 0.764 for seven established cardiac markers. Compared with non-graph and non-ODE approaches, the proposed model gave the best trade-off between reconstruction fidelity, generative realism, and downstream prognostic performance. These results suggest that continuous full-cycle modeling of ventricular motion provides informative cardiac phenotypes beyond conventional CMR summaries, while external validation in more representative patient cohorts is required before clinical risk-prediction use.

Problem

• spatiotemporal modeling
• cardiac MRI
• heart failure prediction
• ventricular motion
• latent dynamics

Innovation

• Latent ODE
• Spatiotemporal Modeling
• Graph-based Mesh Autoencoder
• Cine Cardiac MRI
• Heart Failure Prediction