A Latent ODE Approach to Spatiotemporal Modeling of Cine Cardiac MRI
For cardiovascular risk prediction, this work demonstrates that continuous modeling of ventricular motion can yield more informative phenotypes than conventional discrete indices, though external validation is needed before clinical use.
The authors developed a latent ODE model that encodes full-cycle cardiac motion from cine MRI into a continuous trajectory, and showed that deviations from a learned prior predict incident heart failure. In a UK Biobank cohort of 72,386 participants, the model improved the stratified C-index from 0.704 to 0.785, outperforming seven established cardiac markers (0.764).
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.