arXiv cs.AI· David Br\"uggemann, Ekaterina Krymova, Firat \"Ozdemir, Jochen von Spiczak, Sebastian Kozerke, Samia Mora, Robert Manka, Mathieu Salzmann, Olga V. Demler·· 12 小时前AI 评分31
基于潜在 ODE 的 cine MRI 全周期双心室运动建模
A latent ODE approach to full-cycle biventricular cardiac motion modeling from cine MRI
AI 导读
研究提出一种潜在动力学模型，用心率感知的神经 ODE 动力学与基于图的网格自编码器，将双心室解剖结构与全周期 cine 运动编码为连续潜在轨迹，重建解剖一致的 3D+t 心室运动。
正文 · 原文
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.
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2606.26718 [cs.AI] |
| (or arXiv:2606.26718v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.26718 arXiv-issued DOI via DataCite |
|
| Journal reference: | Medical Image Analysis, Volume 116, 2027, 104376 |
| Related DOI: | https://doi.org/10.1016/j.media.2026.104376
DOI(s) linking to related resources |
Submission history
From: David Bruggemann [view email]
[v1]
Thu, 25 Jun 2026 07:53:45 UTC (4,383 KB)
[v2]
Thu, 5 Nov 2026 16:14:35 UTC (6,162 KB)
来源：arXiv cs.AI · arxiv.org