RePCM: Region-Specific and Phenotype-Adaptive Bi-Ventricular Cardiac Motion Synthesis

2026-05-20

AI Summary

This work addresses the over-smoothing of cardiac motion in existing methods for reconstructing a full cardiac cycle from a single ventricular mesh, which often arises from neglecting regional heterogeneity and disease-specific characteristics. The authors propose a two-stage framework: first, a reconstruction network coupled with clustering learns data-driven functional segments; second, a conditional variational autoencoder incorporates a region-injection mechanism and an anatomy-guided, phenotype-adaptive mixture-of-experts prior to preserve local dynamics and model motion variability across diseases. By explicitly integrating motion-derived regional structure, region-specific feature injection, and disease-phenotype priors, the method significantly outperforms baseline approaches across three distinct cardiovascular disease datasets, achieving notable improvements in geometric and functional metrics as well as regional dynamic fidelity.

Abstract

Cardiac motion over a cardiac cycle is crucial for quantifying regional function and is strongly affected by cardiovascular diseases. Since temporally dense mesh sequences are difficult to obtain in practice, we focus on leveraging the more accessible end-diastolic frame to infer a full-cycle sequence. Due to strong regional and disease-specific differences, traditional methods often oversmooth the data by relying on generative models that are optimized for global patterns. To address this problem, we propose Region-Aware and Phenotype-Adaptive Bi-Ventricular Cardiac Motion Synthesis (RePCM) for single frame Bi-ventricular mesh motion completion. In Stage I, a reconstruction network learns vertex wise motion descriptors and clustering yields a data driven functional partition, providing an explicit motion derived region structure. In Stage II, a Region-Specific Injection Module enforces masked, synchronized region exchange within a conditional VAE, preserving localized specific dynamics and restricting cross-region mixing. A Phenotype-Adaptive Mixture-of-Experts prior conditioned on ED shape uses anatomy-guided cues to model latent motion trends and capture inter-disease variability. Experiments on three datasets covering different cardiovascular diseases show consistent gains in geometric and functional metrics and improved preservation of region specific dynamics.

Problem

• cardiac motion synthesis
• region-specific dynamics
• phenotype-adaptive modeling
• bi-ventricular mesh
• temporal motion completion

Innovation

• Region-Specific Motion Synthesis
• Phenotype-Adaptive Modeling
• Bi-Ventricular Mesh Completion
• Conditional VAE with Region Injection
• Functional Partitioning