A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics

TL;DR

This paper introduces MeshHeart, a personalized generative model for 3D heart shape and motion, enabling detailed analysis of normal and abnormal cardiac dynamics for improved diagnosis and treatment.

Contribution

The paper presents MeshHeart, a novel conditional generative model that captures high-dimensional spatio-temporal cardiac mesh data and introduces a distance metric for deviation analysis.

Findings

High accuracy in cardiac mesh sequence reconstruction and generation.

Latent features effectively classify cardiac diseases.

Latent delta correlates with clinical phenotypes.

Abstract

Understanding the structure and motion of the heart is crucial for diagnosing and managing cardiovascular diseases, the leading cause of global death. There is wide variation in cardiac shape and motion patterns, influenced by demographic, anthropometric and disease factors. Unravelling normal patterns of shape and motion, and understanding how each individual deviates from the norm, would facilitate accurate diagnosis and personalised treatment strategies. To this end, we developed a conditional generative model, MeshHeart, to learn the distribution of shape and motion patterns for the left and right ventricles of the heart. To model the high-dimensional spatio-temporal mesh data, MeshHeart employs a geometric encoder to represent cardiac meshes in a latent space, and a temporal Transformer to model the motion dynamics of latent representations. Based on MeshHeart, we investigate the latent space of 3D+t cardiac mesh sequences and propose a distance metric, latent delta, which quantifies the deviation of a real heart from its personalised normative pattern. In experiments using a large cardiac magnetic resonance image dataset of 38,309 subjects from the UK Biobank, MeshHeart demonstrates high performance in cardiac mesh sequence reconstruction and generation. Latent space features are discriminative for cardiac disease classification, whereas latent delta exhibits strong correlations with clinical phenotypes in phenome-wide association studies. The code and the trained model are released to support further research.