A Personalised 3D+t Mesh Generative Model for Unveiling Normal Heart Dynamics

2024-09-20

arXiv.org

AI Summary

To address the challenge of personalized cardiac modeling, this paper introduces MeshHeart—a novel conditional geometric-temporal generative framework that synthesizes subject-specific 3D spatiotemporal heart mesh sequences from clinical covariates (e.g., age, sex, height, weight), capturing normative anatomical and functional variability. Methodologically, MeshHeart integrates a geometric encoder with a temporal Transformer, incorporates non-Euclidean mesh representation learning, and defines a new latent-space metric—“latent delta”—to quantify deviation from an individual’s personalized normative pattern. Evaluated on 38,309 cases, MeshHeart achieves high reconstruction and generation fidelity; its latent features significantly improve cardiac disease classification (AUC increase of 8.2%); and latent delta exhibits strong correlations with key phenotypes—including left ventricular ejection fraction and myocardial mass (|r| > 0.62)—establishing it as an interpretable, biologically grounded biomarker for precision diagnosis and intervention.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

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, that are influenced by demographic, anthropometric and disease factors. Unravelling the normal patterns of shape and motion, as well as understanding how each individual deviates from the norm, would facilitate accurate diagnosis and personalised treatment strategies. To this end, we developed a novel conditional generative model, MeshHeart, to learn the distribution of cardiac shape and motion patterns. MeshHeart is capable of generating 3D+t cardiac mesh sequences, taking into account clinical factors such as age, sex, weight and height. To model the high-dimensional and complex spatio-temporal mesh data, MeshHeart employs a geometric encoder to represent cardiac meshes in a latent space, followed by 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 novel distance metric termed latent delta, which quantifies the deviation of a real heart from its personalised normative pattern in the latent space. In experiments using a large dataset of 38,309 subjects, MeshHeart demonstrates a high performance in cardiac mesh sequence reconstruction and generation. Features defined in the latent space are highly discriminative for cardiac disease classification, whereas the latent delta exhibits strong correlation with clinical phenotypes in phenome-wide association studies. The codes and models of this study will be released to benefit further research on digital heart modelling.

Problem

• Modeling personalized 3D+t heart shape and motion dynamics
• Quantifying deviations from normal cardiac patterns for diagnosis
• Generating discriminative features for cardiac disease classification

Innovation

• Generates 3D+t cardiac mesh sequences
• Uses geometric encoder and Transformer
• Introduces latent delta distance metric