3D Cardiac Anatomy Generation Using Mesh Latent Diffusion Models

TL;DR

This paper introduces MeshLDM, a novel latent diffusion model for generating realistic 3D cardiac mesh anatomies, demonstrating high fidelity and diversity crucial for medical applications like simulations and data augmentation.

Contribution

The paper presents MeshLDM, the first application of latent diffusion models to 3D cardiac mesh generation, improving realism and diversity in synthetic cardiac anatomies.

Findings

MeshLDM accurately captures cardiac shape characteristics.

Generated meshes show only 2.4% difference from gold standard.

Model performs well on clinical and 3D reconstruction metrics.

Abstract

Diffusion models have recently gained immense interest for their generative capabilities, specifically the high quality and diversity of the synthesized data. However, examples of their applications in 3D medical imaging are still scarce, especially in cardiology. Generating diverse realistic cardiac anatomies is crucial for applications such as in silico trials, electromechanical computer simulations, or data augmentations for machine learning models. In this work, we investigate the application of Latent Diffusion Models (LDMs) for generating 3D meshes of human cardiac anatomies. To this end, we propose a novel LDM architecture -- MeshLDM. We apply the proposed model on a dataset of 3D meshes of left ventricular cardiac anatomies from patients with acute myocardial infarction and evaluate its performance in terms of both qualitative and quantitative clinical and 3D mesh reconstruction metrics. The proposed MeshLDM successfully captures characteristics of the cardiac shapes at end-diastolic (relaxation) and end-systolic (contraction) cardiac phases, generating meshes with a 2.4% difference in population mean compared to the gold standard.