S2MNet: Speckle-To-Mesh Net for Three-Dimensional Cardiac Morphology Reconstruction via Echocardiogram

2025-05-09

AI Summary

To address the limitations of low resolution, poor clinical applicability, and high cost associated with 3D echocardiography, this paper proposes a high-fidelity, temporally continuous 3D cardiac mesh reconstruction method from standard six-view 2D echocardiographic images. We introduce an end-to-end, deformation-field-driven mesh reconstruction paradigm that integrates differentiable mesh deformation, multi-view geometric constraints, and a synthetic paired-data training strategy—effectively circumventing the scarcity of ground-truth 3D annotations. The resulting reconstructions are anatomically accurate, topologically continuous, and free of artifacts. Evaluated on clinical data, the method achieves strong negative correlation (r = −0.89) between estimated left ventricular volumes and gold-standard GLPS measurements—matching theoretical expectations. This demonstrates both clinical reliability and practical utility for quantitative cardiac assessment.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Learning with Manifolds
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

Echocardiogram is the most commonly used imaging modality in cardiac assessment duo to its non-invasive nature, real-time capability, and cost-effectiveness. Despite its advantages, most clinical echocardiograms provide only two-dimensional views, limiting the ability to fully assess cardiac anatomy and function in three dimensions. While three-dimensional echocardiography exists, it often suffers from reduced resolution, limited availability, and higher acquisition costs. To overcome these challenges, we propose a deep learning framework S2MNet that reconstructs continuous and high-fidelity 3D heart models by integrating six slices of routinely acquired 2D echocardiogram views. Our method has three advantages. First, our method avoid the difficulties on training data acquasition by simulate six of 2D echocardiogram images from corresponding slices of a given 3D heart mesh. Second, we introduce a deformation field-based method, which avoid spatial discontinuities or structural artifacts in 3D echocardiogram reconstructions. We validate our method using clinically collected echocardiogram and demonstrate that our estimated left ventricular volume, a key clinical indicator of cardiac function, is strongly correlated with the doctor measured GLPS, a clinical measurement that should demonstrate a negative correlation with LVE in medical theory. This association confirms the reliability of our proposed 3D construction method.

Problem

• Reconstructs 3D heart models from 2D echocardiogram views
• Overcomes limitations of low-resolution 3D echocardiography
• Ensures continuous high-fidelity cardiac morphology reconstruction

Innovation

• Deep learning reconstructs 3D heart from 2D echocardiogram
• Simulates 2D images from 3D mesh for training
• Deformation field ensures smooth 3D reconstruction