Local2Mesh: Spatially Localized Contour-to-Mesh for Left Ventricular Reconstruction from Sparse 2D Cardiac MRI

2026-10-05

AI Summary

This study addresses the challenge of 3D left ventricular reconstruction from sparse cardiac MRI, where slice misalignment and insufficient local information degrade geometric fidelity. We propose a spatially localized contour-to-mesh framework that reconstructs 3D geometry from sparse 2D contours without requiring 3D annotations. Specifically, we introduce a geometry-aware alignment module to correct inter-slice misalignment and design a plane-aware router for precise mapping of local features to mesh vertices. These components are integrated with graph-based template deformation to achieve high-quality reconstruction. Evaluated on the M&Ms-2 and ACDC datasets, our method surpasses existing baselines in reconstruction accuracy, demonstrates strong cross-domain generalization, and effectively enhances downstream disease classification performance.

Abstract

Three-dimensional (3D) left ventricular (LV) reconstruction from sparse cardiac magnetic resonance (CMR) imaging remains challenging due to inter-slice misalignment and insufficient local spatial information between slices. Global aggregation of contour features may obscure local contour-to-surface relationships. We propose Local2Mesh, a spatially localized contour-to-mesh framework that deforms a template mesh to reconstruct 3D LV geometry from sparse 2D contours without 3D mesh annotations. The framework introduces geometry-aware alignment to correct inter-slice misalignment and a plane-aware Local Router that routes contour features to template vertices using vertex-to-plane distances. Local and global contour features then jointly guide graph-based template deformation for 3D LV reconstruction. Experiments on two public datasets, M\&Ms-2 and ACDC, demonstrate superior geometric reconstruction and functional estimation over existing methods. Zero-shot transfer from M\&Ms-2 to ACDC demonstrates strong cross-dataset generalization. Reconstructed meshes also improve disease classification over sparse contours, supporting their utility for downstream cardiac analysis. These results demonstrate that combining geometry-aware alignment with local contour-to-vertex modeling improves LV reconstruction from sparse 2D contours and supports downstream cardiac analysis. The code is available at \url{https://github.com/hwu918945-alt/loca2mesh}.

Problem

• 3D left ventricular reconstruction
• sparse cardiac MRI
• inter-slice misalignment
• contour-to-mesh

Innovation

• Contour-to-Mesh
• Geometry-aware Alignment
• Plane-aware Local Router
• Graph-based Deformation
• Left Ventricular Reconstruction