Anatomy aligned learning improves heart surface reconstruction from MRI
Anatomy-Aligned Surface Field Learning for Myocardial Reconstruction from Sparse Short-Axis Cine MRI
Computer Vision and Pattern Recognition
Summary
Reconstructing the 3D shape of the heart muscle from MRI images is tricky because standard scans only take thin slices, leaving gaps in the data. The authors developed a method that lines up heart surface shapes within a shared coordinate system, making it easier to complete the missing parts accurately. Their approach helps create a smooth and consistent surface model of the heart’s inner and outer walls from sparse MRI slices. Tests on public datasets show this method reconstructs heart shapes more precisely and keeps important heart function measures accurate.
What this means in practice
- •For medical imaging engineers: Build tools to reconstruct detailed heart surface models from limited MRI slices to enhance clinical heart function analysis.
- •For cardiac simulation developers: Create accurate personalized heart models from sparse MRI data for use in simulation-based cardiac studies.
Authors
Xiaohan Yuan, Xuan Yang, Qingya Li, Yangang Wang, Lei Li
Abstract
Patient-specific 4D myocardial reconstruction from cine MRI supports quantitative functional assessment, regional motion analysis, and simulation-based modeling. However, routinely acquired short-axis (SAX) cine MRI is sparsely sampled along the through-plane direction, making dense and anatomically consistent surface reconstruction challenging. In this study, we propose an anatomy-aligned surface learning framework that parameterizes the epicardial and endocardial surfaces on a shared circumferential-longitudinal UV domain. This formulation converts irregular 3D reconstruction into structured coordinate-field completion with explicit correspondence across subjects and cardiac phases. Sparse SAX contours are encoded as UV observation fields, coverage-aware sampling improves robustness to incomplete slice coverage, and topology- and distortion-aware learning preserves circumferential continuity and local surface quality. Experiments on three public cine MRI datasets showed that the proposed method consistently outperformed representative mesh-based and implicit reconstruction approaches, achieving overall Chamfer distances of $2.887$~mm on ACDC, $2.641$~mm on M\&Ms, and $2.810$~mm on M\&Ms-2. The reconstructed sequences also preserved ventricular function, with end-diastolic volume and ejection fraction errors of $3.3$~mL and $1.1 \%$, respectively. These results demonstrate that anatomy-aligned UV learning provides an accurate, efficient, and correspondence-aware representation for sparse cine MRI reconstruction and myocardial modeling. The source code will be available at https://github.com/yuan-xiaohan/SAX2MyoSurf.