# Relational Anatomical Supervision for Accurate 3D Multi-Chamber Cardiac Mesh Reconstruction

arXiv: https://arxiv.org/abs/2503.07874 · HTML: https://mlsanity.com/paper/2503.07874/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 16 of 16)

- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://mlsanity.com/paper/2003.07311/) (2020)
- [Neural Cages for Detail-Preserving 3D Deformations](https://mlsanity.com/paper/1912.06395/) (2019)
- [Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge](https://mlsanity.com/paper/1902.07880/) (2019)
- [ImageCAS: A Large-Scale Dataset and Benchmark for Coronary Artery Segmentation based on Computed Tomography Angiography Images](https://mlsanity.com/paper/2211.01607/) (2022)
- [Voxel2Mesh: 3D Mesh Model Generation from Volumetric Data](https://mlsanity.com/paper/1912.03681/) (2019)
- [A Deep-Learning Approach For Direct Whole-Heart Mesh Reconstruction](https://mlsanity.com/paper/2102.07899/) (2021)
- [DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates](https://mlsanity.com/paper/2102.09105/) (2021)
- [Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes](https://mlsanity.com/paper/2206.04942/) (2022)
- [SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images](https://mlsanity.com/paper/2008.05742/) (2020)
- [Learning Whole Heart Mesh Generation From Patient Images For Computational Simulations](https://mlsanity.com/paper/2203.10517/) (2022)
- [Whole Heart Mesh Generation For Image-Based Computational Simulations By Learning Free-From Deformations](https://mlsanity.com/paper/2107.10839/) (2021)
- [Multi-view Hybrid Graph Convolutional Network for Volume-to-mesh Reconstruction in Cardiovascular MRI](https://mlsanity.com/paper/2311.13706/) (2023)
- [LinFlo-Net: A two-stage deep learning method to generate simulation ready meshes of the heart](https://mlsanity.com/paper/2310.20065/) (2023)
- [Differentiable Voxelization and Mesh Morphing](https://mlsanity.com/paper/2407.11272/) (2024)
- [Preserving Cardiac Integrity: A Topology-Infused Approach to Whole Heart Segmentation](https://mlsanity.com/paper/2410.10551/) (2024)

## Built on by (most cited first, 1 of 1)

- [HeartFormer: Semantic-Aware Dual-Structure Transformers for 3D Four-Chamber Cardiac Point Cloud Reconstruction](https://mlsanity.com/paper/2512.00264/) (2025)

## Abstract (arXiv)

Accurate reconstruction of multi-chamber cardiac anatomy from medical images is a cornerstone for patient-specific modeling, physiological simulation, and interventional planning. However, current reconstruction pipelines fundamentally rely on surface-wise geometric supervision and model each chamber in isolation, resulting in anatomically implausible inter-chamber violations despite apparently favorable overlap or distance metrics. In this work, we propose a relational anatomical supervision framework for multi-chamber cardiac mesh reconstruction by introducing a Mesh Interrelation Enhancement (MIE) loss. The proposed formulation explicitly encodes spatial relationships between cardiac structures into a differentiable occupancy-based objective, thereby transforming qualitative anatomical rules into quantitative geometric supervision. We further establish violation-aware evaluation metrics to directly quantify inter-chamber structural correctness, revealing systematic limitations of commonly used geometric measures such as Dice and Chamfer distance. Extensive experiments on multi-center CT data, densely sampled MR data, and two independent external cohorts, including a highly heterogeneous congenital heart disease population, demonstrate that the proposed method consistently suppresses clinically critical boundary violations by up to 83%, while maintaining competitive volumetric accuracy and achieving superior surface fidelity. Notably, the proposed relational supervision generalizes robustly across imaging modalities, centers, and pathological conditions, even under severe anatomical deformation. These results demonstrate that distance-based supervision alone is insufficient to guarantee anatomically faithful reconstruction, and that explicit enforcement of multi-structure anatomical relations provides a principled and robust pathway toward reliable patient-specific cardiac modeling.