# MorphiNet: A Graph Subdivision Network for Adaptive Bi-ventricle Surface Reconstruction

arXiv: https://arxiv.org/abs/2412.10985 · HTML: https://mlsanity.com/paper/2412.10985/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 65 references that are in the map.
- First posted on arXiv 14 Dec 2024.

## Builds on (most cited first, 22 of 22)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [3D MRI brain tumor segmentation using autoencoder regularization](https://mlsanity.com/paper/1810.11654/) (2018)
- [Multivariate mixture model for myocardium segmentation combining multi-source images](https://mlsanity.com/paper/1612.08820/) (2016)
- [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)
- [Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow](https://mlsanity.com/paper/2203.08652/) (2022)
- [NISF: Neural Implicit Segmentation Functions](https://mlsanity.com/paper/2309.08643/) (2023)
- [Learning Whole Heart Mesh Generation From Patient Images For Computational Simulations](https://mlsanity.com/paper/2203.10517/) (2022)
- [SDF4CHD: Generative Modeling of Cardiac Anatomies with Congenital Heart Defects](https://mlsanity.com/paper/2311.00332/) (2023)
- [Multi-class point cloud completion networks for 3D cardiac anatomy reconstruction from cine magnetic resonance images](https://mlsanity.com/paper/2307.08535/) (2023)
- [4D Myocardium Reconstruction with Decoupled Motion and Shape Model](https://mlsanity.com/paper/2308.14083/) (2023)
- [DeepMesh: Mesh-based Cardiac Motion Tracking using Deep Learning](https://mlsanity.com/paper/2309.14306/) (2023)
- [MONAIfbs: MONAI-based fetal brain MRI deep learning segmentation](https://mlsanity.com/paper/2103.13314/) (2021)
- [CorticalFlow++: Boosting Cortical Surface Reconstruction Accuracy, Regularity, and Interoperability](https://mlsanity.com/paper/2206.06598/) (2022)
- [Shape of my heart: Cardiac models through learned signed distance functions](https://mlsanity.com/paper/2308.16568/) (2023)
- [A Comprehensive Approach for Learning-based Fully-Automated Inter-slice Motion Correction for Short-Axis Cine Cardiac MR Image Stacks](https://mlsanity.com/paper/1810.02201/) (2018)

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

- [A Strong Linear Baseline for Whole-Heart Cardiac Shape Completion on CT, with an Open Eleven-Structure Statistical Shape Model](https://mlsanity.com/paper/2608.19932/) (2026)

## Abstract (arXiv)

Cardiac Magnetic Resonance (CMR) imaging is widely used for heart model reconstruction and digital twin computational analysis because of its ability to visualize soft tissues and capture dynamic functions. However, CMR images have an anisotropic nature, characterized by large inter-slice distances and misalignments from cardiac motion. These limitations result in data loss and measurement inaccuracies, hindering the capture of detailed anatomical structures. In this work, we introduce MorphiNet, a novel network that reproduces heart anatomy learned from high-resolution Computed Tomography (CT) images, unpaired with CMR images. MorphiNet encodes the anatomical structure as gradient fields, deforming template meshes into patient-specific geometries. A multilayer graph subdivision network refines these geometries while maintaining a dense point correspondence, suitable for computational analysis. MorphiNet achieved state-of-the-art bi-ventricular myocardium reconstruction on CMR patients with tetralogy of Fallot with 0.3 higher Dice score and 2.6 lower Hausdorff distance compared to the best existing template-based methods. While matching the anatomical fidelity of comparable neural implicit function methods, MorphiNet delivered 50× faster inference. Cross-dataset validation on the Automated Cardiac Diagnosis Challenge confirmed robust generalization, achieving a 0.7 Dice score with 30% improvement over previous template-based approaches. We validate our anatomical learning approach through the successful restoration of missing cardiac structures and demonstrate significant improvement over standard Loop subdivision. Motion tracking experiments further confirm MorphiNet's capability for cardiac function analysis, including accurate ejection fraction calculation that correctly identifies myocardial dysfunction in tetralogy of Fallot patients.