TetHeart

KO | EN

gitlite — search

#javascript #llm #go #golang #machine-learning #docker #java #nodejs #windows #awesome #kubernetes #vue #openai #ios

(★ 13)

[TMLR 2026] End-to-End 4D Heart Mesh Recovery Across Full-Stack and Sparse Cardiac MRI

TetHeart Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# TetHeart

By [Yihong Chen](https://scalsol.github.io/), [Jiancheng Yang](https://jiancheng-yang.com/), [Deniz Sayin Mercadier](https://scholar.google.com/citations?user=kpTb5N8AAAAJ&hl=en), [Hieu Le](https://hieulem.github.io/), [Juerg Schwitter](https://www.chuv.ch/en/cardiologie/car-home/le-service-en-bref/crmc), [Pascal Fua](https://scholar.google.com/citations?user=kzFmAkYAAAAJ&hl=en).

This repo is an official implementation of the paper "[End-to-End 4D Heart Mesh Recovery Across Full-Stack and Sparse Cardiac MRI](https://arxiv.org/abs/2509.12090)" accepted by TMLR.

## Introduction

TetHeart is an end-to-end framework for unified 4D (3D + time) heart mesh recovery from both offline full-stack and intra-procedural sparse-slice cardiac MRI. Using deformable tetrahedra to model shape and motion in a coherent space shared across cardiac structures, it initializes detailed patient-specific meshes from high-quality full stacks and updates them from whatever slices are available in real-time, down to a single one.

## Installation

Please refer to [INSTALL.md](INSTALL.md) for installation instructions.

## Data

We use the public [ACDC](https://www.creatis.insa-lyon.fr/Challenge/acdc/), [M\&Ms](https://www.ub.edu/mnms/), [M\&Ms-2](https://www.ub.edu/mnms-2/) datasets. Please find at [here](https://drive.google.com/file/d/1IBITs6BXfgck4duu4ykTaimLpslryHxE/view?usp=sharing) for the private dataset we use.

Please refer to [Bi-ventricle SSM](https://github.com/UK-Digital-Heart-Project/Statistical-Shape-Model) and [4DMR](https://arxiv.org/abs/2308.14083) to prepare GT meshes. After generation, you may need to register the meshes to the MRI image coordinate system.

### Image preprocessing

Set `DATA_ROOT` at the top of each `tools/preprocess/handle_*.py` to the directory that holds the raw datasets. Then, for each dataset, first convert it into the nnU-Net/MSD layout (`handle_*`) and then preprocess it into the per-patient `.npy` volumes consumed by the configs (`preprocess`):

```bash
# ACDC
python tools/preprocess/handle_acdc.py --task acdc
python tools/preprocess/preprocess.py --task 914 --n_jobs 4

# M&Ms
python tools/preprocess/handle_mm.py --task mm
python tools/preprocess/preprocess.py --task 933 --n_jobs 4

# M&Ms-2
python tools/preprocess/handle_mm2.py --task mm2
python tools/preprocess/preprocess.py --task 943 --n_jobs 4
```

The `handle_*` step writes the MSD folders under `data/`, and the `preprocess` step writes the final `data/{914,933,943}_3d/` folders. If you would rather keep the data elsewhere, point `target_path` (in `handle_*`) and `--results` (in `preprocess`) at another location and symlink it to `./data`.

For the private dataset, please refer to [ukbb_cardiac](https://github.com/baiwenjia/ukbb_cardiac) to process the DICOM data first.

We provide a sample processed [data](https://drive.google.com/file/d/1UXoSKUZOLRGJbMjYPJoWhScOo2PxSO8W/view?usp=sharing) from the ACDC dataset as reference.

## Get Started

### Train

```bash
python tools/train.py configs/debug.py
```

### Test / Evaluate

```bash
python tools/test.py <config> <checkpoint> --eval
```

### Inference / Visualization

```bash
python tools/test.py <config> <checkpoint> --show --show-dir <output_dir>
```

Configs live under [configs/](configs/). At there you could find some other configs for datasets like CHAOS and MMWHS. Our model can also achieve good static reconstruction results.

If you want to modify something, simply add new models, datasets, metrics and register them. Then create a new config and you are ready to go.

## Acknowledgement

We thank [NVIDIA nnU-Net](https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Segmentation/nnUNet) for its well-structured and extensible nnU-Net implementation, and [MMCV](https://github.com/open-mmlab/mmcv) for its flexible configuration system.

## Citation

If you find this work useful in your research, please consider citing:

```bibtex
@article{chen2026tetheart,
  title   = {End-to-End 4D Heart Mesh Recovery Across Full-Stack and Sparse Cardiac MRI},
  author  = {Chen, Yihong and Yang, Jiancheng and Mercadier, Deniz Sayin and Le, Hieu and Schwitter, Juerg and Fua, Pascal},
  journal = {Transactions on Machine Learning Research (TMLR)},
  year    = {2026}
}
```

TetHeart

TetHeart Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

TetHeart

TetHeart Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README