[MICCAI'24] Epicardium Prompt-guided Real-time Cardiac Ultrasound Frame-to-volume Registration

Official Implementation of "Epicardium Prompt-guided Real-time Cardiac Ultrasound Frame-to-volume Registration"

Long Lei, Jun Zhou, Jialun Pei✉, Baoliang Zhao, Yueming Jin, Yuen-Chun Jeremy Teoh, Jing Qin, and Pheng-Ann Heng

[Paper]; [Official Version]

Contact: peijialun@gmail.com, longlei@cuhk.edu.hk

Installation

Conda virtual environment

We recommend using conda to setup the environment.

If you have already installed conda, please use the following commands.

conda create -n CU-Reg python=3.8
conda activate CU-Reg
pip install -r requirements.txt

Dataset

Download the processed CAMUS dataset, you can download it here.

Evaluation

Please download our trained model here and put it in the 'experiments/trained_models' directory. Then, you can have a quick evaluation using the following command.

python test.py

Train

In order to train the model, remember to download the complete dataset.

train.py is the main file for training. You can simply start training using the following command.

python train.py

Citation

If you find the code useful, please cite our paper.

@article{lei2024epicardium,
      title={Epicardium Prompt-guided Real-time Cardiac Ultrasound Frame-to-volume Registration}, 
      author={Long Lei and Jun Zhou and Jialun Pei and Baoliang Zhao and Yueming Jin and Yuen-Chun Jeremy Teoh and Jing Qin and Pheng-Ann Heng},
      journal={arXiv preprint arXiv:2406.14534},
      year={2024},
}

Acknowledgment

Our code is developed based on FVR-Net.