Cephalometric Landmark Detection across Ages with Prototypical Network

by Han Wu*, Chong Wang*, Lanzhuju Mei, Tong Yang, Min Zhu, Dingggang Shen, and Zhiming Cui⁺.

[Paper] [Project Page]

This repository contains the code and dataset for our paper "Cephalometric Landmark Detection across Ages with Prototypical Network" in MICCAI 2024.

Updates

• [09/2024] Dataset released!
• [07/2024] Source code released!
• [06/2024] Our paper is accepted by MICCAI 2024!

Getting Started

Run the following command to install the required packages:

git clone https://github.com/ShanghaiTech-IMPACT/CeLDA.git

cd CeLDA

pip install -r requirements.txt

Training and Testing

To train the model, run the following command:

python code/train_CeLDA.py --batch_size 2 --base_lr 0.001 --max_epochs 150 --decay [50,100] --lamda_c 1 --lamda_m 0.1 --theta 1 --mask_num 7

To test the model, run the following command:

python code/test.py --base_dir /path/to/your/saved/model

Dataset

★ Our dataset is available for reserach purpose only. To apply for CephAdoAdu dataset, please fill out the form and send the signed e-copy to Han Wu (email: [email protected]) as well as CC your advisor as mentioned in Sec.5 of the form. We will send you the dataset link and password when recieving the data registration form.

Citation

If you find this code or dataset useful, please cite our paper:

@inproceedings{wu2024cephalometric,
  title={Cephalometric Landmark Detection across Ages with Prototypical Network},
  author={Wu, Han and Wang, Chong and Mei, Lanzhuju and Yang, Tong and Zhu, Min and Shen, Dinggang and Cui, Zhiming},
  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
  pages={155--165},
  year={2024},
  organization={Springer Nature Switzerland Cham}
}