This repository is created for our organized MICCAI 2022 Challenge: Multi-site, Multi-Domain Airway Tree Modeling (ATM’22)
Airway segmentation is a crucial step for the analysis of pulmonary diseases including asthma, bronchiectasis, and emphysema. The accurate segmentation based on X-Ray computed tomography (CT) enables the quantitative measurements of airway dimensions and wall thickness, which can reveal the abnormality of patients with chronic obstructive pulmonary disease (COPD). Besides, the extraction of patient-specific airway models from CT images is required for navigation in bronchoscopic-assisted surgery. Due to the fine-grained pulmonary airway structure, manual annotation is however time-consuming, error-prone, and highly relies on the expertise of clinicians.
We collected 500 CT scans from multi-sites. The airway tree structures are carefully labeled by three radiologists with more than five years of professional experience. The intra-class imbalance among the trachea, main bronchi, lobar bronchi, and distal segmental bronchi affects the segmentation performance of peripheral bronchi. In conclusion, we encourage the participating teams to design robust algorithms, which can extract the airway tree structure with high topological completeness and accuracy for clinical use. Our challenge is open call (challenge opens for new submissions after MICCAI 2022 deadline). The registration page and detailed information could refer to the Registration Page.
If you find this repo's papers and codes are helpful to your research, and if you use our dataset provided by ATM'22 for your scientific research, please cite the following works:
@incollection{zhang2021fda,
title={Fda: Feature decomposition and aggregation for robust airway segmentation},
author={Zhang, Minghui and Yu, Xin and Zhang, Hanxiao and Zheng, Hao and Yu, Weihao and Pan, Hong and Cai, Xiangran and Gu, Yun},
booktitle={Domain Adaptation and Representation Transfer, and Affordable Healthcare and AI for Resource Diverse Global Health},
pages={25--34},
year={2021},
publisher={Springer}
}
@article{zheng2021alleviating,
title={Alleviating class-wise gradient imbalance for pulmonary airway segmentation},
author={Zheng, Hao and Qin, Yulei and Gu, Yun and Xie, Fangfang and Yang, Jie and Sun, Jiayuan and Yang, Guang-Zhong},
journal={IEEE Transactions on Medical Imaging},
volume={40},
number={9},
pages={2452--2462},
year={2021},
publisher={IEEE}
}
@inproceedings{yu2022break,
title={BREAK: Bronchi Reconstruction by gEodesic transformation And sKeleton embedding},
author={Yu, Weihao and Zheng, Hao and Zhang, Minghui and Zhang, Hanxiao and Sun, Jiayuan and Yang, Jie},
booktitle={2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)},
pages={1--5},
year={2022},
organization={IEEE}
}
@inproceedings{qin2019airwaynet,
title={Airwaynet: a voxel-connectivity aware approach for accurate airway segmentation using convolutional neural networks},
author={Qin, Yulei and Chen, Mingjian and Zheng, Hao and Gu, Yun and Shen, Mali and Yang, Jie and Huang, Xiaolin and Zhu, Yue-Min and Yang, Guang-Zhong},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages={212--220},
year={2019},
organization={Springer}
}
We collected the papers related to pulmonary airway segmentation and bronchoscopy navigation as belows:
We provide a baseline model and a detailed docker tutorial for the ATM 22 Challenge. Please refer to baseline-and-docker-example for detailed instructions.