MICCAI 2020 RibFrac Challenge: 
Rib Fracture Detection and Classification


This competition is part of MICCAI 2020: the 23rd International Conference on Medical Image Computing and Computer Assisted Intervention. This year,  due to the ongoing COVID-19 pandemic, MICCAI will be held from October 4th to 8th, 2020 in Lima, Peru as a fully virtual conference. As part of the conference, the competition's organizers will host a workshop on the results of the RibFrac challenge. 



Be a part of the RibFrac Challenge workshop 

As challenge organizers, we will invite top 3 teams for detection and classification task (up to 6 teams in total), to present their method and results at the challenge workshop. Teams with interesting solution could also be invited. The workshop will be hold on October 4, 2020 as an official satellite event of MICCAI 2020. These teams will be offered partial expense to attend the satellite events, which is a good opportunity to showcase your work to the public.

Participants in this competition are not required to attend the workshop. However, only teams that are attending the workshop will be considered for presenting their work. 



Contribute to a challenge review paper

Top teams will be invited to contribute to a challenge review paper, which could be potentially accepted by a top medical image journal. Up to 10 teams will be invited  to submit a 4-page brief solution (following Springer LNCS format, i.e.,  the same format as MICCAI submissions), 2 members per team could be qualified as authors for the challenge review paper. If a public dataset is used in any form (including pretraining, domain adaption), it should be clearly stated in the solution. Besides, if the participants use fully automatic algorithms to generative auxillary labels,  it should also be clearly stated in the submitted solution. Please note that any manual labeling on training, validation or test set is strictly forbidden.

Top-3 teams for each task are required to submit the 4-page solution. If a team ranks top 3 in both detection and classification tasks, up to 3 authors could be included in the challenge review paper, as performance of the two tasks are correlated, 

The organizers reserve the right to identify the "top" teams to be invited, whch depends on leaderboard ranks (mainly), technical contributions of the solution, and numbers of participants in each task. We will send invitation to the top teams for team information, solution paper, and potential solution presentation on the challenge.



Citation

Our method and dataset was accepted by EBioMedcine (by The Lancet). We are also working on a challenge review paper.

If you find this work useful in your research, please acknowledge the RibFrac project teams in the paper and cite this project as:

Liang Jin, Jiancheng Yang, Kaiming Kuang, Bingbing Ni, Yiyi Gao, Yingli Sun, Pan Gao, Weiling Ma, Mingyu Tan, Hui Kang, Jiajun Chen, Ming Li. Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet. EBioMedicine (2020). (DOI)

or using  bibtex

@article{ribfrac2020,
                    title={Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet},
                    author={Jin, Liang and Yang, Jiancheng and Kuang, Kaiming and Ni, Bingbing and Gao, Yiyi and Sun, Yingli and Gao, Pan and Ma, Weiling and Tan, Mingyu and Kang, Hui and Chen, Jiajun and Li, Ming},
                    journal={EBioMedicine},
                    year={2020},
                    publisher={Elsevier}
}


The RibFrac dataset is a research effort of thousands of hours by experienced radiologists, computer scientists and engineers. We kindly ask you to respect our effort by appropriate citation and keeping data license.



This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.