TopCoW 2024 Challenge
๐ฐ News:
[09-05] Repo for 2024 algorithm submission template is now on GitHub! ๐ TopCoW_Algo_Submission ๐
[07-17] All training data (125 pairs of MRA and CTA) with annotations have now been released!
-
39% increase of training data from 90 to 125 pairs of CTA and MRA
-
Corrected mask and bounding box labels for 2023 data
-
Two new tasks with annotations
-
A more open data license for 2024 data release
๐ Check out our Data page
and Tasks page!
Last year, TopCoW 2023 welcomed over 140 registered participants from four continents, and 20 teams successfully made a submission to our challenge. We presented the results and gave out small prizes to winning teams in Vancouver during the challenge event on October 12th at MICCAI 2023.
arXiv Summary Paper
๐ ๐ฐ Last year's challenge results have been summarized in a pre-print on arXiv! https://arxiv.org/abs/2312.17670@misc{topcowchallenge, title={Benchmarking the CoW with the TopCoW Challenge: Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA}, author={Kaiyuan Yang and Fabio Musio and Yihui Ma and Norman Juchler and Johannes C. Paetzold and Rami Al-Maskari and Luciano Hรถher and Hongwei Bran Li and Ibrahim Ethem Hamamci and Anjany Sekuboyina and Suprosanna Shit and Houjing Huang and Chinmay Prabhakar and Ezequiel de la Rosa and Diana Waldmannstetter and Florian Kofler and Fernando Navarro and Martin Menten and Ivan Ezhov and Daniel Rueckert and Iris Vos and Ynte Ruigrok and Birgitta Velthuis and Hugo Kuijf and Julien Hรคmmerli and Catherine Wurster and Philippe Bijlenga and Laura Westphal and Jeroen Bisschop and Elisa Colombo and Hakim Baazaoui and Andrew Makmur and James Hallinan and Bene Wiestler and Jan S. Kirschke and Roland Wiest and Emmanuel Montagnon and Laurent Letourneau-Guillon and Adrian Galdran and Francesco Galati and Daniele Falcetta and Maria A. Zuluaga and Chaolong Lin and Haoran Zhao and Zehan Zhang and Sinyoung Ra and Jongyun Hwang and Hyunjin Park and Junqiang Chen and Marek Wodzinski and Henning Mรผller and Pengcheng Shi and Wei Liu and Ting Ma and Cansu Yalรงin and Rachika E. Hamadache and Joaquim Salvi and Xavier Llado and Uma Maria Lal-Trehan Estrada and Valeriia Abramova and Luca Giancardo and Arnau Oliver and Jialu Liu and Haibin Huang and Yue Cui and Zehang Lin and Yusheng Liu and Shunzhi Zhu and Tatsat R. Patel and Vincent M. Tutino and Maysam Orouskhani and Huayu Wang and Mahmud Mossa-Basha and Chengcheng Zhu and Maximilian R. Rokuss and Yannick Kirchhoff and Nico Disch and Julius Holzschuh and Fabian Isensee and Klaus Maier-Hein and Yuki Sato and Sven Hirsch and Susanne Wegener and Bjoern Menze}, year={2024}, eprint={2312.17670}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2312.17670}, }
And now we are back for Season 2!
In the new 2024 edition of TopCoW, we release more training data, expand the test set, and introduce new tasks!
Here is what's new in 2024:
More Data
We increase both the training data and test data size. In particular, we double the test set for benchmarking and make it multi-center.
- 39% increase in training data from 90 to 125 pairs of CTA and MRA
- Double the online test data from 35 to 70 pairs (and maybe more!)
- Additional multi-center test data
- A new and more open data usage license
- ๐ Our Data page has more details!
Two New Tasks
On top of the multi-class segmentation task continued from last year, we introduce two new tasks in 2024: CoW object detection and CoW graph classification. The two new tasks are closely related to our theme of CoW topological segmentation.
- CoW object detection with 3D bounding box annotations
- CoW graph classification with edge list annotations
- Potential integration of three CoW tasks to help solve one another
- ๐ Go to our Tasks page to find out more!
Updated Labels
We updated mask and bounding box labels for some of the 2023 data, both for training and the test data.
- Corrected Betti-0 issues in mask labels for 19 cases from 2023 data
- Refined CoW ROI 3D bounding box labels
Timeline ๐
- ๐ Submit to ๐ final test phases:
September 21 - September 30, 2024
- Submit to Final Test CTA Task-1 Segmentation
- Submit to Final Test CTA Task-2 ObjDet
- Submit to Final Test CTA Task-3 Classification
- Submit to Final Test MRA Task-1 Segmentation
- Submit to Final Test MRA Task-2 ObjDet
- Submit to Final Test MRA Task-3 Classification
- ๐ Submit to validation phases:
September 14 - September 30, 2024
- Submit to Validation CTA Task-1 Segmentation
- Submit to Validation CTA Task-2 ObjDet
- Submit to Validation CTA Task-3 Classification
- Submit to Validation MRA Task-1 Segmentation
- Submit to Validation MRA Task-2 ObjDet
- Submit to Validation MRA Task-3 Classification
- โ
Release of all 125 pairs of MRA and CTA of the training data with annotations for all three tasks:
July 17, 2024
Links
TopCoW in Research
๐ ๐ฐ We are very glad to see that our TopCoW challenge has somewhat piqued the interest of the community on both the technical and clinical aspects of the CoW segmentation task. Here are just some publications that cited our TopCoW dataset in their research since March 2024:
- Berger, Alexander H., et al. "Topologically faithful multi-class segmentation in medical images." arXiv preprint arXiv:2403.11001 (2024). [Link] (Accepted to MICCAI 2024)
- Aydin, Orhun Utku, et al. "Generative Modeling of the Circle of Willis Using 3D-StyleGAN." medRxiv (2024): 2024-04. [Link]
- Kirchhoff, Yannick, et al. "Skeleton recall loss for connectivity conserving and resource efficient segmentation of thin tubular structures." arXiv preprint arXiv:2404.03010 (2024). [Link] (Accepted to ECCV 2024)
- Lengyel, Balรกzs, et al. "Non-Invasive Tools in Perioperative Stroke Risk Assessment for Asymptomatic Carotid Artery Stenosis with a Focus on the Circle of Willis." Journal of Clinical Medicine 13.9 (2024): 2487. [Link]
- Winter, Patrick, et al. "Automated intracranial vessel segmentation of 4D flow MRI data in patients with atherosclerotic stenosis using a convolutional neural network." Frontiers in Radiology 4 (2024): 1385424. [Link]
- Shi, Pengcheng, et al. "Centerline Boundary Dice Loss for Vascular Segmentation." arXiv preprint arXiv:2407.01517 (2024). [Link] (Accepted to MICCAI 2024)
- Stucki, Nico, et al. "Efficient Betti Matching Enables Topology-Aware 3D Segmentation via Persistent Homology." arXiv preprint arXiv:2407.04683 (2024). [Link]
- Prabhakar, Chinmay, et al. "3D Vessel Graph Generation Using Denoising Diffusion." arXiv preprint arXiv:2407.05842 (2024). [Link] (Accepted to MICCAI 2024)
Our GitHub
Please visit our GitHub for repos and documentations on:
Forum
We have a forum to post your questions! Link