TopCoW 2024 Challenge Banner
Join

TopCoW Challenge Data

The challenge data cohort was composed of patients admitted to the Stroke Center of the University Hospital Zurich (USZ) in 2018 and 2019. The inclusion criteria for the challenge data were: 1) both MRA and CTA scans were available for that patient; 2) at least the MRA or CTA allowed for an assessment of the CoW anatomy. The patients of the challenge cohort were admitted for or recovering from a stroke-related neurological disorder, including ischemic stroke, transient ischemic attack, stroke mimic, retinal infarct or amaurosis fugax, intracerebral hemorrhage, and cerebral sinus vein thrombosis.

More information on the additional multi-center test sets will come soon.

Data Acquisition

The two imaging modalities used were: Computed tomography Angiography (CTA) and Time of Flight Magnetic Resonance Angiography (TOF-MRA) or MRA. The MRA and CTA data were typically acquired by various Siemens scanners during routine examinations following standard clinical protocols. MRA scans were imaged with magnetic field strength of 3 Tesla or 1.5 Tesla. Most of the data were acquired at the USZ during routine examinations following standard procedures for MRA and CTA. Some of the data were acquired by neighbouring Swiss hospitals before the patients were transferred to USZ.

For CTA, the voxel size was around 0.45 mm in the X-Y dimension, and around 0.7 mm in the Z dimension. For MRA, the voxel size was around 0.3 mm in the X-Y dimension, and around 0.6 mm in the Z dimension.

Anonymization and Defacing

The data were anonymized (removal and anonymization of relevant DICOM patient information). Additional de-facing and cropping procedures were performed to ensure patient privacy in the image data. Specifically, we masked out or shear-cutted the facial regions, and then cropped the image data to include only the braincase region.

Training and Test Set

Training, validation, and test cases all have the MRA and CTA joint-modality pairs, with one scan for each modality.

  • Training dataset: 125 patients (both images and annotations released)
  • Validation set: 5 patients (only images released to public but without annotations)
  • Test set: 70 patients (not released to public)
  • In-house multi-center test sets: more info coming soon

Contents of Released Training Data

The training data consist of:

  • 250 (=125 pairs) CTA and MRA for TopCoW 2024 challenge
  • voxel annotations for CoW multi-class segmentation
  • bounding box annotations for CoW object detection
  • edge list annotations for CoW graph classification

The training (Tr) data folder has the following sub-folders:

  • imagesTr: Angiographic scans in nifti format, 16-bit signed. LPS+ orientation
    • The nifti filenames are saved with schema: topcow_{modality}_{pat_id}_0000.nii.gz
      • modality: mr for MRA, ct for CTA
      • pat_id: patient ID, 001, 002, ...
  • cow_seg_labelsTr: Multi-class segmentation mask nifti with CoW anatomical labels
    • Voxel values for different CoW vessel segments:
      • 0: Background, 1: BA, 2: R-PCA, 3: L-PCA, 4: R-ICA, 5: R-MCA, 6: L-ICA, 7: L-MCA, 8: R-Pcom, 9: L-Pcom, 10: Acom,11: R-ACA, 12: L-ACA, 15: 3rd-A2
  • roi_loc_labelsTr: Size and location info for the CoW region of interest (ROI) i.e. the 3D bounding box:
    • Text file containing the size and location of the 3D bounding box info
      • Size = number of pixels along the x, y, z axis
      • Location = coordinate of the x-min, y-min, z-min (0-indexed)
  • antpos_edges_labelsTr: Edge list of anterior and posterior edges of the CoW graph
    • Yml file indicating the presence of edges (0: absent, 1: present)
      • 4 edges for anterior part, roughly from left to right:
        • L-A1
        • Acom
        • 3rd-A2
        • R-A1
      • 4 edges for posterior part, roughly from left to right:
        • L-Pcom
        • L-P1
        • R-P1
        • R-Pcom

We also released 10 (=5 pairs) CTA and MRA from TopCoW challenge in folder imagesVal but without the accompanying annotations. The small validation set is intended to validate the docker submission technically and not counted towards the ranking.

Example tree view of the released data folder for pat_id of 001 and 091:

# Note that TopCoW data has two modalities `mr` and `ct`
TopCoW2024_Data_Release/
├── antpos_edges_labelsTr
│   ├── topcow_ct_001.yml
│   ├── topcow_mr_001.yml
├── cow_seg_labelsTr
│   ├── topcow_ct_001.nii.gz
│   ├── topcow_mr_001.nii.gz
├── imagesTr
│   ├── topcow_ct_001_0000.nii.gz
│   ├── topcow_mr_001_0000.nii.gz
├── roi_loc_labelsTr
│   ├── topcow_ct_001.txt
│   ├── topcow_mr_001.txt
├── imagesVal
│   ├── topcow_ct_091_0000.nii.gz
│   ├── topcow_mr_091_0000.nii.gz
├── License.txt
└── README.txt

Data Usage License

Following the definitions of "https://opendata.swiss/en/terms-of-use" on open data use, the following license is chosen for our data release:

Open use. Must provide the source. Use for commercial purposes requires permission of the data owner.

  • You may use this dataset for non-commercial purposes.
  • You may use this dataset for commercial purposes, but you must seek prior permission from the data owner.
  • You must provide the source (author, title and link to the dataset).

By downloading the data, you agree with the license terms.

For more information, please refer to the "License.txt" file in the data release folder.

Citation

If you use TopCoW challenge data in your work, please cite our challenge pre-print:

@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 Höher 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 Hämmerli 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 Müller and Pengcheng Shi and Wei Liu and Ting Ma and Cansu Yalçin 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},
}

Last updated on July 23, 2024