VerSe'20 CT Dataset
A. Sekuboyina and J. Kirschke

folder VerSe-complete (3 files)
filedataset-verse20validation.zip 13.15GB
filedataset-verse20training.zip 11.51GB
filedataset-verse20test.zip 14.02GB
Type: Dataset
Tags:

Metadata:
@article{,
title= {VerSe'20 CT Dataset},
doi= {10.1016/j.media.2021.102166},
year= {2020},
keywords= {},
author= {A. Sekuboyina and Malek El Husseini and Amirhossein Bayat and M. Löffler and H. Liebl and H. Li and Giles Tetteh and J. Kukačka and Christian Payer and Darko Štern and Martin Urschler and Maodong Chen and Dalong Cheng and N. Lessmann and Yujin Hu and Tian-Fu Wang and Dong Yang and Da-Guang Xu and F. Ambellan and Tamaz Amiranashvili and M. Ehlke and H. Lamecker and S. Lehnert and Marilia Lirio and Nicolás Pérez de Olaguer and H. Ramm and Manish Sahu and A. Tack and S. Zachow and Tao Jiang and Xinjun Ma and C. Angerman and Xin Wang and K. Brown and Alexandre Kirszenberg and É. Puybareau and Dian-Xin Chen and Yi-Wei Bai and Brandon H. Rapazzo and Timyoas Yeah and Amber Zhang and Shang-Liang Xu and Feng Hou and Zhi-Qiang He and Chang-Sha-Chi-Na-Liu-Wang Zeng and Xiang-Shang Zheng and Li-Ming Xu and T. Netherton and R. Mumme and L. Court and Zi-Xun Huang and Chen-Hang He and Li-Wen Wang and Sai H. Ling and Huynh Duy Lê and Nicolas Boutry and Roman Jakubícek and Jirí Chmelík and Supriti Mulay and M. Sivaprakasam and J. Paetzold and Suprosanna Shit and I. Ezhov and B. Wiestler and Ben Glocker and A. Valentinitsch and M. Rempfler and B. Menze and J. Kirschke},
abstract= {VerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images

## What is VerSe?
Spine or vertebral segmentation is a crucial step in all applications regarding automated quantification of spinal morphology and pathology. With the advent of deep learning, for such a task on computed tomography (CT) scans, a big and varied data is a primary sought-after resource. However, a large-scale, public dataset is currently unavailable.

We believe *VerSe* can help here. VerSe is a large scale, multi-detector, multi-site, CT spine dataset consisting of 374 scans from 355 patients. The challenge was held in two iterations in conjunction with MICCAI 2019 and 2020. The tasks evaluated for include: vertebral labelling and segmentation.  

## Citing VerSe

If you use VerSe, we would appreciate references to the following papers. 

1. **Sekuboyina A et al., VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images, 2021.**<br />In Medical Image Analysis: https://doi.org/10.1016/j.media.2021.102166<br />Pre-print: https://arxiv.org/abs/2001.09193

2. **Löffler M et al., A Vertebral Segmentation Dataset with Fracture Grading. Radiology: Artificial Intelligence, 2020.**<br />In Radiology AI: https://doi.org/10.1148/ryai.2020190138

3. **Liebl H and Schinz D et al., A Computed Tomography Vertebral Segmentation Dataset with Anatomical Variations and Multi-Vendor Scanner Data, 2021.**<br />Pre-print: https://arxiv.org/pdf/2103.06360.pdf


## Data

* The dataset has four files corresponding to one data sample: image, segmentation mask, centroid annotations, a PNG overview of the annotations.

* Data structure 
    - 01_training - Train data
    - 02_validation - (Formerly) PUBLIC test data
    - 03_test - (Formerly) HIDDEN test data

* Sub-directory-based arrangement for each patient. File names are constructed of entities, a suffix and a file extension following the conventions of the Brain Imaging Data Structure (BIDS; https://bids.neuroimaging.io/)

```
Example:
-------
training/rawdata/sub-verse000
    sub-verse000_dir-orient_ct.nii.gz - CT image series

training/derivatives/sub-verse000/
    sub-verse000_dir-orient_seg-vert_msk.nii.gz - Segmentation mask of the vertebrae
    sub-verse000_dir-orient_seg-subreg_ctd.json - Centroid coordinates in image space
    sub-verse000_dir-orient_seg-vert_snp.png - Preview reformations of the annotated CT data.

```


* Centroid coordinates of the subject based structure (.json file) are given in voxels in the image space. 'label' corresponds to the vertebral label: 
    - 1-7: cervical spine: C1-C7 
    - 8-19: thoracic spine: T1-T12 
    - 20-25: lumbar spine: L1-L6 
    - 26: sacrum - not labeled in this dataset 
    - 27: cocygis - not labeled in this dataset 
    - 28: additional 13th thoracic vertebra, T13

**Reference:** Sekuboyina et al., VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images. 2020. https://doi.org/10.1016/j.media.2021.102166 (arXiv: https://arxiv.org/abs/2001.09193)},
terms= {},
license= {https://creativecommons.org/licenses/by-sa/4.0/},
superseded= {},
url= {https://github.com/anjany/verse}
}

Citation:
Sekuboyina, A. & Kirschke, J.. (2020). VerSe'20 CT Dataset [Data set]. Academic Torrents. https://academictorrents.com/details/0ac07fd4ddf1802208f88c61c5ccf7d029d87a18

Send Feedback