VerSe
VerSe（Vertebrae Segmentation，椎体分割）数据集是一个大规模、多设备、多中心的CT影像脊柱分割数据集，包含来自355名患者的374次扫描。该数据集整合了2019年和2020年MICCAI会议上VerSe19和VerSe20挑战赛的数据。具体而言，VerSe19包含141名患者的160次扫描，VerSe20包含300名患者的319次扫描。但由于两个数据集之间存在86名患者重叠，VerSe中实际独立患者数并非简单相加。
骨头可视化图片
可视化图片 1
可视化图片 2
数据集元信息
| 维度 | 3D |
| 模态 | ct |
| 任务类型 | segmentation |
| 解剖结构 | 椎体 |
| 解剖区域 | 脊柱 |
| 类别数 | 26 |
| 数据量 | 训练141例，验证120例，测试113例 |
| 文件格式 | .nii.gz |
文件结构
dataset-01training
├── rawdata
│ └── sub-gl003
│ └── sub-gl003_dir-ax_ct.nii.gz
└── derivatives
└── sub-gl003
├── sub-gl003_dir-ax_seg-subreg_ctd.json
├── sub-gl003_dir-ax_seg-vert_msk.nii.gz
└── sub-gl003_dir-ax_seg-vert_snp.png图像尺寸统计
| 统计类型 | 间距 (mm) | 尺寸 |
|---|---|---|
| 最小值 | (0.19, 0.19, 0.40) |
(103, 144, 34) |
| 中位值 | (0.92, 0.92, 1.0) |
(512, 512, 292) |
| 最大值 | (1.67, 1.67, 5.0) |
(960, 2048, 2023) |
引用
@article{Sekuboyina2021,
title={VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images},
author={Sekuboyina, Anjany and Husseini, Malek E and Bayat, Amirhossein and Löffler, Maximilian and Liebl, Hans and Li, Hongwei and Tetteh, Giles and Kukačka, Jan and Payer, Christian and Štern, Darko and others},
journal={Medical image analysis},
volume={71},
pages={102166},
year={2021},
publisher={Elsevier}
}
@article{Loffler2020,
title={A Vertebral Segmentation Dataset with Fracture Grading},
author={L{\"o}ffler, Maximilian T and Sekuboyina, Anjany and Jacob, Alina and Grau, Anna-Lena and Scharr, Andreas and El Husseini, Malek and Kallweit, Mareike and Zimmer, Claus and Baum, Thomas and Kirschke, Jan S},
journal={Radiology: Artificial Intelligence},
volume={2},
number={4},
pages={e190138},
year={2020},
publisher={Radiological Society of North America}
}
@article{Liebl2021,
title={A Computed Tomography Vertebral Segmentation Dataset with Anatomical Variations and Multi-Vendor Scanner Data},
author={Liebl, Hans and Schinz, David and Sekuboyina, Anjany and Malagutti, Luca and L{\"o}ffler, Maximilian T and Bayat, Amirhossein and El Husseini, Malek and Tetteh, Giles and Grau, Katharina and Niederreiter, Eva and others},
journal={arXiv preprint arXiv:2103.06360},
year={2021}
}