CTPelvic1K
CTPelvic1K 是一个专为盆骨分割设计的大型 CT 数据集。此数据集综合了 7 个不同数据源的共计 1184例 CT数据 (包括 75 例具有金属伪影的数据)，其中 5 个是公开数据集，另外 2 个是新收集的。这些数据已针对腰椎、骶骨、左髋和右髋这 4 类盆骨部分进行了分割标注。所引用的5个公开数据集分别是：BTCV Abdomen, COLONOG, MSD Colon, KiTS19 和 BTCV CERVIX。
骨头可视化图片
可视化图片 1
可视化图片 2
可视化图片 3
可视化图片 4
数据集元信息
| 维度 | 3D |
| 模态 | ct |
| 任务类型 | segmentation |
| 解剖结构 | Pelvis |
| 解剖区域 | Pelvic cavity |
| 类别数 | 4 |
| 数据量 | 1184 |
| 文件格式 | .nii.gz |
文件结构
CTPelvic1K_dataset6_data
│
├── dataset6_CLINIC_0001_data.nii.gz
├── ...
├── dataset6_CLINIC_0103_data.nii.gz
ipcai2021_dataset6_Anonymized
│
├── dataset6_CLINIC_0001_mask_4label.nii.gz
├── ...
├── dataset6_CLINIC_0103_mask_4label.nii.gz图像尺寸统计
| 统计类型 | 间距 (mm) | 尺寸 |
|---|---|---|
| 最小值 | (0.5, 0.527, 0.625) |
(129, 512, 55) |
| 中位值 | (0.78, 0.78, 0.8) |
(512, 512, 515) |
| 最大值 | (3.75, 1.27, 7.5) |
(1059, 512, 739) |
引用
@article{deep_learning_to_segment_pelvic_bones:_large-scale_ct_datasets_and_baseline_models,
title = {Deep learning to segment pelvic bones: large-scale CT datasets and baseline models},
author = {Liu, Pengbo and Han, Hu and Du, Yuanqi and Zhu, Heqin and Li, Yinhao and Gu, Feng and Xiao, Honghu and Li, Jun and Zhao, Chunpeng and Xiao, Li and Wu, Xinbao and Zhou, S. Kevin},
journal = {International Journal of Computer Assisted Radiology and Surgery},
volume = {16},
number = {5},
year = {2021},
pages = {749},
doi = {10.1007/s11548-021-02363-8},
abstract = {Pelvic bone segmentation in CT has always been an essential step in clinical diagnosis and surgery planning of pelvic bone diseases. Existing methods for pelvic bone segmentation are either hand-crafted or semi-automatic and achieve limited accuracy when dealing with image appearance variations due to the multi-site domain shift, the presence of contrasted vessels, coprolith and chyme, bone fractures, low dose, metal artifacts, etc. Due to the lack of a large-scale pelvic CT dataset with annotations, deep learning methods are not fully explored.},
url = {https://doi.org/10.1007/s11548-021-02363-8},
}