RibFrac
RibFrac 2020（肋骨骨折检测与分类挑战赛）数据集是一个大规模CT影像数据集，专注于肋骨骨折研究。该数据集包含来自660例CT扫描的约5000处肋骨骨折，其中包含420例训练CT（均含骨折）、80例验证CT（其中20例无骨折）和160例评估CT。训练集和验证集均提供影像和标注，而测试集仅提供影像数据。每例标注包含肋骨骨折区域的像素级掩膜（用于检测）以及四种骨折类型之一的分类标注。
骨头可视化图片
RibFrac_1.webp
RibFrac_4.webp
RibFrac_2.webp
RibFrac_0.png
RibFrac_3.webp
数据集元信息
| 维度 | 3D |
| 模态 | ct |
| 任务类型 | detection |
| 解剖结构 | 肋骨骨折 |
| 解剖区域 | 胸部 |
| 类别数 | 4 |
| 数据量 | 660 |
| 文件格式 | .nii.gz |
文件结构
RibFrac 2020
├── ribfrac-train-images
│ ├── RibFrac1-image.nii.gz
│ ├── RibFrac2-image.nii.gz
│ └── ...
│
├── ribfrac-train-info.csv
│
└── ribfrac-train-labels
├── RibFrac1-label.nii.gz
├── RibFrac2-label.nii.gz
└── ...
│
├── ribfrac-val-images
│ ├── RibFrac421-image.nii.gz
│ ├── RibFrac422-image.nii.gz
│ └── ...
│
├── ribfrac-val-info.csv
│
└── ribfrac-val-labels
├── RibFrac421-label.nii.gz
├── RibFrac422-label.nii.gz
└── ...图像尺寸统计
| 统计类型 | 间距 (mm) | 尺寸 |
|---|---|---|
| 最小值 | (0.56, 0.56, 0.63) |
(512, 512, 74) |
| 中位值 | (0.74, 0.74, 1.25) |
(512, 512, 357) |
| 最大值 | (0.98, 0.98, 1.5) |
(512, 512, 721) |
引用
@article{ribfracchallenge2024,
title={Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challenge},
author={Yang, Jiancheng and Shi, Rui and Jin, Liang and Huang, Xiaoyang and Kuang, Kaiming and Wei, Donglai and Gu, Shixuan and Liu, Jianying and Liu, Pengfei and Chai, Zhizhong and Xiao, Yongjie and Chen, Hao and Xu, Liming and Du, Bang and Yan, Xiangyi and Tang, Hao and Alessio, Adam and Holste, Gregory and Zhang, Jiapeng and Wang, Xiaoming and He, Jianye and Che, Lixuan and Pfister, Hanspeter and Li, Ming and Ni, Bingbing},
journal={arXiv Preprint},
year={2024}
}
@article{ribfracclinical2020,
title={Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet},
author={Jin, Liang and Yang, Jiancheng and Kuang, Kaiming and Ni, Bingbing and Gao, Yiyi and Sun, Yingli and Gao, Pan and Ma, Weiling and Tan, Mingyu and Kang, Hui and Chen, Jiajun and Li, Ming},
journal={eBioMedicine},
year={2020},
publisher={Elsevier}
}