CrossMoDA2021数据集是医学图像分割领域中跨模态域适应任务的经典数据集。作为当时医学影像领域首个无监督域适应基准,该数据集提供了两种模态的脑部MRI图像:对比增强T1加权(T1-CE)和高分辨率T2加权(T2-HR),并包含两种模态下前庭神经鞘瘤和耳蜗的手动标注掩膜。训练集包含105例带分割掩膜的T1-CE模态脑部图像和105例无标注的T2-HR模态脑部图像,验证集包含32例T2-HR模态MRI脑部图像,测试集包含107例T2-HR模态MRI脑部图像。
toujingbu维度 | 3D |
模态 | multimodal |
任务类型 | segmentation |
解剖结构 | 肿瘤、耳蜗 |
解剖区域 | 脑部 |
类别数 | 2 |
数据量 | 349 |
文件格式 | .nii.gz |
CrossMoDA21/
├── crossmoda_training/
│ ├── source_training/
│ │ ├── crossmoda_1_ceT1.nii.gz
│ │ ├── crossmoda_1_Label.nii.gz
│ │ ├── crossmoda_2_ceT1.nii.gz
│ │ ├── crossmoda_2_Label.nii.gz
│ │ ├── crossmoda_3_ceT1.nii.gz
│ │ ├── crossmoda_3_Label.nii.gz
│ │ ├── ...
│ ├── target_training/
│ │ ├── crossmoda_106_hrT2.nii.gz
│ │ ├── crossmoda_107_hrT2.nii.gz
│ │ ├── crossmoda_108_hrT2.nii.gz
│ │ ├── crossmoda_109_hrT2.nii.gz
│ │ ├── ...
├── crossmoda_validation/
│ ├── target_validation/
│ │ ├── crossmoda_211_hrT2.nii.gz
│ │ ├── crossmoda_212_hrT2.nii.gz
│ │ ├── crossmoda_213_hrT2.nii.gz
│ │ ├── crossmoda_214_hrT2.nii.gz
│ │ ├── ...
统计类型 | 间距 (mm) | 尺寸 |
---|---|---|
最小值 | (0.41015625,0.41015625,1) |
512x512x120 |
中位值 | (0.41015625,0.41015625,1.5) |
512x512x120 |
最大值 | (0.41015625,0.41015625,1.5) |
512x512x160 |
@article{shapey2021segmentation,
title={Segmentation of vestibular schwannoma from MRI, an open annotated dataset and baseline algorithm},
author={Shapey, Jonathan and Kujawa, Aaron and Dorent, Reuben and Wang, Guotai and Dimitriadis, Alexis and Grishchuk, Diana and Paddick, Ian and Kitchen, Neil and Bradford, Robert and Saeed, Shakeel R and others},
journal={Scientific Data},
volume={8},
number={1},
pages={286},
year={2021},
publisher={Nature Publishing Group UK London}
}