PatchCamelyon
PatchCamelyon数据集是一个专注于乳腺癌转移检测的图像分类挑战赛，源自CAMELYON16挑战赛的组织病理学图像。该数据集包含327,680张彩色图像（每张96x96像素），每张图像都有二元标签标注是否存在转移性组织。本数据集的目标是检测淋巴结切片中的乳腺癌转移灶。
xianweichengxiang可视化图片
可视化图片 1
数据集元信息
| 维度 | 2D |
| 模态 | pathology |
| 任务类型 | classification |
| 解剖结构 | 淋巴结 |
| 解剖区域 | 乳腺 |
| 类别数 | 2 |
| 数据量 | 327,680 |
| 文件格式 | JPG |
文件结构
├── camelyonpatch_level_2_split_test_meta.csv
├── camelyonpatch_level_2_split_test_x.h5
├── camelyonpatch_level_2_split_test_y.h5
├── camelyonpatch_level_2_split_train_mask.h5
├── camelyonpatch_level_2_split_train_meta.csv
├── camelyonpatch_level_2_split_train_x.h5
├── camelyonpatch_level_2_split_train_y.h5
├── camelyonpatch_level_2_split_train_y.h5.gz
├── camelyonpatch_level_2_split_valid_x.h5
├── camelyonpatch_level_2_split_valid_x.h5.gz
└── camelyonpatch_level_2_split_valid_y.h5图像尺寸统计
| 统计类型 | 间距 (mm) | 尺寸 |
|---|---|---|
| 最小值 | - |
[96, 96] |
| 中位值 | - |
[96, 96] |
| 最大值 | - |
[96, 96] |
引用
@inproceedings{veeling2018rotation,
title={Rotation equivariant CNNs for digital pathology},
author={Veeling, Bastiaan S and Linmans, Jasper and Winkens, Jim and Cohen, Taco and Welling, Max},
booktitle={Medical Image Computing and Computer Assisted Intervention--MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part II 11},
pages={210--218},
year={2018},
organization={Springer}
}