OCCISC(重叠宫颈细胞学图像分割挑战赛)数据集旨在从重叠的宫颈细胞学图像中提取单个细胞质和细胞核的边界。该数据集包含16张真实的扩展景深(EDF, Extended Depth of Field)宫颈细胞学图像和945张合成图像。在原挑战赛中,定性评估基于16张真实EDF图像,而945张合成图像用于对提交算法进行定量评估。
xianweichengxiang维度 | 2D |
模态 | microscopy |
任务类型 | segmentation |
解剖结构 | 细胞结构 |
解剖区域 | 宫颈细胞 |
类别数 | 2 |
数据量 | 945 |
文件格式 | .png, .mat |
Dataset
│
├── EDF
│ ├── EDF000.png
│ ├── EDF000_GT.png
│ ├── EDF001.png
│ ├── EDF001_GT.png
│ └── ...
│
└── Synthetic
├── trainset.mat
├── trainset_GT.mat
├── testset.mat
└── testset_GT.mat
统计类型 | 间距 (mm) | 尺寸 |
---|---|---|
最小值 | - |
512x512 |
中位值 | - |
512x512 |
最大值 | - |
512x512 |
@article{lu2016evaluation,
title={Evaluation of three algorithms for the segmentation of overlapping cervical cells},
author={Lu, Zhi and Carneiro, Gustavo and Bradley, Andrew P and Ushizima, Daniela and Nosrati, Masoud S and Bianchi, Andrea GC and Carneiro, Claudia M and Hamarneh, Ghassan},
journal={IEEE journal of biomedical and health informatics},
volume={21},
number={2},
pages={441--450},
year={2016},
publisher={IEEE}
},
@article{lu2015improved,
title={An improved joint optimization of multiple level set functions for the segmentation of overlapping cervical cells},
author={Lu, Zhi and Carneiro, Gustavo and Bradley, Andrew P},
journal={IEEE transactions on image processing},
volume={24},
number={4},
pages={1261--1272},
year={2015},
publisher={IEEE}
}