COVID_CT_COVID-CT
There are a total of 746 lung CT images in COVID_CT_COVID-CT, among which 349 are of COVID-19 infection and 397 are of non-COVID-19 infection. Default divisions for train, val and test data are provided. In addition, for each CT image of COVID-19 infection, this dataset provides a basic information description of the corresponding patient (including the patient's location, age, disease description, brief medical history, onset time and other symptoms). It should be particularly noted that in the dataset, the original CT is 3D, but only the slices that the doctor considers to have key features in each 3D CT data were selected. According to radiologists, this will not significantly affect the accuracy of diagnostic decisions, especially under conditions like this dataset that contain sufficient clinical information. This dataset aims to promote the research on the recognition algorithm of COVID-19 infection in lung CT (2D).
xiongbu可视化图片
数据集元信息
| 维度 | 2D |
| 模态 | ct |
| 任务类型 | classification |
| 解剖结构 | 肺部 |
| 解剖区域 | 胸部 |
| 类别数 | 2 |
| 数据量 | 746 |
| 文件格式 | JPG, PNG |
文件结构
COVID_CT_COVID-CT
├── Data-split
│ ├── COVID
│ │ ├── testCT_COVID.txt
│ │ ├── trainCT_COVID.txt
│ │ ├── valCT_COVID.txt
│ ├── NonCOVID
│ │ ├── CT_NonCOVID_test_id.csv
│ │ ├── CT_NonCOVID_train_id.csv
│ │ ├── CT_NonCOVID_val_id.csv
│ │ ├── testCT_NonCOVID.txt
│ │ ├── trainCT_NonCOVID.txt
│ │ ├── valCT_NonCOVID.txt
├── Images-processed
│ ├── CT_COVID
│ │ ├── 2019-novel-Coronavirus-severe-adult-respiratory-dist_2020_International-Jour-p3-89%0.txt
│ │ ├── ...
│ ├── CT_NonCOVID
│ │ ├── 0.jpg
│ │ ├── ...
├── COVID-CT-MetaInfo.xlsx
├── NonCOVID-CT-MetaInfo.csv
├── README.md图像尺寸统计
| 统计类型 | 间距 (mm) | 尺寸 |
|---|---|---|
| 最小值 | - |
[148,61] |
| 中位值 | - |
[404,299] |
| 最大值 | - |
[1637,1225] |
引用
@article{zhao2020COVID-CT-Dataset,
title={COVID-CT-Dataset: a CT scan dataset about COVID-19},
author={Zhao, Jinyu and Zhang, Yichen and He, Xuehai and Xie, Pengtao},
journal={arXiv preprint arXiv:2003.13865},
year={2020}
}