UESTC-COVID-19 Dataset contains CT scans (3D volumes) of 120 patients diagnosized with COVID-19. The dataset was constructed for the purpose of pneumonia lesion segmentation. It contains two parts: 1) Part 1 consists of 70 volumes where lesion regions were annotated by non-experts and the lesion labels contain some noise. 2) Part 2 consists of 50 volumes where leions were annotated by experts, and the labels can be seen as clean. See the following figure for two examples of these images.
All the images have been cropped based on the bounding box of the lung region. The intensity has been normalized into [0,1] using window width/level of 1500/-650.
We have also released a pretrained model for the segmentation task, which is availabe at: https://github.com/HiLab-git/COPLE-Net
If you use this dataset, please cite the following publication:
Guotai Wang, Xinglong Liu, Chaoping Li, Zhiyong Xu, Jiugen Ruan, Haifeng Zhu, Tao Meng, Kang Li, Ning Huang, Shaoting Zhang. “A Noise-robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions from CT Images.” IEEE Transactions on Medical Imaging, 39, no. 8(2020): 2653 - 2663..
To request an access to the this dataset, please sign the end-user agreement (see attachment or download here) and send it to: firstname.lastname@example.org.