Published April 20, 2020 | Version Verson 1.0
Dataset Open

COVID-19 CT Lung and Infection Segmentation Dataset

  • 1. Department of Mathematics, Nanjing University of Science and Technology
  • 2. Institute of Bioinformatics and Medical Engineering, Jiangsu University of Technology
  • 3. Institute of Computing Technology, Chinese Academy of Sciences;University of Chinese Academy of Sciences
  • 4. CEC Brain
  • 5. Shanghai University
  • 6. Institute of Science and Technology for Brain-inspired Intelligence, Fudan University
  • 7. Southeast University
  • 8. Suzhou LungCare Medical Technology Co., Ltd
  • 9. Chongqing University of Posts and Telecommunications
  • 10. School of Engineering, China Pharmaceutical University
  • 11. School of Computer Science and Engineering, Central South University
  • 12. School of Information Engineering, Zhengzhou University
  • 13. College of Electronics and Information Engineering, Tongji University
  • 14. Department of Mathematics, Nanjing University
  • 15. Department of Radiology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School

Description

This dataset contains 20 labeled COVID-19 CT scans. Left lung, right lung, and infections are labeled by two radiologists and verified by an experienced radiologist. 
To promote the studies of annotation-efficient deep learning methods, we set up three segmentation benchmark tasks based on this dataset https://gitee.com/junma11/COVID-19-CT-Seg-Benchmark.

In particular, we focus on learning to segment left lung, right lung, and infections using

  • pure but limited COVID-19 CT scans;
  • existing labeled lung CT dataset from other non-COVID-19 lung diseases;
  • heterogeneous datasets include both COVID-19 and non-COVID-19 CT scans.

Files

COVID-19-CT-Seg_20cases.zip

Files (1.1 GB)

Name Size Download all
md5:873617e1fdcbe92f8aa0ce83a4798a1f
1.1 GB Preview Download
md5:98fa9f5401fa8409dccd1681a36febcf
2.6 MB Preview Download
md5:40fa1fa124f6aab6daf9feea9c373313
11.7 MB Preview Download
md5:972b3d9b4c7b64d2c518b936bd98cb47
10.1 MB Preview Download

Additional details

Related works