Software Open Access

Trained Models of Semi-supervised COVID-19 Infection Segmentation

Jun Ma

Trained models in the following paper.

@article{Ma20SemiCOVIDSeg,
    author={Jun Ma and Ziwei Nie and Congcong Wang and Guoqiang Dong and Qiongjie Zhu and Jian He and Luying Gui and Xiaoping Yang},
    title={Active contour regularized semi-supervised learning for COVID-19 CT infection segmentation with limited annotations},
    journal={Physics in Medicine & Biology},
    url={http://iopscience.iop.org/article/10.1088/1361-6560/abc04e},
    year={2020}
}

These trained models were built on nnUNet (https://github.com/MIC-DKFZ/nnUNet).

We also use them to infer this public COVID-19 CT dataset:https://wiki.cancerimagingarchive.net/display/Public/CT+Images+in+COVID-19.

These pseudo labels are also provided.

Files (714.1 MB)
Name Size
COVID-19-650 Cases-Infection Pseudo Labels.zip
md5:d4cd2f8ddc08ffaf27d6818e6dcabdb7
4.2 MB Download
COVID-19-650 Cases-Lung Pseudo Labels.zip
md5:dd050ee660c4b08da9f44e0326346054
37.7 MB Download
Task110_LungCT.zip
md5:8618f7a906d198b2e12a96ce2105c67b
339.1 MB Download
Task111_LungInfection.zip
md5:cf60bcb0722587dd7d9643ed204ad300
333.0 MB Download
  • https://doi.org/10.1088/1361-6560/abc04e

387
98
views
downloads
Views 387
Downloads 98
Data volume 22.1 GB
Unique views 343
Unique downloads 34

Share

Cite as