Following subprojects are included (in the subfolders)
- lung_mask - lung segmentation using NiftyNet
- lung_report - lung HU quantification report
To run this pipeline, Linux, Git, Docker, NVIDIA Container Toolkit are needed.
docker build -t lung_opacity .
bash run.sh -i input_path_in_nii -o output_path_for_mask_in_nii
If you use LungOpacity in your work, please cite Anastasopoulos et al.
- C. Anastasopoulos, T. Weikert, S. Yang, A. Abdulkadir, L. Schmuelling, C. Buehler, F. Paciolla, R. Sexauer, J. Cyriac, I. Nesic, R. Twerenbold, J. Bremerich, B. Stieltjes, A. W. Sauter, G. Sommer Development and clinical implementation of tailored image analysis tools for COVID-19 in the midst of the pandemic: The synergetic effect of an open, clinically embedded software development platform and machine learning European Journal of Radiology, 2020,109233, ISSN 0720-048X, DOI: 10.1016/j.ejrad.2020.109233