Spaces:
Sleeping
Automatic lung tumor segmentation in CT
This is the official repository for the paper "Teacher-Student Architecture for Mixed Supervised Lung Tumor Segmentation", submitted to PLOS ONE.
A pretrained model is made available in a command line tool and can be used as you please. However, the current model is not intended for clinical use. The model is the result of a proof-of-concept study. An improved model will be made available in the future, when more training data is made available.
Dependencies
In addition to the python packages specified in requirements.txt, PyTorch and lungmask must be installed.
Installation
pip install git+https://github.com/VemundFredriksen/LungTumorMask
Usage
After install, the software can be used as a command line tool. Simply specify the input and output filenames to run:
# Format
lungtumormask input_file output_file
# Example
lungtumormask patient_01.nii.gz mask_01.nii.gz
Acknowledgements
If you found this repository useful in your study, please, cite the following paper:
@misc{fredriksen2021teacherstudent,
title={Teacher-Student Architecture for Mixed Supervised Lung Tumor Segmentation},
author={Vemund Fredriksen and Svein Ole M. Svele and André Pedersen and Thomas Langø and Gabriel Kiss and Frank Lindseth},
year={2021},
eprint={2112.11541},
archivePrefix={arXiv},
primaryClass={eess.IV}}