This codebase implements our final solution for the nodule detection track in NODE21.
It contains files to build a docker image which can be submitted as an algorithm on the grand-challenge platform. The final algorithm can be found here.
The code in this repository is based on this template repository with docker and evalutils.
For the generation of additional Nodules, only the process.py script from the generation track template was modified (see /src/nodule_generation/) to generate the nodules given in nodules_to_generate.csv. In addition to the csv file, the algorithm requires the images to work with as input.
The paper describing our approach is available HERE.
If you make use of this method, we would be happy if you cite our work:
@article{behrendt2023systematic,
title={A systematic approach to deep learning-based nodule detection in chest radiographs},
author={Behrendt, Finn and Bengs, Marcel and Bhattacharya, Debayan and Kr{\"u}ger, Julia and Opfer, Roland and Schlaefer, Alexander},
journal={Scientific Reports},
volume={13},
number={1},
pages={10120},
year={2023},
publisher={Nature Publishing Group UK London}
}