Code for preprocessing the LIDC-IDRI lung cancer screening CT scan dataset
This repository contains code for preprocessing the LIDC-IDRI dataset, a publicly available collection of annotated lung cancer screening CT scans.
The preprocessing code is broken up into two stages:
stage1
extracts image data and annotations from the DICOM and XML filesstage2
extracts axial, sagittal, and coronal slices from the stage1
output.If you use this preprocessing code in your research, we would greatly appreciate you citing the following paper:
@article{nibali2017pulmonary,
author="Nibali, Aiden and He, Zhen and Wollersheim, Dennis",
title="Pulmonary nodule classification with deep residual networks",
journal="International Journal of Computer Assisted Radiology and Surgery",
year="2017",
issn="1861-6429",
doi="10.1007/s11548-017-1605-6",
}
And, of course, don't forget to cite the original sources of data and annotations: