Par0058 - elastix


Head-neck, lung and breast cancer patients acquired between 2016-2018.

Image data

The values are reported in RL, AP, FH directions.


Acquired on Synergy Linac with XVI (v5.0.2b72 Elekta AB, Sweden)


Acquired on Brilliance Big Bore (Philips Healthcare, Ohio, USA).


For each subject, each CT was translated and resampled to CBCT to minimise set-up errors.

Registration Settings

For parameter files see the Elastix Model Zoo repository on GitHub.

elastix version: 4.700


The translation used to register CT to CBCT in all subjects

A fixed image mask was always used, given by the FOV of the CBCT, called Cylinder.gipl

Command line call:

elastix -f Fixed_CBCT.gipl -m Moving_CT.gipl -out ./  -mMask Cylinder.gipl -fMask Cylinder.gipl -p par0058trans.txt

Published in

Maspero M, Houweling AC, Savenije MH, van Heijst TC, Verhoeff JJ, Kotte AN, van den Berg CA. A single neural network for cone-beam computed tomography-based radiotherapy of head-and-neck, lung and breast cancer. Physics and Imaging in Radiation Oncology. 2020 Apr 1;14:24-31. doi:;

Maspero M, Savenije MH, van Heijst TC, Verhoeff JJ, Kotte AN, Houweling AC, van den Berg CA. CBCT-to-CT synthesis with a single neural network for head-and-neck, lung and breast cancer adaptive radiotherapy. arXiv preprint arXiv:1912.11136. 2019 Dec 23. arXiv:

© 2020 Viktor van der Valk