Dataset Open Access
Data publication: A deep-learning-based surrogate model for Monte-Carlo simulations of the linear energy transfer in primary brain tumor patients treated with proton-beam radiotherapy
Starke, Sebastian;
Kieslich, Aaron Markus;
Palkowitsch, Martina;
Hennings, Fabian;
Troost, Esther Gera Cornelia;
Krause, Mechthild;
Bensberg, Jona;
Hahn, Christian;
Heinzelmann, Feline;
Bäumer, Christian;
Lühr, Armin;
Timmermann, Beate;
Löck, Steffen
This repository contains the outputs and result data of our deep-learning-based experiments for the approximation of Monte-Carlo-simulated linear energy transfer distributions, which build the foundation for the corresponding article.
The Pytorch checkpoint of our finally chosen SegResNet architecture trained on the UPTD dose distributions is located at dd_pbs/Dose-LETd/clip_let_below_0.04/segresnet/all_trainvalid_data/training/lightning_logs/version_6358843/checkpoints/last.ckpt.
Moreover, we provide an exemplary data sample from a water phantom for trying our analysis pipeline.
| Name | Size | |
|---|---|---|
|
analysis_data.zip
md5:d0b670f5cee1de6f117919f2e83d92f9 |
342.7 MB | Download |
|
water_phantom.zip
md5:75ae4c12df1ec734429e041cf0d50182 |
93.7 MB | Download |
| All versions | This version | |
|---|---|---|
| Views | 95 | 95 |
| Downloads | 11 | 11 |
| Data volume | 2.5 GB | 2.5 GB |
| Unique views | 89 | 89 |
| Unique downloads | 9 | 9 |
- Publication date:
- March 15, 2024
- DOI:
-
- Keyword(s):
- proton-beam therapy relative biological effectiveness linear energy transfer NTCP models deep learning brain tumor
- Related identifiers:
- Identical to:
https://www.hzdr.de/publications/Publ-38860 - Referenced by:
https://www.hzdr.de/publications/Publ-38858 - Communities:
- License (for files):
- Creative Commons Attribution 4.0 International