There is a newer version of this record available.

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.

Files (436.4 MB)
Name Size
342.7 MB Download
93.7 MB Download
All versions This version
Views 331270
Downloads 2218
Data volume 4.4 GB3.9 GB
Unique views 301252
Unique downloads 1715


Cite as