% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Xiao:294399,
author = {F. Xiao and D. Radonic and M. Kriechbaum and N. Wahl$^*$
and A. Neishabouri$^*$ and N. Delopoulos and K. Parodi and
S. Corradini and C. Belka$^*$ and C. Kurz and G. Landry and
G. Dedes},
title = {{P}rompt gamma emission prediction using a long short-term
memory network.},
journal = {Physics in medicine and biology},
volume = {69},
number = {23},
issn = {0031-9155},
address = {Bristol},
publisher = {IOP Publ.},
reportid = {DKFZ-2024-02228},
pages = {235003},
year = {2024},
note = {Physics in Medicine $\&$ Biology, Volume 69, Number 23 ,
2024 Phys. Med. Biol. 235003},
abstract = {To present a long short-term memory (LSTM)-based prompt
gamma (PG) emission prediction method for proton
therapy.Computed tomography (CT) scans of 33 patients with a
prostate tumor were included in the dataset. A set of 10
million histories proton pencil beam (PB)s was generated for
Monte Carlo (MC) dose and PG simulation. For training (20
patients) and validation (3 patients), over 6000 PBs at 150,
175 and 200 MeV were simulated. 3D relative stopping power
(RSP), PG and dose cuboids that included the PB were
extracted. Three models were trained, validated and tested
based on an LSTM-based network: (1) input RSP and output PG,
(2) input RSP with dose and output PG (single-energy), and
(3) input RSP/dose and output PG (multi-energy). 540 PBs at
each of the four energy levels (150, 175, 200, and 125-210
MeV) were simulated across 10 patients to test the three
models. The gamma passing rate $(2\%/2mm)$ and PG range
shift were evaluated and compared among the three models.The
model with input RSP/dose and output PG (multi-energy)
showed the best performance in terms of gamma passing rate
and range shift metrics. Its mean gamma passing rate of
testing PBs of 125-210 MeV was $98.5\%$ and the worst case
was $92.8\%.$ Its mean absolute range shift between
predicted and MC PGs was 0.15 mm, where the maximum shift
was 1.1mm. The prediction time of our models was within 130
ms per PB.We developed a sub-second LSTM-based PG emission
prediction method. Its accuracy in prostate patients has
been confirmed across an extensive range of proton
energies.},
keywords = {LSTM (Other) / deep learning (Other) / prompt gamma (Other)
/ proton therapy (Other) / range verification (Other)},
cin = {E040 / E050 / MU01},
ddc = {530},
cid = {I:(DE-He78)E040-20160331 / I:(DE-He78)E050-20160331 /
I:(DE-He78)MU01-20160331},
pnm = {315 - Bildgebung und Radioonkologie (POF4-315)},
pid = {G:(DE-HGF)POF4-315},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:39488071},
doi = {10.1088/1361-6560/ad8e2a},
url = {https://inrepo02.dkfz.de/record/294399},
}