% 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{Pettersen:169833,
author = {H. E. S. Pettersen and M. Aehle and J. Alme and G. G.
Barnaföldi and V. Borshchov and A. van den Brink and M.
Chaar and V. Eikeland and G. Feofilov and C. Garth and N. R.
Gauger and G. Genov and O. Grøttvik and H. Helstrup and S.
Igolkin and R. Keidel and C. Kobdaj and T. Kortus and V.
Leonhardt and S. Mehendale and R. N. Mulawade and O. H.
Odland and G. Papp and T. Peitzmann and P. Piersimoni and M.
Protsenko and A. U. Rehman and M. Richter and J. Santana and
A. Schilling and J. Seco$^*$ and A. Songmoolnak and J. R.
Sølie and G. Tambave and I. Tymchuk and K. Ullaland and M.
Varga-Kofarago and L. Volz and B. Wagner and S. Wendzel and
A. Wiebel and R. Xiao and S. Yang and H. Yokoyama and S.
Zillien and D. Röhrich},
title = {{I}nvestigating particle track topology for range
telescopes in particle radiography using convolutional
neural networks.},
journal = {Acta oncologica},
volume = {60},
number = {11},
issn = {0001-6926},
address = {Abingdon},
publisher = {Taylor $\&$ Francis Group},
reportid = {DKFZ-2021-01577},
pages = {1413-1418},
year = {2021},
note = {2021 Nov;60(11):1413-1418},
abstract = {Proton computed tomography (pCT) and radiography (pRad) are
proposed modalities for improved treatment plan accuracy and
in situ treatment validation in proton therapy. The pCT
system of the Bergen pCT collaboration is able to handle
very high particle intensities by means of track
reconstruction. However, incorrectly reconstructed and
secondary tracks degrade the image quality. We have
investigated whether a convolutional neural network
(CNN)-based filter is able to improve the image quality.The
CNN was trained by simulation and reconstruction of tens of
millions of proton and helium tracks. The CNN filter was
then compared to simple energy loss threshold methods using
the Area Under the Receiver Operating Characteristics curve
(AUROC), and by comparing the image quality and Water
Equivalent Path Length (WEPL) error of proton and helium
radiographs filtered with the same methods.The CNN method
led to a considerable improvement of the AUROC, from
$74.3\%$ to $97.5\%$ with protons and from $94.2\%$ to
$99.5\%$ with helium. The CNN filtering reduced the WEPL
error in the helium radiograph from 1.03 mm to 0.93 mm while
no improvement was seen in the CNN filtered pRads.The CNN
improved the filtering of proton and helium tracks. Only in
the helium radiograph did this lead to improved image
quality.},
keywords = {Monte Carlo simulation (Other) / Proton computed tomography
(Other) / convolutional neural network (Other) / machine
learning (Other) / secondary particles (Other) / track
reconstruction (Other)},
cin = {E041},
ddc = {610},
cid = {I:(DE-He78)E041-20160331},
pnm = {315 - Bildgebung und Radioonkologie (POF4-315)},
pid = {G:(DE-HGF)POF4-315},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:34259117},
doi = {10.1080/0284186X.2021.1949037},
url = {https://inrepo02.dkfz.de/record/169833},
}