% 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{Thummerer:181308,
author = {A. Thummerer and C. S. Oria and P. Zaffino and S. Visser
and A. Meijers and G. G. Marmitt and R. Wijsman and J.
Seco$^*$ and J. A. Langendijk and A. C. Knopf and M. F.
Spadea and S. Both},
title = {{D}eep learning based 4{D}-synthetic {CT}s from sparse-view
{CBCT}s for dose calculations in adaptive proton therapy.},
journal = {Medical physics},
volume = {49},
number = {11},
issn = {0094-2405},
address = {College Park, Md.},
publisher = {AAPM},
reportid = {DKFZ-2022-01935},
pages = {6824-6839},
year = {2022},
note = {2022 Nov;49(11):6824-6839},
abstract = {Time resolved 4D cone beam computed tomography (4D-CBCT)
allows a daily assessment of patient anatomy and respiratory
motion. However, 4D-CBCTs suffer from imaging artifacts that
affect the CT number accuracy and prevent accurate proton
dose calculations. Deep learning can be used to correct CT
numbers and generate synthetic CTs which can enable
CBCT-based proton dose calculations.In this work, sparse
view 4D-CBCTs were converted into 4D synthetic CTs (4D-sCT)
utilizing a deep convolutional neural network (DCNN).
4D-sCTs were evaluated in terms of image quality and
dosimetric accuracy to determine if accurate proton dose
calculations for adaptive proton therapy workflows of lung
cancer patients are feasible.A dataset of 45 thoracic cancer
patients was utilized to train and evaluate a DCNN to
generate 4D-sCTs, based on sparse view 4D-CBCTs
reconstructed from projections acquired with a 3D
acquisition protocol. Mean absolute error (MAE) and mean
error (ME) were used as metrics to evaluate image quality of
single phases and average 4D-sCTs against 4D-CTs acquired on
the same day. The dosimetric accuracy was checked globally
(gamma analysis) and locally for target volumes and organs
at risk (lung, heart, and esophagus). Furthermore, 4D-sCTs
were also compared to 3D-sCTs. To evaluate CT number
accuracy, proton radiography simulations in 4D-sCT and
4D-CTs were compared in terms of range errors. The clinical
suitability of 4D-sCTs was demonstrated by performing a 4D
dose reconstruction using patient specific treatment
delivery log-files and breathing signals.4D-sCTs resulted in
average MAEs of 48.1 ± 6.5 HU (single phase) and 37.7 ±
6.2 HU (average). The global dosimetric evaluation showed
gamma pass ratios of 92.3 ± 3.2 $\%$ (single phase) and
94.4 ± 2.1 $\%$ (average). The target volume (CTV) showed
high agreement in D98 between 4D-CT and 4D-sCT, with
differences below $2.4\%$ for all patients. Larger dose
differences were observed in mean doses of organs-at-risk
(up to $8.4\%).$ The comparison with 3D-sCTs showed no
substantial image quality and dosimetric differences for the
4D-sCT average. Individual 4D-sCT phases showed slightly
lower dosimetric accuracy. The range error evaluation
revealed that lung tissues cause range errors about 3 times
higher than the other tissues.In this study, we have
investigated the accuracy of deep learning based 4D-sCTs for
daily dose calculations in adaptive proton therapy. Despite
image quality differences between 4D-sCTs and 3D-sCTs,
comparable dosimetric accuracy was observed globally and
locally. Further improvement of 3D and 4D lung sCTs could be
achieved by increasing CT number accuracy in lung tissues.
This article is protected by copyright. All rights
reserved.},
keywords = {4D imaging (Other) / adaptive proton therapy (Other) / deep
learning (Other) / synthetic CT (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:35982630},
doi = {10.1002/mp.15930},
url = {https://inrepo02.dkfz.de/record/181308},
}