% 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{SaboridoMoral:284386,
author = {J. D. Saborido-Moral and M. Fernández-Patón and N.
Tejedor-Aguilar and A. Cristian-Marín and I.
Torres-Espallardo and J. M. Campayo-Esteban and J.
Pérez-Calatayud and D. Baltas$^*$ and L. Martí-Bonmatí
and M. Carles},
title = {{F}ree automatic software for quality assurance of computed
tomography calibration, edges and radiomics metrics
reproducibility.},
journal = {Physica medica},
volume = {114},
issn = {1120-1797},
address = {Amsterdam},
publisher = {Elsevier},
reportid = {DKFZ-2023-01980},
pages = {103153},
year = {2023},
abstract = {To develop a QA procedure, easy to use, reproducible and
based on open-source code, to automatically evaluate the
stability of different metrics extracted from CT images:
Hounsfield Unit (HU) calibration, edge characterization
metrics (contrast and drop range) and radiomic features.The
QA protocol was based on electron density phantom imaging.
Home-made open-source Python code was developed for the
automatic computation of the metrics and their
reproducibility analysis. The impact on reproducibility was
evaluated for different radiation therapy protocols, and
phantom positions within the field of view and systems, in
terms of variability (Shapiro-Wilk test for 15 repeated
measurements carried out over three days) and comparability
(Bland-Altman analysis and Wilcoxon Rank Sum Test or Kendall
Rank Correlation Coefficient).Regarding intrinsic
variability, most metrics followed a normal distribution
$(88\%$ of HU, $63\%$ of edge parameters and $82\%$ of
radiomic features). Regarding comparability, HU and contrast
were comparable in all conditions, and drop range only in
the same CT scanner and phantom position. The percentages of
comparable radiomic features independent of protocol,
position and system were $59\%,$ $78\%$ and $54\%,$
respectively. The non-significantly differences in HU
calibration curves obtained for two different institutions
$(7\%)$ translated in comparable Gamma Index G (1 mm, $1\%,$
$>99\%).An$ automated software to assess the reproducibility
of different CT metrics was successfully created and
validated. A QA routine proposal is suggested.},
keywords = {Automatic quality assurance (Other) / Computed tomography
(Other) / Radiomics (Other) / Reproducibility (Other)},
cin = {FR01},
ddc = {610},
cid = {I:(DE-He78)FR01-20160331},
pnm = {899 - ohne Topic (POF4-899)},
pid = {G:(DE-HGF)POF4-899},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:37778209},
doi = {10.1016/j.ejmp.2023.103153},
url = {https://inrepo02.dkfz.de/record/284386},
}