% 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{LopesMarinho:616536,
author = {Lopes Marinho, André and Kazimi, Bashir and Ćwieka, Hanna
and Marek, Romy and Beckmann, Felix and Willumeit-Römer,
Regine and Moosmann, Julian and Zeller-Plumhoff, Berit},
title = {{A} comparison of deep learning segmentation models for
synchrotron radiation based tomograms of biodegradable bone
implants},
journal = {Frontiers in physics},
volume = {12},
issn = {2296-424X},
address = {Lausanne},
publisher = {Frontiers Media},
reportid = {PUBDB-2024-06448},
pages = {1257512},
year = {2024},
abstract = {ntroduction: Synchrotron radiation micro-computed
tomography (SRμCT) has been used as a non-invasive
technique to examine the microstructure and tissue
integration of biodegradable bone implants. To be able to
characterize parameters regarding the disintegration and
osseointegration of such materials quantitatively, the
three-dimensional (3D) image data provided by SRμCT needs
to be processed by means of semantic segmentation. However,
accurate image segmentation is challenging using traditional
automated techniques. This study investigates the
effectiveness of deep learning approaches for semantic
segmentation of SRμCT volumes of Mg-based implants in sheep
bone ex vivo.Methodology: For this purpose different
convolutional neural networks (CNNs), including U-Net,
HR-Net, U²-Net, from the TomoSeg framework, the Scaled
U-Net framework, and 2D/3D U-Net from the nnU-Net framework
were trained and validated. The image data used in this work
was part of a previous study where biodegradable screws were
surgically implanted in sheep tibiae and imaged using SRμCT
after different healing periods. The comparative analysis of
CNN models considers their performance in semantic
segmentation and subsequent calculation of degradation and
osseointegration parameters. The models’ performance is
evaluated using the intersection over union (IoU) metric,
and their generalization ability is tested on unseen
datasets.Results and discussion: This work shows that the 2D
nnU-Net achieves better generalization performance, with the
degradation layer being the most challenging label to
segment for all models.},
cin = {Hereon / DOOR ; HAS-User},
ddc = {530},
cid = {I:(DE-H253)Hereon-20210428 / I:(DE-H253)HAS-User-20120731},
pnm = {6G3 - PETRA III (DESY) (POF4-6G3) / FS-Proposal: I-20200278
(I-20200278) / FS-Proposal: I-20191467 (I-20191467)},
pid = {G:(DE-HGF)POF4-6G3 / G:(DE-H253)I-20200278 /
G:(DE-H253)I-20191467},
experiment = {EXP:(DE-H253)P-P05-20150101 / EXP:(DE-H253)P-P07-20150101},
typ = {PUB:(DE-HGF)16},
UT = {WOS:001156897500001},
doi = {10.3389/fphy.2024.1257512},
url = {https://bib-pubdb1.desy.de/record/616536},
}