Navigation überspringen
Universitätsbibliothek Heidelberg
Status: Bibliographieeintrag

Verfügbarkeit
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Strittmatter, Anika [VerfasserIn]   i
 Zöllner, Frank G. [VerfasserIn]   i
Titel:Multistep networks for deformable multimodal medical image registration
Verf.angabe:Anika Strittmatter and Frank G. Zöllner, (Senior Member, IEEE)
E-Jahr:2024
Jahr:11 June 2024
Umfang:17 S.
Illustrationen:Illustrationen
Fussnoten:Gesehen am 22.10.2024
Titel Quelle:Enthalten in: Institute of Electrical and Electronics EngineersIEEE access
Ort Quelle:New York, NY : IEEE, 2013
Jahr Quelle:2024
Band/Heft Quelle:12(2024), Seite 82676-82692
ISSN Quelle:2169-3536
Abstract:We proposed neural networks for deformable multimodal medical image registration that use multiple steps and varying resolutions. The networks were trained jointly in an unsupervised manner with Mutual Information and Gradient L2 loss. By comparing the multistep neural networks to each other and to a monostep/monoresolution network as a benchmark and the classical registration methods SimpleElastix and NiftyReg as a baseline, we investigated the impact of using multiple resolutions on the registration result. To assess the performance of the multistep networks, we used four three-dimensional multimodal datasets (a synthetic and an in-vivo liver dataset with CT and T1-weighted MR scans, an in-vivo kidney MR dataset with T1-weighted and T2-weighted MR scans and an in-vivo prostate MR dataset with T2-weighted and DWI MR scans). Experimental results showed that incorporating multiple steps and resolutions in a neural network leads to registration results with high structural similarity (NMI up to 0.33 ± 0.02, Dice up to 90.8 ± 3.1) and minimal image folding (|J \vert łe 0 : less than 0.5%), resulting in a medically plausible transformation, while maintaining a low registration time (<0.5 s). Moreover, our results demonstrate that spatial alignment improves with more resolutions/steps (up to 4 in this study), and multistep networks outperform monostage/monoresolution networks.
DOI:doi:10.1109/ACCESS.2024.3412216
URL:Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.

kostenfrei: Volltext: https://doi.org/10.1109/ACCESS.2024.3412216
 kostenfrei: Volltext: http://ieeexplore.ieee.org/document/10552697
 DOI: https://doi.org/10.1109/ACCESS.2024.3412216
Datenträger:Online-Ressource
Sprache:eng
Sach-SW:Biomedical imaging
 Computed tomography
 Deep learning
 Deformation
 image registration
 Image registration
 Kidney
 Liver
 machine learning
 Medical diagnostic imaging
 medical images
 multimodal data
 multistep
 Spatial resolution
K10plus-PPN:1906382433
Verknüpfungen:→ Zeitschrift

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/69264242   QR-Code
zum Seitenanfang