File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: 4D-CT deformable image registration using unsupervised recursive cascaded full-resolution residual networks

Title4D-CT deformable image registration using unsupervised recursive cascaded full-resolution residual networks
Authors
Keywords4D-CT
deformable image registration
full-resolution residual networks
unsupervised learning
Issue Date22-Aug-2023
PublisherWiley Open Access
Citation
Bioengineering and Translational Medicine, 2023, v. 8, n. 6 How to Cite?
AbstractA novel recursive cascaded full-resolution residual network (RCFRR-Net) for abdominal four-dimensional computed tomography (4D-CT) image registration was proposed. The entire network was end-to-end and trained in the unsupervised approach, which meant that the deformation vector field, which presented the ground truth, was not needed during training. The network was designed by cascading three full-resolution residual subnetworks with different architectures. The training loss consisted of the image similarity loss and the deformation vector field regularization loss, which were calculated based on the final warped image and the fixed image, allowing all cascades to be trained jointly and perform the progressive registration cooperatively. Extensive network testing was conducted using diverse datasets, including an internal 4D-CT dataset, a public DIRLAB 4D-CT dataset, and a 4D cone-beam CT (4D-CBCT) dataset. Compared with the iteration-based demon method and two deep learning-based methods (VoxelMorph and recursive cascaded network), the RCFRR-Net achieved consistent and significant gains, which demonstrated that the proposed method had superior performance and generalization capability in medical image registration. The proposed RCFRR-Net was a promising tool for various clinical applications.
Persistent Identifierhttp://hdl.handle.net/10722/340955
ISSN
2023 Impact Factor: 6.1
2023 SCImago Journal Rankings: 1.655
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorXu, L-
dc.contributor.authorJiang, P-
dc.contributor.authorTsui, T-
dc.contributor.authorLiu, JY-
dc.contributor.authorZhang, XP-
dc.contributor.authorYu, LQ-
dc.contributor.authorNiu, TY -
dc.date.accessioned2024-03-11T10:48:33Z-
dc.date.available2024-03-11T10:48:33Z-
dc.date.issued2023-08-22-
dc.identifier.citationBioengineering and Translational Medicine, 2023, v. 8, n. 6-
dc.identifier.issn2380-6761-
dc.identifier.urihttp://hdl.handle.net/10722/340955-
dc.description.abstractA novel recursive cascaded full-resolution residual network (RCFRR-Net) for abdominal four-dimensional computed tomography (4D-CT) image registration was proposed. The entire network was end-to-end and trained in the unsupervised approach, which meant that the deformation vector field, which presented the ground truth, was not needed during training. The network was designed by cascading three full-resolution residual subnetworks with different architectures. The training loss consisted of the image similarity loss and the deformation vector field regularization loss, which were calculated based on the final warped image and the fixed image, allowing all cascades to be trained jointly and perform the progressive registration cooperatively. Extensive network testing was conducted using diverse datasets, including an internal 4D-CT dataset, a public DIRLAB 4D-CT dataset, and a 4D cone-beam CT (4D-CBCT) dataset. Compared with the iteration-based demon method and two deep learning-based methods (VoxelMorph and recursive cascaded network), the RCFRR-Net achieved consistent and significant gains, which demonstrated that the proposed method had superior performance and generalization capability in medical image registration. The proposed RCFRR-Net was a promising tool for various clinical applications.-
dc.languageeng-
dc.publisherWiley Open Access-
dc.relation.ispartofBioengineering and Translational Medicine-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subject4D-CT-
dc.subjectdeformable image registration-
dc.subjectfull-resolution residual networks-
dc.subjectunsupervised learning-
dc.title4D-CT deformable image registration using unsupervised recursive cascaded full-resolution residual networks-
dc.typeArticle-
dc.identifier.doi10.1002/btm2.10587-
dc.identifier.pmid38023695-
dc.identifier.scopuseid_2-s2.0-85168701760-
dc.identifier.volume8-
dc.identifier.issue6-
dc.identifier.eissn2380-6761-
dc.identifier.isiWOS:001052444500001-
dc.publisher.placeHOBOKEN-
dc.identifier.issnl2380-6761-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats