A CNN‐transformer‐based unsupervised aware hierarchical network for medical image registration

Abstract Medical image registration is a fundamental and important technique in the field of medical image analysis. This study proposes a novel unsupervised end‐to‐end registration network, aiming to enable the model to actively acquire image features in the field of medical imaging with limited sa...

Full description

Saved in:
Bibliographic Details
Main Authors: Bo Fang, Lisheng Wang
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:Electronics Letters
Subjects:
Online Access:https://doi.org/10.1049/ell2.70124
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846108042474553344
author Bo Fang
Lisheng Wang
author_facet Bo Fang
Lisheng Wang
author_sort Bo Fang
collection DOAJ
description Abstract Medical image registration is a fundamental and important technique in the field of medical image analysis. This study proposes a novel unsupervised end‐to‐end registration network, aiming to enable the model to actively acquire image features in the field of medical imaging with limited samples, which efficiently integrates multi‐scale features to achieve higher accuracy in registration. By utilizing region‐to‐region routing, this model actively preserves the most relevant features of the images, thereby improving training and learning efficiency. The model is evaluated by several publicly available datasets. The new network proposed in this study achieved the best registration accuracy among various advanced traditional and learning‐based methods.
format Article
id doaj-art-fdb86f64efcf4a368dab366e7a4cef32
institution Kabale University
issn 0013-5194
1350-911X
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series Electronics Letters
spelling doaj-art-fdb86f64efcf4a368dab366e7a4cef322024-12-26T07:11:10ZengWileyElectronics Letters0013-51941350-911X2024-12-016024n/an/a10.1049/ell2.70124A CNN‐transformer‐based unsupervised aware hierarchical network for medical image registrationBo Fang0Lisheng Wang1School of Medicine GuangXi University Nanning ChinaSchool of Medicine GuangXi University Nanning ChinaAbstract Medical image registration is a fundamental and important technique in the field of medical image analysis. This study proposes a novel unsupervised end‐to‐end registration network, aiming to enable the model to actively acquire image features in the field of medical imaging with limited samples, which efficiently integrates multi‐scale features to achieve higher accuracy in registration. By utilizing region‐to‐region routing, this model actively preserves the most relevant features of the images, thereby improving training and learning efficiency. The model is evaluated by several publicly available datasets. The new network proposed in this study achieved the best registration accuracy among various advanced traditional and learning‐based methods.https://doi.org/10.1049/ell2.70124artificial intelligenceimage fusionimage registrationlearning (artificial intelligence)
spellingShingle Bo Fang
Lisheng Wang
A CNN‐transformer‐based unsupervised aware hierarchical network for medical image registration
Electronics Letters
artificial intelligence
image fusion
image registration
learning (artificial intelligence)
title A CNN‐transformer‐based unsupervised aware hierarchical network for medical image registration
title_full A CNN‐transformer‐based unsupervised aware hierarchical network for medical image registration
title_fullStr A CNN‐transformer‐based unsupervised aware hierarchical network for medical image registration
title_full_unstemmed A CNN‐transformer‐based unsupervised aware hierarchical network for medical image registration
title_short A CNN‐transformer‐based unsupervised aware hierarchical network for medical image registration
title_sort cnn transformer based unsupervised aware hierarchical network for medical image registration
topic artificial intelligence
image fusion
image registration
learning (artificial intelligence)
url https://doi.org/10.1049/ell2.70124
work_keys_str_mv AT bofang acnntransformerbasedunsupervisedawarehierarchicalnetworkformedicalimageregistration
AT lishengwang acnntransformerbasedunsupervisedawarehierarchicalnetworkformedicalimageregistration
AT bofang cnntransformerbasedunsupervisedawarehierarchicalnetworkformedicalimageregistration
AT lishengwang cnntransformerbasedunsupervisedawarehierarchicalnetworkformedicalimageregistration