Biomechanically Regularized Deep Deformable Registration for CT and US Fusion

<p dir="ltr">Accurate registration of liver computed tomography (CT) and ultra‐sound (US) images is crucial for image‐guided interventions, enabling precise navigation and treatment planning. However, aligning these multimodal images is challenging due to differences in imaging chara...

Full description

Saved in:
Bibliographic Details
Main Author: Snigdha Mohanty (16904919) (author)
Other Authors: Sara Yavari (9669843) (author), Sarada Prasad Dakua (14151789) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513531978711040
author Snigdha Mohanty (16904919)
author2 Sara Yavari (9669843)
Sarada Prasad Dakua (14151789)
author2_role author
author
author_facet Snigdha Mohanty (16904919)
Sara Yavari (9669843)
Sarada Prasad Dakua (14151789)
author_role author
dc.creator.none.fl_str_mv Snigdha Mohanty (16904919)
Sara Yavari (9669843)
Sarada Prasad Dakua (14151789)
dc.date.none.fl_str_mv 2025-11-06T03:00:00Z
dc.identifier.none.fl_str_mv 10.1049/ell2.70351
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Biomechanically_Regularized_Deep_Deformable_Registration_for_CT_and_US_Fusion/30859112
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Biomedical engineering
Information and computing sciences
Machine learning
Liver CT and Ultrasound (US)
Deep Learning
Convolutional Neural Networks (CNN)
Biomechanical Regularization
Image-Guided Interventions
dc.title.none.fl_str_mv Biomechanically Regularized Deep Deformable Registration for CT and US Fusion
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Accurate registration of liver computed tomography (CT) and ultra‐sound (US) images is crucial for image‐guided interventions, enabling precise navigation and treatment planning. However, aligning these multimodal images is challenging due to differences in imaging characteristics, patient positioning, and organ deformation. This paper proposes a novel biomechanically regularized deep deformable registration framework for liver CT and US fusion. Our approach leverages deep learning to model complex deformation fields while incorporating biomechanical priors derived from liver anatomy and tissue properties to enhance the physical plausibility and robustness of the registration process. We utilize a convolutional neural network to predict the deformation field between the CT and US images, guided by a biomechanical regularization term that penalizes unrealistic deformations. The framework is trained on a dataset of paired liver CT and US images, incorporating both synthetic and real‐world deformation scenarios. The results show that the values of mean square error, normalized cross‐correlation, structural similarity, mutual information, feature similarity index, and mean absolute error are 1.2132, 0.9932, 0.9907, 0.913, 0.9971 and 1.39 1.02, respectively. This work represents a step forward in bridging the gap between multimodal image registration and biomechanically informed modelling, advancing precision in image‐guided liver interventions.</p><h2>Other Information</h2><p dir="ltr">Published in: Electronics Letters<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1049/ell2.70351" target="_blank">https://dx.doi.org/10.1049/ell2.70351</a></p>
eu_rights_str_mv openAccess
id Manara2_60b3cca7d42b104c8ac98c62631d6cae
identifier_str_mv 10.1049/ell2.70351
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30859112
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Biomechanically Regularized Deep Deformable Registration for CT and US FusionSnigdha Mohanty (16904919)Sara Yavari (9669843)Sarada Prasad Dakua (14151789)EngineeringBiomedical engineeringInformation and computing sciencesMachine learningLiver CT and Ultrasound (US)Deep LearningConvolutional Neural Networks (CNN)Biomechanical RegularizationImage-Guided Interventions<p dir="ltr">Accurate registration of liver computed tomography (CT) and ultra‐sound (US) images is crucial for image‐guided interventions, enabling precise navigation and treatment planning. However, aligning these multimodal images is challenging due to differences in imaging characteristics, patient positioning, and organ deformation. This paper proposes a novel biomechanically regularized deep deformable registration framework for liver CT and US fusion. Our approach leverages deep learning to model complex deformation fields while incorporating biomechanical priors derived from liver anatomy and tissue properties to enhance the physical plausibility and robustness of the registration process. We utilize a convolutional neural network to predict the deformation field between the CT and US images, guided by a biomechanical regularization term that penalizes unrealistic deformations. The framework is trained on a dataset of paired liver CT and US images, incorporating both synthetic and real‐world deformation scenarios. The results show that the values of mean square error, normalized cross‐correlation, structural similarity, mutual information, feature similarity index, and mean absolute error are 1.2132, 0.9932, 0.9907, 0.913, 0.9971 and 1.39 1.02, respectively. This work represents a step forward in bridging the gap between multimodal image registration and biomechanically informed modelling, advancing precision in image‐guided liver interventions.</p><h2>Other Information</h2><p dir="ltr">Published in: Electronics Letters<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1049/ell2.70351" target="_blank">https://dx.doi.org/10.1049/ell2.70351</a></p>2025-11-06T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1049/ell2.70351https://figshare.com/articles/journal_contribution/Biomechanically_Regularized_Deep_Deformable_Registration_for_CT_and_US_Fusion/30859112CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/308591122025-11-06T03:00:00Z
spellingShingle Biomechanically Regularized Deep Deformable Registration for CT and US Fusion
Snigdha Mohanty (16904919)
Engineering
Biomedical engineering
Information and computing sciences
Machine learning
Liver CT and Ultrasound (US)
Deep Learning
Convolutional Neural Networks (CNN)
Biomechanical Regularization
Image-Guided Interventions
status_str publishedVersion
title Biomechanically Regularized Deep Deformable Registration for CT and US Fusion
title_full Biomechanically Regularized Deep Deformable Registration for CT and US Fusion
title_fullStr Biomechanically Regularized Deep Deformable Registration for CT and US Fusion
title_full_unstemmed Biomechanically Regularized Deep Deformable Registration for CT and US Fusion
title_short Biomechanically Regularized Deep Deformable Registration for CT and US Fusion
title_sort Biomechanically Regularized Deep Deformable Registration for CT and US Fusion
topic Engineering
Biomedical engineering
Information and computing sciences
Machine learning
Liver CT and Ultrasound (US)
Deep Learning
Convolutional Neural Networks (CNN)
Biomechanical Regularization
Image-Guided Interventions