Towards automatic US-MR fetal brain image registration with learning-based methods

Fetal brain imaging is essential for prenatal care, with ultrasound (US) and magnetic resonance imaging (MRI) providing complementary strengths. While MRI has superior soft tissue contrast, US offers portable and inexpensive screening of neurological abnormalities. Despite the great potential synerg...

Full description

Saved in:
Bibliographic Details
Main Authors: Qi Zeng, Weide Liu, Bo Li, Ryne Didier, P. Ellen Grant, Davood Karimi
Format: Article
Language:English
Published: Elsevier 2025-04-01
Series:NeuroImage
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1053811925001065
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850213548411584512
author Qi Zeng
Weide Liu
Bo Li
Ryne Didier
P. Ellen Grant
Davood Karimi
author_facet Qi Zeng
Weide Liu
Bo Li
Ryne Didier
P. Ellen Grant
Davood Karimi
author_sort Qi Zeng
collection DOAJ
description Fetal brain imaging is essential for prenatal care, with ultrasound (US) and magnetic resonance imaging (MRI) providing complementary strengths. While MRI has superior soft tissue contrast, US offers portable and inexpensive screening of neurological abnormalities. Despite the great potential synergy of combined fetal brain US and MR imaging to enhance diagnostic accuracy, little effort has been made to integrate these modalities. An essential step towards this integration is accurate automatic spatial alignment, which is technically very challenging due to the inherent differences in contrast and modality-specific imaging artifacts. In this work, we present a novel atlas-assisted multi-task learning technique to address this problem. Instead of training the registration model solely with intra-subject US-MR image pairs, our approach enables the network to also learn from domain-specific image-to-atlas registration tasks. This leads to an end-to-end multi-task learning framework with superior registration performance. Our proposed method was validated using a dataset of same-day intra-subject 3D US-MR image pairs. The results show that our method outperforms conventional optimization-based methods and recent learning-based techniques for rigid image registration. Specifically, the average target registration error for our method is less than 4 mm, which is significantly better than existing methods. Extensive experiments have also shown that our method has a much wider capture range and is robust to brain abnormalities. Given these advantages over existing techniques, our method is more suitable for deployment in clinical workflows and may contribute to streamlined multimodal imaging pipelines for fetal brain assessment.
format Article
id doaj-art-2c016501e3b743348bfa72fc85bbf498
institution OA Journals
issn 1095-9572
language English
publishDate 2025-04-01
publisher Elsevier
record_format Article
series NeuroImage
spelling doaj-art-2c016501e3b743348bfa72fc85bbf4982025-08-20T02:09:07ZengElsevierNeuroImage1095-95722025-04-0131012110410.1016/j.neuroimage.2025.121104Towards automatic US-MR fetal brain image registration with learning-based methodsQi Zeng0Weide Liu1Bo Li2Ryne Didier3P. Ellen Grant4Davood Karimi5Correspondence to: Landmark Center, 401 Park Dr, Boston, MA 02215, USA.; Department of Radiology, Boston Children’s Hospital, USA; Harvard Medical School, USADepartment of Radiology, Boston Children’s Hospital, USA; Harvard Medical School, USADepartment of Radiology, Boston Children’s Hospital, USA; Harvard Medical School, USADepartment of Radiology, Boston Children’s Hospital, USA; Harvard Medical School, USADepartment of Radiology, Boston Children’s Hospital, USA; Harvard Medical School, USADepartment of Radiology, Boston Children’s Hospital, USA; Harvard Medical School, USAFetal brain imaging is essential for prenatal care, with ultrasound (US) and magnetic resonance imaging (MRI) providing complementary strengths. While MRI has superior soft tissue contrast, US offers portable and inexpensive screening of neurological abnormalities. Despite the great potential synergy of combined fetal brain US and MR imaging to enhance diagnostic accuracy, little effort has been made to integrate these modalities. An essential step towards this integration is accurate automatic spatial alignment, which is technically very challenging due to the inherent differences in contrast and modality-specific imaging artifacts. In this work, we present a novel atlas-assisted multi-task learning technique to address this problem. Instead of training the registration model solely with intra-subject US-MR image pairs, our approach enables the network to also learn from domain-specific image-to-atlas registration tasks. This leads to an end-to-end multi-task learning framework with superior registration performance. Our proposed method was validated using a dataset of same-day intra-subject 3D US-MR image pairs. The results show that our method outperforms conventional optimization-based methods and recent learning-based techniques for rigid image registration. Specifically, the average target registration error for our method is less than 4 mm, which is significantly better than existing methods. Extensive experiments have also shown that our method has a much wider capture range and is robust to brain abnormalities. Given these advantages over existing techniques, our method is more suitable for deployment in clinical workflows and may contribute to streamlined multimodal imaging pipelines for fetal brain assessment.http://www.sciencedirect.com/science/article/pii/S1053811925001065Fetal brain imagingUltrasoundMRIImage registrationMachine learning
spellingShingle Qi Zeng
Weide Liu
Bo Li
Ryne Didier
P. Ellen Grant
Davood Karimi
Towards automatic US-MR fetal brain image registration with learning-based methods
NeuroImage
Fetal brain imaging
Ultrasound
MRI
Image registration
Machine learning
title Towards automatic US-MR fetal brain image registration with learning-based methods
title_full Towards automatic US-MR fetal brain image registration with learning-based methods
title_fullStr Towards automatic US-MR fetal brain image registration with learning-based methods
title_full_unstemmed Towards automatic US-MR fetal brain image registration with learning-based methods
title_short Towards automatic US-MR fetal brain image registration with learning-based methods
title_sort towards automatic us mr fetal brain image registration with learning based methods
topic Fetal brain imaging
Ultrasound
MRI
Image registration
Machine learning
url http://www.sciencedirect.com/science/article/pii/S1053811925001065
work_keys_str_mv AT qizeng towardsautomaticusmrfetalbrainimageregistrationwithlearningbasedmethods
AT weideliu towardsautomaticusmrfetalbrainimageregistrationwithlearningbasedmethods
AT boli towardsautomaticusmrfetalbrainimageregistrationwithlearningbasedmethods
AT rynedidier towardsautomaticusmrfetalbrainimageregistrationwithlearningbasedmethods
AT pellengrant towardsautomaticusmrfetalbrainimageregistrationwithlearningbasedmethods
AT davoodkarimi towardsautomaticusmrfetalbrainimageregistrationwithlearningbasedmethods