iRegNet: Non-Rigid Registration of MRI to Interventional US for Brain-Shift Compensation Using Convolutional Neural Networks

Accurate and safe neurosurgical intervention can be affected by intra-operative tissue deformation, known as brain-shift. In this study, we propose an automatic, fast, and accurate deformable method, called iRegNet, for registering pre-operative magnetic resonance images to intra-operative ultrasoun...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ramy A. Zeineldin, Mohamed E. Karar, Ziad Elshaer, Markus Schmidhammer, Jan Coburger, Christian R. Wirtz, Oliver Burgert, Franziska Mathis-Ullrich
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Brain-Shift computer-aided diagnosis medical image registration neurosurgery intra-operative ultrasound Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/b1bbf5bbb9cd4e6fa898e6363daf2102
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b1bbf5bbb9cd4e6fa898e6363daf2102
record_format	dspace
spelling	oai:doaj.org-article:b1bbf5bbb9cd4e6fa898e6363daf21022021-11-18T00:10:53ZiRegNet: Non-Rigid Registration of MRI to Interventional US for Brain-Shift Compensation Using Convolutional Neural Networks2169-353610.1109/ACCESS.2021.3120306https://doaj.org/article/b1bbf5bbb9cd4e6fa898e6363daf21022021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9570282/https://doaj.org/toc/2169-3536Accurate and safe neurosurgical intervention can be affected by intra-operative tissue deformation, known as brain-shift. In this study, we propose an automatic, fast, and accurate deformable method, called iRegNet, for registering pre-operative magnetic resonance images to intra-operative ultrasound volumes to compensate for brain-shift. iRegNet is a robust end-to-end deep learning approach for the non-linear registration of MRI-iUS images in the context of image-guided neurosurgery. Pre-operative MRI (as moving image) and iUS (as fixed image) are first appended to our convolutional neural network, after which a non-rigid transformation field is estimated. The MRI image is then transformed using the output displacement field to the iUS coordinate system. Extensive experiments have been conducted on two multi-location databases, which are the BITE and the RESECT. Quantitatively, iRegNet reduced the mean landmark errors from pre-registration value of (4.18 ± 1.84 and 5.35 ± 4.19 mm) to the lowest value of (1.47 ± 0.61 and 0.84 ± 0.16 mm) for the BITE and RESECT datasets, respectively. Additional qualitative validation of this study was conducted by two expert neurosurgeons through overlaying MRI-iUS pairs before and after the deformable registration. Experimental findings show that our proposed iRegNet is fast and achieves state-of-the-art accuracies outperforming state-of-the-art approaches. Furthermore, the proposed iRegNet can deliver competitive results, even in the case of non-trained images as proof of its generality and can therefore be valuable in intra-operative neurosurgical guidance.Ramy A. ZeineldinMohamed E. KararZiad ElshaerMarkus SchmidhammerJan CoburgerChristian R. WirtzOliver BurgertFranziska Mathis-UllrichIEEEarticleBrain-Shiftcomputer-aided diagnosismedical image registrationneurosurgeryintra-operative ultrasoundElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 147579-147590 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Brain-Shift computer-aided diagnosis medical image registration neurosurgery intra-operative ultrasound Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Brain-Shift computer-aided diagnosis medical image registration neurosurgery intra-operative ultrasound Electrical engineering. Electronics. Nuclear engineering TK1-9971 Ramy A. Zeineldin Mohamed E. Karar Ziad Elshaer Markus Schmidhammer Jan Coburger Christian R. Wirtz Oliver Burgert Franziska Mathis-Ullrich iRegNet: Non-Rigid Registration of MRI to Interventional US for Brain-Shift Compensation Using Convolutional Neural Networks
description	Accurate and safe neurosurgical intervention can be affected by intra-operative tissue deformation, known as brain-shift. In this study, we propose an automatic, fast, and accurate deformable method, called iRegNet, for registering pre-operative magnetic resonance images to intra-operative ultrasound volumes to compensate for brain-shift. iRegNet is a robust end-to-end deep learning approach for the non-linear registration of MRI-iUS images in the context of image-guided neurosurgery. Pre-operative MRI (as moving image) and iUS (as fixed image) are first appended to our convolutional neural network, after which a non-rigid transformation field is estimated. The MRI image is then transformed using the output displacement field to the iUS coordinate system. Extensive experiments have been conducted on two multi-location databases, which are the BITE and the RESECT. Quantitatively, iRegNet reduced the mean landmark errors from pre-registration value of (4.18 ± 1.84 and 5.35 ± 4.19 mm) to the lowest value of (1.47 ± 0.61 and 0.84 ± 0.16 mm) for the BITE and RESECT datasets, respectively. Additional qualitative validation of this study was conducted by two expert neurosurgeons through overlaying MRI-iUS pairs before and after the deformable registration. Experimental findings show that our proposed iRegNet is fast and achieves state-of-the-art accuracies outperforming state-of-the-art approaches. Furthermore, the proposed iRegNet can deliver competitive results, even in the case of non-trained images as proof of its generality and can therefore be valuable in intra-operative neurosurgical guidance.
format	article
author	Ramy A. Zeineldin Mohamed E. Karar Ziad Elshaer Markus Schmidhammer Jan Coburger Christian R. Wirtz Oliver Burgert Franziska Mathis-Ullrich
author_facet	Ramy A. Zeineldin Mohamed E. Karar Ziad Elshaer Markus Schmidhammer Jan Coburger Christian R. Wirtz Oliver Burgert Franziska Mathis-Ullrich
author_sort	Ramy A. Zeineldin
title	iRegNet: Non-Rigid Registration of MRI to Interventional US for Brain-Shift Compensation Using Convolutional Neural Networks
title_short	iRegNet: Non-Rigid Registration of MRI to Interventional US for Brain-Shift Compensation Using Convolutional Neural Networks
title_full	iRegNet: Non-Rigid Registration of MRI to Interventional US for Brain-Shift Compensation Using Convolutional Neural Networks
title_fullStr	iRegNet: Non-Rigid Registration of MRI to Interventional US for Brain-Shift Compensation Using Convolutional Neural Networks
title_full_unstemmed	iRegNet: Non-Rigid Registration of MRI to Interventional US for Brain-Shift Compensation Using Convolutional Neural Networks
title_sort	iregnet: non-rigid registration of mri to interventional us for brain-shift compensation using convolutional neural networks
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/b1bbf5bbb9cd4e6fa898e6363daf2102
work_keys_str_mv	AT ramyazeineldin iregnetnonrigidregistrationofmritointerventionalusforbrainshiftcompensationusingconvolutionalneuralnetworks AT mohamedekarar iregnetnonrigidregistrationofmritointerventionalusforbrainshiftcompensationusingconvolutionalneuralnetworks AT ziadelshaer iregnetnonrigidregistrationofmritointerventionalusforbrainshiftcompensationusingconvolutionalneuralnetworks AT markusschmidhammer iregnetnonrigidregistrationofmritointerventionalusforbrainshiftcompensationusingconvolutionalneuralnetworks AT jancoburger iregnetnonrigidregistrationofmritointerventionalusforbrainshiftcompensationusingconvolutionalneuralnetworks AT christianrwirtz iregnetnonrigidregistrationofmritointerventionalusforbrainshiftcompensationusingconvolutionalneuralnetworks AT oliverburgert iregnetnonrigidregistrationofmritointerventionalusforbrainshiftcompensationusingconvolutionalneuralnetworks AT franziskamathisullrich iregnetnonrigidregistrationofmritointerventionalusforbrainshiftcompensationusingconvolutionalneuralnetworks
_version_	1718425186612543488

iRegNet: Non-Rigid Registration of MRI to Interventional US for Brain-Shift Compensation Using Convolutional Neural Networks

Ejemplares similares