MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks

Background: Quantitative cardiovascular magnetic resonance (CMR) T1 mapping has shown promise for advanced tissue characterisation in routine clinical practise. However, T1 mapping is prone to motion artefacts, which affects its robustness and clinical interpretation. Current methods for motion corr...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ricardo A. Gonzales, Qiang Zhang, Bartłomiej W. Papież, Konrad Werys, Elena Lukaschuk, Iulia A. Popescu, Matthew K. Burrage, Mayooran Shanmuganathan, Vanessa M. Ferreira, Stefan K. Piechnik
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	cardiovascular magnetic resonance deep learning image registration ShMOLLI T1 mapping Diseases of the circulatory (Cardiovascular) system RC666-701
Acceso en línea:	https://doaj.org/article/b23d9ebf5a7e48dd830b04b907644f6b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b23d9ebf5a7e48dd830b04b907644f6b
record_format	dspace
spelling	oai:doaj.org-article:b23d9ebf5a7e48dd830b04b907644f6b2021-11-30T12:29:15ZMOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks2297-055X10.3389/fcvm.2021.768245https://doaj.org/article/b23d9ebf5a7e48dd830b04b907644f6b2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fcvm.2021.768245/fullhttps://doaj.org/toc/2297-055XBackground: Quantitative cardiovascular magnetic resonance (CMR) T1 mapping has shown promise for advanced tissue characterisation in routine clinical practise. However, T1 mapping is prone to motion artefacts, which affects its robustness and clinical interpretation. Current methods for motion correction on T1 mapping are model-driven with no guarantee on generalisability, limiting its widespread use. In contrast, emerging data-driven deep learning approaches have shown good performance in general image registration tasks. We propose MOCOnet, a convolutional neural network solution, for generalisable motion artefact correction in T1 maps.Methods: The network architecture employs U-Net for producing distance vector fields and utilises warping layers to apply deformation to the feature maps in a coarse-to-fine manner. Using the UK Biobank imaging dataset scanned at 1.5T, MOCOnet was trained on 1,536 mid-ventricular T1 maps (acquired using the ShMOLLI method) with motion artefacts, generated by a customised deformation procedure, and tested on a different set of 200 samples with a diverse range of motion. MOCOnet was compared to a well-validated baseline multi-modal image registration method. Motion reduction was visually assessed by 3 human experts, with motion scores ranging from 0% (strictly no motion) to 100% (very severe motion).Results: MOCOnet achieved fast image registration (<1 second per T1 map) and successfully suppressed a wide range of motion artefacts. MOCOnet significantly reduced motion scores from 37.1±21.5 to 13.3±10.5 (p < 0.001), whereas the baseline method reduced it to 15.8±15.6 (p < 0.001). MOCOnet was significantly better than the baseline method in suppressing motion artefacts and more consistently (p = 0.007).Conclusion: MOCOnet demonstrated significantly better motion correction performance compared to a traditional image registration approach. Salvaging data affected by motion with robustness and in a time-efficient manner may enable better image quality and reliable images for immediate clinical interpretation.Ricardo A. GonzalesQiang ZhangBartłomiej W. PapieżBartłomiej W. PapieżKonrad WerysElena LukaschukIulia A. PopescuMatthew K. BurrageMayooran ShanmuganathanVanessa M. FerreiraStefan K. PiechnikFrontiers Media S.A.articlecardiovascular magnetic resonancedeep learningimage registrationShMOLLIT1 mappingDiseases of the circulatory (Cardiovascular) systemRC666-701ENFrontiers in Cardiovascular Medicine, Vol 8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	cardiovascular magnetic resonance deep learning image registration ShMOLLI T1 mapping Diseases of the circulatory (Cardiovascular) system RC666-701
spellingShingle	cardiovascular magnetic resonance deep learning image registration ShMOLLI T1 mapping Diseases of the circulatory (Cardiovascular) system RC666-701 Ricardo A. Gonzales Qiang Zhang Bartłomiej W. Papież Bartłomiej W. Papież Konrad Werys Elena Lukaschuk Iulia A. Popescu Matthew K. Burrage Mayooran Shanmuganathan Vanessa M. Ferreira Stefan K. Piechnik MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks
description	Background: Quantitative cardiovascular magnetic resonance (CMR) T1 mapping has shown promise for advanced tissue characterisation in routine clinical practise. However, T1 mapping is prone to motion artefacts, which affects its robustness and clinical interpretation. Current methods for motion correction on T1 mapping are model-driven with no guarantee on generalisability, limiting its widespread use. In contrast, emerging data-driven deep learning approaches have shown good performance in general image registration tasks. We propose MOCOnet, a convolutional neural network solution, for generalisable motion artefact correction in T1 maps.Methods: The network architecture employs U-Net for producing distance vector fields and utilises warping layers to apply deformation to the feature maps in a coarse-to-fine manner. Using the UK Biobank imaging dataset scanned at 1.5T, MOCOnet was trained on 1,536 mid-ventricular T1 maps (acquired using the ShMOLLI method) with motion artefacts, generated by a customised deformation procedure, and tested on a different set of 200 samples with a diverse range of motion. MOCOnet was compared to a well-validated baseline multi-modal image registration method. Motion reduction was visually assessed by 3 human experts, with motion scores ranging from 0% (strictly no motion) to 100% (very severe motion).Results: MOCOnet achieved fast image registration (<1 second per T1 map) and successfully suppressed a wide range of motion artefacts. MOCOnet significantly reduced motion scores from 37.1±21.5 to 13.3±10.5 (p < 0.001), whereas the baseline method reduced it to 15.8±15.6 (p < 0.001). MOCOnet was significantly better than the baseline method in suppressing motion artefacts and more consistently (p = 0.007).Conclusion: MOCOnet demonstrated significantly better motion correction performance compared to a traditional image registration approach. Salvaging data affected by motion with robustness and in a time-efficient manner may enable better image quality and reliable images for immediate clinical interpretation.
format	article
author	Ricardo A. Gonzales Qiang Zhang Bartłomiej W. Papież Bartłomiej W. Papież Konrad Werys Elena Lukaschuk Iulia A. Popescu Matthew K. Burrage Mayooran Shanmuganathan Vanessa M. Ferreira Stefan K. Piechnik
author_facet	Ricardo A. Gonzales Qiang Zhang Bartłomiej W. Papież Bartłomiej W. Papież Konrad Werys Elena Lukaschuk Iulia A. Popescu Matthew K. Burrage Mayooran Shanmuganathan Vanessa M. Ferreira Stefan K. Piechnik
author_sort	Ricardo A. Gonzales
title	MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks
title_short	MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks
title_full	MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks
title_fullStr	MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks
title_full_unstemmed	MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks
title_sort	moconet: robust motion correction of cardiovascular magnetic resonance t1 mapping using convolutional neural networks
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/b23d9ebf5a7e48dd830b04b907644f6b
work_keys_str_mv	AT ricardoagonzales moconetrobustmotioncorrectionofcardiovascularmagneticresonancet1mappingusingconvolutionalneuralnetworks AT qiangzhang moconetrobustmotioncorrectionofcardiovascularmagneticresonancet1mappingusingconvolutionalneuralnetworks AT bartłomiejwpapiez moconetrobustmotioncorrectionofcardiovascularmagneticresonancet1mappingusingconvolutionalneuralnetworks AT bartłomiejwpapiez moconetrobustmotioncorrectionofcardiovascularmagneticresonancet1mappingusingconvolutionalneuralnetworks AT konradwerys moconetrobustmotioncorrectionofcardiovascularmagneticresonancet1mappingusingconvolutionalneuralnetworks AT elenalukaschuk moconetrobustmotioncorrectionofcardiovascularmagneticresonancet1mappingusingconvolutionalneuralnetworks AT iuliaapopescu moconetrobustmotioncorrectionofcardiovascularmagneticresonancet1mappingusingconvolutionalneuralnetworks AT matthewkburrage moconetrobustmotioncorrectionofcardiovascularmagneticresonancet1mappingusingconvolutionalneuralnetworks AT mayooranshanmuganathan moconetrobustmotioncorrectionofcardiovascularmagneticresonancet1mappingusingconvolutionalneuralnetworks AT vanessamferreira moconetrobustmotioncorrectionofcardiovascularmagneticresonancet1mappingusingconvolutionalneuralnetworks AT stefankpiechnik moconetrobustmotioncorrectionofcardiovascularmagneticresonancet1mappingusingconvolutionalneuralnetworks
_version_	1718406644627406848

MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks

Ejemplares similares