Fast data-driven learning of parallel MRI sampling patterns for large scale problems

Abstract In this study, a fast data-driven optimization approach, named bias-accelerated subset selection (BASS), is proposed for learning efficacious sampling patterns (SPs) with the purpose of reducing scan time in large-dimensional parallel MRI. BASS is applicable when Cartesian fully-sampled k-s...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Marcelo V. W. Zibetti, Gabor T. Herman, Ravinder R. Regatte
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/ba5a48c509ba4cda8e1e0b2270ad0ef3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ba5a48c509ba4cda8e1e0b2270ad0ef3
record_format	dspace
spelling	oai:doaj.org-article:ba5a48c509ba4cda8e1e0b2270ad0ef32021-12-02T19:16:54ZFast data-driven learning of parallel MRI sampling patterns for large scale problems10.1038/s41598-021-97995-w2045-2322https://doaj.org/article/ba5a48c509ba4cda8e1e0b2270ad0ef32021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97995-whttps://doaj.org/toc/2045-2322Abstract In this study, a fast data-driven optimization approach, named bias-accelerated subset selection (BASS), is proposed for learning efficacious sampling patterns (SPs) with the purpose of reducing scan time in large-dimensional parallel MRI. BASS is applicable when Cartesian fully-sampled k-space measurements of specific anatomy are available for training and the reconstruction method for undersampled measurements is specified; such information is used to define the efficacy of any SP for recovering the values at the non-sampled k-space points. BASS produces a sequence of SPs with the aim of finding one of a specified size with (near) optimal efficacy. BASS was tested with five reconstruction methods for parallel MRI based on low-rankness and sparsity that allow a free choice of the SP. Three datasets were used for testing, two of high-resolution brain images ( $$\text {T}_{2}$$ T 2 -weighted images and, respectively, $$\text {T}_{1\rho }$$ T 1 ρ -weighted images) and another of knee images for quantitative mapping of the cartilage. The proposed approach has low computational cost and fast convergence; in the tested cases it obtained SPs up to 50 times faster than the currently best greedy approach. Reconstruction quality increased by up to 45% over that provided by variable density and Poisson disk SPs, for the same scan time. Optionally, the scan time can be nearly halved without loss of reconstruction quality. Quantitative MRI and prospective accelerated MRI results show improvements. Compared with greedy approaches, BASS rapidly learns effective SPs for various reconstruction methods, using larger SPs and larger datasets; enabling better selection of sampling-reconstruction pairs for specific MRI problems.Marcelo V. W. ZibettiGabor T. HermanRavinder R. RegatteNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-19 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Marcelo V. W. Zibetti Gabor T. Herman Ravinder R. Regatte Fast data-driven learning of parallel MRI sampling patterns for large scale problems
description	Abstract In this study, a fast data-driven optimization approach, named bias-accelerated subset selection (BASS), is proposed for learning efficacious sampling patterns (SPs) with the purpose of reducing scan time in large-dimensional parallel MRI. BASS is applicable when Cartesian fully-sampled k-space measurements of specific anatomy are available for training and the reconstruction method for undersampled measurements is specified; such information is used to define the efficacy of any SP for recovering the values at the non-sampled k-space points. BASS produces a sequence of SPs with the aim of finding one of a specified size with (near) optimal efficacy. BASS was tested with five reconstruction methods for parallel MRI based on low-rankness and sparsity that allow a free choice of the SP. Three datasets were used for testing, two of high-resolution brain images ( $$\text {T}_{2}$$ T 2 -weighted images and, respectively, $$\text {T}_{1\rho }$$ T 1 ρ -weighted images) and another of knee images for quantitative mapping of the cartilage. The proposed approach has low computational cost and fast convergence; in the tested cases it obtained SPs up to 50 times faster than the currently best greedy approach. Reconstruction quality increased by up to 45% over that provided by variable density and Poisson disk SPs, for the same scan time. Optionally, the scan time can be nearly halved without loss of reconstruction quality. Quantitative MRI and prospective accelerated MRI results show improvements. Compared with greedy approaches, BASS rapidly learns effective SPs for various reconstruction methods, using larger SPs and larger datasets; enabling better selection of sampling-reconstruction pairs for specific MRI problems.
format	article
author	Marcelo V. W. Zibetti Gabor T. Herman Ravinder R. Regatte
author_facet	Marcelo V. W. Zibetti Gabor T. Herman Ravinder R. Regatte
author_sort	Marcelo V. W. Zibetti
title	Fast data-driven learning of parallel MRI sampling patterns for large scale problems
title_short	Fast data-driven learning of parallel MRI sampling patterns for large scale problems
title_full	Fast data-driven learning of parallel MRI sampling patterns for large scale problems
title_fullStr	Fast data-driven learning of parallel MRI sampling patterns for large scale problems
title_full_unstemmed	Fast data-driven learning of parallel MRI sampling patterns for large scale problems
title_sort	fast data-driven learning of parallel mri sampling patterns for large scale problems
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/ba5a48c509ba4cda8e1e0b2270ad0ef3
work_keys_str_mv	AT marcelovwzibetti fastdatadrivenlearningofparallelmrisamplingpatternsforlargescaleproblems AT gabortherman fastdatadrivenlearningofparallelmrisamplingpatternsforlargescaleproblems AT ravinderrregatte fastdatadrivenlearningofparallelmrisamplingpatternsforlargescaleproblems
_version_	1718376934385123328

Fast data-driven learning of parallel MRI sampling patterns for large scale problems

Ejemplares similares