Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction

Abstract Recent years have seen a resurgence of interest in inexpensive low magnetic field (< 0.3 T) MRI systems mainly due to advances in magnet, coil and gradient set designs. Most of these advances have focused on improving hardware and signal acquisition strategies, and far less on the use of...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	N. Koonjoo, B. Zhu, G. Cody Bagnall, D. Bhutto, M. S. Rosen
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/37120cbf0d8a41e6857b2c949ac83c70
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:37120cbf0d8a41e6857b2c949ac83c70
record_format	dspace
spelling	oai:doaj.org-article:37120cbf0d8a41e6857b2c949ac83c702021-12-02T18:03:07ZBoosting the signal-to-noise of low-field MRI with deep learning image reconstruction10.1038/s41598-021-87482-72045-2322https://doaj.org/article/37120cbf0d8a41e6857b2c949ac83c702021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87482-7https://doaj.org/toc/2045-2322Abstract Recent years have seen a resurgence of interest in inexpensive low magnetic field (< 0.3 T) MRI systems mainly due to advances in magnet, coil and gradient set designs. Most of these advances have focused on improving hardware and signal acquisition strategies, and far less on the use of advanced image reconstruction methods to improve attainable image quality at low field. We describe here the use of our end-to-end deep neural network approach (AUTOMAP) to improve the image quality of highly noise-corrupted low-field MRI data. We compare the performance of this approach to two additional state-of-the-art denoising pipelines. We find that AUTOMAP improves image reconstruction of data acquired on two very different low-field MRI systems: human brain data acquired at 6.5 mT, and plant root data acquired at 47 mT, demonstrating SNR gains above Fourier reconstruction by factors of 1.5- to 4.5-fold, and 3-fold, respectively. In these applications, AUTOMAP outperformed two different contemporary image-based denoising algorithms, and suppressed noise-like spike artifacts in the reconstructed images. The impact of domain-specific training corpora on the reconstruction performance is discussed. The AUTOMAP approach to image reconstruction will enable significant image quality improvements at low-field, especially in highly noise-corrupted environments.N. KoonjooB. ZhuG. Cody BagnallD. BhuttoM. S. RosenNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q N. Koonjoo B. Zhu G. Cody Bagnall D. Bhutto M. S. Rosen Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction
description	Abstract Recent years have seen a resurgence of interest in inexpensive low magnetic field (< 0.3 T) MRI systems mainly due to advances in magnet, coil and gradient set designs. Most of these advances have focused on improving hardware and signal acquisition strategies, and far less on the use of advanced image reconstruction methods to improve attainable image quality at low field. We describe here the use of our end-to-end deep neural network approach (AUTOMAP) to improve the image quality of highly noise-corrupted low-field MRI data. We compare the performance of this approach to two additional state-of-the-art denoising pipelines. We find that AUTOMAP improves image reconstruction of data acquired on two very different low-field MRI systems: human brain data acquired at 6.5 mT, and plant root data acquired at 47 mT, demonstrating SNR gains above Fourier reconstruction by factors of 1.5- to 4.5-fold, and 3-fold, respectively. In these applications, AUTOMAP outperformed two different contemporary image-based denoising algorithms, and suppressed noise-like spike artifacts in the reconstructed images. The impact of domain-specific training corpora on the reconstruction performance is discussed. The AUTOMAP approach to image reconstruction will enable significant image quality improvements at low-field, especially in highly noise-corrupted environments.
format	article
author	N. Koonjoo B. Zhu G. Cody Bagnall D. Bhutto M. S. Rosen
author_facet	N. Koonjoo B. Zhu G. Cody Bagnall D. Bhutto M. S. Rosen
author_sort	N. Koonjoo
title	Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction
title_short	Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction
title_full	Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction
title_fullStr	Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction
title_full_unstemmed	Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction
title_sort	boosting the signal-to-noise of low-field mri with deep learning image reconstruction
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/37120cbf0d8a41e6857b2c949ac83c70
work_keys_str_mv	AT nkoonjoo boostingthesignaltonoiseoflowfieldmriwithdeeplearningimagereconstruction AT bzhu boostingthesignaltonoiseoflowfieldmriwithdeeplearningimagereconstruction AT gcodybagnall boostingthesignaltonoiseoflowfieldmriwithdeeplearningimagereconstruction AT dbhutto boostingthesignaltonoiseoflowfieldmriwithdeeplearningimagereconstruction AT msrosen boostingthesignaltonoiseoflowfieldmriwithdeeplearningimagereconstruction
_version_	1718378800246423552

Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction

Ejemplares similares