Noise-Robust MRI Upsampling Using Adaptive Local Steering Kernel

Upsampling and denoising of magnetic resonance images are conventionally performed separately, which would introduce unwanted artifacts such as blurring. To address this problem, we propose an innovative adaptive interpolation framework to achieve simultaneous image upsampling, denoising, and detail...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jing Hu, Xinyan Li, Xiaolong Wang, Yan Li, Xi Wu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2020
Materias:	Adaptive sharpening image upsampling local steering kernel magnetic resonance imaging noise robust Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/85ff433152ea4796a0151bd70a81ed1f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:85ff433152ea4796a0151bd70a81ed1f
record_format	dspace
spelling	oai:doaj.org-article:85ff433152ea4796a0151bd70a81ed1f2021-11-19T00:05:20ZNoise-Robust MRI Upsampling Using Adaptive Local Steering Kernel2169-353610.1109/ACCESS.2020.3020133https://doaj.org/article/85ff433152ea4796a0151bd70a81ed1f2020-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9179731/https://doaj.org/toc/2169-3536Upsampling and denoising of magnetic resonance images are conventionally performed separately, which would introduce unwanted artifacts such as blurring. To address this problem, we propose an innovative adaptive interpolation framework to achieve simultaneous image upsampling, denoising, and detail enhancement. First, local steering kernel (LSK) function is leveraged to adapt the interpolation weights according to geometric structures in the magnetic resonance (MR) images. An adaptive sharpening of the LSK weight matrix and a Rician bias correction are then adopted to remove Rician noise and enhance fine details. In this regard, the adaptive LSK extends the zero-order point estimation framework to higher orders of regression, and therefore facilitates edge preservation and detail reconstruction. The post-processing Rician correction avoids the bias caused by the asymmetry of Rician noise distributions. Experimental results using both real and synthetic clinical MR cranial images (with and without noise) demonstrated that our algorithm produced better reconstruction results than several traditional interpolation-based upsampling methods, including nearest neighbor (NN), non-local means (NLM), self-learning super resolution (SLSR), Gaussian process regression (GPR), and even comparable to four deep-learning-based methods but with less data requirements and computational complexity. The proposed technique resulted in PSNR and SSIM values were ~3%–16% higher than any of the other traditional algorithms tested, and our method recovered more clear textures from noisy images compared with deep-learning-based methods. As such, the presented technique is a viable new approach to MR upsampling, particularly for noisy images.Jing HuXinyan LiXiaolong WangYan LiXi WuIEEEarticleAdaptive sharpeningimage upsamplinglocal steering kernelmagnetic resonance imagingnoise robustElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 8, Pp 158538-158548 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Adaptive sharpening image upsampling local steering kernel magnetic resonance imaging noise robust Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Adaptive sharpening image upsampling local steering kernel magnetic resonance imaging noise robust Electrical engineering. Electronics. Nuclear engineering TK1-9971 Jing Hu Xinyan Li Xiaolong Wang Yan Li Xi Wu Noise-Robust MRI Upsampling Using Adaptive Local Steering Kernel
description	Upsampling and denoising of magnetic resonance images are conventionally performed separately, which would introduce unwanted artifacts such as blurring. To address this problem, we propose an innovative adaptive interpolation framework to achieve simultaneous image upsampling, denoising, and detail enhancement. First, local steering kernel (LSK) function is leveraged to adapt the interpolation weights according to geometric structures in the magnetic resonance (MR) images. An adaptive sharpening of the LSK weight matrix and a Rician bias correction are then adopted to remove Rician noise and enhance fine details. In this regard, the adaptive LSK extends the zero-order point estimation framework to higher orders of regression, and therefore facilitates edge preservation and detail reconstruction. The post-processing Rician correction avoids the bias caused by the asymmetry of Rician noise distributions. Experimental results using both real and synthetic clinical MR cranial images (with and without noise) demonstrated that our algorithm produced better reconstruction results than several traditional interpolation-based upsampling methods, including nearest neighbor (NN), non-local means (NLM), self-learning super resolution (SLSR), Gaussian process regression (GPR), and even comparable to four deep-learning-based methods but with less data requirements and computational complexity. The proposed technique resulted in PSNR and SSIM values were ~3%–16% higher than any of the other traditional algorithms tested, and our method recovered more clear textures from noisy images compared with deep-learning-based methods. As such, the presented technique is a viable new approach to MR upsampling, particularly for noisy images.
format	article
author	Jing Hu Xinyan Li Xiaolong Wang Yan Li Xi Wu
author_facet	Jing Hu Xinyan Li Xiaolong Wang Yan Li Xi Wu
author_sort	Jing Hu
title	Noise-Robust MRI Upsampling Using Adaptive Local Steering Kernel
title_short	Noise-Robust MRI Upsampling Using Adaptive Local Steering Kernel
title_full	Noise-Robust MRI Upsampling Using Adaptive Local Steering Kernel
title_fullStr	Noise-Robust MRI Upsampling Using Adaptive Local Steering Kernel
title_full_unstemmed	Noise-Robust MRI Upsampling Using Adaptive Local Steering Kernel
title_sort	noise-robust mri upsampling using adaptive local steering kernel
publisher	IEEE
publishDate	2020
url	https://doaj.org/article/85ff433152ea4796a0151bd70a81ed1f
work_keys_str_mv	AT jinghu noiserobustmriupsamplingusingadaptivelocalsteeringkernel AT xinyanli noiserobustmriupsamplingusingadaptivelocalsteeringkernel AT xiaolongwang noiserobustmriupsamplingusingadaptivelocalsteeringkernel AT yanli noiserobustmriupsamplingusingadaptivelocalsteeringkernel AT xiwu noiserobustmriupsamplingusingadaptivelocalsteeringkernel
_version_	1718420677786075136

Noise-Robust MRI Upsampling Using Adaptive Local Steering Kernel

Ejemplares similares