Shearlet‐based compressed sensing with non‐local similarity for MRI breast image reconstruction

Abstract Magnetic resonance imaging (MRI) requires long detection time and makes patients uncomfortable. The proposed compressed sensing MRI compressed sensing with shearlet dictionary and non‐local similarity model is established with shearlet dictionary and non‐local similarity. The shearlet dicti...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiaotao Shao, Caike Wei, Yi Xie, Zhongli Wang, Yan Shen
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Telecommunication TK5101-6720
Acceso en línea:	https://doaj.org/article/18f5150f07234102a0f6a5afe6a8de24
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:18f5150f07234102a0f6a5afe6a8de24
record_format	dspace
spelling	oai:doaj.org-article:18f5150f07234102a0f6a5afe6a8de242021-11-09T10:16:47ZShearlet‐based compressed sensing with non‐local similarity for MRI breast image reconstruction1751-96831751-967510.1049/sil2.12062https://doaj.org/article/18f5150f07234102a0f6a5afe6a8de242021-12-01T00:00:00Zhttps://doi.org/10.1049/sil2.12062https://doaj.org/toc/1751-9675https://doaj.org/toc/1751-9683Abstract Magnetic resonance imaging (MRI) requires long detection time and makes patients uncomfortable. The proposed compressed sensing MRI compressed sensing with shearlet dictionary and non‐local similarity model is established with shearlet dictionary and non‐local similarity. The shearlet dictionary is adopted in MRI compressed sensing to represent breast tissues with sparser data in different scales and directions. The non‐local similarity of an image is integrated to the model to preserve the lesion details of the reconstructed MRI images. The proposed model is solved by the split Bregman algorithm to obtain the optimized image iteratively. Experiments are performed on practical MRI breast images with sampling data of 13% and 10%. With the decrease of sampling data, the proposed method can reconstruct the image with better visual effect and higher peak signal‐to‐noise ratio (PSNR) and structural similarity index (SSIM) than traditional methods. There is an improvement of 13 dB of PSNR and 0.2 of SSIM under 10% data. The proposed method can reconstruct MRI images with less data and higher reconstruction quality compared with the traditional methods.Xiaotao ShaoCaike WeiYi XieZhongli WangYan ShenWileyarticleTelecommunicationTK5101-6720ENIET Signal Processing, Vol 15, Iss 9, Pp 573-583 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Telecommunication TK5101-6720
spellingShingle	Telecommunication TK5101-6720 Xiaotao Shao Caike Wei Yi Xie Zhongli Wang Yan Shen Shearlet‐based compressed sensing with non‐local similarity for MRI breast image reconstruction
description	Abstract Magnetic resonance imaging (MRI) requires long detection time and makes patients uncomfortable. The proposed compressed sensing MRI compressed sensing with shearlet dictionary and non‐local similarity model is established with shearlet dictionary and non‐local similarity. The shearlet dictionary is adopted in MRI compressed sensing to represent breast tissues with sparser data in different scales and directions. The non‐local similarity of an image is integrated to the model to preserve the lesion details of the reconstructed MRI images. The proposed model is solved by the split Bregman algorithm to obtain the optimized image iteratively. Experiments are performed on practical MRI breast images with sampling data of 13% and 10%. With the decrease of sampling data, the proposed method can reconstruct the image with better visual effect and higher peak signal‐to‐noise ratio (PSNR) and structural similarity index (SSIM) than traditional methods. There is an improvement of 13 dB of PSNR and 0.2 of SSIM under 10% data. The proposed method can reconstruct MRI images with less data and higher reconstruction quality compared with the traditional methods.
format	article
author	Xiaotao Shao Caike Wei Yi Xie Zhongli Wang Yan Shen
author_facet	Xiaotao Shao Caike Wei Yi Xie Zhongli Wang Yan Shen
author_sort	Xiaotao Shao
title	Shearlet‐based compressed sensing with non‐local similarity for MRI breast image reconstruction
title_short	Shearlet‐based compressed sensing with non‐local similarity for MRI breast image reconstruction
title_full	Shearlet‐based compressed sensing with non‐local similarity for MRI breast image reconstruction
title_fullStr	Shearlet‐based compressed sensing with non‐local similarity for MRI breast image reconstruction
title_full_unstemmed	Shearlet‐based compressed sensing with non‐local similarity for MRI breast image reconstruction
title_sort	shearlet‐based compressed sensing with non‐local similarity for mri breast image reconstruction
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/18f5150f07234102a0f6a5afe6a8de24
work_keys_str_mv	AT xiaotaoshao shearletbasedcompressedsensingwithnonlocalsimilarityformribreastimagereconstruction AT caikewei shearletbasedcompressedsensingwithnonlocalsimilarityformribreastimagereconstruction AT yixie shearletbasedcompressedsensingwithnonlocalsimilarityformribreastimagereconstruction AT zhongliwang shearletbasedcompressedsensingwithnonlocalsimilarityformribreastimagereconstruction AT yanshen shearletbasedcompressedsensingwithnonlocalsimilarityformribreastimagereconstruction
_version_	1718441086995660800

Shearlet‐based compressed sensing with non‐local similarity for MRI breast image reconstruction

Ejemplares similares