Reconstruction of 7T-Like Images from 3T MRI

Khosro Bahrami, Feng Shi, Xiaopeng Zong, Hae Won Shin, Hongyu An, Dinggang Shen

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

In the recent MRI scanning, ultra-high-field (7T) MR imaging provides higher resolution and better tissue contrast compared to routine 3T MRI, which may help in more accurate and early brain diseases diagnosis. However, currently, 7T MRI scanners are more expensive and less available at clinical and research centers. These motivate us to propose a method for the reconstruction of images close to the quality of 7T MRI, called 7T-like images, from 3T MRI, to improve the quality in terms of resolution and contrast. By doing so, the post-processing tasks, such as tissue segmentation, can be done more accurately and brain tissues details can be seen with higher resolution and contrast. To do this, we have acquired a unique dataset which includes paired 3T and 7T images scanned from same subjects, and then propose a hierarchical reconstruction based on group sparsity in a novel multi-level Canonical Correlation Analysis (CCA) space, to improve the quality of 3T MR image to be 7T-like MRI. First, overlapping patches are extracted from the input 3T MR image. Then, by extracting the most similar patches from all the aligned 3T and 7T images in the training set, the paired 3T and 7T dictionaries are constructed for each patch. It is worth noting that, for the training, we use pairs of 3T and 7T MR images from each training subject. Then, we propose multi-level CCA to map the paired 3T and 7T patch sets to a common space to increase their correlations. In such space, each input 3T MRI patch is sparsely represented by the 3T dictionary and then the obtained sparse coefficients are used together with the corresponding 7T dictionary to reconstruct the 7T-like patch. Also, to have the structural consistency between adjacent patches, the group sparsity is employed. This reconstruction is performed with changing patch sizes in a hierarchical framework. Experiments have been done using 13 subjects with both 3T and 7T MR images. The results show that our method outperforms previous methods and is able to recover better structural details. Also, to place our proposed method in a medical application context, we evaluated the influence of post-processing methods such as brain tissue segmentation on the reconstructed 7T-like MR images. Results show that our 7T-like images lead to higher accuracy in segmentation of white matter (WM), gray matter (GM), cerebrospinal fluid (CSF), and skull, compared to segmentation of 3T MR images.

Original languageEnglish
Article number7445872
Pages (from-to)2085-2097
Number of pages13
JournalIEEE Transactions on Medical Imaging
Volume35
Issue number9
DOIs
Publication statusPublished - 2016 Sep 1

Fingerprint

Magnetic resonance imaging
Glossaries
Tissue
Brain
Computer-Assisted Image Processing
Brain Diseases
Skull
Cerebrospinal fluid
Cerebrospinal Fluid
Medical applications
Processing
Research
Scanning
Imaging techniques
Experiments

Keywords

  • 3T MRI
  • 7T MRI
  • canonical correlation analysis
  • image enhancement
  • magnetic resonance imaging (MRI)
  • ultra-high-field MRI

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Bahrami, K., Shi, F., Zong, X., Shin, H. W., An, H., & Shen, D. (2016). Reconstruction of 7T-Like Images from 3T MRI. IEEE Transactions on Medical Imaging, 35(9), 2085-2097. [7445872]. https://doi.org/10.1109/TMI.2016.2549918

Reconstruction of 7T-Like Images from 3T MRI. / Bahrami, Khosro; Shi, Feng; Zong, Xiaopeng; Shin, Hae Won; An, Hongyu; Shen, Dinggang.

In: IEEE Transactions on Medical Imaging, Vol. 35, No. 9, 7445872, 01.09.2016, p. 2085-2097.

Research output: Contribution to journalArticle

Bahrami, K, Shi, F, Zong, X, Shin, HW, An, H & Shen, D 2016, 'Reconstruction of 7T-Like Images from 3T MRI', IEEE Transactions on Medical Imaging, vol. 35, no. 9, 7445872, pp. 2085-2097. https://doi.org/10.1109/TMI.2016.2549918
Bahrami, Khosro ; Shi, Feng ; Zong, Xiaopeng ; Shin, Hae Won ; An, Hongyu ; Shen, Dinggang. / Reconstruction of 7T-Like Images from 3T MRI. In: IEEE Transactions on Medical Imaging. 2016 ; Vol. 35, No. 9. pp. 2085-2097.
@article{0ff33f71692f4a95af02931cb0ca75cf,
title = "Reconstruction of 7T-Like Images from 3T MRI",
abstract = "In the recent MRI scanning, ultra-high-field (7T) MR imaging provides higher resolution and better tissue contrast compared to routine 3T MRI, which may help in more accurate and early brain diseases diagnosis. However, currently, 7T MRI scanners are more expensive and less available at clinical and research centers. These motivate us to propose a method for the reconstruction of images close to the quality of 7T MRI, called 7T-like images, from 3T MRI, to improve the quality in terms of resolution and contrast. By doing so, the post-processing tasks, such as tissue segmentation, can be done more accurately and brain tissues details can be seen with higher resolution and contrast. To do this, we have acquired a unique dataset which includes paired 3T and 7T images scanned from same subjects, and then propose a hierarchical reconstruction based on group sparsity in a novel multi-level Canonical Correlation Analysis (CCA) space, to improve the quality of 3T MR image to be 7T-like MRI. First, overlapping patches are extracted from the input 3T MR image. Then, by extracting the most similar patches from all the aligned 3T and 7T images in the training set, the paired 3T and 7T dictionaries are constructed for each patch. It is worth noting that, for the training, we use pairs of 3T and 7T MR images from each training subject. Then, we propose multi-level CCA to map the paired 3T and 7T patch sets to a common space to increase their correlations. In such space, each input 3T MRI patch is sparsely represented by the 3T dictionary and then the obtained sparse coefficients are used together with the corresponding 7T dictionary to reconstruct the 7T-like patch. Also, to have the structural consistency between adjacent patches, the group sparsity is employed. This reconstruction is performed with changing patch sizes in a hierarchical framework. Experiments have been done using 13 subjects with both 3T and 7T MR images. The results show that our method outperforms previous methods and is able to recover better structural details. Also, to place our proposed method in a medical application context, we evaluated the influence of post-processing methods such as brain tissue segmentation on the reconstructed 7T-like MR images. Results show that our 7T-like images lead to higher accuracy in segmentation of white matter (WM), gray matter (GM), cerebrospinal fluid (CSF), and skull, compared to segmentation of 3T MR images.",
keywords = "3T MRI, 7T MRI, canonical correlation analysis, image enhancement, magnetic resonance imaging (MRI), ultra-high-field MRI",
author = "Khosro Bahrami and Feng Shi and Xiaopeng Zong and Shin, {Hae Won} and Hongyu An and Dinggang Shen",
year = "2016",
month = "9",
day = "1",
doi = "10.1109/TMI.2016.2549918",
language = "English",
volume = "35",
pages = "2085--2097",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "9",

}

TY - JOUR

T1 - Reconstruction of 7T-Like Images from 3T MRI

AU - Bahrami, Khosro

AU - Shi, Feng

AU - Zong, Xiaopeng

AU - Shin, Hae Won

AU - An, Hongyu

AU - Shen, Dinggang

PY - 2016/9/1

Y1 - 2016/9/1

N2 - In the recent MRI scanning, ultra-high-field (7T) MR imaging provides higher resolution and better tissue contrast compared to routine 3T MRI, which may help in more accurate and early brain diseases diagnosis. However, currently, 7T MRI scanners are more expensive and less available at clinical and research centers. These motivate us to propose a method for the reconstruction of images close to the quality of 7T MRI, called 7T-like images, from 3T MRI, to improve the quality in terms of resolution and contrast. By doing so, the post-processing tasks, such as tissue segmentation, can be done more accurately and brain tissues details can be seen with higher resolution and contrast. To do this, we have acquired a unique dataset which includes paired 3T and 7T images scanned from same subjects, and then propose a hierarchical reconstruction based on group sparsity in a novel multi-level Canonical Correlation Analysis (CCA) space, to improve the quality of 3T MR image to be 7T-like MRI. First, overlapping patches are extracted from the input 3T MR image. Then, by extracting the most similar patches from all the aligned 3T and 7T images in the training set, the paired 3T and 7T dictionaries are constructed for each patch. It is worth noting that, for the training, we use pairs of 3T and 7T MR images from each training subject. Then, we propose multi-level CCA to map the paired 3T and 7T patch sets to a common space to increase their correlations. In such space, each input 3T MRI patch is sparsely represented by the 3T dictionary and then the obtained sparse coefficients are used together with the corresponding 7T dictionary to reconstruct the 7T-like patch. Also, to have the structural consistency between adjacent patches, the group sparsity is employed. This reconstruction is performed with changing patch sizes in a hierarchical framework. Experiments have been done using 13 subjects with both 3T and 7T MR images. The results show that our method outperforms previous methods and is able to recover better structural details. Also, to place our proposed method in a medical application context, we evaluated the influence of post-processing methods such as brain tissue segmentation on the reconstructed 7T-like MR images. Results show that our 7T-like images lead to higher accuracy in segmentation of white matter (WM), gray matter (GM), cerebrospinal fluid (CSF), and skull, compared to segmentation of 3T MR images.

AB - In the recent MRI scanning, ultra-high-field (7T) MR imaging provides higher resolution and better tissue contrast compared to routine 3T MRI, which may help in more accurate and early brain diseases diagnosis. However, currently, 7T MRI scanners are more expensive and less available at clinical and research centers. These motivate us to propose a method for the reconstruction of images close to the quality of 7T MRI, called 7T-like images, from 3T MRI, to improve the quality in terms of resolution and contrast. By doing so, the post-processing tasks, such as tissue segmentation, can be done more accurately and brain tissues details can be seen with higher resolution and contrast. To do this, we have acquired a unique dataset which includes paired 3T and 7T images scanned from same subjects, and then propose a hierarchical reconstruction based on group sparsity in a novel multi-level Canonical Correlation Analysis (CCA) space, to improve the quality of 3T MR image to be 7T-like MRI. First, overlapping patches are extracted from the input 3T MR image. Then, by extracting the most similar patches from all the aligned 3T and 7T images in the training set, the paired 3T and 7T dictionaries are constructed for each patch. It is worth noting that, for the training, we use pairs of 3T and 7T MR images from each training subject. Then, we propose multi-level CCA to map the paired 3T and 7T patch sets to a common space to increase their correlations. In such space, each input 3T MRI patch is sparsely represented by the 3T dictionary and then the obtained sparse coefficients are used together with the corresponding 7T dictionary to reconstruct the 7T-like patch. Also, to have the structural consistency between adjacent patches, the group sparsity is employed. This reconstruction is performed with changing patch sizes in a hierarchical framework. Experiments have been done using 13 subjects with both 3T and 7T MR images. The results show that our method outperforms previous methods and is able to recover better structural details. Also, to place our proposed method in a medical application context, we evaluated the influence of post-processing methods such as brain tissue segmentation on the reconstructed 7T-like MR images. Results show that our 7T-like images lead to higher accuracy in segmentation of white matter (WM), gray matter (GM), cerebrospinal fluid (CSF), and skull, compared to segmentation of 3T MR images.

KW - 3T MRI

KW - 7T MRI

KW - canonical correlation analysis

KW - image enhancement

KW - magnetic resonance imaging (MRI)

KW - ultra-high-field MRI

UR - http://www.scopus.com/inward/record.url?scp=84990198688&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84990198688&partnerID=8YFLogxK

U2 - 10.1109/TMI.2016.2549918

DO - 10.1109/TMI.2016.2549918

M3 - Article

C2 - 27046894

AN - SCOPUS:84990198688

VL - 35

SP - 2085

EP - 2097

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 9

M1 - 7445872

ER -