Brain atlas fusion from high-thickness diagnostic magnetic resonance images by learning-based super-resolution

Jinpeng Zhang, Lichi Zhang, Lei Xiang, Yeqin Shao, Guorong Wu, Xiaodong Zhou, Dinggang Shen, Qian Wang

Research output: Contribution to journalArticle

  • 6 Citations

Abstract

It is fundamentally important to fuse the brain atlas from magnetic resonance (MR) images for many imaging-based studies. Most existing works focus on fusing the atlases from high-quality MR images. However, for low-quality diagnostic images (i.e., with high inter-slice thickness), the problem of atlas fusion has not been addressed yet. In this paper, we intend to fuse the brain atlas from the high-thickness diagnostic MR images that are prevalent for clinical routines. The main idea of our works is to extend the conventional groupwise registration by incorporating a novel super-resolution strategy. The contribution of the proposed super-resolution framework is two-fold. First, each high-thickness subject image is reconstructed to be isotropic by the patch-based sparsity learning. Then, the reconstructed isotropic image is enhanced for better quality through the random-forest-based regression model. In this way, the images obtained by the super-resolution strategy can be fused together by applying the groupwise registration method to construct the required atlas. Our experiments have shown that the proposed framework can effectively solve the problem of atlas fusion from the low-quality brain MR images.

LanguageEnglish (US)
Pages531-541
Number of pages11
JournalPattern Recognition
Volume63
DOIs
StatePublished - Mar 1 2017

Fingerprint

Magnetic resonance
Brain
Fusion reactions
Electric fuses
Imaging techniques
Experiments

Keywords

  • Brain atlas
  • Groupwise registration
  • Image enhancement
  • Random forest regression
  • Sparsity learning
  • Super-resolution

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Brain atlas fusion from high-thickness diagnostic magnetic resonance images by learning-based super-resolution. / Zhang, Jinpeng; Zhang, Lichi; Xiang, Lei; Shao, Yeqin; Wu, Guorong; Zhou, Xiaodong; Shen, Dinggang; Wang, Qian.

In: Pattern Recognition, Vol. 63, 01.03.2017, p. 531-541.

Research output: Contribution to journalArticle

Zhang, Jinpeng ; Zhang, Lichi ; Xiang, Lei ; Shao, Yeqin ; Wu, Guorong ; Zhou, Xiaodong ; Shen, Dinggang ; Wang, Qian. / Brain atlas fusion from high-thickness diagnostic magnetic resonance images by learning-based super-resolution. In: Pattern Recognition. 2017 ; Vol. 63. pp. 531-541
@article{1624686d1ee84a16aa7173d2b744f23d,
title = "Brain atlas fusion from high-thickness diagnostic magnetic resonance images by learning-based super-resolution",
abstract = "It is fundamentally important to fuse the brain atlas from magnetic resonance (MR) images for many imaging-based studies. Most existing works focus on fusing the atlases from high-quality MR images. However, for low-quality diagnostic images (i.e., with high inter-slice thickness), the problem of atlas fusion has not been addressed yet. In this paper, we intend to fuse the brain atlas from the high-thickness diagnostic MR images that are prevalent for clinical routines. The main idea of our works is to extend the conventional groupwise registration by incorporating a novel super-resolution strategy. The contribution of the proposed super-resolution framework is two-fold. First, each high-thickness subject image is reconstructed to be isotropic by the patch-based sparsity learning. Then, the reconstructed isotropic image is enhanced for better quality through the random-forest-based regression model. In this way, the images obtained by the super-resolution strategy can be fused together by applying the groupwise registration method to construct the required atlas. Our experiments have shown that the proposed framework can effectively solve the problem of atlas fusion from the low-quality brain MR images.",
keywords = "Brain atlas, Groupwise registration, Image enhancement, Random forest regression, Sparsity learning, Super-resolution",
author = "Jinpeng Zhang and Lichi Zhang and Lei Xiang and Yeqin Shao and Guorong Wu and Xiaodong Zhou and Dinggang Shen and Qian Wang",
year = "2017",
month = "3",
day = "1",
doi = "10.1016/j.patcog.2016.09.019",
language = "English (US)",
volume = "63",
pages = "531--541",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Brain atlas fusion from high-thickness diagnostic magnetic resonance images by learning-based super-resolution

AU - Zhang,Jinpeng

AU - Zhang,Lichi

AU - Xiang,Lei

AU - Shao,Yeqin

AU - Wu,Guorong

AU - Zhou,Xiaodong

AU - Shen,Dinggang

AU - Wang,Qian

PY - 2017/3/1

Y1 - 2017/3/1

N2 - It is fundamentally important to fuse the brain atlas from magnetic resonance (MR) images for many imaging-based studies. Most existing works focus on fusing the atlases from high-quality MR images. However, for low-quality diagnostic images (i.e., with high inter-slice thickness), the problem of atlas fusion has not been addressed yet. In this paper, we intend to fuse the brain atlas from the high-thickness diagnostic MR images that are prevalent for clinical routines. The main idea of our works is to extend the conventional groupwise registration by incorporating a novel super-resolution strategy. The contribution of the proposed super-resolution framework is two-fold. First, each high-thickness subject image is reconstructed to be isotropic by the patch-based sparsity learning. Then, the reconstructed isotropic image is enhanced for better quality through the random-forest-based regression model. In this way, the images obtained by the super-resolution strategy can be fused together by applying the groupwise registration method to construct the required atlas. Our experiments have shown that the proposed framework can effectively solve the problem of atlas fusion from the low-quality brain MR images.

AB - It is fundamentally important to fuse the brain atlas from magnetic resonance (MR) images for many imaging-based studies. Most existing works focus on fusing the atlases from high-quality MR images. However, for low-quality diagnostic images (i.e., with high inter-slice thickness), the problem of atlas fusion has not been addressed yet. In this paper, we intend to fuse the brain atlas from the high-thickness diagnostic MR images that are prevalent for clinical routines. The main idea of our works is to extend the conventional groupwise registration by incorporating a novel super-resolution strategy. The contribution of the proposed super-resolution framework is two-fold. First, each high-thickness subject image is reconstructed to be isotropic by the patch-based sparsity learning. Then, the reconstructed isotropic image is enhanced for better quality through the random-forest-based regression model. In this way, the images obtained by the super-resolution strategy can be fused together by applying the groupwise registration method to construct the required atlas. Our experiments have shown that the proposed framework can effectively solve the problem of atlas fusion from the low-quality brain MR images.

KW - Brain atlas

KW - Groupwise registration

KW - Image enhancement

KW - Random forest regression

KW - Sparsity learning

KW - Super-resolution

UR - http://www.scopus.com/inward/record.url?scp=84991228403&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991228403&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2016.09.019

DO - 10.1016/j.patcog.2016.09.019

M3 - Article

VL - 63

SP - 531

EP - 541

JO - Pattern Recognition

T2 - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

ER -