Compressed sensing MRI exploiting complementary dual decomposition

Suhyung Park, Jaeseok Park

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Compressed sensing (CS) MRI exploits the sparsity of an image in a transform domain to reconstruct the image from incoherently under-sampled k-space data. However, it has been shown that CS suffers particularly from loss of low-contrast image features with increasing reduction factors. To retain image details in such degraded experimental conditions, in this work we introduce a novel CS reconstruction method exploiting feature-based complementary dual decomposition with joint estimation of local scale mixture (LSM) model and images. Images are decomposed into dual block sparse components: total variation for piecewise smooth parts and wavelets for residuals. The LSM model parameters of residuals in the wavelet domain are estimated and then employed as a regional constraint in spatially adaptive reconstruction of high frequency subbands to restore image details missing in piecewise smooth parts. Alternating minimization of the dual image components subject to data consistency is performed to extract image details from residuals and add them back to their complementary counterparts while the LSM model parameters and images are jointly estimated in a sequential fashion. Simulations and experiments demonstrate the superior performance of the proposed method in preserving low-contrast image features even at high reduction factors.

Original languageEnglish
Pages (from-to)472-486
Number of pages15
JournalMedical Image Analysis
Volume18
Issue number3
DOIs
Publication statusPublished - 2014 Apr 1

Fingerprint

Compressed sensing
Magnetic resonance imaging
Decomposition
Joints
Experiments

Keywords

  • Complementary decomposition
  • Compressed sensing
  • Magnetic resonance imaging
  • Total variation
  • Wavelet

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Radiology Nuclear Medicine and imaging
  • Health Informatics
  • Radiological and Ultrasound Technology

Cite this

Compressed sensing MRI exploiting complementary dual decomposition. / Park, Suhyung; Park, Jaeseok.

In: Medical Image Analysis, Vol. 18, No. 3, 01.04.2014, p. 472-486.

Research output: Contribution to journalArticle

@article{e615042c094941f99e150e734e174945,
title = "Compressed sensing MRI exploiting complementary dual decomposition",
abstract = "Compressed sensing (CS) MRI exploits the sparsity of an image in a transform domain to reconstruct the image from incoherently under-sampled k-space data. However, it has been shown that CS suffers particularly from loss of low-contrast image features with increasing reduction factors. To retain image details in such degraded experimental conditions, in this work we introduce a novel CS reconstruction method exploiting feature-based complementary dual decomposition with joint estimation of local scale mixture (LSM) model and images. Images are decomposed into dual block sparse components: total variation for piecewise smooth parts and wavelets for residuals. The LSM model parameters of residuals in the wavelet domain are estimated and then employed as a regional constraint in spatially adaptive reconstruction of high frequency subbands to restore image details missing in piecewise smooth parts. Alternating minimization of the dual image components subject to data consistency is performed to extract image details from residuals and add them back to their complementary counterparts while the LSM model parameters and images are jointly estimated in a sequential fashion. Simulations and experiments demonstrate the superior performance of the proposed method in preserving low-contrast image features even at high reduction factors.",
keywords = "Complementary decomposition, Compressed sensing, Magnetic resonance imaging, Total variation, Wavelet",
author = "Suhyung Park and Jaeseok Park",
year = "2014",
month = "4",
day = "1",
doi = "10.1016/j.media.2014.01.004",
language = "English",
volume = "18",
pages = "472--486",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Compressed sensing MRI exploiting complementary dual decomposition

AU - Park, Suhyung

AU - Park, Jaeseok

PY - 2014/4/1

Y1 - 2014/4/1

N2 - Compressed sensing (CS) MRI exploits the sparsity of an image in a transform domain to reconstruct the image from incoherently under-sampled k-space data. However, it has been shown that CS suffers particularly from loss of low-contrast image features with increasing reduction factors. To retain image details in such degraded experimental conditions, in this work we introduce a novel CS reconstruction method exploiting feature-based complementary dual decomposition with joint estimation of local scale mixture (LSM) model and images. Images are decomposed into dual block sparse components: total variation for piecewise smooth parts and wavelets for residuals. The LSM model parameters of residuals in the wavelet domain are estimated and then employed as a regional constraint in spatially adaptive reconstruction of high frequency subbands to restore image details missing in piecewise smooth parts. Alternating minimization of the dual image components subject to data consistency is performed to extract image details from residuals and add them back to their complementary counterparts while the LSM model parameters and images are jointly estimated in a sequential fashion. Simulations and experiments demonstrate the superior performance of the proposed method in preserving low-contrast image features even at high reduction factors.

AB - Compressed sensing (CS) MRI exploits the sparsity of an image in a transform domain to reconstruct the image from incoherently under-sampled k-space data. However, it has been shown that CS suffers particularly from loss of low-contrast image features with increasing reduction factors. To retain image details in such degraded experimental conditions, in this work we introduce a novel CS reconstruction method exploiting feature-based complementary dual decomposition with joint estimation of local scale mixture (LSM) model and images. Images are decomposed into dual block sparse components: total variation for piecewise smooth parts and wavelets for residuals. The LSM model parameters of residuals in the wavelet domain are estimated and then employed as a regional constraint in spatially adaptive reconstruction of high frequency subbands to restore image details missing in piecewise smooth parts. Alternating minimization of the dual image components subject to data consistency is performed to extract image details from residuals and add them back to their complementary counterparts while the LSM model parameters and images are jointly estimated in a sequential fashion. Simulations and experiments demonstrate the superior performance of the proposed method in preserving low-contrast image features even at high reduction factors.

KW - Complementary decomposition

KW - Compressed sensing

KW - Magnetic resonance imaging

KW - Total variation

KW - Wavelet

UR - http://www.scopus.com/inward/record.url?scp=84894046681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894046681&partnerID=8YFLogxK

U2 - 10.1016/j.media.2014.01.004

DO - 10.1016/j.media.2014.01.004

M3 - Article

C2 - 24561485

AN - SCOPUS:84894046681

VL - 18

SP - 472

EP - 486

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 3

ER -