Mri reconstruction with analysis sparse regularization under impulsive noise

A. Korhan Tanc; Ender M. Eksioglu

doi:10.1109/EUSIPCO.2016.7760306

Mri reconstruction with analysis sparse regularization under impulsive noise

A. Korhan Tanc, Ender M. Eksioglu

Department of Electronics and Communication Engineering

Kirklareli University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We will be considering analysis sparsity based regularization for Magnetic Resonance Imaging reconstruction. The analysis sparsity regularization is based on the recently introduced Transform Learning framework, which has reduced complexity regarding other sparse regularization methods. We will formulate a variational reconstruction problem which utilizes the analysis sparsity regularization together with an ℓ₁norm based data fidelity term. The use of the non-smooth data fidelity term results in robustness against outliers and impulsive noise in the observed data. The resulting algorithm with the ℓ₁observation fidelity showcases enhanced performance under impulsive observation noise when compared to a similar algorithm utilizing the conventional quadratic error term.

Original language	English
Title of host publication	2016 24th European Signal Processing Conference, EUSIPCO 2016
Publisher	European Signal Processing Conference, EUSIPCO
Pages	538-541
Number of pages	4
ISBN (Electronic)	9780992862657
DOIs	https://doi.org/10.1109/EUSIPCO.2016.7760306
Publication status	Published - 28 Nov 2016
Event	24th European Signal Processing Conference, EUSIPCO 2016 - Budapest, Hungary Duration: 28 Aug 2016 → 2 Sept 2016

Publication series

Name	European Signal Processing Conference
Volume	2016-November
ISSN (Print)	2219-5491

Conference

Conference	24th European Signal Processing Conference, EUSIPCO 2016
Country/Territory	Hungary
City	Budapest
Period	28/08/16 → 2/09/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Analysis sparsity
Compressed sensing
Image reconstruction
Impulsive noise
Magnetic Resonance

Access to Document

10.1109/EUSIPCO.2016.7760306

Cite this

@inproceedings{534e4cc211614ad3be4f24009222d697,

title = "Mri reconstruction with analysis sparse regularization under impulsive noise",

abstract = "We will be considering analysis sparsity based regularization for Magnetic Resonance Imaging reconstruction. The analysis sparsity regularization is based on the recently introduced Transform Learning framework, which has reduced complexity regarding other sparse regularization methods. We will formulate a variational reconstruction problem which utilizes the analysis sparsity regularization together with an ℓ1norm based data fidelity term. The use of the non-smooth data fidelity term results in robustness against outliers and impulsive noise in the observed data. The resulting algorithm with the ℓ1observation fidelity showcases enhanced performance under impulsive observation noise when compared to a similar algorithm utilizing the conventional quadratic error term.",

keywords = "Analysis sparsity, Compressed sensing, Image reconstruction, Impulsive noise, Magnetic Resonance",

author = "Tanc, {A. Korhan} and Eksioglu, {Ender M.}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 24th European Signal Processing Conference, EUSIPCO 2016 ; Conference date: 28-08-2016 Through 02-09-2016",

year = "2016",

month = nov,

day = "28",

doi = "10.1109/EUSIPCO.2016.7760306",

language = "English",

series = "European Signal Processing Conference",

publisher = "European Signal Processing Conference, EUSIPCO",

pages = "538--541",

booktitle = "2016 24th European Signal Processing Conference, EUSIPCO 2016",

}

Tanc, AK & Eksioglu, EM 2016, Mri reconstruction with analysis sparse regularization under impulsive noise. in 2016 24th European Signal Processing Conference, EUSIPCO 2016., 7760306, European Signal Processing Conference, vol. 2016-November, European Signal Processing Conference, EUSIPCO, pp. 538-541, 24th European Signal Processing Conference, EUSIPCO 2016, Budapest, Hungary, 28/08/16. https://doi.org/10.1109/EUSIPCO.2016.7760306

Mri reconstruction with analysis sparse regularization under impulsive noise. / Tanc, A. Korhan; Eksioglu, Ender M.
2016 24th European Signal Processing Conference, EUSIPCO 2016. European Signal Processing Conference, EUSIPCO, 2016. p. 538-541 7760306 (European Signal Processing Conference; Vol. 2016-November).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Mri reconstruction with analysis sparse regularization under impulsive noise

AU - Tanc, A. Korhan

AU - Eksioglu, Ender M.

PY - 2016/11/28

Y1 - 2016/11/28

N2 - We will be considering analysis sparsity based regularization for Magnetic Resonance Imaging reconstruction. The analysis sparsity regularization is based on the recently introduced Transform Learning framework, which has reduced complexity regarding other sparse regularization methods. We will formulate a variational reconstruction problem which utilizes the analysis sparsity regularization together with an ℓ1norm based data fidelity term. The use of the non-smooth data fidelity term results in robustness against outliers and impulsive noise in the observed data. The resulting algorithm with the ℓ1observation fidelity showcases enhanced performance under impulsive observation noise when compared to a similar algorithm utilizing the conventional quadratic error term.

AB - We will be considering analysis sparsity based regularization for Magnetic Resonance Imaging reconstruction. The analysis sparsity regularization is based on the recently introduced Transform Learning framework, which has reduced complexity regarding other sparse regularization methods. We will formulate a variational reconstruction problem which utilizes the analysis sparsity regularization together with an ℓ1norm based data fidelity term. The use of the non-smooth data fidelity term results in robustness against outliers and impulsive noise in the observed data. The resulting algorithm with the ℓ1observation fidelity showcases enhanced performance under impulsive observation noise when compared to a similar algorithm utilizing the conventional quadratic error term.

KW - Analysis sparsity

KW - Compressed sensing

KW - Image reconstruction

KW - Impulsive noise

KW - Magnetic Resonance

UR - http://www.scopus.com/inward/record.url?scp=85006056362&partnerID=8YFLogxK

U2 - 10.1109/EUSIPCO.2016.7760306

DO - 10.1109/EUSIPCO.2016.7760306

M3 - Conference contribution

AN - SCOPUS:85006056362

T3 - European Signal Processing Conference

SP - 538

EP - 541

BT - 2016 24th European Signal Processing Conference, EUSIPCO 2016

PB - European Signal Processing Conference, EUSIPCO

T2 - 24th European Signal Processing Conference, EUSIPCO 2016

Y2 - 28 August 2016 through 2 September 2016

ER -

Mri reconstruction with analysis sparse regularization under impulsive noise

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this