Acceleration of MAP-EM algorithm via over-relaxation

Yu Jung Tsai; Hsuan Ming Huang; Yu Hua Dean Fang; Shi Ing Chang; Ing Tsung Hsiao

doi:10.1016/j.compmedimag.2014.11.004

Acceleration of MAP-EM algorithm via over-relaxation

Yu Jung Tsai, Hsuan Ming Huang, Yu Hua Dean Fang, Shi Ing Chang, Ing Tsung Hsiao

Department of Biomedical Engineering

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

Abstract

To improve the convergence rate of the effective maximum a posteriori expectation-maximization (MAP-EM) algorithm in tomographic reconstructions, this study proposes a modified MAP-EM which uses an over-relaxation factor to accelerate image reconstruction. The proposed method, called MAP-AEM, is evaluated and compared with the results for MAP-EM and for an ordered-subset algorithm, in terms of the convergence rate and noise properties. The results show that the proposed method converges numerically much faster than MAP-EM and with a speed that is comparable to that for an ordered-subset type method. The proposed method is effective in accelerating MAP-EM tomographic reconstruction.

Original language	English
Pages (from-to)	100-107
Number of pages	8
Journal	Computerized Medical Imaging and Graphics
Volume	40
DOIs	https://doi.org/10.1016/j.compmedimag.2014.11.004
Publication status	Published - 2015 Mar 1

All Science Journal Classification (ASJC) codes

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

Access to Document

10.1016/j.compmedimag.2014.11.004

Cite this

@article{0985fd9fd55345cfbfd4885aeff2cfb9,

title = "Acceleration of MAP-EM algorithm via over-relaxation",

abstract = "To improve the convergence rate of the effective maximum a posteriori expectation-maximization (MAP-EM) algorithm in tomographic reconstructions, this study proposes a modified MAP-EM which uses an over-relaxation factor to accelerate image reconstruction. The proposed method, called MAP-AEM, is evaluated and compared with the results for MAP-EM and for an ordered-subset algorithm, in terms of the convergence rate and noise properties. The results show that the proposed method converges numerically much faster than MAP-EM and with a speed that is comparable to that for an ordered-subset type method. The proposed method is effective in accelerating MAP-EM tomographic reconstruction.",

author = "Tsai, {Yu Jung} and Huang, {Hsuan Ming} and Fang, {Yu Hua Dean} and Chang, {Shi Ing} and Hsiao, {Ing Tsung}",

note = "Funding Information: This work was supported by Grants MOST 103-2314-B-182-010-MY3 from NSC , Taiwan, and CMRPD1C0641 , CMRPD1C0642 , CMRPD1C0671 , CMRPD1C0672 and CMRPD1C0382 from the Research Fund of Chang Gung Memorial Hospital, Taiwan . Conflict of interest statement Publisher Copyright: {\textcopyright} 2014 Elsevier Ltd.",

year = "2015",

month = mar,

day = "1",

doi = "10.1016/j.compmedimag.2014.11.004",

language = "English",

volume = "40",

pages = "100--107",

journal = "Computerized Medical Imaging and Graphics",

issn = "0895-6111",

publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Acceleration of MAP-EM algorithm via over-relaxation

AU - Tsai, Yu Jung

AU - Huang, Hsuan Ming

AU - Fang, Yu Hua Dean

AU - Chang, Shi Ing

AU - Hsiao, Ing Tsung

N1 - Funding Information: This work was supported by Grants MOST 103-2314-B-182-010-MY3 from NSC , Taiwan, and CMRPD1C0641 , CMRPD1C0642 , CMRPD1C0671 , CMRPD1C0672 and CMRPD1C0382 from the Research Fund of Chang Gung Memorial Hospital, Taiwan . Conflict of interest statement Publisher Copyright: © 2014 Elsevier Ltd.

PY - 2015/3/1

Y1 - 2015/3/1

N2 - To improve the convergence rate of the effective maximum a posteriori expectation-maximization (MAP-EM) algorithm in tomographic reconstructions, this study proposes a modified MAP-EM which uses an over-relaxation factor to accelerate image reconstruction. The proposed method, called MAP-AEM, is evaluated and compared with the results for MAP-EM and for an ordered-subset algorithm, in terms of the convergence rate and noise properties. The results show that the proposed method converges numerically much faster than MAP-EM and with a speed that is comparable to that for an ordered-subset type method. The proposed method is effective in accelerating MAP-EM tomographic reconstruction.

AB - To improve the convergence rate of the effective maximum a posteriori expectation-maximization (MAP-EM) algorithm in tomographic reconstructions, this study proposes a modified MAP-EM which uses an over-relaxation factor to accelerate image reconstruction. The proposed method, called MAP-AEM, is evaluated and compared with the results for MAP-EM and for an ordered-subset algorithm, in terms of the convergence rate and noise properties. The results show that the proposed method converges numerically much faster than MAP-EM and with a speed that is comparable to that for an ordered-subset type method. The proposed method is effective in accelerating MAP-EM tomographic reconstruction.

UR - http://www.scopus.com/inward/record.url?scp=84923044659&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923044659&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2014.11.004

DO - 10.1016/j.compmedimag.2014.11.004

M3 - Article

C2 - 25465068

AN - SCOPUS:84923044659

VL - 40

SP - 100

EP - 107

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

ER -

Acceleration of MAP-EM algorithm via over-relaxation

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this