A novel MRI-SPECT registration scheme using eight similarity measures

Chung Hsien Huang; Jiann Der Lee; Yi Hsin Weng

doi:10.1109/IECON.2006.348113

A novel MRI-SPECT registration scheme using eight similarity measures

Chung Hsien Huang^*, Jiann Der Lee, Yi Hsin Weng

^*Corresponding author for this work

Department of Electrical Engineering

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

Abstract

In this paper, we propose a novel image registration scheme for MRI/SPECT registration. First, MRI is decomposed into some different brain maps by fuzzy c-means algorithm. Then, Gaussian convolution is performed with the map represented gray and white matter to simulate the radiation phenomenon of SPECT. Finally, the MRI/SPECT registration is carried out by optimizing a similarity measure. Finally, the best transformation for registration is reached by Powell's direction set method. In order to determine the most appropriate similarity measure, eight similarity measures are evaluated by performing the proposed registration scheme. The results show that Pattern Intensity has best results, and Mean Square Difference of Intensities is the worst.

Original language	English
Title of host publication	IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics
Pages	3492-3495
Number of pages	4
DOIs	https://doi.org/10.1109/IECON.2006.348113
State	Published - 2006
Event	IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics - Paris, France Duration: 06 11 2006 → 10 11 2006

Publication series

Name	IECON Proceedings (Industrial Electronics Conference)

Conference

Conference	IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics
Country/Territory	France
City	Paris
Period	06/11/06 → 10/11/06

Access to Document

10.1109/IECON.2006.348113

Cite this

@inproceedings{7eced178b8414b65ac4c87e369aee735,

title = "A novel MRI-SPECT registration scheme using eight similarity measures",

abstract = "In this paper, we propose a novel image registration scheme for MRI/SPECT registration. First, MRI is decomposed into some different brain maps by fuzzy c-means algorithm. Then, Gaussian convolution is performed with the map represented gray and white matter to simulate the radiation phenomenon of SPECT. Finally, the MRI/SPECT registration is carried out by optimizing a similarity measure. Finally, the best transformation for registration is reached by Powell's direction set method. In order to determine the most appropriate similarity measure, eight similarity measures are evaluated by performing the proposed registration scheme. The results show that Pattern Intensity has best results, and Mean Square Difference of Intensities is the worst.",

author = "Huang, {Chung Hsien} and Lee, {Jiann Der} and Weng, {Yi Hsin}",

year = "2006",

doi = "10.1109/IECON.2006.348113",

language = "英语",

isbn = "1424401364",

series = "IECON Proceedings (Industrial Electronics Conference)",

pages = "3492--3495",

booktitle = "IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics",

note = "IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics ; Conference date: 06-11-2006 Through 10-11-2006",

}

Huang, CH, Lee, JD & Weng, YH 2006, A novel MRI-SPECT registration scheme using eight similarity measures. in IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics., 4153652, IECON Proceedings (Industrial Electronics Conference), pp. 3492-3495, IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, Paris, France, 06/11/06. https://doi.org/10.1109/IECON.2006.348113

A novel MRI-SPECT registration scheme using eight similarity measures. / Huang, Chung Hsien; Lee, Jiann Der; Weng, Yi Hsin.
IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics. 2006. p. 3492-3495 4153652 (IECON Proceedings (Industrial Electronics Conference)).

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

TY - GEN

T1 - A novel MRI-SPECT registration scheme using eight similarity measures

AU - Huang, Chung Hsien

AU - Lee, Jiann Der

AU - Weng, Yi Hsin

PY - 2006

Y1 - 2006

N2 - In this paper, we propose a novel image registration scheme for MRI/SPECT registration. First, MRI is decomposed into some different brain maps by fuzzy c-means algorithm. Then, Gaussian convolution is performed with the map represented gray and white matter to simulate the radiation phenomenon of SPECT. Finally, the MRI/SPECT registration is carried out by optimizing a similarity measure. Finally, the best transformation for registration is reached by Powell's direction set method. In order to determine the most appropriate similarity measure, eight similarity measures are evaluated by performing the proposed registration scheme. The results show that Pattern Intensity has best results, and Mean Square Difference of Intensities is the worst.

AB - In this paper, we propose a novel image registration scheme for MRI/SPECT registration. First, MRI is decomposed into some different brain maps by fuzzy c-means algorithm. Then, Gaussian convolution is performed with the map represented gray and white matter to simulate the radiation phenomenon of SPECT. Finally, the MRI/SPECT registration is carried out by optimizing a similarity measure. Finally, the best transformation for registration is reached by Powell's direction set method. In order to determine the most appropriate similarity measure, eight similarity measures are evaluated by performing the proposed registration scheme. The results show that Pattern Intensity has best results, and Mean Square Difference of Intensities is the worst.

UR - http://www.scopus.com/inward/record.url?scp=50249109091&partnerID=8YFLogxK

U2 - 10.1109/IECON.2006.348113

DO - 10.1109/IECON.2006.348113

M3 - 会议稿件

AN - SCOPUS:50249109091

SN - 1424401364

SN - 9781424401369

T3 - IECON Proceedings (Industrial Electronics Conference)

SP - 3492

EP - 3495

BT - IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics

T2 - IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics

Y2 - 6 November 2006 through 10 November 2006

ER -

A novel MRI-SPECT registration scheme using eight similarity measures

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this