A novel region growing method for segmenting ultrasound images

Research output: Chapter in Book/Report/Conference proceedingConference contribution

52 Citations (Scopus)

Abstract

A new region growing method for ultrasound image segmentation is presented in this paper. Here, region growing is performed in a multi-feature vector space. Three novel criteria are developed for region growing control. First, instead of using the local information as do the conventional region growing methods, this method uses global information. Second, to overcome the effects of speckle noise and attenuation artifacts, a new idea termed, "geographic similarity", is introduced. Third, an equal opportunity competence criterion is employed to make results independent of processing order. Segmentation results for in vivo intracardiac ultrasound images and the corresponding statistical analyses show that this method is reliable and effective.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Ultrasonics Symposium
EditorsS.C. Schneider, M. Levy, B.R. McAvoy
Pages1717-1720
Number of pages4
Volume2
StatePublished - 2000
Event2000 IEEE Ultrasonics Symposium - San Juan, Puerto Rico
Duration: Oct 22 2000Oct 25 2000

Other

Other2000 IEEE Ultrasonics Symposium
CountryPuerto Rico
CitySan Juan
Period10/22/0010/25/00

Fingerprint

Ultrasonics
Vector spaces
Speckle
Image segmentation
Processing

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Hao, X., Bruce, C. J., Pislaru, C. D., & Greenleaf, J. F. (2000). A novel region growing method for segmenting ultrasound images. In S. C. Schneider, M. Levy, & B. R. McAvoy (Eds.), Proceedings of the IEEE Ultrasonics Symposium (Vol. 2, pp. 1717-1720)

A novel region growing method for segmenting ultrasound images. / Hao, Xiaohui; Bruce, Charles J; Pislaru, Cristina D; Greenleaf, James F.

Proceedings of the IEEE Ultrasonics Symposium. ed. / S.C. Schneider; M. Levy; B.R. McAvoy. Vol. 2 2000. p. 1717-1720.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hao, X, Bruce, CJ, Pislaru, CD & Greenleaf, JF 2000, A novel region growing method for segmenting ultrasound images. in SC Schneider, M Levy & BR McAvoy (eds), Proceedings of the IEEE Ultrasonics Symposium. vol. 2, pp. 1717-1720, 2000 IEEE Ultrasonics Symposium, San Juan, Puerto Rico, 10/22/00.
Hao X, Bruce CJ, Pislaru CD, Greenleaf JF. A novel region growing method for segmenting ultrasound images. In Schneider SC, Levy M, McAvoy BR, editors, Proceedings of the IEEE Ultrasonics Symposium. Vol. 2. 2000. p. 1717-1720
Hao, Xiaohui ; Bruce, Charles J ; Pislaru, Cristina D ; Greenleaf, James F. / A novel region growing method for segmenting ultrasound images. Proceedings of the IEEE Ultrasonics Symposium. editor / S.C. Schneider ; M. Levy ; B.R. McAvoy. Vol. 2 2000. pp. 1717-1720
@inproceedings{ee3e6c9bed1a4ccfa8ae563082fc42d0,
title = "A novel region growing method for segmenting ultrasound images",
abstract = "A new region growing method for ultrasound image segmentation is presented in this paper. Here, region growing is performed in a multi-feature vector space. Three novel criteria are developed for region growing control. First, instead of using the local information as do the conventional region growing methods, this method uses global information. Second, to overcome the effects of speckle noise and attenuation artifacts, a new idea termed, {"}geographic similarity{"}, is introduced. Third, an equal opportunity competence criterion is employed to make results independent of processing order. Segmentation results for in vivo intracardiac ultrasound images and the corresponding statistical analyses show that this method is reliable and effective.",
author = "Xiaohui Hao and Bruce, {Charles J} and Pislaru, {Cristina D} and Greenleaf, {James F}",
year = "2000",
language = "English (US)",
volume = "2",
pages = "1717--1720",
editor = "S.C. Schneider and M. Levy and B.R. McAvoy",
booktitle = "Proceedings of the IEEE Ultrasonics Symposium",

}

TY - GEN

T1 - A novel region growing method for segmenting ultrasound images

AU - Hao, Xiaohui

AU - Bruce, Charles J

AU - Pislaru, Cristina D

AU - Greenleaf, James F

PY - 2000

Y1 - 2000

N2 - A new region growing method for ultrasound image segmentation is presented in this paper. Here, region growing is performed in a multi-feature vector space. Three novel criteria are developed for region growing control. First, instead of using the local information as do the conventional region growing methods, this method uses global information. Second, to overcome the effects of speckle noise and attenuation artifacts, a new idea termed, "geographic similarity", is introduced. Third, an equal opportunity competence criterion is employed to make results independent of processing order. Segmentation results for in vivo intracardiac ultrasound images and the corresponding statistical analyses show that this method is reliable and effective.

AB - A new region growing method for ultrasound image segmentation is presented in this paper. Here, region growing is performed in a multi-feature vector space. Three novel criteria are developed for region growing control. First, instead of using the local information as do the conventional region growing methods, this method uses global information. Second, to overcome the effects of speckle noise and attenuation artifacts, a new idea termed, "geographic similarity", is introduced. Third, an equal opportunity competence criterion is employed to make results independent of processing order. Segmentation results for in vivo intracardiac ultrasound images and the corresponding statistical analyses show that this method is reliable and effective.

UR - http://www.scopus.com/inward/record.url?scp=0034579311&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034579311&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034579311

VL - 2

SP - 1717

EP - 1720

BT - Proceedings of the IEEE Ultrasonics Symposium

A2 - Schneider, S.C.

A2 - Levy, M.

A2 - McAvoy, B.R.

ER -