Edge intensity normalization as a bias field correction during balloon snake segmentation of breast MRI

Andrew Hill; Andrew Mehnert; Stuart Crozier

Edge intensity normalization as a bias field correction during balloon snake segmentation of breast MRI

Andrew Hill, Andrew Mehnert, Stuart Crozier

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

Abstract

Segmentation of fat suppressed dynamic contrast enhanced MRI (DCE-MRI) image data can pose significant problems because of the inherently poor signal-to-noise ratio (SNR) and intensity variations due to the bias field. Segmentation methods such as balloon snakes, while able to operate in a poor SNR environment, are sensitive to variations in edge intensity, which are regularly encountered within DCE-MRI due to the bias field. In order to overcome the effects of the bias field, an intensity normalization based on the strength of the strongest edge, i. e. the skin-air-boundary, is proposed and evaluated. This normalization allows balloon segmentations to be run three times faster while maintaining, or even improving accuracy.

Original language	English
Title of host publication	Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
Pages	3040-3043
Number of pages	4
Publication status	Published - 1 Dec 2008
Externally published	Yes
Event	30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - Vancouver, BC, Canada Duration: 20 Aug 2008 → 25 Aug 2008

Conference

Conference	30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
Country/Territory	Canada
City	Vancouver, BC
Period	20/08/08 → 25/08/08

Cite this

@inproceedings{95fce8b0b5ef47679ca4d065e9e10f7f,

title = "Edge intensity normalization as a bias field correction during balloon snake segmentation of breast MRI",

abstract = "Segmentation of fat suppressed dynamic contrast enhanced MRI (DCE-MRI) image data can pose significant problems because of the inherently poor signal-to-noise ratio (SNR) and intensity variations due to the bias field. Segmentation methods such as balloon snakes, while able to operate in a poor SNR environment, are sensitive to variations in edge intensity, which are regularly encountered within DCE-MRI due to the bias field. In order to overcome the effects of the bias field, an intensity normalization based on the strength of the strongest edge, i. e. the skin-air-boundary, is proposed and evaluated. This normalization allows balloon segmentations to be run three times faster while maintaining, or even improving accuracy.",

author = "Andrew Hill and Andrew Mehnert and Stuart Crozier",

year = "2008",

month = dec,

day = "1",

language = "English",

isbn = "9781424418152",

pages = "3040--3043",

booktitle = "Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08",

note = "30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 ; Conference date: 20-08-2008 Through 25-08-2008",

}

Hill, A, Mehnert, A & Crozier, S 2008, Edge intensity normalization as a bias field correction during balloon snake segmentation of breast MRI. in Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08., 4649844, pp. 3040-3043, 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08, Vancouver, BC, Canada, 20/08/08.

Edge intensity normalization as a bias field correction during balloon snake segmentation of breast MRI. / Hill, Andrew; Mehnert, Andrew; Crozier, Stuart.
Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. p. 3040-3043 4649844.

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

TY - GEN

T1 - Edge intensity normalization as a bias field correction during balloon snake segmentation of breast MRI

AU - Hill, Andrew

AU - Mehnert, Andrew

AU - Crozier, Stuart

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Segmentation of fat suppressed dynamic contrast enhanced MRI (DCE-MRI) image data can pose significant problems because of the inherently poor signal-to-noise ratio (SNR) and intensity variations due to the bias field. Segmentation methods such as balloon snakes, while able to operate in a poor SNR environment, are sensitive to variations in edge intensity, which are regularly encountered within DCE-MRI due to the bias field. In order to overcome the effects of the bias field, an intensity normalization based on the strength of the strongest edge, i. e. the skin-air-boundary, is proposed and evaluated. This normalization allows balloon segmentations to be run three times faster while maintaining, or even improving accuracy.

AB - Segmentation of fat suppressed dynamic contrast enhanced MRI (DCE-MRI) image data can pose significant problems because of the inherently poor signal-to-noise ratio (SNR) and intensity variations due to the bias field. Segmentation methods such as balloon snakes, while able to operate in a poor SNR environment, are sensitive to variations in edge intensity, which are regularly encountered within DCE-MRI due to the bias field. In order to overcome the effects of the bias field, an intensity normalization based on the strength of the strongest edge, i. e. the skin-air-boundary, is proposed and evaluated. This normalization allows balloon segmentations to be run three times faster while maintaining, or even improving accuracy.

UR - http://www.scopus.com/inward/record.url?scp=61849142877&partnerID=8YFLogxK

M3 - Conference paper

C2 - 19163347

AN - SCOPUS:61849142877

SN - 9781424418152

SP - 3040

EP - 3043

BT - Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08

T2 - 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08

Y2 - 20 August 2008 through 25 August 2008

ER -

Edge intensity normalization as a bias field correction during balloon snake segmentation of breast MRI

Abstract

Conference

Other files and links

Fingerprint

Cite this