A regularization technique for closed contour segmentation in ultrasound images

Chi Young Ahn, Yoon Mo Jung, Oh In Kwon, Jin Keun Seo

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Segmentation of a target object in the form of a closed curve has many potential applications in medical imaging because it provides quantitative information related to the target objext's size and shape. However, ultrasound image segmentation for boundary delineation of the target object is a very difficult task because of its inherent drawbacks, including uncertainty of the segmentation boundary caused by speckle noise, relatively low SNR, and low contrast. Indeed, in automatic ultrasound image segmentation, conventional techniques with standard regularization often fail to reach the desired segmentation in the form of a simple closed curve because of the weakness of edge detector functions in finding the likely target boundary. In this paper, we propose a new regularization model which has the property of encouraging a closed curve by deliberately controlling the curve smoothness. The new model may be combined with various fitting terms to enhance segmentation results. The key features of the proposed model are demonstrated in detail. Numerical simulations and experiments show that the proposed model enhances the segmentation ability for extracting the target boundary as a closed contour.

Original languageEnglish
Article number5995215
Pages (from-to)1577-1589
Number of pages13
JournalIEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
Volume58
Issue number8
DOIs
Publication statusPublished - 2011 Aug 1

Fingerprint

Ultrasonics
Image segmentation
curves
Medical imaging
Speckle
delineation
low noise
Detectors
Computer simulation
detectors
Experiments
simulation

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Acoustics and Ultrasonics
  • Electrical and Electronic Engineering

Cite this

@article{1f1e14cd9dce4d02a085982eb22cd502,
title = "A regularization technique for closed contour segmentation in ultrasound images",
abstract = "Segmentation of a target object in the form of a closed curve has many potential applications in medical imaging because it provides quantitative information related to the target objext's size and shape. However, ultrasound image segmentation for boundary delineation of the target object is a very difficult task because of its inherent drawbacks, including uncertainty of the segmentation boundary caused by speckle noise, relatively low SNR, and low contrast. Indeed, in automatic ultrasound image segmentation, conventional techniques with standard regularization often fail to reach the desired segmentation in the form of a simple closed curve because of the weakness of edge detector functions in finding the likely target boundary. In this paper, we propose a new regularization model which has the property of encouraging a closed curve by deliberately controlling the curve smoothness. The new model may be combined with various fitting terms to enhance segmentation results. The key features of the proposed model are demonstrated in detail. Numerical simulations and experiments show that the proposed model enhances the segmentation ability for extracting the target boundary as a closed contour.",
author = "Ahn, {Chi Young} and Jung, {Yoon Mo} and Kwon, {Oh In} and Seo, {Jin Keun}",
year = "2011",
month = "8",
day = "1",
doi = "10.1109/TUFFC.2011.1985",
language = "English",
volume = "58",
pages = "1577--1589",
journal = "IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control",
issn = "0885-3010",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

A regularization technique for closed contour segmentation in ultrasound images. / Ahn, Chi Young; Jung, Yoon Mo; Kwon, Oh In; Seo, Jin Keun.

In: IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, Vol. 58, No. 8, 5995215, 01.08.2011, p. 1577-1589.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A regularization technique for closed contour segmentation in ultrasound images

AU - Ahn, Chi Young

AU - Jung, Yoon Mo

AU - Kwon, Oh In

AU - Seo, Jin Keun

PY - 2011/8/1

Y1 - 2011/8/1

N2 - Segmentation of a target object in the form of a closed curve has many potential applications in medical imaging because it provides quantitative information related to the target objext's size and shape. However, ultrasound image segmentation for boundary delineation of the target object is a very difficult task because of its inherent drawbacks, including uncertainty of the segmentation boundary caused by speckle noise, relatively low SNR, and low contrast. Indeed, in automatic ultrasound image segmentation, conventional techniques with standard regularization often fail to reach the desired segmentation in the form of a simple closed curve because of the weakness of edge detector functions in finding the likely target boundary. In this paper, we propose a new regularization model which has the property of encouraging a closed curve by deliberately controlling the curve smoothness. The new model may be combined with various fitting terms to enhance segmentation results. The key features of the proposed model are demonstrated in detail. Numerical simulations and experiments show that the proposed model enhances the segmentation ability for extracting the target boundary as a closed contour.

AB - Segmentation of a target object in the form of a closed curve has many potential applications in medical imaging because it provides quantitative information related to the target objext's size and shape. However, ultrasound image segmentation for boundary delineation of the target object is a very difficult task because of its inherent drawbacks, including uncertainty of the segmentation boundary caused by speckle noise, relatively low SNR, and low contrast. Indeed, in automatic ultrasound image segmentation, conventional techniques with standard regularization often fail to reach the desired segmentation in the form of a simple closed curve because of the weakness of edge detector functions in finding the likely target boundary. In this paper, we propose a new regularization model which has the property of encouraging a closed curve by deliberately controlling the curve smoothness. The new model may be combined with various fitting terms to enhance segmentation results. The key features of the proposed model are demonstrated in detail. Numerical simulations and experiments show that the proposed model enhances the segmentation ability for extracting the target boundary as a closed contour.

UR - http://www.scopus.com/inward/record.url?scp=80052075227&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052075227&partnerID=8YFLogxK

U2 - 10.1109/TUFFC.2011.1985

DO - 10.1109/TUFFC.2011.1985

M3 - Article

VL - 58

SP - 1577

EP - 1589

JO - IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control

JF - IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control

SN - 0885-3010

IS - 8

M1 - 5995215

ER -