A wavelet frame method with shape prior for ultrasound video segmentation

Jiulong Liu, Xiaoqun Zhang, Bin Dong, Zuowei Shen, Lixu Gu

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Ultrasound video segmentation is a challenging task due to low contrast, shadow effects, complex noise statistics, and the need for high precision and efficiency in real time applications such as operation navigation and therapy planning. In this paper, we propose a wavelet frame based video segmentation framework incorporating different noise statistics and sequential distance shape priors. The proposed individual frame nonconvex segmentation model is solved by a proximal alternating minimization algorithm, and the convergence of the scheme is established based on the recently proposed Kurdyka—Łojasiewicz property. The performance of the overall method is demonstrated through numerical results on two real ultrasound video data sets. The proposed method is shown to achieve better results compared to the related level sets models and edge indicator shape priors, in terms of both segmentation quality and computational time.

Original languageEnglish (US)
Pages (from-to)495-519
Number of pages25
JournalSIAM Journal on Imaging Sciences
Volume9
Issue number2
DOIs
StatePublished - Apr 7 2016
Externally publishedYes

Fingerprint

Video Segmentation
Wavelet Frames
Ultrasound
Segmentation
Ultrasonics
Statistics
Level Set
Therapy
Navigation
Planning
Numerical Results
Model
Framework

Keywords

  • Alternating proximal methods
  • Gaussian and poisson noise
  • Real time tracking
  • Shape prior
  • Variational model
  • Wavelet frames

ASJC Scopus subject areas

  • Mathematics(all)
  • Applied Mathematics

Cite this

A wavelet frame method with shape prior for ultrasound video segmentation. / Liu, Jiulong; Zhang, Xiaoqun; Dong, Bin; Shen, Zuowei; Gu, Lixu.

In: SIAM Journal on Imaging Sciences, Vol. 9, No. 2, 07.04.2016, p. 495-519.

Research output: Contribution to journalArticle

Liu, Jiulong ; Zhang, Xiaoqun ; Dong, Bin ; Shen, Zuowei ; Gu, Lixu. / A wavelet frame method with shape prior for ultrasound video segmentation. In: SIAM Journal on Imaging Sciences. 2016 ; Vol. 9, No. 2. pp. 495-519.
@article{3bbe334b4f394bdda00c5df2fcd18560,
title = "A wavelet frame method with shape prior for ultrasound video segmentation",
abstract = "Ultrasound video segmentation is a challenging task due to low contrast, shadow effects, complex noise statistics, and the need for high precision and efficiency in real time applications such as operation navigation and therapy planning. In this paper, we propose a wavelet frame based video segmentation framework incorporating different noise statistics and sequential distance shape priors. The proposed individual frame nonconvex segmentation model is solved by a proximal alternating minimization algorithm, and the convergence of the scheme is established based on the recently proposed Kurdyka—Łojasiewicz property. The performance of the overall method is demonstrated through numerical results on two real ultrasound video data sets. The proposed method is shown to achieve better results compared to the related level sets models and edge indicator shape priors, in terms of both segmentation quality and computational time.",
keywords = "Alternating proximal methods, Gaussian and poisson noise, Real time tracking, Shape prior, Variational model, Wavelet frames",
author = "Jiulong Liu and Xiaoqun Zhang and Bin Dong and Zuowei Shen and Lixu Gu",
year = "2016",
month = "4",
day = "7",
doi = "10.1137/15M1033344",
language = "English (US)",
volume = "9",
pages = "495--519",
journal = "SIAM Journal on Imaging Sciences",
issn = "1936-4954",
publisher = "Society for Industrial and Applied Mathematics Publications",
number = "2",

}

TY - JOUR

T1 - A wavelet frame method with shape prior for ultrasound video segmentation

AU - Liu, Jiulong

AU - Zhang, Xiaoqun

AU - Dong, Bin

AU - Shen, Zuowei

AU - Gu, Lixu

PY - 2016/4/7

Y1 - 2016/4/7

N2 - Ultrasound video segmentation is a challenging task due to low contrast, shadow effects, complex noise statistics, and the need for high precision and efficiency in real time applications such as operation navigation and therapy planning. In this paper, we propose a wavelet frame based video segmentation framework incorporating different noise statistics and sequential distance shape priors. The proposed individual frame nonconvex segmentation model is solved by a proximal alternating minimization algorithm, and the convergence of the scheme is established based on the recently proposed Kurdyka—Łojasiewicz property. The performance of the overall method is demonstrated through numerical results on two real ultrasound video data sets. The proposed method is shown to achieve better results compared to the related level sets models and edge indicator shape priors, in terms of both segmentation quality and computational time.

AB - Ultrasound video segmentation is a challenging task due to low contrast, shadow effects, complex noise statistics, and the need for high precision and efficiency in real time applications such as operation navigation and therapy planning. In this paper, we propose a wavelet frame based video segmentation framework incorporating different noise statistics and sequential distance shape priors. The proposed individual frame nonconvex segmentation model is solved by a proximal alternating minimization algorithm, and the convergence of the scheme is established based on the recently proposed Kurdyka—Łojasiewicz property. The performance of the overall method is demonstrated through numerical results on two real ultrasound video data sets. The proposed method is shown to achieve better results compared to the related level sets models and edge indicator shape priors, in terms of both segmentation quality and computational time.

KW - Alternating proximal methods

KW - Gaussian and poisson noise

KW - Real time tracking

KW - Shape prior

KW - Variational model

KW - Wavelet frames

UR - http://www.scopus.com/inward/record.url?scp=84976621740&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976621740&partnerID=8YFLogxK

U2 - 10.1137/15M1033344

DO - 10.1137/15M1033344

M3 - Article

AN - SCOPUS:84976621740

VL - 9

SP - 495

EP - 519

JO - SIAM Journal on Imaging Sciences

JF - SIAM Journal on Imaging Sciences

SN - 1936-4954

IS - 2

ER -