Home > Research > Publications & Outputs > Contour segmentation in 2D ultrasound medical i...
View graph of relations

Contour segmentation in 2D ultrasound medical images with particle filtering.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Contour segmentation in 2D ultrasound medical images with particle filtering. / Angelova, Donka; Mihaylova, Lyudmila.

In: Machine Vision and Applications, Vol. 22, No. 3, 05.2011, p. 551-561.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Author

Angelova, Donka ; Mihaylova, Lyudmila. / Contour segmentation in 2D ultrasound medical images with particle filtering. In: Machine Vision and Applications. 2011 ; Vol. 22, No. 3. pp. 551-561.

Bibtex

@article{84361c040d644bc7a1cc2c69ea72f998,
title = "Contour segmentation in 2D ultrasound medical images with particle filtering.",
abstract = "Object segmentation in medical images is an actively investigated research area. Segmentation techniques are a valuable tool in medical diagnostics for cancer tumours and cysts, for planning surgery operations and other medical treatment. In this paper, a Monte Carlo algorithm for extracting lesion contours in ultrasound medical images is proposed. An efficient multiple model particle filter for progressive contour growing (tracking) from a starting point is developed, accounting for convex, non-circular forms of delineated contour areas. The driving idea of the proposed particle filter consists in the incorporation of different image intensity inside and outside the contour into the filter likelihood function. The filter employs image intensity gradients as measurements and requires information about four manually selected points: a seed point, a starting point, arbitrarily selected on the contour, and two additional points, bounding the measurement formation area around the contour. The filter performance is studied by segmenting contours from a number of real and simulated ultrasound medical images. Accurate contour segmentation is achieved with the proposed approach in ultrasound images with a high level of speckle noise.",
keywords = "Ultrasound (US) image segmentation · Contour Tracking, Bayesian inference, Sequential Monte Carlo methods, Particle filter (PF), Speckle noise",
author = "Donka Angelova and Lyudmila Mihaylova",
note = "The original publication is available at www.springerlink.com",
year = "2011",
month = may,
doi = "10.1007/s00138-010-0261-4",
language = "English",
volume = "22",
pages = "551--561",
journal = "Machine Vision and Applications",
issn = "0932-8092",
publisher = "Springer Verlag",
number = "3",

}

RIS

TY - JOUR

T1 - Contour segmentation in 2D ultrasound medical images with particle filtering.

AU - Angelova, Donka

AU - Mihaylova, Lyudmila

N1 - The original publication is available at www.springerlink.com

PY - 2011/5

Y1 - 2011/5

N2 - Object segmentation in medical images is an actively investigated research area. Segmentation techniques are a valuable tool in medical diagnostics for cancer tumours and cysts, for planning surgery operations and other medical treatment. In this paper, a Monte Carlo algorithm for extracting lesion contours in ultrasound medical images is proposed. An efficient multiple model particle filter for progressive contour growing (tracking) from a starting point is developed, accounting for convex, non-circular forms of delineated contour areas. The driving idea of the proposed particle filter consists in the incorporation of different image intensity inside and outside the contour into the filter likelihood function. The filter employs image intensity gradients as measurements and requires information about four manually selected points: a seed point, a starting point, arbitrarily selected on the contour, and two additional points, bounding the measurement formation area around the contour. The filter performance is studied by segmenting contours from a number of real and simulated ultrasound medical images. Accurate contour segmentation is achieved with the proposed approach in ultrasound images with a high level of speckle noise.

AB - Object segmentation in medical images is an actively investigated research area. Segmentation techniques are a valuable tool in medical diagnostics for cancer tumours and cysts, for planning surgery operations and other medical treatment. In this paper, a Monte Carlo algorithm for extracting lesion contours in ultrasound medical images is proposed. An efficient multiple model particle filter for progressive contour growing (tracking) from a starting point is developed, accounting for convex, non-circular forms of delineated contour areas. The driving idea of the proposed particle filter consists in the incorporation of different image intensity inside and outside the contour into the filter likelihood function. The filter employs image intensity gradients as measurements and requires information about four manually selected points: a seed point, a starting point, arbitrarily selected on the contour, and two additional points, bounding the measurement formation area around the contour. The filter performance is studied by segmenting contours from a number of real and simulated ultrasound medical images. Accurate contour segmentation is achieved with the proposed approach in ultrasound images with a high level of speckle noise.

KW - Ultrasound (US) image segmentation · Contour Tracking

KW - Bayesian inference

KW - Sequential Monte Carlo methods

KW - Particle filter (PF)

KW - Speckle noise

U2 - 10.1007/s00138-010-0261-4

DO - 10.1007/s00138-010-0261-4

M3 - Journal article

VL - 22

SP - 551

EP - 561

JO - Machine Vision and Applications

JF - Machine Vision and Applications

SN - 0932-8092

IS - 3

ER -