Segmentation of prostate boundaries from ultrasound images using statistical shape model

Dinggang Shen, Yiqiang Zhan, Christos Davatzikos

Research output: Contribution to journalArticle

Abstract

This paper presents a statistical shape model for the automatic prostate segmentation in transrectal ultrasound images. A Gabor filter bank is first used to characterize the prostate boundaries in ultrasound images in both multiple scales and multiple orientations. The Gabor features are further reconstructed to be invariant to the rotation of the ultrasound probe and incorporated in the prostate model as image attributes for guiding the deformable segmentation. A hierarchical deformation strategy is then employed, in which the model adaptively focuses on the similarity of different Gabor features at different deformation stages using a multiresolution technique, i.e., coarse features first and fine features later. A number of successful experiments validate the algorithm.

Original languageEnglish (US)
Pages (from-to)539-551
Number of pages13
JournalIEEE Transactions on Medical Imaging
Volume22
Issue number4
DOIs
StatePublished - Apr 2003

Fingerprint

Statistical Models
Prostate
Ultrasonics
Gabor filters
Filter banks
Experiments

Keywords

  • Attribute vector
  • Deformable registration
  • Deformable segmentation
  • Gabor filter
  • Hierarchical strategy
  • Prostate segmentation
  • Statistical shape model
  • Ultrasound image

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology
  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Segmentation of prostate boundaries from ultrasound images using statistical shape model. / Shen, Dinggang; Zhan, Yiqiang; Davatzikos, Christos.

In: IEEE Transactions on Medical Imaging, Vol. 22, No. 4, 04.2003, p. 539-551.

Research output: Contribution to journalArticle

Shen, Dinggang ; Zhan, Yiqiang ; Davatzikos, Christos. / Segmentation of prostate boundaries from ultrasound images using statistical shape model. In: IEEE Transactions on Medical Imaging. 2003 ; Vol. 22, No. 4. pp. 539-551.
@article{df132d3be8c54b178f9bf7eeac40542d,
title = "Segmentation of prostate boundaries from ultrasound images using statistical shape model",
abstract = "This paper presents a statistical shape model for the automatic prostate segmentation in transrectal ultrasound images. A Gabor filter bank is first used to characterize the prostate boundaries in ultrasound images in both multiple scales and multiple orientations. The Gabor features are further reconstructed to be invariant to the rotation of the ultrasound probe and incorporated in the prostate model as image attributes for guiding the deformable segmentation. A hierarchical deformation strategy is then employed, in which the model adaptively focuses on the similarity of different Gabor features at different deformation stages using a multiresolution technique, i.e., coarse features first and fine features later. A number of successful experiments validate the algorithm.",
keywords = "Attribute vector, Deformable registration, Deformable segmentation, Gabor filter, Hierarchical strategy, Prostate segmentation, Statistical shape model, Ultrasound image",
author = "Dinggang Shen and Yiqiang Zhan and Christos Davatzikos",
year = "2003",
month = "4",
doi = "10.1109/TMI.2003.809057",
language = "English (US)",
volume = "22",
pages = "539--551",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Segmentation of prostate boundaries from ultrasound images using statistical shape model

AU - Shen, Dinggang

AU - Zhan, Yiqiang

AU - Davatzikos, Christos

PY - 2003/4

Y1 - 2003/4

N2 - This paper presents a statistical shape model for the automatic prostate segmentation in transrectal ultrasound images. A Gabor filter bank is first used to characterize the prostate boundaries in ultrasound images in both multiple scales and multiple orientations. The Gabor features are further reconstructed to be invariant to the rotation of the ultrasound probe and incorporated in the prostate model as image attributes for guiding the deformable segmentation. A hierarchical deformation strategy is then employed, in which the model adaptively focuses on the similarity of different Gabor features at different deformation stages using a multiresolution technique, i.e., coarse features first and fine features later. A number of successful experiments validate the algorithm.

AB - This paper presents a statistical shape model for the automatic prostate segmentation in transrectal ultrasound images. A Gabor filter bank is first used to characterize the prostate boundaries in ultrasound images in both multiple scales and multiple orientations. The Gabor features are further reconstructed to be invariant to the rotation of the ultrasound probe and incorporated in the prostate model as image attributes for guiding the deformable segmentation. A hierarchical deformation strategy is then employed, in which the model adaptively focuses on the similarity of different Gabor features at different deformation stages using a multiresolution technique, i.e., coarse features first and fine features later. A number of successful experiments validate the algorithm.

KW - Attribute vector

KW - Deformable registration

KW - Deformable segmentation

KW - Gabor filter

KW - Hierarchical strategy

KW - Prostate segmentation

KW - Statistical shape model

KW - Ultrasound image

UR - http://www.scopus.com/inward/record.url?scp=0037941623&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037941623&partnerID=8YFLogxK

U2 - 10.1109/TMI.2003.809057

DO - 10.1109/TMI.2003.809057

M3 - Article

VL - 22

SP - 539

EP - 551

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 4

ER -