Automatic 3D segmentation of ultrasound images using atlas registration and statistical texture prior

Xiaofeng Yang, David Schuster, Viraj Master, Peter Nieh, Aaron Fenster, Baowei Fei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

25 Citations (Scopus)

Abstract

We are developing a molecular image-directed, 3D ultrasound-guided, targeted biopsy system for improved detection of prostate cancer. In this paper, we propose an automatic 3D segmentation method for transrectal ultrasound (TRUS) images, which is based on multi-atlas registration and statistical texture prior. The atlas database includes registered TRUS images from previous patients and their segmented prostate surfaces. Three orthogonal Gabor filter banks are used to extract texture features from each image in the database. Patient-specific Gabor features from the atlas database are used to train kernel support vector machines (KSVMs) and then to segment the prostate image from a new patient. The segmentation method was tested in TRUS data from 5 patients. The average surface distance between our method and manual segmentation is 1.61 ± 0.35 mm, indicating that the atlas-based automatic segmentation method works well and could be used for 3D ultrasound-guided prostate biopsy.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2011
Subtitle of host publicationVisualization, Image-Guided Procedures, and Modeling
DOIs
StatePublished - May 16 2011
Externally publishedYes
EventMedical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling - Lake Buena Vista, FL, United States
Duration: Feb 13 2011Feb 15 2011

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7964
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling
CountryUnited States
CityLake Buena Vista, FL
Period2/13/112/15/11

Fingerprint

Atlases
textures
Textures
Ultrasonics
Prostate
Databases
Biopsy
Gabor filters
Filter banks
Prostatic Neoplasms
Support vector machines
cancer

Keywords

  • Atlas registration
  • Automatic 3D segmentation
  • Gabor filter
  • Prostate cancer
  • Support vector machine
  • Ultrasound imaging

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Cite this

Yang, X., Schuster, D., Master, V., Nieh, P., Fenster, A., & Fei, B. (2011). Automatic 3D segmentation of ultrasound images using atlas registration and statistical texture prior. In Medical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling [796432] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7964). https://doi.org/10.1117/12.877888

Automatic 3D segmentation of ultrasound images using atlas registration and statistical texture prior. / Yang, Xiaofeng; Schuster, David; Master, Viraj; Nieh, Peter; Fenster, Aaron; Fei, Baowei.

Medical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling. 2011. 796432 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7964).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yang, X, Schuster, D, Master, V, Nieh, P, Fenster, A & Fei, B 2011, Automatic 3D segmentation of ultrasound images using atlas registration and statistical texture prior. in Medical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling., 796432, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 7964, Medical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling, Lake Buena Vista, FL, United States, 2/13/11. https://doi.org/10.1117/12.877888
Yang X, Schuster D, Master V, Nieh P, Fenster A, Fei B. Automatic 3D segmentation of ultrasound images using atlas registration and statistical texture prior. In Medical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling. 2011. 796432. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.877888
Yang, Xiaofeng ; Schuster, David ; Master, Viraj ; Nieh, Peter ; Fenster, Aaron ; Fei, Baowei. / Automatic 3D segmentation of ultrasound images using atlas registration and statistical texture prior. Medical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling. 2011. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{0ecc5c65df7e4d3caf8643ce29d86721,
title = "Automatic 3D segmentation of ultrasound images using atlas registration and statistical texture prior",
abstract = "We are developing a molecular image-directed, 3D ultrasound-guided, targeted biopsy system for improved detection of prostate cancer. In this paper, we propose an automatic 3D segmentation method for transrectal ultrasound (TRUS) images, which is based on multi-atlas registration and statistical texture prior. The atlas database includes registered TRUS images from previous patients and their segmented prostate surfaces. Three orthogonal Gabor filter banks are used to extract texture features from each image in the database. Patient-specific Gabor features from the atlas database are used to train kernel support vector machines (KSVMs) and then to segment the prostate image from a new patient. The segmentation method was tested in TRUS data from 5 patients. The average surface distance between our method and manual segmentation is 1.61 ± 0.35 mm, indicating that the atlas-based automatic segmentation method works well and could be used for 3D ultrasound-guided prostate biopsy.",
keywords = "Atlas registration, Automatic 3D segmentation, Gabor filter, Prostate cancer, Support vector machine, Ultrasound imaging",
author = "Xiaofeng Yang and David Schuster and Viraj Master and Peter Nieh and Aaron Fenster and Baowei Fei",
year = "2011",
month = "5",
day = "16",
doi = "10.1117/12.877888",
language = "English (US)",
isbn = "9780819485069",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
booktitle = "Medical Imaging 2011",

}

TY - GEN

T1 - Automatic 3D segmentation of ultrasound images using atlas registration and statistical texture prior

AU - Yang, Xiaofeng

AU - Schuster, David

AU - Master, Viraj

AU - Nieh, Peter

AU - Fenster, Aaron

AU - Fei, Baowei

PY - 2011/5/16

Y1 - 2011/5/16

N2 - We are developing a molecular image-directed, 3D ultrasound-guided, targeted biopsy system for improved detection of prostate cancer. In this paper, we propose an automatic 3D segmentation method for transrectal ultrasound (TRUS) images, which is based on multi-atlas registration and statistical texture prior. The atlas database includes registered TRUS images from previous patients and their segmented prostate surfaces. Three orthogonal Gabor filter banks are used to extract texture features from each image in the database. Patient-specific Gabor features from the atlas database are used to train kernel support vector machines (KSVMs) and then to segment the prostate image from a new patient. The segmentation method was tested in TRUS data from 5 patients. The average surface distance between our method and manual segmentation is 1.61 ± 0.35 mm, indicating that the atlas-based automatic segmentation method works well and could be used for 3D ultrasound-guided prostate biopsy.

AB - We are developing a molecular image-directed, 3D ultrasound-guided, targeted biopsy system for improved detection of prostate cancer. In this paper, we propose an automatic 3D segmentation method for transrectal ultrasound (TRUS) images, which is based on multi-atlas registration and statistical texture prior. The atlas database includes registered TRUS images from previous patients and their segmented prostate surfaces. Three orthogonal Gabor filter banks are used to extract texture features from each image in the database. Patient-specific Gabor features from the atlas database are used to train kernel support vector machines (KSVMs) and then to segment the prostate image from a new patient. The segmentation method was tested in TRUS data from 5 patients. The average surface distance between our method and manual segmentation is 1.61 ± 0.35 mm, indicating that the atlas-based automatic segmentation method works well and could be used for 3D ultrasound-guided prostate biopsy.

KW - Atlas registration

KW - Automatic 3D segmentation

KW - Gabor filter

KW - Prostate cancer

KW - Support vector machine

KW - Ultrasound imaging

UR - http://www.scopus.com/inward/record.url?scp=79955817767&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955817767&partnerID=8YFLogxK

U2 - 10.1117/12.877888

DO - 10.1117/12.877888

M3 - Conference contribution

C2 - 22708024

AN - SCOPUS:79955817767

SN - 9780819485069

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2011

ER -