Learning-based prostate localization for image guided radiation therapy

Luping Zhou, Shu Liao, Wei Li, Dinggang Shen

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

6 Citations (Scopus)

Abstract

Accurate prostate localization is the key to the success of radiotherapy. It remains a difficult problem for CT images due to the low image contrast, the prostate motion, and the uncertain presence of rectum gas. In this paper, a learning based framework is proposed to improve the accuracy of prostate detection in CT. It adaptively determines distinctive feature types at distinctive image regions, thus filtering out features that are salient in image appearance, but irrelevant to prostate localization. Furthermore, an image similarity function is learned to make the image appearance distance consistent with the underlying prostate alignment. The efficacy of our proposed method has been demonstrated by the experiment.

Original languageEnglish
Title of host publicationProceedings - International Symposium on Biomedical Imaging
Pages2103-2106
Number of pages4
DOIs
Publication statusPublished - 2011 Nov 2
Externally publishedYes
Event2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 - Chicago, IL, United States
Duration: 2011 Mar 302011 Apr 2

Other

Other2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
CountryUnited States
CityChicago, IL
Period11/3/3011/4/2

Fingerprint

Image-Guided Radiotherapy
Radiotherapy
Prostate
Learning
Gases
Experiments
Rectum

Keywords

  • Feature Selection
  • IGRT
  • Image Similarity Learning
  • Prostate Localization

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Zhou, L., Liao, S., Li, W., & Shen, D. (2011). Learning-based prostate localization for image guided radiation therapy. In Proceedings - International Symposium on Biomedical Imaging (pp. 2103-2106). [5872827] https://doi.org/10.1109/ISBI.2011.5872827

Learning-based prostate localization for image guided radiation therapy. / Zhou, Luping; Liao, Shu; Li, Wei; Shen, Dinggang.

Proceedings - International Symposium on Biomedical Imaging. 2011. p. 2103-2106 5872827.

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

Zhou, L, Liao, S, Li, W & Shen, D 2011, Learning-based prostate localization for image guided radiation therapy. in Proceedings - International Symposium on Biomedical Imaging., 5872827, pp. 2103-2106, 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11, Chicago, IL, United States, 11/3/30. https://doi.org/10.1109/ISBI.2011.5872827
Zhou L, Liao S, Li W, Shen D. Learning-based prostate localization for image guided radiation therapy. In Proceedings - International Symposium on Biomedical Imaging. 2011. p. 2103-2106. 5872827 https://doi.org/10.1109/ISBI.2011.5872827
Zhou, Luping ; Liao, Shu ; Li, Wei ; Shen, Dinggang. / Learning-based prostate localization for image guided radiation therapy. Proceedings - International Symposium on Biomedical Imaging. 2011. pp. 2103-2106
@inproceedings{123080fa0d9441159dd219b1a5cf6e8b,
title = "Learning-based prostate localization for image guided radiation therapy",
abstract = "Accurate prostate localization is the key to the success of radiotherapy. It remains a difficult problem for CT images due to the low image contrast, the prostate motion, and the uncertain presence of rectum gas. In this paper, a learning based framework is proposed to improve the accuracy of prostate detection in CT. It adaptively determines distinctive feature types at distinctive image regions, thus filtering out features that are salient in image appearance, but irrelevant to prostate localization. Furthermore, an image similarity function is learned to make the image appearance distance consistent with the underlying prostate alignment. The efficacy of our proposed method has been demonstrated by the experiment.",
keywords = "Feature Selection, IGRT, Image Similarity Learning, Prostate Localization",
author = "Luping Zhou and Shu Liao and Wei Li and Dinggang Shen",
year = "2011",
month = "11",
day = "2",
doi = "10.1109/ISBI.2011.5872827",
language = "English",
isbn = "9781424441280",
pages = "2103--2106",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Learning-based prostate localization for image guided radiation therapy

AU - Zhou, Luping

AU - Liao, Shu

AU - Li, Wei

AU - Shen, Dinggang

PY - 2011/11/2

Y1 - 2011/11/2

N2 - Accurate prostate localization is the key to the success of radiotherapy. It remains a difficult problem for CT images due to the low image contrast, the prostate motion, and the uncertain presence of rectum gas. In this paper, a learning based framework is proposed to improve the accuracy of prostate detection in CT. It adaptively determines distinctive feature types at distinctive image regions, thus filtering out features that are salient in image appearance, but irrelevant to prostate localization. Furthermore, an image similarity function is learned to make the image appearance distance consistent with the underlying prostate alignment. The efficacy of our proposed method has been demonstrated by the experiment.

AB - Accurate prostate localization is the key to the success of radiotherapy. It remains a difficult problem for CT images due to the low image contrast, the prostate motion, and the uncertain presence of rectum gas. In this paper, a learning based framework is proposed to improve the accuracy of prostate detection in CT. It adaptively determines distinctive feature types at distinctive image regions, thus filtering out features that are salient in image appearance, but irrelevant to prostate localization. Furthermore, an image similarity function is learned to make the image appearance distance consistent with the underlying prostate alignment. The efficacy of our proposed method has been demonstrated by the experiment.

KW - Feature Selection

KW - IGRT

KW - Image Similarity Learning

KW - Prostate Localization

UR - http://www.scopus.com/inward/record.url?scp=80053495849&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053495849&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2011.5872827

DO - 10.1109/ISBI.2011.5872827

M3 - Conference contribution

AN - SCOPUS:80053495849

SN - 9781424441280

SP - 2103

EP - 2106

BT - Proceedings - International Symposium on Biomedical Imaging

ER -