Segmenting ct prostate images using population and patient-Specific statistics for radiotherapy

Qianjin Fenga, Mark Foskey, Songyuan Tang, Wufan Chen, Dinggang Shen

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

11 Citations (Scopus)

Abstract

This paper presents a new deformable model using both population and patient-specific statistics to segment the prostate from CT images. There are two novelties in the proposed method. First, a modified scale invariant feature transform (SIFT) local descriptor, which is more distinctive than general intensity and gradient features, is used to characterize the image features. Second, an online training approach is used to build the shape statistics for accurately capturing intra-patient variation, which is more important than inter-patient variation for prostate segmentation in clinical radiotherapy. Experimental results show that the proposed method is robust and accurate, suitable for clinical application.

Original languageEnglish
Title of host publicationProceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009
Pages282-285
Number of pages4
DOIs
Publication statusPublished - 2009 Nov 17
Externally publishedYes
Event2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009 - Boston, MA, United States
Duration: 2009 Jun 282009 Jul 1

Other

Other2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009
CountryUnited States
CityBoston, MA
Period09/6/2809/7/1

Fingerprint

Radiotherapy
Prostate
Statistics
Population

Keywords

  • Deformable model
  • Prostate CT images
  • Segmentation
  • Shape statistics
  • SIFT

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Fenga, Q., Foskey, M., Tang, S., Chen, W., & Shen, D. (2009). Segmenting ct prostate images using population and patient-Specific statistics for radiotherapy. In Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009 (pp. 282-285). [5193039] https://doi.org/10.1109/ISBI.2009.5193039

Segmenting ct prostate images using population and patient-Specific statistics for radiotherapy. / Fenga, Qianjin; Foskey, Mark; Tang, Songyuan; Chen, Wufan; Shen, Dinggang.

Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. p. 282-285 5193039.

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

Fenga, Q, Foskey, M, Tang, S, Chen, W & Shen, D 2009, Segmenting ct prostate images using population and patient-Specific statistics for radiotherapy. in Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009., 5193039, pp. 282-285, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009, Boston, MA, United States, 09/6/28. https://doi.org/10.1109/ISBI.2009.5193039
Fenga Q, Foskey M, Tang S, Chen W, Shen D. Segmenting ct prostate images using population and patient-Specific statistics for radiotherapy. In Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. p. 282-285. 5193039 https://doi.org/10.1109/ISBI.2009.5193039
Fenga, Qianjin ; Foskey, Mark ; Tang, Songyuan ; Chen, Wufan ; Shen, Dinggang. / Segmenting ct prostate images using population and patient-Specific statistics for radiotherapy. Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. pp. 282-285
@inproceedings{9edada13a89740328cd03c56aa0607ba,
title = "Segmenting ct prostate images using population and patient-Specific statistics for radiotherapy",
abstract = "This paper presents a new deformable model using both population and patient-specific statistics to segment the prostate from CT images. There are two novelties in the proposed method. First, a modified scale invariant feature transform (SIFT) local descriptor, which is more distinctive than general intensity and gradient features, is used to characterize the image features. Second, an online training approach is used to build the shape statistics for accurately capturing intra-patient variation, which is more important than inter-patient variation for prostate segmentation in clinical radiotherapy. Experimental results show that the proposed method is robust and accurate, suitable for clinical application.",
keywords = "Deformable model, Prostate CT images, Segmentation, Shape statistics, SIFT",
author = "Qianjin Fenga and Mark Foskey and Songyuan Tang and Wufan Chen and Dinggang Shen",
year = "2009",
month = "11",
day = "17",
doi = "10.1109/ISBI.2009.5193039",
language = "English",
isbn = "9781424439324",
pages = "282--285",
booktitle = "Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009",

}

TY - GEN

T1 - Segmenting ct prostate images using population and patient-Specific statistics for radiotherapy

AU - Fenga, Qianjin

AU - Foskey, Mark

AU - Tang, Songyuan

AU - Chen, Wufan

AU - Shen, Dinggang

PY - 2009/11/17

Y1 - 2009/11/17

N2 - This paper presents a new deformable model using both population and patient-specific statistics to segment the prostate from CT images. There are two novelties in the proposed method. First, a modified scale invariant feature transform (SIFT) local descriptor, which is more distinctive than general intensity and gradient features, is used to characterize the image features. Second, an online training approach is used to build the shape statistics for accurately capturing intra-patient variation, which is more important than inter-patient variation for prostate segmentation in clinical radiotherapy. Experimental results show that the proposed method is robust and accurate, suitable for clinical application.

AB - This paper presents a new deformable model using both population and patient-specific statistics to segment the prostate from CT images. There are two novelties in the proposed method. First, a modified scale invariant feature transform (SIFT) local descriptor, which is more distinctive than general intensity and gradient features, is used to characterize the image features. Second, an online training approach is used to build the shape statistics for accurately capturing intra-patient variation, which is more important than inter-patient variation for prostate segmentation in clinical radiotherapy. Experimental results show that the proposed method is robust and accurate, suitable for clinical application.

KW - Deformable model

KW - Prostate CT images

KW - Segmentation

KW - Shape statistics

KW - SIFT

UR - http://www.scopus.com/inward/record.url?scp=70449334554&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449334554&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2009.5193039

DO - 10.1109/ISBI.2009.5193039

M3 - Conference contribution

AN - SCOPUS:70449334554

SN - 9781424439324

SP - 282

EP - 285

BT - Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009

ER -