Robust shape-constrained active contour for whole heart segmentation in 3-D CT images for radiotherapy planning

Xuan Zhao, Yao Wang, Gabor Jozsef

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

Abstract

Automatic segmentation of the whole heart in computed tomography(CT) image is crucial for efficient treatment planning of thoracic radiotherapy. In this paper, we propose a fully automatic method for whole heart segmentation of thoracic CT images. A robust active shape model (Robust ASM) is proposed using shape models developed from training data to reduce outliers due to similar intensity of neighboring organs. A novel shape constrained active contour model is presented to further improve the segmentation result. A mean point-to-surface error of 2.37mm was measured based on 38 images. The averaged Dice index is 0.90.

Original languageEnglish (US)
Title of host publication2014 IEEE International Conference on Image Processing, ICIP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
Number of pages5
ISBN (Print)9781479957514
DOIs
StatePublished - Jan 28 2014

Fingerprint

Radiotherapy
Tomography
Planning

Keywords

  • CT image
  • Radiotherapy
  • Whole heart segmentation

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Zhao, X., Wang, Y., & Jozsef, G. (2014). Robust shape-constrained active contour for whole heart segmentation in 3-D CT images for radiotherapy planning. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 1-5). [7024999] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7024999

Robust shape-constrained active contour for whole heart segmentation in 3-D CT images for radiotherapy planning. / Zhao, Xuan; Wang, Yao; Jozsef, Gabor.

2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1-5 7024999.

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

Zhao, X, Wang, Y & Jozsef, G 2014, Robust shape-constrained active contour for whole heart segmentation in 3-D CT images for radiotherapy planning. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7024999, Institute of Electrical and Electronics Engineers Inc., pp. 1-5. https://doi.org/10.1109/ICIP.2014.7024999
Zhao X, Wang Y, Jozsef G. Robust shape-constrained active contour for whole heart segmentation in 3-D CT images for radiotherapy planning. In 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 1-5. 7024999 https://doi.org/10.1109/ICIP.2014.7024999
Zhao, Xuan ; Wang, Yao ; Jozsef, Gabor. / Robust shape-constrained active contour for whole heart segmentation in 3-D CT images for radiotherapy planning. 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 1-5
@inproceedings{4d70601f368445748c577da57c7150b1,
title = "Robust shape-constrained active contour for whole heart segmentation in 3-D CT images for radiotherapy planning",
abstract = "Automatic segmentation of the whole heart in computed tomography(CT) image is crucial for efficient treatment planning of thoracic radiotherapy. In this paper, we propose a fully automatic method for whole heart segmentation of thoracic CT images. A robust active shape model (Robust ASM) is proposed using shape models developed from training data to reduce outliers due to similar intensity of neighboring organs. A novel shape constrained active contour model is presented to further improve the segmentation result. A mean point-to-surface error of 2.37mm was measured based on 38 images. The averaged Dice index is 0.90.",
keywords = "CT image, Radiotherapy, Whole heart segmentation",
author = "Xuan Zhao and Yao Wang and Gabor Jozsef",
year = "2014",
month = "1",
day = "28",
doi = "10.1109/ICIP.2014.7024999",
language = "English (US)",
isbn = "9781479957514",
pages = "1--5",
booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Robust shape-constrained active contour for whole heart segmentation in 3-D CT images for radiotherapy planning

AU - Zhao, Xuan

AU - Wang, Yao

AU - Jozsef, Gabor

PY - 2014/1/28

Y1 - 2014/1/28

N2 - Automatic segmentation of the whole heart in computed tomography(CT) image is crucial for efficient treatment planning of thoracic radiotherapy. In this paper, we propose a fully automatic method for whole heart segmentation of thoracic CT images. A robust active shape model (Robust ASM) is proposed using shape models developed from training data to reduce outliers due to similar intensity of neighboring organs. A novel shape constrained active contour model is presented to further improve the segmentation result. A mean point-to-surface error of 2.37mm was measured based on 38 images. The averaged Dice index is 0.90.

AB - Automatic segmentation of the whole heart in computed tomography(CT) image is crucial for efficient treatment planning of thoracic radiotherapy. In this paper, we propose a fully automatic method for whole heart segmentation of thoracic CT images. A robust active shape model (Robust ASM) is proposed using shape models developed from training data to reduce outliers due to similar intensity of neighboring organs. A novel shape constrained active contour model is presented to further improve the segmentation result. A mean point-to-surface error of 2.37mm was measured based on 38 images. The averaged Dice index is 0.90.

KW - CT image

KW - Radiotherapy

KW - Whole heart segmentation

UR - http://www.scopus.com/inward/record.url?scp=84949928683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949928683&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7024999

DO - 10.1109/ICIP.2014.7024999

M3 - Conference contribution

AN - SCOPUS:84949928683

SN - 9781479957514

SP - 1

EP - 5

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -