Prostate segmentation in CT images via spatial-constrained transductive lasso

Yinghuan Shi, Shu Liao, Yaozong Gao, Daoqiang Zhang, Yang Gao, Dinggang Shen

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

24 Citations (Scopus)

Abstract

Accurate prostate segmentation in CT images is a significant yet challenging task for image guided radiotherapy. In this paper, a novel semi-automated prostate segmentation method is presented. Specifically, to segment the prostate in the current treatment image, the physician first takes a few seconds to manually specify the first and last slices of the prostate in the image space. Then, the prostate is segmented automatically by the proposed two steps: (i) The first step of prostate-likelihood estimation to predict the prostate likelihood for each voxel in the current treatment image, aiming to generate the 3-D prostate-likelihood map by the proposed Spatial-COnstrained Transductive LassO (SCOTO), (ii) The second step of multi-atlases based label fusion to generate the final segmentation result by using the prostate shape information obtained from the planning and previous treatment images. The experimental result shows that the proposed method outperforms several state-of-the-art methods on prostate segmentation in a real prostate CT dataset, consisting of 24 patients with 330 images. Moreover, it is also clinically feasible since our method just requires the physician to spend a few seconds on manual specification of the first and last slices of the prostate.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages2227-2234
Number of pages8
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013 - Portland, OR, United States
Duration: 2013 Jun 232013 Jun 28

Other

Other26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013
CountryUnited States
CityPortland, OR
Period13/6/2313/6/28

Fingerprint

Radiotherapy
Labels
Fusion reactions
Specifications
Planning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Shi, Y., Liao, S., Gao, Y., Zhang, D., Gao, Y., & Shen, D. (2013). Prostate segmentation in CT images via spatial-constrained transductive lasso. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 2227-2234). [6619133] https://doi.org/10.1109/CVPR.2013.289

Prostate segmentation in CT images via spatial-constrained transductive lasso. / Shi, Yinghuan; Liao, Shu; Gao, Yaozong; Zhang, Daoqiang; Gao, Yang; Shen, Dinggang.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2013. p. 2227-2234 6619133.

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

Shi, Y, Liao, S, Gao, Y, Zhang, D, Gao, Y & Shen, D 2013, Prostate segmentation in CT images via spatial-constrained transductive lasso. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 6619133, pp. 2227-2234, 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013, Portland, OR, United States, 13/6/23. https://doi.org/10.1109/CVPR.2013.289
Shi Y, Liao S, Gao Y, Zhang D, Gao Y, Shen D. Prostate segmentation in CT images via spatial-constrained transductive lasso. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2013. p. 2227-2234. 6619133 https://doi.org/10.1109/CVPR.2013.289
Shi, Yinghuan ; Liao, Shu ; Gao, Yaozong ; Zhang, Daoqiang ; Gao, Yang ; Shen, Dinggang. / Prostate segmentation in CT images via spatial-constrained transductive lasso. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2013. pp. 2227-2234
@inproceedings{c292b363bac748c283358e971cc84425,
title = "Prostate segmentation in CT images via spatial-constrained transductive lasso",
abstract = "Accurate prostate segmentation in CT images is a significant yet challenging task for image guided radiotherapy. In this paper, a novel semi-automated prostate segmentation method is presented. Specifically, to segment the prostate in the current treatment image, the physician first takes a few seconds to manually specify the first and last slices of the prostate in the image space. Then, the prostate is segmented automatically by the proposed two steps: (i) The first step of prostate-likelihood estimation to predict the prostate likelihood for each voxel in the current treatment image, aiming to generate the 3-D prostate-likelihood map by the proposed Spatial-COnstrained Transductive LassO (SCOTO), (ii) The second step of multi-atlases based label fusion to generate the final segmentation result by using the prostate shape information obtained from the planning and previous treatment images. The experimental result shows that the proposed method outperforms several state-of-the-art methods on prostate segmentation in a real prostate CT dataset, consisting of 24 patients with 330 images. Moreover, it is also clinically feasible since our method just requires the physician to spend a few seconds on manual specification of the first and last slices of the prostate.",
author = "Yinghuan Shi and Shu Liao and Yaozong Gao and Daoqiang Zhang and Yang Gao and Dinggang Shen",
year = "2013",
doi = "10.1109/CVPR.2013.289",
language = "English",
pages = "2227--2234",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Prostate segmentation in CT images via spatial-constrained transductive lasso

AU - Shi, Yinghuan

AU - Liao, Shu

AU - Gao, Yaozong

AU - Zhang, Daoqiang

AU - Gao, Yang

AU - Shen, Dinggang

PY - 2013

Y1 - 2013

N2 - Accurate prostate segmentation in CT images is a significant yet challenging task for image guided radiotherapy. In this paper, a novel semi-automated prostate segmentation method is presented. Specifically, to segment the prostate in the current treatment image, the physician first takes a few seconds to manually specify the first and last slices of the prostate in the image space. Then, the prostate is segmented automatically by the proposed two steps: (i) The first step of prostate-likelihood estimation to predict the prostate likelihood for each voxel in the current treatment image, aiming to generate the 3-D prostate-likelihood map by the proposed Spatial-COnstrained Transductive LassO (SCOTO), (ii) The second step of multi-atlases based label fusion to generate the final segmentation result by using the prostate shape information obtained from the planning and previous treatment images. The experimental result shows that the proposed method outperforms several state-of-the-art methods on prostate segmentation in a real prostate CT dataset, consisting of 24 patients with 330 images. Moreover, it is also clinically feasible since our method just requires the physician to spend a few seconds on manual specification of the first and last slices of the prostate.

AB - Accurate prostate segmentation in CT images is a significant yet challenging task for image guided radiotherapy. In this paper, a novel semi-automated prostate segmentation method is presented. Specifically, to segment the prostate in the current treatment image, the physician first takes a few seconds to manually specify the first and last slices of the prostate in the image space. Then, the prostate is segmented automatically by the proposed two steps: (i) The first step of prostate-likelihood estimation to predict the prostate likelihood for each voxel in the current treatment image, aiming to generate the 3-D prostate-likelihood map by the proposed Spatial-COnstrained Transductive LassO (SCOTO), (ii) The second step of multi-atlases based label fusion to generate the final segmentation result by using the prostate shape information obtained from the planning and previous treatment images. The experimental result shows that the proposed method outperforms several state-of-the-art methods on prostate segmentation in a real prostate CT dataset, consisting of 24 patients with 330 images. Moreover, it is also clinically feasible since our method just requires the physician to spend a few seconds on manual specification of the first and last slices of the prostate.

UR - http://www.scopus.com/inward/record.url?scp=84887342481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887342481&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2013.289

DO - 10.1109/CVPR.2013.289

M3 - Conference contribution

AN - SCOPUS:84887342481

SP - 2227

EP - 2234

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ER -