Lung nodule growth analysis from 3D CT data with a coupled segmentation and registration framework

Yuanjie Zheng, Karl Steiner, Thomas Bauer, Jingyi Yu, Dinggang Shen, Chandra Kambhamettu

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

27 Citations (Scopus)

Abstract

In this paper we propose a new framework to simultaneously segment and register lung and tumor in serial CT data. Our method assumes nonrigid transformation on lung deformation and rigid structure on the tumor. We use the B-Spline-based nonrigid transformation to model the lung deformation while imposing rigid transformation on the tumor to preserve the volume and the shape of the tumor. In particular, we set the control points within the tumor to form a control mesh and thus assume the tumor region follows the same rigid transformation as the control mesh. For segmentation, we apply a 2D graph-cut algorithm on the 3D lung and tumor datasets. By iteratively performing segmentation and registration, our method achieves highly accurate segmentation and registration on serial CT data. Finally, since our method eliminates the possible volume variations of the tumor during registration, we can further estimate accurately the tumor growth, an important evidence in lung cancer diagnosis. Initial experiments on five sets of patients' serial CT data show that our method is robust and reliable.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Computer Vision
DOIs
Publication statusPublished - 2007 Dec 1
Externally publishedYes
Event2007 IEEE 11th International Conference on Computer Vision, ICCV - Rio de Janeiro, Brazil
Duration: 2007 Oct 142007 Oct 21

Other

Other2007 IEEE 11th International Conference on Computer Vision, ICCV
CountryBrazil
CityRio de Janeiro
Period07/10/1407/10/21

Fingerprint

Tumors
Rigid structures
Splines

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Zheng, Y., Steiner, K., Bauer, T., Yu, J., Shen, D., & Kambhamettu, C. (2007). Lung nodule growth analysis from 3D CT data with a coupled segmentation and registration framework. In Proceedings of the IEEE International Conference on Computer Vision [4409150] https://doi.org/10.1109/ICCV.2007.4409150

Lung nodule growth analysis from 3D CT data with a coupled segmentation and registration framework. / Zheng, Yuanjie; Steiner, Karl; Bauer, Thomas; Yu, Jingyi; Shen, Dinggang; Kambhamettu, Chandra.

Proceedings of the IEEE International Conference on Computer Vision. 2007. 4409150.

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

Zheng, Y, Steiner, K, Bauer, T, Yu, J, Shen, D & Kambhamettu, C 2007, Lung nodule growth analysis from 3D CT data with a coupled segmentation and registration framework. in Proceedings of the IEEE International Conference on Computer Vision., 4409150, 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brazil, 07/10/14. https://doi.org/10.1109/ICCV.2007.4409150
Zheng Y, Steiner K, Bauer T, Yu J, Shen D, Kambhamettu C. Lung nodule growth analysis from 3D CT data with a coupled segmentation and registration framework. In Proceedings of the IEEE International Conference on Computer Vision. 2007. 4409150 https://doi.org/10.1109/ICCV.2007.4409150
Zheng, Yuanjie ; Steiner, Karl ; Bauer, Thomas ; Yu, Jingyi ; Shen, Dinggang ; Kambhamettu, Chandra. / Lung nodule growth analysis from 3D CT data with a coupled segmentation and registration framework. Proceedings of the IEEE International Conference on Computer Vision. 2007.
@inproceedings{8790f0aeb33c493d8fe60c03e5d0f632,
title = "Lung nodule growth analysis from 3D CT data with a coupled segmentation and registration framework",
abstract = "In this paper we propose a new framework to simultaneously segment and register lung and tumor in serial CT data. Our method assumes nonrigid transformation on lung deformation and rigid structure on the tumor. We use the B-Spline-based nonrigid transformation to model the lung deformation while imposing rigid transformation on the tumor to preserve the volume and the shape of the tumor. In particular, we set the control points within the tumor to form a control mesh and thus assume the tumor region follows the same rigid transformation as the control mesh. For segmentation, we apply a 2D graph-cut algorithm on the 3D lung and tumor datasets. By iteratively performing segmentation and registration, our method achieves highly accurate segmentation and registration on serial CT data. Finally, since our method eliminates the possible volume variations of the tumor during registration, we can further estimate accurately the tumor growth, an important evidence in lung cancer diagnosis. Initial experiments on five sets of patients' serial CT data show that our method is robust and reliable.",
author = "Yuanjie Zheng and Karl Steiner and Thomas Bauer and Jingyi Yu and Dinggang Shen and Chandra Kambhamettu",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ICCV.2007.4409150",
language = "English",
booktitle = "Proceedings of the IEEE International Conference on Computer Vision",

}

TY - GEN

T1 - Lung nodule growth analysis from 3D CT data with a coupled segmentation and registration framework

AU - Zheng, Yuanjie

AU - Steiner, Karl

AU - Bauer, Thomas

AU - Yu, Jingyi

AU - Shen, Dinggang

AU - Kambhamettu, Chandra

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper we propose a new framework to simultaneously segment and register lung and tumor in serial CT data. Our method assumes nonrigid transformation on lung deformation and rigid structure on the tumor. We use the B-Spline-based nonrigid transformation to model the lung deformation while imposing rigid transformation on the tumor to preserve the volume and the shape of the tumor. In particular, we set the control points within the tumor to form a control mesh and thus assume the tumor region follows the same rigid transformation as the control mesh. For segmentation, we apply a 2D graph-cut algorithm on the 3D lung and tumor datasets. By iteratively performing segmentation and registration, our method achieves highly accurate segmentation and registration on serial CT data. Finally, since our method eliminates the possible volume variations of the tumor during registration, we can further estimate accurately the tumor growth, an important evidence in lung cancer diagnosis. Initial experiments on five sets of patients' serial CT data show that our method is robust and reliable.

AB - In this paper we propose a new framework to simultaneously segment and register lung and tumor in serial CT data. Our method assumes nonrigid transformation on lung deformation and rigid structure on the tumor. We use the B-Spline-based nonrigid transformation to model the lung deformation while imposing rigid transformation on the tumor to preserve the volume and the shape of the tumor. In particular, we set the control points within the tumor to form a control mesh and thus assume the tumor region follows the same rigid transformation as the control mesh. For segmentation, we apply a 2D graph-cut algorithm on the 3D lung and tumor datasets. By iteratively performing segmentation and registration, our method achieves highly accurate segmentation and registration on serial CT data. Finally, since our method eliminates the possible volume variations of the tumor during registration, we can further estimate accurately the tumor growth, an important evidence in lung cancer diagnosis. Initial experiments on five sets of patients' serial CT data show that our method is robust and reliable.

UR - http://www.scopus.com/inward/record.url?scp=50649105291&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50649105291&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2007.4409150

DO - 10.1109/ICCV.2007.4409150

M3 - Conference contribution

AN - SCOPUS:50649105291

BT - Proceedings of the IEEE International Conference on Computer Vision

ER -