3D-3D tubular organs registration based on bifurcations for the CT images.

Jinghao Zhou, Sukmoon Chang, Dimitris Metaxas, Gig Mageras

Research output: Contribution to journalArticle

Abstract

The registration of tubular organs (pulmonary tracheobronchial tree or vasculature) of 3D medical images is critical in various clinical applications such as surgical planning and radiotherapy. In this paper, we present a novel method for tubular organs registration based on the automatically detected bifurcation points of the tubular organs. We first perform a 3D tubular organ segmentation method to extract the centerlines of tubular organs and radius estimation in both planning and respiration-correlated CT (RCCT) images. This segmentation method automatically detects the bifurcation points by applying Adaboost algorithm with specially designed filters. We then apply a rigid registration method which minimizes the least square error of the corresponding bifurcation points between the planning CT images and the respiration-correlated CT images. Our method has over 96% success rate for detecting bifurcation points.We present very promising results of our method applied to the registration of the planning and respiration-correlated CT images. On average, the mean distance and the root-mean-square error (RMSE) of the corresponding bifurcation points between the respiration-correlated images and the registered planning images are less than 2.7 mm.

Original languageEnglish (US)
Pages (from-to)5394-5397
Number of pages4
JournalAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
StatePublished - 2008

Fingerprint

Planning
Respiration
Bifurcation (mathematics)
Adaptive boosting
Radiotherapy
Mean square error
Least-Squares Analysis
Lung

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

@article{2adf9cd15cde4544aaea1eacf7ac1ab8,
title = "3D-3D tubular organs registration based on bifurcations for the CT images.",
abstract = "The registration of tubular organs (pulmonary tracheobronchial tree or vasculature) of 3D medical images is critical in various clinical applications such as surgical planning and radiotherapy. In this paper, we present a novel method for tubular organs registration based on the automatically detected bifurcation points of the tubular organs. We first perform a 3D tubular organ segmentation method to extract the centerlines of tubular organs and radius estimation in both planning and respiration-correlated CT (RCCT) images. This segmentation method automatically detects the bifurcation points by applying Adaboost algorithm with specially designed filters. We then apply a rigid registration method which minimizes the least square error of the corresponding bifurcation points between the planning CT images and the respiration-correlated CT images. Our method has over 96{\%} success rate for detecting bifurcation points.We present very promising results of our method applied to the registration of the planning and respiration-correlated CT images. On average, the mean distance and the root-mean-square error (RMSE) of the corresponding bifurcation points between the respiration-correlated images and the registered planning images are less than 2.7 mm.",
author = "Jinghao Zhou and Sukmoon Chang and Dimitris Metaxas and Gig Mageras",
year = "2008",
language = "English (US)",
pages = "5394--5397",
journal = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",
issn = "1557-170X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

3D-3D tubular organs registration based on bifurcations for the CT images. / Zhou, Jinghao; Chang, Sukmoon; Metaxas, Dimitris; Mageras, Gig.

In: Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, 2008, p. 5394-5397.

Research output: Contribution to journalArticle

TY - JOUR

T1 - 3D-3D tubular organs registration based on bifurcations for the CT images.

AU - Zhou, Jinghao

AU - Chang, Sukmoon

AU - Metaxas, Dimitris

AU - Mageras, Gig

PY - 2008

Y1 - 2008

N2 - The registration of tubular organs (pulmonary tracheobronchial tree or vasculature) of 3D medical images is critical in various clinical applications such as surgical planning and radiotherapy. In this paper, we present a novel method for tubular organs registration based on the automatically detected bifurcation points of the tubular organs. We first perform a 3D tubular organ segmentation method to extract the centerlines of tubular organs and radius estimation in both planning and respiration-correlated CT (RCCT) images. This segmentation method automatically detects the bifurcation points by applying Adaboost algorithm with specially designed filters. We then apply a rigid registration method which minimizes the least square error of the corresponding bifurcation points between the planning CT images and the respiration-correlated CT images. Our method has over 96% success rate for detecting bifurcation points.We present very promising results of our method applied to the registration of the planning and respiration-correlated CT images. On average, the mean distance and the root-mean-square error (RMSE) of the corresponding bifurcation points between the respiration-correlated images and the registered planning images are less than 2.7 mm.

AB - The registration of tubular organs (pulmonary tracheobronchial tree or vasculature) of 3D medical images is critical in various clinical applications such as surgical planning and radiotherapy. In this paper, we present a novel method for tubular organs registration based on the automatically detected bifurcation points of the tubular organs. We first perform a 3D tubular organ segmentation method to extract the centerlines of tubular organs and radius estimation in both planning and respiration-correlated CT (RCCT) images. This segmentation method automatically detects the bifurcation points by applying Adaboost algorithm with specially designed filters. We then apply a rigid registration method which minimizes the least square error of the corresponding bifurcation points between the planning CT images and the respiration-correlated CT images. Our method has over 96% success rate for detecting bifurcation points.We present very promising results of our method applied to the registration of the planning and respiration-correlated CT images. On average, the mean distance and the root-mean-square error (RMSE) of the corresponding bifurcation points between the respiration-correlated images and the registered planning images are less than 2.7 mm.

UR - http://www.scopus.com/inward/record.url?scp=84903867401&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903867401&partnerID=8YFLogxK

M3 - Article

SP - 5394

EP - 5397

JO - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

JF - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

SN - 1557-170X

ER -