Accurate and efficient separation of left and right lungs from 3D CT scans: A generic hysteresis approach

Ziyue Xu, Ulas Bagci, Colleen Jonsson, Sanjay Jain, Daniel J. Mollura

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

Abstract

Separation of left and right lungs from binary segmentation is often necessary for quantitative image-based pulmonary disease evaluation. In this article, we present a new fully automated approach for accurate, robust, and efficient lung separation using 3-D CT scans. Our method follows a hysteresis setting that utilizes information from both lung regions and background gaps. First, original segmentation is separated by subtracting the gaps between left and right lungs, which are enhanced with Hessian filtering. Second, the 2-D separation manifold in 3-D image space is estimated based on the distance information from the two subsets. Finally, the separation manifold is projected back to the original segmentation in order to produce the separated lungs through optimization for addressing minor local variations. An evaluation on over 400 human and 100 small animal 3-D CT images with various abnormalities is performed. The proposed scheme successfully separated all connections on the candidate CT images. Using hysteresis mechanism, each phase is performed robustly and 3-D information is utilized to achieve a generic, efficient, and accurate solution.

Original languageEnglish (US)
Title of host publication2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6036-6039
Number of pages4
ISBN (Print)9781424479290
DOIs
StatePublished - Nov 2 2014
Event2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 - Chicago, United States
Duration: Aug 26 2014Aug 30 2014

Other

Other2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
CountryUnited States
CityChicago
Period8/26/148/30/14

Fingerprint

Computerized tomography
Hysteresis
Lung
Three-Dimensional Imaging
Pulmonary diseases
Animals
Lung Diseases

Keywords

  • distance transform
  • Hessian
  • hysteresis
  • Left and right lung separation
  • lung segmentation

ASJC Scopus subject areas

  • Health Informatics
  • Computer Science Applications
  • Biomedical Engineering

Cite this

Xu, Z., Bagci, U., Jonsson, C., Jain, S., & Mollura, D. J. (2014). Accurate and efficient separation of left and right lungs from 3D CT scans: A generic hysteresis approach. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 (pp. 6036-6039). [6945005] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2014.6945005

Accurate and efficient separation of left and right lungs from 3D CT scans : A generic hysteresis approach. / Xu, Ziyue; Bagci, Ulas; Jonsson, Colleen; Jain, Sanjay; Mollura, Daniel J.

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 6036-6039 6945005.

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

Xu, Z, Bagci, U, Jonsson, C, Jain, S & Mollura, DJ 2014, Accurate and efficient separation of left and right lungs from 3D CT scans: A generic hysteresis approach. in 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014., 6945005, Institute of Electrical and Electronics Engineers Inc., pp. 6036-6039, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014, Chicago, United States, 8/26/14. https://doi.org/10.1109/EMBC.2014.6945005
Xu Z, Bagci U, Jonsson C, Jain S, Mollura DJ. Accurate and efficient separation of left and right lungs from 3D CT scans: A generic hysteresis approach. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 6036-6039. 6945005 https://doi.org/10.1109/EMBC.2014.6945005
Xu, Ziyue ; Bagci, Ulas ; Jonsson, Colleen ; Jain, Sanjay ; Mollura, Daniel J. / Accurate and efficient separation of left and right lungs from 3D CT scans : A generic hysteresis approach. 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 6036-6039
@inproceedings{976a972ed6f24c92b09c047573700eac,
title = "Accurate and efficient separation of left and right lungs from 3D CT scans: A generic hysteresis approach",
abstract = "Separation of left and right lungs from binary segmentation is often necessary for quantitative image-based pulmonary disease evaluation. In this article, we present a new fully automated approach for accurate, robust, and efficient lung separation using 3-D CT scans. Our method follows a hysteresis setting that utilizes information from both lung regions and background gaps. First, original segmentation is separated by subtracting the gaps between left and right lungs, which are enhanced with Hessian filtering. Second, the 2-D separation manifold in 3-D image space is estimated based on the distance information from the two subsets. Finally, the separation manifold is projected back to the original segmentation in order to produce the separated lungs through optimization for addressing minor local variations. An evaluation on over 400 human and 100 small animal 3-D CT images with various abnormalities is performed. The proposed scheme successfully separated all connections on the candidate CT images. Using hysteresis mechanism, each phase is performed robustly and 3-D information is utilized to achieve a generic, efficient, and accurate solution.",
keywords = "distance transform, Hessian, hysteresis, Left and right lung separation, lung segmentation",
author = "Ziyue Xu and Ulas Bagci and Colleen Jonsson and Sanjay Jain and Mollura, {Daniel J.}",
year = "2014",
month = "11",
day = "2",
doi = "10.1109/EMBC.2014.6945005",
language = "English (US)",
isbn = "9781424479290",
pages = "6036--6039",
booktitle = "2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Accurate and efficient separation of left and right lungs from 3D CT scans

T2 - A generic hysteresis approach

AU - Xu, Ziyue

AU - Bagci, Ulas

AU - Jonsson, Colleen

AU - Jain, Sanjay

AU - Mollura, Daniel J.

PY - 2014/11/2

Y1 - 2014/11/2

N2 - Separation of left and right lungs from binary segmentation is often necessary for quantitative image-based pulmonary disease evaluation. In this article, we present a new fully automated approach for accurate, robust, and efficient lung separation using 3-D CT scans. Our method follows a hysteresis setting that utilizes information from both lung regions and background gaps. First, original segmentation is separated by subtracting the gaps between left and right lungs, which are enhanced with Hessian filtering. Second, the 2-D separation manifold in 3-D image space is estimated based on the distance information from the two subsets. Finally, the separation manifold is projected back to the original segmentation in order to produce the separated lungs through optimization for addressing minor local variations. An evaluation on over 400 human and 100 small animal 3-D CT images with various abnormalities is performed. The proposed scheme successfully separated all connections on the candidate CT images. Using hysteresis mechanism, each phase is performed robustly and 3-D information is utilized to achieve a generic, efficient, and accurate solution.

AB - Separation of left and right lungs from binary segmentation is often necessary for quantitative image-based pulmonary disease evaluation. In this article, we present a new fully automated approach for accurate, robust, and efficient lung separation using 3-D CT scans. Our method follows a hysteresis setting that utilizes information from both lung regions and background gaps. First, original segmentation is separated by subtracting the gaps between left and right lungs, which are enhanced with Hessian filtering. Second, the 2-D separation manifold in 3-D image space is estimated based on the distance information from the two subsets. Finally, the separation manifold is projected back to the original segmentation in order to produce the separated lungs through optimization for addressing minor local variations. An evaluation on over 400 human and 100 small animal 3-D CT images with various abnormalities is performed. The proposed scheme successfully separated all connections on the candidate CT images. Using hysteresis mechanism, each phase is performed robustly and 3-D information is utilized to achieve a generic, efficient, and accurate solution.

KW - distance transform

KW - Hessian

KW - hysteresis

KW - Left and right lung separation

KW - lung segmentation

UR - http://www.scopus.com/inward/record.url?scp=84914139376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84914139376&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2014.6945005

DO - 10.1109/EMBC.2014.6945005

M3 - Conference contribution

C2 - 25571373

SN - 9781424479290

SP - 6036

EP - 6039

BT - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -