Upper airway segmentation and measurement in MRI using fuzzy connectedness

Jianguo Liu, Jayaram K. Udupa, Dewey Odhner, Joe M. McDonough, Raanan Arens

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

6 Citations (Scopus)

Abstract

The purpose of this work is to build a computerized system for the delineation of upper airway structures via MRI and to evaluate its effectiveness for routine clinical use in aiding diagnosis of upper airway disorders in children. We use two MRI protocols, axial T1 and T2, to gather information about different aspects of the airway and its surrounding soft tissue structures including adenoid, tonsils, tongue and soft palate. These images are processed and segmented to compute the architectural parameters of the airway such as its surface description, volume, central (medial) line, and cross-sectional areas at planes orthogonal to the central line. We have built a software package based on 3DVIEWNIX and running on a 450 MHz Pentium PC under Linux system (and on a Sun workstation under Unix) for the various operations of visualization, segmentation, registration, prefiltering, interpolation, standardization, and quantitative analysis of the airway. The system has been tested utilizing 40 patient studies. For every study, the system segmented and displayed a smooth 3D rendition of the airway, its central line and a plot of the cross-sectional area of the airway orthogonal to the central line as a function of the distance from one end of the central line. The tests indicate 97% precision and accuracy for segmentation. The mean time taken per study is about 4 minutes for the airway. This includes operator interaction time and processing time. This method provides a robust and fast means of assessing the airway size, shape, and places of restriction, as well as providing a structural data set suitable for use in modeling studies of airflow and mechanics.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsA.V. Clough, C.T. Chen
Pages238-247
Number of pages10
Volume4683
DOIs
StatePublished - 2002
Externally publishedYes
EventMedical Imaging 2002: Physiology and Function from Multidimensional Images - San Diego, CA, United States
Duration: Feb 24 2002Feb 26 2002

Other

OtherMedical Imaging 2002: Physiology and Function from Multidimensional Images
CountryUnited States
CitySan Diego, CA
Period2/24/022/26/02

Fingerprint

Magnetic resonance imaging
tongue
delineation
workstations
standardization
quantitative analysis
interpolation
constrictions
sun
plots
disorders
computer programs
operators
interactions
Software packages
Sun
Standardization
Interpolation
Mechanics
Visualization

Keywords

  • Fuzzy connectedness
  • Magnetic resonance imaging
  • Quantitative evaluation
  • Segmentation
  • Upper airway
  • Visualization

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Liu, J., Udupa, J. K., Odhner, D., McDonough, J. M., & Arens, R. (2002). Upper airway segmentation and measurement in MRI using fuzzy connectedness. In A. V. Clough, & C. T. Chen (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 4683, pp. 238-247) https://doi.org/10.1117/12.463588

Upper airway segmentation and measurement in MRI using fuzzy connectedness. / Liu, Jianguo; Udupa, Jayaram K.; Odhner, Dewey; McDonough, Joe M.; Arens, Raanan.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / A.V. Clough; C.T. Chen. Vol. 4683 2002. p. 238-247.

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

Liu, J, Udupa, JK, Odhner, D, McDonough, JM & Arens, R 2002, Upper airway segmentation and measurement in MRI using fuzzy connectedness. in AV Clough & CT Chen (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 4683, pp. 238-247, Medical Imaging 2002: Physiology and Function from Multidimensional Images, San Diego, CA, United States, 2/24/02. https://doi.org/10.1117/12.463588
Liu J, Udupa JK, Odhner D, McDonough JM, Arens R. Upper airway segmentation and measurement in MRI using fuzzy connectedness. In Clough AV, Chen CT, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 4683. 2002. p. 238-247 https://doi.org/10.1117/12.463588
Liu, Jianguo ; Udupa, Jayaram K. ; Odhner, Dewey ; McDonough, Joe M. ; Arens, Raanan. / Upper airway segmentation and measurement in MRI using fuzzy connectedness. Proceedings of SPIE - The International Society for Optical Engineering. editor / A.V. Clough ; C.T. Chen. Vol. 4683 2002. pp. 238-247
@inproceedings{abf06dc34d7542c1905e0fe56b0756ff,
title = "Upper airway segmentation and measurement in MRI using fuzzy connectedness",
abstract = "The purpose of this work is to build a computerized system for the delineation of upper airway structures via MRI and to evaluate its effectiveness for routine clinical use in aiding diagnosis of upper airway disorders in children. We use two MRI protocols, axial T1 and T2, to gather information about different aspects of the airway and its surrounding soft tissue structures including adenoid, tonsils, tongue and soft palate. These images are processed and segmented to compute the architectural parameters of the airway such as its surface description, volume, central (medial) line, and cross-sectional areas at planes orthogonal to the central line. We have built a software package based on 3DVIEWNIX and running on a 450 MHz Pentium PC under Linux system (and on a Sun workstation under Unix) for the various operations of visualization, segmentation, registration, prefiltering, interpolation, standardization, and quantitative analysis of the airway. The system has been tested utilizing 40 patient studies. For every study, the system segmented and displayed a smooth 3D rendition of the airway, its central line and a plot of the cross-sectional area of the airway orthogonal to the central line as a function of the distance from one end of the central line. The tests indicate 97{\%} precision and accuracy for segmentation. The mean time taken per study is about 4 minutes for the airway. This includes operator interaction time and processing time. This method provides a robust and fast means of assessing the airway size, shape, and places of restriction, as well as providing a structural data set suitable for use in modeling studies of airflow and mechanics.",
keywords = "Fuzzy connectedness, Magnetic resonance imaging, Quantitative evaluation, Segmentation, Upper airway, Visualization",
author = "Jianguo Liu and Udupa, {Jayaram K.} and Dewey Odhner and McDonough, {Joe M.} and Raanan Arens",
year = "2002",
doi = "10.1117/12.463588",
language = "English (US)",
volume = "4683",
pages = "238--247",
editor = "A.V. Clough and C.T. Chen",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Upper airway segmentation and measurement in MRI using fuzzy connectedness

AU - Liu, Jianguo

AU - Udupa, Jayaram K.

AU - Odhner, Dewey

AU - McDonough, Joe M.

AU - Arens, Raanan

PY - 2002

Y1 - 2002

N2 - The purpose of this work is to build a computerized system for the delineation of upper airway structures via MRI and to evaluate its effectiveness for routine clinical use in aiding diagnosis of upper airway disorders in children. We use two MRI protocols, axial T1 and T2, to gather information about different aspects of the airway and its surrounding soft tissue structures including adenoid, tonsils, tongue and soft palate. These images are processed and segmented to compute the architectural parameters of the airway such as its surface description, volume, central (medial) line, and cross-sectional areas at planes orthogonal to the central line. We have built a software package based on 3DVIEWNIX and running on a 450 MHz Pentium PC under Linux system (and on a Sun workstation under Unix) for the various operations of visualization, segmentation, registration, prefiltering, interpolation, standardization, and quantitative analysis of the airway. The system has been tested utilizing 40 patient studies. For every study, the system segmented and displayed a smooth 3D rendition of the airway, its central line and a plot of the cross-sectional area of the airway orthogonal to the central line as a function of the distance from one end of the central line. The tests indicate 97% precision and accuracy for segmentation. The mean time taken per study is about 4 minutes for the airway. This includes operator interaction time and processing time. This method provides a robust and fast means of assessing the airway size, shape, and places of restriction, as well as providing a structural data set suitable for use in modeling studies of airflow and mechanics.

AB - The purpose of this work is to build a computerized system for the delineation of upper airway structures via MRI and to evaluate its effectiveness for routine clinical use in aiding diagnosis of upper airway disorders in children. We use two MRI protocols, axial T1 and T2, to gather information about different aspects of the airway and its surrounding soft tissue structures including adenoid, tonsils, tongue and soft palate. These images are processed and segmented to compute the architectural parameters of the airway such as its surface description, volume, central (medial) line, and cross-sectional areas at planes orthogonal to the central line. We have built a software package based on 3DVIEWNIX and running on a 450 MHz Pentium PC under Linux system (and on a Sun workstation under Unix) for the various operations of visualization, segmentation, registration, prefiltering, interpolation, standardization, and quantitative analysis of the airway. The system has been tested utilizing 40 patient studies. For every study, the system segmented and displayed a smooth 3D rendition of the airway, its central line and a plot of the cross-sectional area of the airway orthogonal to the central line as a function of the distance from one end of the central line. The tests indicate 97% precision and accuracy for segmentation. The mean time taken per study is about 4 minutes for the airway. This includes operator interaction time and processing time. This method provides a robust and fast means of assessing the airway size, shape, and places of restriction, as well as providing a structural data set suitable for use in modeling studies of airflow and mechanics.

KW - Fuzzy connectedness

KW - Magnetic resonance imaging

KW - Quantitative evaluation

KW - Segmentation

KW - Upper airway

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=0036034933&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036034933&partnerID=8YFLogxK

U2 - 10.1117/12.463588

DO - 10.1117/12.463588

M3 - Conference contribution

AN - SCOPUS:0036034933

VL - 4683

SP - 238

EP - 247

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Clough, A.V.

A2 - Chen, C.T.

ER -