Modeling, segmentation, and caliber estimation of bronchi in high-resolution computerized tomography

Françoise J. Prêteux; Catalin I. Fetita; Philippe Grenier

doi:10.1117/12.279646

Modeling, segmentation, and caliber estimation of bronchi in high-resolution computerized tomography

Françoise J. Prêteux, Catalin I. Fetita, Philippe Grenier

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this paper, we address bronchi segmentation in high resolution computerized tomography in order to estimate the bronchial caliber. The method developed is based on mathematical morphology theory, and relies on morphological filtering, marking techniques derived from the concept of connection cost, and conditional watershed. In order to evaluate the robustness of the segmentation and the accuracy of the caliber estimates, a realistic bronchi modeling based on physiological characteristics has been developed. According to the size of the bronchi, the accuracy is up to 90%. Results are presented and discussed.

Original language	English
Pages (from-to)	58-69
Number of pages	12
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	3167
DOIs	https://doi.org/10.1117/12.279646
Publication status	Published - 1 Dec 1997
Externally published	Yes
Event	Statistical and Stochastic Methods in Image Processing II - San Diego, CA, United States Duration: 31 Jul 1997 → 31 Jul 1997

Keywords

Bronchi caliber
Bronchi modeling
Connection cost-based segmentation
HRCT images
Mathematical morphology

Access to Document

10.1117/12.279646

Cite this

@article{c409bd5fb7f04aa9b44b793225aa921d,

title = "Modeling, segmentation, and caliber estimation of bronchi in high-resolution computerized tomography",

abstract = "In this paper, we address bronchi segmentation in high resolution computerized tomography in order to estimate the bronchial caliber. The method developed is based on mathematical morphology theory, and relies on morphological filtering, marking techniques derived from the concept of connection cost, and conditional watershed. In order to evaluate the robustness of the segmentation and the accuracy of the caliber estimates, a realistic bronchi modeling based on physiological characteristics has been developed. According to the size of the bronchi, the accuracy is up to 90\%. Results are presented and discussed.",

keywords = "Bronchi caliber, Bronchi modeling, Connection cost-based segmentation, HRCT images, Mathematical morphology",

author = "Pr{\^e}teux, \{Fran{\c c}oise J.\} and Fetita, \{Catalin I.\} and Philippe Grenier",

year = "1997",

month = dec,

day = "1",

doi = "10.1117/12.279646",

language = "English",

volume = "3167",

pages = "58--69",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

note = "Statistical and Stochastic Methods in Image Processing II ; Conference date: 31-07-1997 Through 31-07-1997",

}

TY - JOUR

T1 - Modeling, segmentation, and caliber estimation of bronchi in high-resolution computerized tomography

AU - Prêteux, Françoise J.

AU - Fetita, Catalin I.

AU - Grenier, Philippe

PY - 1997/12/1

Y1 - 1997/12/1

N2 - In this paper, we address bronchi segmentation in high resolution computerized tomography in order to estimate the bronchial caliber. The method developed is based on mathematical morphology theory, and relies on morphological filtering, marking techniques derived from the concept of connection cost, and conditional watershed. In order to evaluate the robustness of the segmentation and the accuracy of the caliber estimates, a realistic bronchi modeling based on physiological characteristics has been developed. According to the size of the bronchi, the accuracy is up to 90%. Results are presented and discussed.

AB - In this paper, we address bronchi segmentation in high resolution computerized tomography in order to estimate the bronchial caliber. The method developed is based on mathematical morphology theory, and relies on morphological filtering, marking techniques derived from the concept of connection cost, and conditional watershed. In order to evaluate the robustness of the segmentation and the accuracy of the caliber estimates, a realistic bronchi modeling based on physiological characteristics has been developed. According to the size of the bronchi, the accuracy is up to 90%. Results are presented and discussed.

KW - Bronchi caliber

KW - Bronchi modeling

KW - Connection cost-based segmentation

KW - HRCT images

KW - Mathematical morphology

U2 - 10.1117/12.279646

DO - 10.1117/12.279646

M3 - Conference article

AN - SCOPUS:29144483161

SN - 0277-786X

VL - 3167

SP - 58

EP - 69

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

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

T2 - Statistical and Stochastic Methods in Image Processing II

Y2 - 31 July 1997 through 31 July 1997

ER -

Modeling, segmentation, and caliber estimation of bronchi in high-resolution computerized tomography

Abstract

Keywords

Access to Document

Fingerprint

Cite this