RULE-BASED DETECTION OF INTRATHORACIC AIRWAY TREES

Citation
M. Sonka et al., RULE-BASED DETECTION OF INTRATHORACIC AIRWAY TREES, IEEE transactions on medical imaging, 15(3), 1996, pp. 314-326
Citations number
32
Categorie Soggetti
Engineering, Biomedical","Radiology,Nuclear Medicine & Medical Imaging
ISSN journal
02780062
Volume
15
Issue
3
Year of publication
1996
Pages
314 - 326
Database
ISI
SICI code
0278-0062(1996)15:3<314:RDOIAT>2.0.ZU;2-O
Abstract
New sensitive and reliable methods for assessing alterations in region al lung structure and function are critically important for the invest igation and treatment of pulmonary diseases, Accurate identification o f the airway tree will provide an assessment of airway structure and w ill provide a means by which multiple volumetric images of the lung at the same lung volume over time can be used to assess regional parench ymal changes, We describe a novel rule-based method for the segmentati on of airway trees from three-dimensional (3-D) sets of computed tomog raphy (CT) images, and its validation, The presented method takes adva ntage of a priori anatomical knowledge about pulmonary airway and vasc ular trees and their interrelationships, The method is based on a comb ination of 3-D seeded region growing that is used to identify large ai rways, rule-based two-dimensional (2-D) segmentation of individual CT slices to identify probable locations of smaller diameter airways, and merging of airway regions across the 3-D set of slices resulting in a tree-like airway structure, The method was validated in 40 3-mm-thick CT sections from five data sets of canine lungs scanned via electron beam CT in vivo with lung volume held at a constant pressure, The meth od's performance was compared with that of the conventional 3-D region growing method, The method substantially outperformed an existing con ventional approach to airway tree detection.