Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2005 Dec;24(12):1540-7.
doi: 10.1109/TMI.2005.857653.

Matching and anatomical labeling of human airway tree

Juerg Tschirren  1 , Geoffrey McLennan, Kálmán Palágyi, Eric A Hoffman, Milan Sonka
Affiliations

Matching and anatomical labeling of human airway tree

Juerg Tschirren et al. IEEE Trans Med Imaging. 2005 Dec.

Abstract

Matching of corresponding branchpoints between two human airway trees, as well as assigning anatomical names to the segments and branchpoints of the human airway tree, are of significant interest for clinical applications and physiological studies. In the past, these tasks were often performed manually due to the lack of automated algorithms that can tolerate false branches and anatomical variability typical for in vivo trees. In this paper, we present algorithms that perform both matching of branchpoints and anatomical labeling of in vivo trees without any human intervention and within a short computing time. No hand-pruning of false branches is required. The results from the automated methods show a high degree of accuracy when validated against reference data provided by human experts. 92.9% of the verifiable branchpoint matches found by the computer agree with experts' results. For anatomical labeling, 97.1% of the automatically assigned segment labels were found to be correct.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Skeletonized tree represented as a directed acyclic graph (DAG).
Fig. 2
Fig. 2
Airway tree with assigned labels. Labels refer to segments, but are assigned to terminating branchpoint of respective segment. Drawing based on [1].
Fig. 3
Fig. 3
Vector notation used in population average.
Fig. 4
Fig. 4
Long false branches. a) “False” branches may be too long for fixed-length thresholding. b) Introducing parallel edges to bridge potential false branches.
Fig. 5
Fig. 5
Stepwise labeling. Reducing computing time by splitting the task into sub-problems. Segments labeled during a step are marked gray. The labels ‘s’ and ‘t’ mark start- and terminal-segments, respectively.
Fig. 6
Fig. 6
Examples of the fully automated labeling result on three different subjects (partial view of trees, showing carina and right upper lobe). Note that spurious branches do not negatively influence the labeling result. Also note the varying branching patterns for RB1, RB2, and RB3 among the different subjects. The labeling algorithm tolerates all possible variations very well.
See this image and copyright information in PMC

References

    1. Boyden EA. Segmental anatomy of the lungs. McGraw-Hill; 1955.
    1. Wood SA, Zerhouni EA, Hoford JD, Hoffman EA, Mitzner W. Measurement of three-dimensional lung tree structures by using computed tomography. Journal of Applied Physiology. 1995;79:1687–1697. - PubMed
    1. Pisupati C, Wolff L, Mitzner W, Zerhouni E. Tracking 3-D pulmonary tree structures. Mathematical Methods in Biomedical Image Analysis, 1996; Proceedings of the Workshop; Jun, 1996. pp. 160–169.
    1. Pisupati C, Wolff L, Mitzner W, Zerhouni E. Geometric Tree Matching with applications to 3D Lung Structures. ACM Symposium on Computational Geometry; Philadelphia, PA. Jun, 1996.
    1. Park Y. PhD dissertation. Osaka University, Japan: Department of Informatics and Mathematical Science; Jan, 2002. Registration of linear structures in 3-D medical images.

Publication types

MeSH terms