Logo image
Unsupervised Clustering Of Airway Tree Structures On High-Resolution CT: The Mesa Lung Study
Conference proceeding   Open access

Unsupervised Clustering Of Airway Tree Structures On High-Resolution CT: The Mesa Lung Study

Artur Wysoczanski, Elsa D Angelini, Benjamin M Smith, Eric A Hoffman, Grant T Hiura, Yifei Sun, R. Graham Barr and Andrew F Laine
2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Vol.2021-, pp.1568-1572
04/13/2021
DOI: 10.1109/ISBI48211.2021.9434172
url
https://www.ncbi.nlm.nih.gov/pmc/articles/11467910View
Open Access

Abstract

The morphology of the proximal human airway tree is highly variable in the general population, and known variants in airway branching patterns are associated with increased risk of COPD and with polymorphisms in growth factors involved in pulmonary development. Variation in the geometry and topology of the airway tree remains incompletely characterized, and their clinical implications are not yet understood. In this work, we present an approach to unsupervised clustering of airway tree structures in Billera-Holmes-Vogtmann tree-space. We validate our pipeline on synthetic airway tree data, and apply our algorithm to identify reproducible and morphologically distinct airway tree subtypes in the MESA Lung CT cohort.
Computed Tomography Geometry Morphology Sociology Airway Morphology Clustering algorithms Community Detection Computational Anatomy Lung Lung CT Pipelines

Details

Metrics

Logo image