Chronic obstructive pulmonary disease (COPD) is a chronic inflammatory lung disease that causes obstructed airflow from the lungs. COPD is the fourth leading cause of death in the United States and currently affects 328 million people worldwide with a projected increase in healthcare costs from $32 billion in 2010 to $49 billion in 2020. Quantitative computed tomography (CT)-based characterizations of bronchial metrics, such as airway lumen area and wall thickness, and parenchymal characterizations of emphysema and air trapping, are garnering research interest to help understand the pathophysiology and mechanism of several lung diseases’ occurrence and progression. Airway segmentation and anatomical branch labeling allow spatial matching and referencing across individuals in large multi-center population-based studies such as, COPDGene, SPIROMICS, CanCOLD, MESA Lung, and SARP and has led to novel insights between COPD and airway phenotypes.
New theory and algorithms to automatically segment the human airway tree using thoracic CT imaging and label clinically significant segmental bronchi are developed and evaluated. First, an image processing framework, called freeze-and-grow, is developed for airway tree segmentation which uses a multi-parametric approach to iteratively capture finer details of the airway tree while detection and correction for segmentation leakages. Then, deep learning is used to enhance the airway lumen regions in the chest CT images to address the inherent challenges in CT intensity-based airway tree segmentation while improving efficiency. The new airway segmentation methods outperform an industry standard method requiring manual intervention as well as recently developed automated methods which use deep learning. Lastly, an automated algorithm for anatomical airway branches is developed and evaluated which uses two stage machine learning and hierarchical features to compartmentalize the labeling process based on the airway tree branching anatomy.
The methods developed in this thesis provides a framework to assess the airway tree for large longitudinal or cross-sectional studies and explore the roles played by resulting bronchial metrics in lung pathology. The major contributions of this thesis include: (1) development of a multiparametric freeze-and-grow airway segmentation algorithm; (2) integration of a deep learning-based airway lumen enhancement into the freeze-and-grow airway segmentation algorithm; (3) evaluation of the new airway segmentation methods with industry and recent deep learning-based standard airway segmentation methods on multi-center COPD study data; (4) development of a new airway anatomic branch labeling algorithm using two step machine learning and novel hierarchical topologic and geometric tree features; (5) applying the developed on data from a multi-center COPD study.
|Advisor:||Saha, Punam K.|
|Commitee:||Saha, Punam K., Comellas, Alejandro P., Hoffman, Eric A., Reinhardt, Joseph M., Sonka, Milan|
|School:||The University of Iowa|
|Department:||Electrical and Computer Engineering|
|School Location:||United States -- Iowa|
|Source:||DAI-B 82/1(E), Dissertation Abstracts International|
|Subjects:||Electrical engineering, Biomedical engineering, Computer science|
|Keywords:||Airway tree labeling, Airway tree segmentation, Computed tomography, Deep learning, Image processing, Segmentation|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be