Conference proceeding
Generalizability of a deep learning airway segmentation algorithm to a blinded low-dose CT dataset
Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol.11596, pp.115963I-115963I-8
02/15/2021
DOI: 10.1117/12.2580224
Abstract
Chronic obstructive pulmonary disease (COPD) is a common inflammatory disease characterized by restricted lung airflow affecting over 300 million people worldwide. Quantitative computed tomography (CT) has become a benchmark for large multi-center pulmonary research studies for assessment of airway and parenchymal physiology and function towards understanding the occurrence and progression of the disease. Airway tree segmentation is a precursor for such approaches; but current industry-standard methods require manual post-segmentation correction to remove leakages and add missing airway branches. Recently, deep learning (DL) methods have gained popularity in medical image segmentation and outperformed traditional image processing methods due to their data-driven optimization schemes of multi-layered and multi-scale features. Generalizability of DL methods is a lingering concern and essential in multi-site CT-based pulmonary studies due to varying CT imaging settings at different sites. In this paper, we examine the generalizability of a recently developed fully automated DL-based airway segmentation method using low-dose chest CT images from the NELSON lung cancer screening study. The DL method was trained using high-dose chest CT scans from the Iowa cohort of COPDGene study at baseline visits and applied on blinded low-dose images. Results show the recent DL-based method is generalizable to blinded low-dose chest CT imaging, and it achieves branch-level accuracies of 100, 99.6, and 96.0% at segmental, sub-segmental, and sub-sub-segmental branches along the five clinically significant bronchial paths (RB1, RB4, RB10, LB1, and LB10).
Details
- Title: Subtitle
- Generalizability of a deep learning airway segmentation algorithm to a blinded low-dose CT dataset
- Creators
- Syed Ahmed Nadeem - University of IowaAlejandro P Comellas - University of IowaEric A Hoffman - University of IowaPunam K Saha - University of Iowa
- Contributors
- Ivana Išgum (Editor) - Amsterdam UMC (Netherlands)Bennett A Landman (Editor) - Vanderbilt University
- Resource Type
- Conference proceeding
- Publication Details
- Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol.11596, pp.115963I-115963I-8
- Publisher
- SPIE
- DOI
- 10.1117/12.2580224
- ISSN
- 1605-7422
- Language
- English
- Date published
- 02/15/2021
- Academic Unit
- ICTS; Electrical and Computer Engineering; Roy J. Carver Department of Biomedical Engineering; Internal Medicine; Pulmonary, Critical Care, and Occupational Medicine; Radiology
- Record Identifier
- 9984197530202771
Metrics
46 Record Views