Latent traits of lung tissue patterns in former smokers derived by dual channel deep learning in computed tomography images
Year: 2021
Type: article
Abstract: Chronic obstructive pulmonary disease (COPD) is a heterogeneous disease and the traditional variables extracted from computed tomography (CT) images may not be sufficient to describe all the topological features of lung tissues in COPD patients. We employed an unsupervised three-dimensional (3D) convolutional autoencoder (CAE)-feature constructor (FC) deep learning network to learn from CT data and derive tissue pattern-clusters jointly. We then applied exploratory factor analysis (EFA) to discover the unobserved latent traits (factors) among pattern-clusters. CT images at total lung capacity (TLC) and residual volume (RV) of 541 former smokers and 59 healthy non-smokers from the cohort of the SubPopulations and Intermediate Outcome Measures in the COPD Study (SPIROMICS) were analyzed. TLC and RV images were registered to calculate the Jacobian (determinant) values for all the voxels in TLC images. 3D Regions of interest (ROIs) with two data channels of CT intensity and Jacobian value were randomly extracted from training images and were fed to the 3D CAE-FC model. 80 pattern-clusters and 7 factors were identified. Factor scores computed for individual subjects were able to predict spirometry-measured pulmonary functions. Two factors which correlated with various emphysema subtypes, parametric response mapping (PRM) metrics, airway variants, and airway tree to lung volume ratio were discriminants of patients across all severity stages. Our findings suggest the potential of developing factor-based surrogate markers for new COPD phenotypes.
Source: Scientific Reports
Authors: Frank Li, Jiwoong Choi, Chunrui Zou, John D. Newell, Alejandro P. Comellas, Chang Hyun Lee, Hongseok Ko, R. Graham Barr, Eugene R. Bleecker, Christopher B. Cooper, Fereidoun Abtin, Igor Barjaktarevic, David Couper, MeiLan Han, Nadia N. Hansel, Richard E. Kanner, Robert Paine, Ella A. Kazerooni, Fernando J. Martinez, Wanda O’Neal, Stephen I. Rennard, Benjamin M. Smith, Prescott G. Woodruff, Eric A. Hoffman, Ching-Long Lin
Institutions: University of Iowa, University of Kansas, Seoul National University, Chungnam National University Sejong Hospital, Columbia University, University of Arizona, University of California, Los Angeles, University of North Carolina at Chapel Hill, University of Michigan, Johns Hopkins University, University of Utah, Cornell University, Weill Cornell Medicine, University of Nebraska Medical Center, McGill University Health Centre, Research Institute of the McGill University Health Centre, University of California, San Francisco
Language: English
Subfield: Pulmonary and Respiratory Medicine
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $1,990
Funders: National Research Foundation, Ministry of Environment, National Research Foundation of Korea, Ministry of Education, India, National Institutes of Health, Korea Environmental Industry and Technology Institute, National Heart, Lung, and Blood Institute, National Institute of Diabetes and Digestive and Kidney Diseases, National Institute of Environmental Health Sciences, National Center for Advancing Translational Sciences
Awards: G1476458040, Iowa Lung Imaging Training Program, An integrative statistics-guided image-based multi-scale lung model, G3148290576, G3782424196, G4085622990, G4582554841, G4923960971, Multi-center Structural & Functional Quantitative CT Pulmonary Phenotyping, SPIROMICS II: Biological underpinnings of COPD heterogeneity and progression, G7600354450, Airway Tree Subtyping on Large Cohorts of CT Images for COPD Risk, Large-Scale Computing and Visualization for Cardiopulmonary Imaging, Ultra-low Dose, High Speed, High Resolution, Multispectral, Multi-Source MDCT Sca, Environmental Health Sciences Research Center, Mentoring Research in Precision Medicine for Lung Disease, Airway trees in the Anthropocene: Defining resilient airway trees and identifying the candidate mechanisms and etiologic factors that increase susceptibility to tobacco smoke and air pollution, Precision Medicine Center for Cystic Fibrosis
OpenAlex ID: W3134620876