Latent traits of lung tissue patterns in former smokers derived by dual channel deep learning in computed tomography images.

TitleLatent traits of lung tissue patterns in former smokers derived by dual channel deep learning in computed tomography images.
Publication TypePublication
Year2021
AuthorsLi F, Choi J, Zou C, Newell JD, Comellas AP, Lee CHyun, Ko H, R Barr G, Bleecker ER, Cooper CB, Abtin F, Barjaktarevic I, Couper D, Han ML, Hansel NN, Kanner RE, Paine R, Kazerooni EA, Martinez FJ, O'Neal W, Rennard SI, Smith BM, Woodruff PG, Hoffman EA, Lin C-L
JournalSci Rep
Volume11
Issue1
Pagination4916
Date Published2021 03 01
ISSN2045-2322
KeywordsAdult, Aged, Case-Control Studies, Cohort Studies, Female, Humans, Lung, Male, Middle Aged, Pulmonary Disease, Chronic Obstructive, Smokers, Tomography, X-Ray Computed
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.

DOI10.1038/s41598-021-84547-5
Alternate JournalSci Rep
PubMed ID33649381
PubMed Central IDPMC7921389
Grant ListP30 ES005605 / ES / NIEHS NIH HHS / United States
T32 HL144461 / HL / NHLBI NIH HHS / United States
K24 HL137013 / HL / NHLBI NIH HHS / United States
U01 HL137880 / HL / NHLBI NIH HHS / United States
P30 DK054759 / DK / NIDDK NIH HHS / United States
R01 HL130506 / HL / NHLBI NIH HHS / United States
R01-HL112986 / NH / NIH HHS / United States
MS#: 
MS200
Manuscript Full Title: 
Latent traits of lung tissue patterns in former smokers derived by dual channel deep learning in computed tomography images.
Manuscript Lead/Corresponding Author Affiliation: 
Clinical Center: Iowa (University of Iowa)
ECI: 
Manuscript Status: 
Published and Public