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

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.

Novel Subtypes of Pulmonary Emphysema Based on Spatially-Informed Lung Texture Learning: The Multi-Ethnic Study of Atherosclerosis (MESA) COPD Study

“…After adjusting for FEV1, there are still sLTPs showing significant correlations with MRC dyspnea scale, 6MWT total distance, baseline and post-6MWT oximetry. Overall, our correlation levels compare well with [ 35 ] performed on a similar cohort size, but with highest COPD-prevalence, while reporting fewer significant positive correlations when proposing 7 radiological emphysema subtypes (called “factors”) learned from 80 emphysema visual patterns. Correlations with standard emphysema subtypes, using similar models, were studied for the same population in [ 4 ].…”

Community-Acquired Pneumonia Progressing to Necrotizing Pneumonia Due to Congenital Anatomical Abnormalities in the Lung

“…Biswas et al reported the prevalence of these lobes as 2.17% and 1.08%, respectively [ 5 ]. Patients with an accessory airway branch have been associated with a 1.64 higher risk of chronic obstructive pulmonary disease (COPD) and bronchitis [ 6 - 7 ].…”

Longitudinal Imaging-Based Clusters in Former Smokers of the COPD Cohort Associate with Clinical Characteristics: The SubPopulations and Intermediate Outcome Measures in COPD Study (SPIROMICS)

“…Deep learning based tissue-pattern phenotypes can be further combined with qCT imaging-based variable for subtyping. 55 Identification of longitudinal COPD subgroups may help us understand the path of disease progression and provide prognostic information to help determine more appropriate, patient-oriented therapies.…”