Computational analysis of HRCT images for characterization and differentiation of ILD and COPD

Several image metrics have been proposed for pulmonary assessment via thoracic high-resolution computed tomography (HRCT) for various pathologies. This paper describes a systematic analysis of several such metrics for differentiating between interstitial lung disease (ILD) and chronic obstructive pulmonary disease (COPD). HRCT inspiratory and expiratory images for 14 patients with ILD and 11 patients with COPD were acquired retrospectively. Data from pulmonary function testings (PFT) were also acquired retrospectively for each patient. Using a discriminative subset of image metrics, our study shows that computational analysis of thoracic HRCT images permits differentiation between ILD and COPD groups.