Case Studies in Physiology: Temporal variations of the lung parenchyma and vasculature in asymptomatic COVID-19 pneumonia: a multispectral CT assessment.

This study reports systematic longitudinal pathophysiology of lung parenchymal and vascular effects of asymptomatic COVID-19 pneumonia in a young, healthy never-smoking male. Inspiratory and expiratory noncontrast along with contrast dual-energy computed tomography (DECT) scans of the chest were performed at baseline on the day of acute COVID-19 diagnosis (day 0), and across a 90-day period. Despite normal vital signs and pulmonary function tests on the day of diagnosis, the CT scans and corresponding quantification metrics detected abnormalities in parenchymal expansion based on image registration, ground-glass (GGO) texture (inflammation) as well as DECT-derived pulmonary blood volume (PBV). Follow-up scans on day 30 showed improvement in the lung parenchymal mechanics as well as reduced GGO and improved PBV distribution. Improvements in lung PBV continued until day 90. However, the heterogeneity of parenchymal mechanics and texture-derived GGO increased on days 60 and 90. We highlight that even asymptomatic COVID-19 infection with unremarkable vital signs and pulmonary function tests can have measurable effects on lung parenchymal mechanics and vascular pathophysiology, which may follow apparently different clinical courses. For this asymptomatic subject, post COVID-19 regional mechanics demonstrated persistent increased heterogeneity concomitant with return of elevated GGOs, despite early improvements in vascular derangement.NEW & NOTEWORTHY We characterized the temporal changes of lung parenchyma and microvascular pathophysiology from COVID-19 infection in an asymptomatic young, healthy nonsmoking male using dual-energy CT. Lung parenchymal mechanics and microvascular disease followed different clinical courses. Heterogeneous perfused blood volume became more uniform on follow-up visits up to 90 days. However, post COVID-19 mechanical heterogeneity of the lung parenchyma increased after apparent improvements in vascular abnormalities, even with normal spirometric indices.

CT image segmentation for inflamed and fibrotic lungs using a multi-resolution convolutional neural network.

The purpose of this study was to develop a fully-automated segmentation algorithm, robust to various density enhancing lung abnormalities, to facilitate rapid quantitative analysis of computed tomography images. A polymorphic training approach is proposed, in which both specifically labeled left and right lungs of humans with COPD, and nonspecifically labeled lungs of animals with acute lung injury, were incorporated into training a single neural network. The resulting network is intended for predicting left and right lung regions in humans with or without diffuse opacification and consolidation. Performance of the proposed lung segmentation algorithm was extensively evaluated on CT scans of subjects with COPD, confirmed COVID-19, lung cancer, and IPF, despite no labeled training data of the latter three diseases. Lobar segmentations were obtained using the left and right lung segmentation as input to the LobeNet algorithm. Regional lobar analysis was performed using hierarchical clustering to identify radiographic subtypes of COVID-19. The proposed lung segmentation algorithm was quantitatively evaluated using semi-automated and manually-corrected segmentations in 87 COVID-19 CT images, achieving an average symmetric surface distance of [Formula: see text] mm and Dice coefficient of [Formula: see text]. Hierarchical clustering identified four radiographical phenotypes of COVID-19 based on lobar fractions of consolidated and poorly aerated tissue. Lower left and lower right lobes were consistently more afflicted with poor aeration and consolidation. However, the most severe cases demonstrated involvement of all lobes. The polymorphic training approach was able to accurately segment COVID-19 cases with diffuse consolidation without requiring COVID-19 cases for training.