Preacinar Arterial Dilation Mediates Outcomes of Quantitative Interstitial Abnormalities in COPDGene.

RATIONALE: Quantitative interstitial abnormalities (QIA) are a computed tomography (CT) measure of early parenchymal lung disease associated with worse clinical outcomes including exercise capacity and symptoms. The presence of pulmonary vasculopathy in QIA and its role in the QIA-outcome relationship is unknown. OBJECTIVES: To quantify radiographic pulmonary vasculopathy in quantitative interstitial abnormalities (QIA) and determine if this vasculopathy mediates the QIA-outcome relationship. METHODS: Ever-smokers with QIA, outcome, and pulmonary vascular mediator data were identified from the COPDGene cohort. CT-based vascular mediators were: right ventricle-to-left ventricle ratio (RV/LV), pulmonary artery-to-aorta ratio (PA/Ao), and pre-acinar intraparenchymal arterial dilation (PA volume 5-20mm2 in cross-sectional area, normalized to total arterial volume). Outcomes were: six-minute walk distance (6MWD) and modified Medical Council Research Council (mMRC) Dyspnea score ≥2. Adjusted causal mediation analyses were used to determine if the pulmonary vasculature mediated the QIA effect on outcomes. Associations of pre-acinar arterial dilation with select plasma biomarkers of pulmonary vascular dysfunction were examined. MAIN RESULTS: Among 8,200 participants, QIA burden correlated positively with vascular damage measures including pre-acinar arterial dilation. Pre-acinar arterial dilation mediated 79.6% of the detrimental impact of QIA on 6MWD (56.2-100%, p<0.001). PA/Ao was a weak mediator and RV/LV was a suppressor. Similar results were observed in the QIA-mMRC relationship. Pre-acinar arterial dilation correlated with increased pulmonary vascular dysfunction biomarker levels including angiopoietin-2 and NT-proBNP. CONCLUSIONS: Parenchymal quantitative interstitial abnormalities (QIA) deleteriously impact outcomes primarily through pulmonary vasculopathy. Pre-acinar arterial dilation may be a novel marker of pulmonary vasculopathy in QIA.

Functional-Consistent CycleGAN for CT to Iodine Perfusion Map Translation.

Image-to-image translation from a source to a target domain by means of generative adversarial neural network (GAN) has gained a lot of attention in the medical imaging field due to their capability to learn the mapping characteristics between different modalities. CycleGAN has been proposed for image-to-image translation with unpaired images by means of a cycle-consistency loss function, which is optimized to reduce the difference between the image reconstructed from the synthetically-generated domain and the original input. However, CycleGAN inherently implies that the mapping between both domains is invertible, i.e., given a mapping G (forward cycle) from domain A to B, there is a mapping F (backward cycle) that is the inverse of G. This is assumption is not always true. For example, when we want to learn functional activity from structural modalities. Although it is well-recognized the relation between structure and function in different physiological processes, the problem is not invertible as the original modality cannot be recovered from a given functional response. In this paper, we propose a functional-consistent CycleGAN that leverages the usage of a proxy structural image in a third domain, shared between source and target, to help the network learn fundamental characteristics while being cycle consistent. To demonstrate the strength of the proposed strategy, we present the application of our method to estimate iodine perfusion maps from contrast CT scans, and we compare the performance of this technique to a traditional CycleGAN framework.

DEEP-LEARNING STRATEGY FOR PULMONARY ARTERY-VEIN CLASSIFICATION OF NON-CONTRAST CT IMAGES.

Artery-vein classification on pulmonary computed tomography (CT) images is becoming of high interest in the scientific community due to the prevalence of pulmonary vascular disease that affects arteries and veins through different mechanisms. In this work, we present a novel approach to automatically segment and classify vessels from chest CT images. We use a scale-space particle segmentation to isolate vessels, and combine a convolutional neural network (CNN) to graph-cut (GC) to classify the single particles. Information about proximity of arteries to airways is learned by the network by means of a bronchus enhanced image. The methodology is evaluated on the superior and inferior lobes of the right lung of twenty clinical cases. Comparison with manual classification and a Random Forests (RF) classifier is performed. The algorithm achieves an overall accuracy of 87% when compared to manual reference, which is higher than the 73% accuracy achieved by RF.