Atherosclerosis inflammation and burden in young adult smokers and vapers measured by PET/MR.

BACKGROUND AND AIMS: Electronic cigarette (EC) use is popular among youth, touted as a safer alternative to smoking and promoted as a tool to aid in smoking cessation. EC cardiovascular safety however is not well established. The aim of this study was to examine cardiovascular consequences of EC use by evaluating their effect on the entire atherosclerotic cascade in young adults using noninvasive combined positron emission tomography (PET)/magnetic resonance imaging (MR) and comparing EC use with age matched smokers of traditional cigarettes and nonsmoking controls. METHODS: Carotid PET/MR was applied to look at vascular inflammation (18-fluorodeoxyglucose (FDG)-PET) and plaque burden (multi-contrast MR of vessel wall) from 60 18-30 year-old subjects (20 electronic cigarette users, 20 traditional smokers and 20 nonsmokers). RESULTS: Groups were reasonably well balanced in terms of age, gender, demographics, cardiovascular risk and most biomarkers. There were no differences in vascular inflammation as measured by 18-FDG-PET target to background ratios (TBR) between EC users, traditional cigarette smokers and nonsmokers. However, measures of carotid plaque burden - wall area, normalized wall index, and wall thickness - measured from MR were significantly higher in both traditional smokers and EC users than in nonsmokers. CONCLUSIONS: Young adult EC users, smokers and nonsmokers in our study did not exhibit vascular inflammation as defined by 18-F-FDG-PET TBR max, but smokers and EC users had significantly more carotid plaque burden compared to matched nonsmokers. Results could indicate that vaping does not cause an increase in vascular inflammation as measured by FDG-PET.

Segmentation of carotid arterial walls using neural networks.

BACKGROUND: Automated, accurate, objective, and quantitative medical image segmentation has remained a challenging goal in computer science since its inception. This study applies the technique of convolutional neural networks (CNNs) to the task of segmenting carotid arteries to aid in the assessment of pathology. AIM: To investigate CNN's utility as an ancillary tool for researchers who require accurate segmentation of carotid vessels. METHODS: An expert reader delineated vessel wall boundaries on 4422 axial T2-weighted magnetic resonance images of bilateral carotid arteries from 189 subjects with clinically evident atherosclerotic disease. A portion of this dataset was used to train two CNNs (one to segment the vessel lumen and the other to segment the vessel wall) with the remaining portion used to test the algorithm's efficacy by comparing CNN segmented images with those of an expert reader. RESULTS: Overall quantitative assessment between automated and manual segmentations was determined by computing the DICE coefficient for each pair of segmented images in the test dataset for each CNN applied. The average DICE coefficient for the test dataset (CNN segmentations compared to expert's segmentations) was 0.96 for the lumen and 0.87 for the vessel wall. Pearson correlation values and the intra-class correlation coefficient (ICC) were computed for the lumen (Pearson = 0.98, ICC = 0.98) and vessel wall (Pearson = 0.88, ICC = 0.86) segmentations. Bland-Altman plots of area measurements for the CNN and expert readers indicate good agreement with a mean bias of 1%-8%. CONCLUSION: Although the technique produces reasonable results that are on par with expert human assessments, our application requires human supervision and monitoring to ensure consistent results. We intend to deploy this algorithm as part of a software platform to lessen researchers' workload to more quickly obtain reliable results.