NAG-Net: Nested attention-guided learning for segmentation of carotid lumen-intima interface and media-adventitia interface.

Cardiovascular diseases (CVD), as the leading cause of death in the world, poses a serious threat to human health. The segmentation of carotid Lumen-intima interface (LII) and Media-adventitia interface (MAI) is a prerequisite for measuring intima-media thickness (IMT), which is of great significance for early screening and prevention of CVD. Despite recent advances, existing methods still fail to incorporate task-related clinical domain knowledge and require complex post-processing steps to obtain fine contours of LII and MAI. In this paper, a nested attention-guided deep learning model (named NAG-Net) is proposed for accurate segmentation of LII and MAI. The NAG-Net consists of two nested sub-networks, the Intima-Media Region Segmentation Network (IMRSN) and the LII and MAI Segmentation Network (LII-MAISN). It innovatively incorporates task-related clinical domain knowledge through the visual attention map generated by IMRSN, enabling LII-MAISN to focus more on the clinician's visual focus region under the same task during segmentation. Moreover, the segmentation results can directly obtain fine contours of LII and MAI through simple refinement without complicated post-processing steps. To further improve the feature extraction ability of the model and reduce the impact of data scarcity, the strategy of transfer learning is also adopted to apply the pretrained weights of VGG-16. In addition, a channel attention-based encoder feature fusion block (EFFB-ATT) is specially designed to achieve efficient representation of useful features extracted by two parallel encoders in LII-MAISN. Extensive experimental results have demonstrated that our proposed NAG-Net outperformed other state-of-the-art methods and achieved the highest performance on all evaluation metrics.

Regional and demographic variations of Carotid artery Intima and Media Thickness (CIMT): A Systematic review and meta-analysis.

BACKGROUND AND OBJECTIVE: Carotid artery intima media thickness (CIMT) is a strong predictor of Coronary Heart Disease (CHD) and independent phenotype of early atherosclerosis. The global variation of CIMT and its demographic association is yet unclear. We evaluated regional variations of CIMT based on WHO regions and assessed the differences by age and sex. METHODS: A systematic search was conducted on studies published between 1980 January up to December 2020. PubMed, Oxford Medicine Online, EBSCO, Taylor & Francis, Oxford University Press and Embase data bases were used for searching. Supplementary searches were conducted on the Web of Science and Google Scholar. Grey literature was searched in "Open Grey" website. The two major criteria used were "adults" and "carotid intima media". The search strategy for PubMed was created first and then adapted for the Oxford Medicine Online, EBSCO, Taylor & Francis, Oxford University Press and Embase databases. Covidence software (Veritas Health Innovation, Melbourne, Australia; http://www.covidence.org) was used to manage the study selection process. Meta-analyses were done using the random-effects model. An I2 ≥ 50% or p< 0:05 were considered to indicate significant heterogeneity. RESULTS: Of 2847 potential articles, 46 eligible articles were included in the review contributing data for 49 381 individuals (mean age: 55.6 years, male: 55.8%). The pooled mean CIMT for the non-CHD group was 0.65mm (95%CI: 0.62-0.69). There was a significant difference in the mean CIMT between regions (p = 0.04). Countries in the African (0.72mm), American (0.71mm) and European (0.71mm) regions had a higher pooled mean CIMT compared to those in the South East Asian (0.62mm), West Pacific (0.60mm) and Eastern Mediterranean (0.60mm) regions. Males had a higher pooled mean CIMT of 0.06mm than females in the non CHD group (p = 0.001); there were also regional differences. The CHD group had a significantly higher mean CIMT than the non-CHD group (difference = 0.23mm, p = 0.001) with regional variations. Carotid artery segment-specific-CIMT variations are present in this population. Older persons and those having CHD group had significantly thicker CIMTs. CONCLUSIONS: CIMT varies according to region, age, sex and whether a person having CHD. There are significant regional differences of mean CIMT between CHD and non-CHD groups. Segment specific CIMT variations exist among regions. There is an association between CHD and CIMT values.

Carotid intima-media thickness and flow-mediated dilation do not predict acute in-hospital outcomes in patients hospitalized with COVID-19.

Studies have suggested a potential role of endothelial dysfunction and atherosclerosis in the pathophysiology of COVID-19. Herein, we tested whether brachial flow-mediated dilation (FMD) and carotid intima-media thickness (cIMT) measured upon hospital admission are associated with acute in-hospital outcomes in patients hospitalized with COVID-19. A total of 211 patients hospitalized with COVID-19 were submitted to assessments of FMD and mean and maximum cIMT (cIMTmean and cIMTmax) within the first 72 h of hospital admission. Study primary outcome was a composite of intensive care unit admission, mechanical ventilation, or death during the hospitalization. These outcomes were also considered independently. Thrombotic events were included as a secondary outcome. Odds ratios (ORs) and confidence intervals (CIs) were calculated using unadjusted and adjusted multivariable logistic regression models. Eighty-eight (42%) participants demonstrated at least one of the composite outcomes. cIMTmean and cIMTmax were predictors of mortality and thrombotic events in the univariate analysis (cIMTmean and mortality: unadjusted OR 12.71 [95% CI 1.71-94.48]; P = 0.014; cIMTmean and thrombotic events: unadjusted OR 11.94 [95% CI 1.64-86.79]; P = 0.015; cIMTmax and mortality: unadjusted OR 8.47 [95% CI 1.41-51.05]; P = 0.021; cIMTmax and thrombotic events: unadjusted OR 12.19 [95% CI 2.03-73.09]; P = 0.007). However, these associations were no longer present after adjustment for potential confounders (P > 0.05). In addition, FMD% was not associated with any outcome. In conclusion, cIMT and FMD are not independent predictors of clinical outcomes in patients hospitalized with COVID-19. These results suggest that subclinical atherosclerosis and endothelial dysfunction may not be the main drivers of COVID-19 complications in patients hospitalized with COVID-19.NEW & NOTEWORTHY Studies have suggested a role of endothelial dysfunction and atherosclerosis in COVID-19 pathophysiology. In this prospective cohort study, we assessed the prognostic value of carotid intima-media thickness (IMT) and flow-mediated dilation (FMD) in patients with COVID-19. Carotid IMT and FMD were not independent predictors of major outcomes. These results suggest that other risk factors may be the main drivers of clinical outcomes in patients with COVID-19.

Intraluminal Carotid Artery Thrombus in COVID-19: Another Danger of Cytokine Storm?

Coronavirus disease 2019 (COVID-19) is associated with a severe inflammatory response. Inflammation affects atherosclerotic plaque vulnerability and promotes a thrombogenic environment. We report a series of 6 patients with COVID-19 with acute ischemic stroke due to intraluminal carotid artery thrombus presenting during an 8-day period. Six patients were included (5 men) with a mean age of 65.8 years (range, 55-78 years). COVID-19 was diagnosed by detection of Severe Acute Respiratory Syndrome coronavirus 2 in 5 patients and was presumed due to typical clinical and imaging findings in 1 patient. All patients had vascular risk factors including diabetes (83%), hyperlipidemia (100%), and smoking (17%). Four patients presented with large infarcts with initial NIHSS scores of 24-30. During their hospitalization, all patients had elevated D-dimer and C-reactive protein levels, 5 patients had elevated lactate dehydrogenase and ferritin levels, 3 had elevated interleukin-6 levels, and 2 had elevated troponin levels. Inflammation related to COVID-19 may result in rupture of vulnerable atherosclerotic plaques, resulting in thrombosis and acute ischemic stroke.