Background: Carotid plaques are major risk factors for stroke. Carotid ultrasound can help to assess the risk and incidence rate of stroke. However, large-scale carotid artery screening is time-consuming and laborious, the diagnostic results inevitably involve the subjectivity of the diagnostician to a certain extent. Deep learning demonstrates the ability to solve the aforementioned challenges. Thus, we attempted to develop an automated algorithm to provide a more consistent and objective diagnostic method and to identify the presence and stability of carotid plaques using deep learning.Methods: A total of 3,860 ultrasound images from 1,339 participants who underwent carotid plaque assessment between January 2021 and March 2023 at the Shanghai Eighth People’s Hospital were divided into a 4:1 ratio for training and internal testing. The external test included 1,564 ultrasound images from 674 participants who underwent carotid plaque assessment between January 2022 and May 2023 at Xinhua Hospital affiliated with Dalian University. Deep learning algorithms, based on the fusion of a bilinear convolutional neural network with a residual neural network (BCNN-ResNet), were used for modeling to detect carotid plaques and assess plaque stability. We chose AUC as the main evaluation index, along with accuracy, sensitivity, and specificity as auxiliary evaluation indices.Results: Modeling for detecting carotid plaques involved training and internal testing on 1,291 ultrasound images, with 617 images showing plaques and 674 without plaques. The external test comprised 470 ultrasound images, including 321 images with plaques and 149 without. Modeling for assessing plaque stability involved training and internal testing on 764 ultrasound images, consisting of 494 images with unstable plaques and 270 with stable plaques. The external test was composed of 279 ultrasound images, including 197 images with unstable plaques and 82 with stable plaques. For the task of identifying the presence of carotid plaques, our model achieved an AUC of 0.989 (95% CI: 0.840, 0.998) with a sensitivity of 93.2% and a specificity of 99.21% on the internal test. On the external test, the AUC was 0.951 (95% CI: 0.962, 0.939) with a sensitivity of 95.3% and a specificity of 82.24%. For the task of identifying the stability of carotid plaques, our model achieved an AUC of 0.896 (95% CI: 0.865, 0.922) on the internal test with a sensitivity of 81.63% and a specificity of 87.27%. On the external test, the AUC was 0.854 (95% CI: 0.889, 0.830) with a sensitivity of 68.52% and a specificity of 89.49%.Conclusion: Deep learning using BCNN-ResNet algorithms based on routine ultrasound images could be useful for detecting carotid plaques and assessing plaque instability.

Background: Blood flowing in the arterial lumen acts on the surface of the vessel wall to form wall shear stress (WSS). To date, there has been limited research on the utility of non-invasive technology in the accurate quantification of carotid WSS in patients with hypertension (HP).Objective: The present study aimed to explore the usage of vascular vector flow mapping (VFM) in the quantitative assessment of carotid WSS in hypertensive patients at an early stage and to validate its clinical utility.Methods: A total of 50 individuals confirmed without carotid plaques were grouped into a HP group (n = 25) and a control (CON) group (n = 25) according to blood pressure. An ALOKA LISENDO 880 Color Doppler Ultrasound with a L441 3–15 MHZ probe was used to obtain a longitudinal section scan to determine the regions of interests (ROIs) of the common carotid artery. VFM-based WSS measurements were obtained by selecting the ROI with optimal image quality from three full cardiac cycles. WSS-derived measurements, including WSS_max, WSS_min, and WSS_mean, were analyzed and compared between the HP and CON groups. In addition, the correlations between WSS-derived measurements and the carotid artery intima-media thickness (IMT) were also analyzed.Results: There were significant statistical differences in WSS_max and WSS_mean between patients in the HP and CON groups. Specifically, the HP group had significantly decreased WSS_max and WSS_mean compared to the CON group (WSS_max: 1.781 ± 0.305 Pa vs. 2.286 ± 0.257 Pa; WSS_mean: 1.276 ± 0.333 Pa vs. 1.599 ± 0.293 Pa, both p < 0.001). However, there was no statistical difference in WSS_min between the groups (0.79 ± 0.36 vs. 0.99 ± 0.42, p = 0.080). Additionally, Spearman’s correlation analysis indicated that the WSS-derived parameters were negatively correlated with the IMT (p < 0.001).Conclusion: Vascular VFM technology shows promising results in the quantitative assessment of difference in hemodynamics of the vascular flow field between patients with HP and normal controls. Difference in WSS may serve as a potential predictor for the development of arteriosclerosis risks.

Background: The association between Estradiol (E2) levels and abdominal aortic calcification (AAC) in postmenopausal women remains unclear.Methods: 614 postmenopausal women from the 2013-2014 NHANES survey cycle were included in this study. The study population was divided into 3 groups according to E2 tertiles: Tertile1 (2.12-3.57pg/mL), Tertile2 (3.60-7.04pg/mL), and Tertile3 (7.06-38.4pg/mL). Estrogen concentration data were natural logarithmically transformed. A Kauppila score > 5 was regarded as prominent arterial calcification and was used to define (EAAC). Logistic regression models were used to assess the association between E2 levels and EAAC prevalence. Subgroup analyses were performed to test whether the association between E2 levels and EAAC prevalence was consistent in different groups. Sensitivity analyses tested the stability of the model in women older than 45 years.Results: EAAC prevalence was significantly higher in Tertile1 (16.6%) than in Tertile2 (9.8%) and Tertile3 (8.3%). On a continuous scale, the adjusted model showed a 58% [OR (95%CI), 1.58 (1.02, 2.54)] increase in the risk of EAAC prevalence for per unit decrease in ln(E2). On a categorical scale, the adjusted model showed that Tertile1 and Tertile2 were 2.55 [OR (95%CI), 2.55 (1.10, 5.92)] and 1.31[OR (95%CI), 1.31(1.03, 2.57)] times higher risk of suffering from EAAC than Tertile3, respectively.Conclusion: This study found that a higher prevalence of AAC in postmenopausal women is closely associated with lower serum E2 levels. Our research further underscores the importance of E2 in maintaining cardiovascular health in postmenopausal women and suggests that monitoring E2 levels may aid in the early prevention and management of AAC and related cardiovascular diseases.

Original Article Age-related wall shear stress changes assessed by vascular vector flow mapping in the carotid arteries of healthy adults: a cross-sectional study Lan He, Yundan Cai, Yuhong Feng, Tienan Feng, Filippo Cademartiri, E Shen