Utilizing artificial intelligence (AI) technology for the segmentation of plaques on ultrasound images to evaluate the stability of carotid artery plaques and analyze its diagnostic accuracy in differentiating vulnerable plaques from stable ones. A retrospective study was conducted on 202 patients with ischemic stroke, who were divided into vulnerable plaque group (85 cases) and stable plaque group (117 cases) based on the results of carotid color Doppler ultrasound examination. From the vulnerable plaque group, 63 cases were randomly selected as the modeling group and 22 cases as the validation group; similarly, from the stable plaque group, 87 cases were randomly selected as the modeling group and 30 cases as the validation group. Based on the ultrasound images of the modeling group, plaques were segmented using artificial intelligence technology, and 1414 radiomics features were extracted. These features were then subjected to dimensionality reduction and feature selection using the least absolute shrinkage and selection operator (LASSO) method. Subsequently, a Support Vector Machine (SVM) model was constructed and validated using the selected features. The sensitivity, specificity, and Area Under the Curve (AUC) of the model were evaluated through the analysis of the receiver operating characteristic (ROC) curve. A total of 43 radiomics feature parameters were selected by the LASSO method. The training group for the SVM model had an AUC of 89.42% (95% CI: 80.74-98.10%), sensitivity of 79.84%, and specificity of 93.10%, while the validation group had an AUC of 82.73% (95% CI: 71.64-93.81%), sensitivity of 81.82%, and specificity of 80.00%. The use of artificial intelligence technology for the segmentation of plaques in ultrasound images, coupled with the analysis of radiomics models, can efficiently distinguish the stability of carotid artery plaques, providing a diagnostic basis for the clinical prediction of ischemic stroke. Not applicable.

Previous research has shown that blood flow abnormalities affect major depressive disorder (MDD) from multiple perspectives. Therefore, this study aims to investigate the relationship between middle cerebral artery (MCA) blood flow velocity parameters and clinical symptom scores (Hamilton Depression Rating Scale [HAMD] and Montgomery–Åsberg Depression Rating Scale [MADRS]) in patients with MDD. We compared the MCA blood flow velocity parameters, including peak systolic velocity (MCA-PSV), end-diastolic velocity (MCA-EDV), and mean velocity (MCA-MV), between 50 MDD patients and 50 control subjects. Additionally, we analyzed the correlation between these parameters and HAMD and MADRS scores. Hemodynamic parameters such as pulsatility index and resistance index were also compared between the 2 groups. MCA-PSV, MCA-EDV, and MCA-MV were significantly lower in MDD patients compared to the control group, while pulsatility index and resistance index were significantly higher. Correlation analysis revealed that MCA-PSV, MCA-EDV, and MCA-MV were significantly negatively correlated with HAMD and MADRS scores in MDD patients, indicating that cerebral blood flow velocity decreases as depressive symptoms worsen. Furthermore, regression analysis confirmed the negative relationship between blood flow velocity parameters and clinical symptom scores. The results of this study suggest that the reduction in cerebral blood flow velocity in MDD patients may be associated with the severity of depressive symptoms. This finding provides new insights into the pathophysiological mechanisms of MDD and offers a potential theoretical basis for developing depression treatment strategies based on cerebral blood flow velocity parameters.

Ultrasound imaging is vital for diagnosing carotid artery vascular lesions, highlighting the importance of accurately segmenting lumens in ultrasound images to prevent, diagnose and treat vascular diseases. However, noise artifacts, blood residue and discontinuous lumens significantly affect segmentation accuracy. To achieve accurate lumen segmentation in low-quality images, we propose a novel segmentation algorithm which is guided by an adaptively generated shape prior. To tackle the above challenges, we introduce a shape-prior-based segmentation method for carotid artery lumen walls. The shape prior in this study is adaptively generated based on the evolutionary trend of vessel growth. Shape priors guide and constrain the active contour, resulting in precise segmentation. The efficacy of the proposed model was confirmed using 247 carotid artery ultrasound images, with experimental results showing an average Dice coefficient of 92.38%, demonstrating superior segmentation performance compared to existing mathematical models. Our method can quickly and effectively perform accurate lumen segmentation on low-quality carotid artery ultrasound images, which is of great significance for the diagnosis of cardiovascular and cerebrovascular diseases.

Objective: To investigate the diagnostic efficacy of thromboelastography (TEG) combined with conventional coagulation tests for lower extremity deep vein thrombosis (DVT) following cerebrovascular surgery. Methods: This single-center retrospective cohort study evaluated 187 patients who underwent open cerebrovascular surgery at Nanjing Brain Hospital between January 2024 and February 2026. TEG parameters (R, K, Angle, MA) and conventional coagulation indices (PT, APTT, FIB, D-dimer) were extracted preoperatively and on postoperative day 3. Bilateral lower extremity ultrasonography performed within 7 days postoperatively served as the gold standard for DVT diagnosis. Multivariable logistic regression was utilized to identify independent predictors, and receiver operating characteristic (ROC) curves were analyzed to assess diagnostic performance. Results: The postoperative DVT incidence was 46.5% (87/187). Patients in the DVT group were significantly older (median: 67.0 vs. 60.5 years, p = 0.001) and exhibited a higher prevalence of comorbid hypertension (66.7% vs. 46.0%, p = 0.007). Univariate analysis showed that the postoperative Angle was significantly larger in the DVT group (72.3° vs. 69.4°, p = 0.001), and the D-dimer level was also significantly elevated (812 μg/L vs. 254 μg/L, p < 0.001). Multivariable logistic regression identified age (OR = 1.036, 95% CI: 1.006–1.066), Angle (OR = 1.107, 95% CI: 1.028–1.192), D-dimer (OR = 1.078 per 100 μg/L increase, 95% CI: 1.036–1.120), and hypertension (OR = 2.678, 95% CI: 1.098–4.724) as independent predictors of postoperative DVT. ROC curve analysis indicated that the AUCs for Angle, D-dimer, and the combined model were 0.638, 0.767, and 0.836, respectively. The combined diagnostic model yielded an optimal cut-off value of 0.513, providing excellent specificity (86.0%) and a sensitivity of 70.1%. The addition of the TEG Angle significantly improved risk reclassification (NRI = 0.078, IDI = 0.034). Subgroup analysis revealed that the combined model had even higher diagnostic efficacy in younger patients (≤ 65 years, AUC = 0.867). Sensitivity analysis showed that the core conclusions remained robust after excluding extreme outliers. Conclusion: The combination of TEG and conventional coagulation tests demonstrates substantial value for the early auxiliary diagnosis of DVT following cerebrovascular surgery. Angle, D-dimer, and hypertension are independent associated factors in this population. The combined diagnostic model provides excellent overall discrimination and high specificity, effectively reducing false positives in clinical screening and offering robust evidence for perioperative targeted anticoagulation management.

Background: This study aimed to investigate the association between thyroid abnormalities (both structural and functional) and bipolar disorder (BD), and to evaluate the relationship between thyroid parameters and mood symptom severity. Methods: In this retrospective cross-sectional study of clinical records (January 2022 to December 2024), data from 593 participants (398 BD patients and 195 healthy controls) were reviewed. Thyroid structure was evaluated via ultrasound (nodules, size), and function was assessed by measuring nine serum parameters, including thyroid hormones and autoantibodies. Clinical symptoms were rated using standardized scales. Statistical analyses employed logistic regression to determine associations and Spearman correlation to assess links with symptom scores. Results: Compared to controls, the BD group had a higher prevalence of structural abnormalities, lower TT3/TT4, elevated TSH, and higher rates of positive TgAb and TPOAb. Multivariate analysis indicated a protective effect of nodules, normal/elevated TT3/TT4/TG, and positive TgAb on outcomes, though some associations lost significance. Correlation analysis revealed no significant relationship between thyroid parameters and mood scale scores. Conclusions: Thyroid structure and function abnormalities were associated with BD in this retrospective analysis, although several associations were attenuated after multivariable adjustment. However, no significant cross-sectional correlation with the severity of manic or depressive symptoms was found, underscoring the complexity of this relationship and the need for further mechanistic investigation. Clinical trial number: Not applicable.