Objective To evaluate the diagnostic value of black blood computed tomography(BBCT)in vulnerable plaques at the carotid bifurcation.Methods The imaging data of 73 patients with suspected carotid atherosclerosis were retrospectively analyzed.The signal-to-noise ratio(SNR)and contrast-to-noise ratio(CNR)of conventional computed tomography angiography(CTA)ima-ges and BBCT images were compared by paired sample t-test.The 5-level scoring method was applied to evaluate the image quality subjectively,and the Friedman test was used to compare the differences in the subjective evaluation of image quality among the groups.Taking high-resolution magnetic resonance vessel wall imaging(HRMR-VWI)as the gold standard,the diagnostic value between BBCT and conventional CTA was compared,and the consistency of BBCT and HRMR-VWI in the evaluation of vulnerable plaques was calculated.Results The standard deviation(SD)value of BBCT images was lower than that of conventional three-phase CTA images,indicating better quality of BBCT images(P＜0.001).The mean CT value and CNRplaque-lumen of non-calcified plaques were higher in BBCT images than those in conventional three-phase CTA images,suggesting that BBCT had a higher contrast with sur-rounding tissues and could better display the fine structure of non-calcified plaques(P＜0.001).BBCT images achieved the highest scores in the subjective evaluation of image quality(P＜0.001).Compared with conventional CTA images,BBCT had higher sensi-tivity(88.2％vs 29.4％)and accuracy(90.9％vs 54.5％)in identifying vulnerable plaques(P＜0.001).The Kappa value between BBCT and HRMR-VWI was 0.813,showed good consistency.Conclusion The image quality of neck BBCT is superior to that of conventional CTA.BBCT has a better effect than conventional CTA in identifying vulnerable plaques at the carotid bifurcation,which is comparable to HRMR-VWI.

Objective To explore the ability of different regions of interest(ROI)location settings for the detection of bronchial artery and pulmonary vascular lesions in children with hemoptysis via computed tomography angiography(CTA)examination.Methods The hemoptysis group(79 cases)who underwent chest CTA examination and the control group(79 cases)with negative CTA results were retrospectively selected.The ROI of the hemoptysis group were placed in the pulmonary trunk,left ventricle,ascending aorta and descending aorta,which were defined as groups 1,2,3 and 4 respectively.Clinical data(age,sex)and CT parameters,including bronchial artery diameter,ascending aorta CT value,pulmonary artery CT value,△CTA-PA,bronchial artery image score,pulmonary artery image score,were recorded and analyzed,respectively.Results There was a statistically significant difference in the diameter of the left and right bronchial arteries between the hemoptysis group and the control group(P＜0.05).In the hemoptysis group,there were statistically significant differences in the image scores of the left and right bronchial arteries,pulmonary artery image scores,and△CTA-PA among the four subgroups(P＜0.05).According to post-hoc comparison results,there was a statistically significant difference in the overall mean scores of the right bronchial artery image score(x2=11.333,P＜0.05)and left bronchial artery image score(x2=8.111,P＜0.05)between groups 2 and 3.Conclusion When ROI is placed in the ascending aorta,bronchial artery lesions and pulmonary vascular lesions can be detected simultaneously in CTA examination,which is helpful for the diagnosis of hemoptysis vascular etiology in children.

Objective:To explore the application value of machine learning prediction model for neural invasion in gallbladder cancer based on enhanced computed tomography (CT) and clinical characteristics.Methods:The retrospective cohort study was conducted. The clinical and imaging data of 502 patients with gallbladder cancer who were admitted to The First Affiliated Hospital of Xinxiang Medical University from January 2010 to June 2024 were collected. There were 171 males and 331 females, aged 65(range, 35?91)years. All patients underwent preoperative abdominal enhanced CT and radical resection. The 502 patients were randomly divided into a training set of 351 cases and a test set of 151 cases at a 7:3 ratio. The training set was used to construct prediction model, and the test set was used to validate prediction model. Observation indicators: (1)neural invasion in gallbladder cancer and influencing factor analysis; (2) construction and validation of machine learning prediction models for neural invasion in gallbladder cancer. Comparison of count data between groups was conducted using the chi-square test. Comparison of ordinal data between groups was conducted using the Mann-Whitney U test. Logistic regression model was performed for univariate and multivariate analyses. Independent influencing factors were incor-porated to construct machine learning models using the standard library modules based on Python 3.9. Receiver operating characteristic (ROC) curves were plotted, and the accuracy, sensitivity, specificity, area under the curve (AUC), precision, F1 score, positive predictive value, negative predic-tive value, and Kappa value were calculated to evaluate the predictive performance of the models. The Delong test was used to assess the differences in AUC among different models in the test set. The Hosmer-Lemeshow test and Brier score were used to evaluate the calibration of the models. Results:(1) Neural invasion in gallbladder cancer and influencing factor analysis. Of the 502 patients with gallbladder cancer, 131 cases had neural invasion, and 371 cases had no neural invasion. Results of multivariate analysis showed that total bilirubin, carcinoembryonic antigen, CA199, CA125, neutrophil-lymphocyte ratio, liver invasion detected by CT, vascular invasion detected by CT, hilar or retroperi-toneal lymph node metastasis detected by CT, and tumor stages T3 and T4 were independent influencing factors for neural invasion in patients with gallbladder cancer [ odds ratios=3.747, 2.395, 3.917, 3.596, 2.805, 2.377, 3.523, 2.774, 5.080, 6.809, 95% confidence interval ( CI) as 1.890?7.430, 1.154?4.971, 2.054?7.472, 1.807?7.155, 1.506?5.225, 1.241?4.553, 1.666?7.449, 1.483?5.189, 2.050?12.589, 2.552?18.168, P<0.05]. (2) Construction and validation of machine learning predic-tion models for neural invasion in gallbladder cancer. Based on the independent influencing factors, seven machine learning models were constructed, including logistic regression, K-nearest neighbors, support vector machine, random forest, decision tree, back-propagation neural network, and gradient boosting machine. The ROC curves of seven machine learning models in the test set were plotted, and the AUC were 0.900(95% CI as 0.851?0.948), 0.741(95% CI as 0.646?0.829), 0.836(95% CI as 0.762?0.895), 0.782(95% CI as 0.701?0.855), 0.839(95% CI as 0.770?0.901), 0.817(95% CI as 0.738?0.887), 0.843(95% CI as 0.770?0.909), respectively. Results of Delong test showed that the logistic regression model had the highest AUC. The sensitivity and specificity of the logistic regression model were 0.868 and 0.805 respectively, indicating the best balance. Results of Hosmer-Lemeshow test showed that the logistic regression model had a good goodness-of-fit ( χ2=5.320, P>0.05). The Brier score of the logistic regression model was relatively low, as 0.168, which verified its calibration advantage. Conclusion:Total bilirubin, carcinoembryonic antigen, CA199, CA125, neutrophil-to-lymphocyte ratio, liver invasion detected by enhanced CT, vascular invasion detected by enhanced CT, hilar or retroperitoneal lymph node metastasis detected by enhanced CT, and tumor stages T3 and T4 are independent influencing factors for nerve invasion in patients with gallbladder cancer. Seven machine learning models are constructed based on enhanced CT and clinical characteristics to predict neural invasion in gallbladder cancer, of which the logistic regression model demonstrates good predictive performance.

Objective A binary Logistic regression model was developed to forecast the pathological grade of invasive adenocarcino-ma by utilizing the CT characteristics of lung nodules.Methods A retrospective analysis was conducted on the clinical data,pathological types,and imaging findings of 303 cases of ground-glass nodules diagnosed with postoperative pathological infiltrative adenocarcinoma at the First Affiliated Hospital of Henan Polytechnic University and the First Affiliated Hospital of Xinxiang Medical College from January 2021 to February 2023.Based on the pathological results,these lesions were categorized into two groups:the low-grade group(compri-sing 262 cases characterized by adherent,acinar,or papillary types as predominant forms of adenocarcinoma with no more than 20％high-grade pattern)and the high-grade group(consisting of 41 cases exhibiting any form of adenocarcinoma with over 20％high-grade components).The Mann-Whitney U test was employed to compare quantitative parameters between both groups,while qualitative parameters were analyzed using the x2 test.Additionally,binary Logistic regression models were utilized to identify independent predictors;further evaluation included area under curve(AUC)values,calibration curves,and decision analysis curves to assess model differentia-tion,calibration accuracy,and clinical applicability.Results Univariate analysis revealed that gender,air bronchial sign,vacuole sign,vascular cluster sign,pleural depression sign,long diameter,short diameter,and CT-enhanced net increment exhibited statistical signifi-cance(P＜0.05),whereas location,burr sign,and solid component ratio did not demonstrate statistical significance(P＞0.05).Binary Logistic regression analysis identified long diameter,CT-enhanced net increment,vascular cluster sign,pleural depression sign,and vacu-ole sign as independent predictors of the pathological grade model for invasive adenocarcinoma.The results of ROC curve analysis indicated that the AUC value of the Logistic regression model was 0.846 with a sensitivity of 81.25％and specificity of 86.52％.Conclusion The logistic regression model based on CT signs has excellent ability and stability in predicting the pathological grade of invasive adenocarcinoma.

Objective To explore the ability of different regions of interest(ROI)location settings for the detection of bronchial artery and pulmonary vascular lesions in children with hemoptysis via computed tomography angiography(CTA)examination.Methods The hemoptysis group(79 cases)who underwent chest CTA examination and the control group(79 cases)with negative CTA results were retrospectively selected.The ROI of the hemoptysis group were placed in the pulmonary trunk,left ventricle,ascending aorta and descending aorta,which were defined as groups 1,2,3 and 4 respectively.Clinical data(age,sex)and CT parameters,including bronchial artery diameter,ascending aorta CT value,pulmonary artery CT value,△CTA-PA,bronchial artery image score,pulmonary artery image score,were recorded and analyzed,respectively.Results There was a statistically significant difference in the diameter of the left and right bronchial arteries between the hemoptysis group and the control group(P＜0.05).In the hemoptysis group,there were statistically significant differences in the image scores of the left and right bronchial arteries,pulmonary artery image scores,and△CTA-PA among the four subgroups(P＜0.05).According to post-hoc comparison results,there was a statistically significant difference in the overall mean scores of the right bronchial artery image score(x2=11.333,P＜0.05)and left bronchial artery image score(x2=8.111,P＜0.05)between groups 2 and 3.Conclusion When ROI is placed in the ascending aorta,bronchial artery lesions and pulmonary vascular lesions can be detected simultaneously in CTA examination,which is helpful for the diagnosis of hemoptysis vascular etiology in children.

Objective:To explore the application value of machine learning prediction model for neural invasion in gallbladder cancer based on enhanced computed tomography (CT) and clinical characteristics.Methods:The retrospective cohort study was conducted. The clinical and imaging data of 502 patients with gallbladder cancer who were admitted to The First Affiliated Hospital of Xinxiang Medical University from January 2010 to June 2024 were collected. There were 171 males and 331 females, aged 65(range, 35?91)years. All patients underwent preoperative abdominal enhanced CT and radical resection. The 502 patients were randomly divided into a training set of 351 cases and a test set of 151 cases at a 7:3 ratio. The training set was used to construct prediction model, and the test set was used to validate prediction model. Observation indicators: (1)neural invasion in gallbladder cancer and influencing factor analysis; (2) construction and validation of machine learning prediction models for neural invasion in gallbladder cancer. Comparison of count data between groups was conducted using the chi-square test. Comparison of ordinal data between groups was conducted using the Mann-Whitney U test. Logistic regression model was performed for univariate and multivariate analyses. Independent influencing factors were incor-porated to construct machine learning models using the standard library modules based on Python 3.9. Receiver operating characteristic (ROC) curves were plotted, and the accuracy, sensitivity, specificity, area under the curve (AUC), precision, F1 score, positive predictive value, negative predic-tive value, and Kappa value were calculated to evaluate the predictive performance of the models. The Delong test was used to assess the differences in AUC among different models in the test set. The Hosmer-Lemeshow test and Brier score were used to evaluate the calibration of the models. Results:(1) Neural invasion in gallbladder cancer and influencing factor analysis. Of the 502 patients with gallbladder cancer, 131 cases had neural invasion, and 371 cases had no neural invasion. Results of multivariate analysis showed that total bilirubin, carcinoembryonic antigen, CA199, CA125, neutrophil-lymphocyte ratio, liver invasion detected by CT, vascular invasion detected by CT, hilar or retroperi-toneal lymph node metastasis detected by CT, and tumor stages T3 and T4 were independent influencing factors for neural invasion in patients with gallbladder cancer [ odds ratios=3.747, 2.395, 3.917, 3.596, 2.805, 2.377, 3.523, 2.774, 5.080, 6.809, 95% confidence interval ( CI) as 1.890?7.430, 1.154?4.971, 2.054?7.472, 1.807?7.155, 1.506?5.225, 1.241?4.553, 1.666?7.449, 1.483?5.189, 2.050?12.589, 2.552?18.168, P<0.05]. (2) Construction and validation of machine learning predic-tion models for neural invasion in gallbladder cancer. Based on the independent influencing factors, seven machine learning models were constructed, including logistic regression, K-nearest neighbors, support vector machine, random forest, decision tree, back-propagation neural network, and gradient boosting machine. The ROC curves of seven machine learning models in the test set were plotted, and the AUC were 0.900(95% CI as 0.851?0.948), 0.741(95% CI as 0.646?0.829), 0.836(95% CI as 0.762?0.895), 0.782(95% CI as 0.701?0.855), 0.839(95% CI as 0.770?0.901), 0.817(95% CI as 0.738?0.887), 0.843(95% CI as 0.770?0.909), respectively. Results of Delong test showed that the logistic regression model had the highest AUC. The sensitivity and specificity of the logistic regression model were 0.868 and 0.805 respectively, indicating the best balance. Results of Hosmer-Lemeshow test showed that the logistic regression model had a good goodness-of-fit ( χ2=5.320, P>0.05). The Brier score of the logistic regression model was relatively low, as 0.168, which verified its calibration advantage. Conclusion:Total bilirubin, carcinoembryonic antigen, CA199, CA125, neutrophil-to-lymphocyte ratio, liver invasion detected by enhanced CT, vascular invasion detected by enhanced CT, hilar or retroperitoneal lymph node metastasis detected by enhanced CT, and tumor stages T3 and T4 are independent influencing factors for nerve invasion in patients with gallbladder cancer. Seven machine learning models are constructed based on enhanced CT and clinical characteristics to predict neural invasion in gallbladder cancer, of which the logistic regression model demonstrates good predictive performance.

Objective To evaluate the diagnostic value of black blood computed tomography(BBCT)in vulnerable plaques at the carotid bifurcation.Methods The imaging data of 73 patients with suspected carotid atherosclerosis were retrospectively analyzed.The signal-to-noise ratio(SNR)and contrast-to-noise ratio(CNR)of conventional computed tomography angiography(CTA)ima-ges and BBCT images were compared by paired sample t-test.The 5-level scoring method was applied to evaluate the image quality subjectively,and the Friedman test was used to compare the differences in the subjective evaluation of image quality among the groups.Taking high-resolution magnetic resonance vessel wall imaging(HRMR-VWI)as the gold standard,the diagnostic value between BBCT and conventional CTA was compared,and the consistency of BBCT and HRMR-VWI in the evaluation of vulnerable plaques was calculated.Results The standard deviation(SD)value of BBCT images was lower than that of conventional three-phase CTA images,indicating better quality of BBCT images(P＜0.001).The mean CT value and CNRplaque-lumen of non-calcified plaques were higher in BBCT images than those in conventional three-phase CTA images,suggesting that BBCT had a higher contrast with sur-rounding tissues and could better display the fine structure of non-calcified plaques(P＜0.001).BBCT images achieved the highest scores in the subjective evaluation of image quality(P＜0.001).Compared with conventional CTA images,BBCT had higher sensi-tivity(88.2％vs 29.4％)and accuracy(90.9％vs 54.5％)in identifying vulnerable plaques(P＜0.001).The Kappa value between BBCT and HRMR-VWI was 0.813,showed good consistency.Conclusion The image quality of neck BBCT is superior to that of conventional CTA.BBCT has a better effect than conventional CTA in identifying vulnerable plaques at the carotid bifurcation,which is comparable to HRMR-VWI.

Objective A binary Logistic regression model was developed to forecast the pathological grade of invasive adenocarcino-ma by utilizing the CT characteristics of lung nodules.Methods A retrospective analysis was conducted on the clinical data,pathological types,and imaging findings of 303 cases of ground-glass nodules diagnosed with postoperative pathological infiltrative adenocarcinoma at the First Affiliated Hospital of Henan Polytechnic University and the First Affiliated Hospital of Xinxiang Medical College from January 2021 to February 2023.Based on the pathological results,these lesions were categorized into two groups:the low-grade group(compri-sing 262 cases characterized by adherent,acinar,or papillary types as predominant forms of adenocarcinoma with no more than 20％high-grade pattern)and the high-grade group(consisting of 41 cases exhibiting any form of adenocarcinoma with over 20％high-grade components).The Mann-Whitney U test was employed to compare quantitative parameters between both groups,while qualitative parameters were analyzed using the x2 test.Additionally,binary Logistic regression models were utilized to identify independent predictors;further evaluation included area under curve(AUC)values,calibration curves,and decision analysis curves to assess model differentia-tion,calibration accuracy,and clinical applicability.Results Univariate analysis revealed that gender,air bronchial sign,vacuole sign,vascular cluster sign,pleural depression sign,long diameter,short diameter,and CT-enhanced net increment exhibited statistical signifi-cance(P＜0.05),whereas location,burr sign,and solid component ratio did not demonstrate statistical significance(P＞0.05).Binary Logistic regression analysis identified long diameter,CT-enhanced net increment,vascular cluster sign,pleural depression sign,and vacu-ole sign as independent predictors of the pathological grade model for invasive adenocarcinoma.The results of ROC curve analysis indicated that the AUC value of the Logistic regression model was 0.846 with a sensitivity of 81.25％and specificity of 86.52％.Conclusion The logistic regression model based on CT signs has excellent ability and stability in predicting the pathological grade of invasive adenocarcinoma.

Objective To compare the safety and efficacy of direct thrombectomy versus bridging thrombectomy in the treatment of acute anterior circulation large vessel occlusion stroke under different collateral circulation statuses.Methods Totally 93 patients with acute anterior circulation ischemic stroke admitted to the First Affiliated Hospital of Xinxiang Medical University from September 2020 to March 2023 were selected as the research subjects.Patients were divided into direct throm-bectomy group(n=47)and bridging thrombectomy group(n=46)based on the type of thrombectomy.Patients in the direct thrombectomy group received direct intravascular thrombectomy,while patients in the bridging thrombectomy group received intravenous thrombolysis with alteplase combined with mechanical thrombectomy.According computed tomography angiography,the collateral circulation Tan classification was applied to divide the patients into good collateral circulation sub-group and poor collateral circulation sub-group.The modified thrombolysis in cerebral infarction grading(mTICI)was used to evaluate vessel recanalization.Head computed tomography plain scan was performed at 24-48 hours postoperatively to assess if there was hemorrhagic transformation,and modified Rankin Scale score was performed at 90 days postoperatively.Information such as imaging examination time,femoral artery puncture time,vessel recanalization time after thrombectomy,prognosis and spontaneous non-traumatic symptomatic intracerebral hemorrhage(SICH)were collected.Results The age,gender,baseline Alberta stroke program early computed tomography score,baseline national institutes of health stroke scale score,proportions of hypertension,diabetes and atrial fibrillation,baseline systolic pressure,creatinine,baseline blood glucose,platelet count,occlusion site,stroke etiologies and collateral circulation status of patients in the two groups were not statistically significantly different(P＞0.05).There were no significant differences in the post-admission imaging examination time,femoral artery puncture time,vessel recanalization time after thrombectomy,successful vascular reperfusion rate,good prognosis rate,mortality rate,and SICH incidence between the two groups(P＞0.05).The hemorrhagic transformation rate of patients in the direct thrombectomy group was significantly lower than that in the bridging thrombectomy group(P＜0.05).There were no significant differences in the post-admission imaging examination time,femoral artery puncture time,vessel recanalization time after thrombectomy,successful vascular reperfusion rate,good prognosis rate,mortality rate,and SICH incidence between patients with good collateral circulation and patients with poor collateral circulation in the two groups(P＞0.05).The hemorrhagic transformation rate of patients with good and poor collateral circulation in the direct thrombectomy group was significantly lower than that in the bridging thrombectomy group(P＜0.05).Conclusion Under different collateral circulation conditions,the safety and efficacy of direct thrombectomy and bridging thrombectomy in the treatment of acute anterior circulation large vessel occlusion stroke are similar,but bridging thrombectomy is more likely to result in cerebral hemorrhage transformation compared with direct thrombectomy.

Objective:To assess the predictive value of a combined multiclassification model for computed tomography(CT)in the patholo-gical analysis of ground-glass nodules(GGN).Methods:Pulmonary GGN lesions that were pathologically confirmed as invasive adenocar-cinoma(IAC),minimally invasive adenocarcinoma(MIA),adenocarcinoma in situ(AIS),and preinvasive lesions(PILs),were collected from pa-tients who were treated at The First Affiliated Hospital of Xinxiang Medical University between February 2019 and March 2023.A total of 324 nodules were retrospectively collected from 285 patients,and divided into three groups:infiltrating IAC,MIA,and PILs.Radiomics and clinical-CT features were selected through recursive feature elimination and univariate Logistic regression.Seven models were constructed using Logistic regression(LR),support vector machine(SVM),random forest(RF),and integrative learning(stacking).Results:The hybrid model combining clinical-CT-radiomics features and an integrative strategy showed superior predictive performance,with an accuracy of 0.791,precision of 0.788,specificity of 0.857,recall of 0.790,and F1-Score of 0.789.Conclusions:The multiclassification joint model based on CT-radiomics is effective in predicting pathological classification of pulmonary GGNs.This model aids in accurate imaging diagnosis and can provide a basis for optimizing treatment plans.