1.Correlations of artificial intelligence measured parameters on anteroposterior and lateral spinal X-ray films with severity of adolescent idiopathic scoliosis
Jinlong LIU ; Danyang SU ; Zhen BAI ; Wenhao GENG ; Fei LI ; Qiuju MIAO ; Xiaopeng YANG
Chinese Journal of Medical Imaging Technology 2025;41(5):778-782
Objective To observe the correlations of artificial intelligence(AI)measured parameters on anteroposterior and lateral spinal X-ray films with the severity of adolescent idiopathic scoliosis(AIS).Methods Totally 1 786 AIS patients were retrospectively enrolled.Parameters including Cobb angle(CA),coronal balance distance(CBD),T1 slope(T1S),pelvic tilt(PT),sacral slope(SS),apical vertebral translation(AVT),thoracic trunk shift(TTS),thoracic kyphosis(TK)and sagittal vertical axis(SVA)on anteroposterior and lateral spinal X-ray films were measured using uAI DR scoliosis analysis system.The severity of AIS was evaluated according to CA,and the correlations between other parameters and the severity of AIS were explored.The above parameters were compared under different severity levels and coronal/sagittal equilibrium states.Multivariate logistic regression analysis was performed to screen the independent impact factors on the severity of AIS.Results Significant differences of the above parameters were found among different severity levels except for SVA(all P<0.001).With the aggravation of AIS,CA,CBD,AVT and TTS increased successively(all P<0.001).T1S of severe AIS was higher than that of mild and moderate AIS(both P<0.001),PT and SS of moderate and severe AIS were all bigger,while their TK were smaller than those of mild AIS(all P<0.001).Significant differences of CA,T1S,PT,SS,AVT,TTS and TK were found between coronal balanced and imbalanced AIS(all P<0.05),while of TK were found between sagittal balanced and unbalanced AIS(P=0.026).CBD,T1S,PT,SS,AVT and TTS were all positively correlated(r,=0.136-0.606,all P<0.001),while TK was negatively correlated(r,=—0.404,P<0.001)with the severity of AIS.T1S,AVT and TTS were all independent impact factors of the severity of AIS(all P<0.001).Conclusion Among AI measured parameters on anteroposterior and lateral spinal X-ray films,CBD,T1S,PT,SS,AVT and TTS were positively correlated,while TK was negatively correlated with the severity of AIS.
2.Construction of artificial intelligence neuroimaging education platform for medical imaging students in clinical practice stage and pre-service resident trainees
Ruili LI ; Zhuangzhi SU ; Miao ZHANG ; Dongdong RONG ; Yi SHAN ; Jie LU
Chinese Journal of Medical Education Research 2025;24(2):150-154
Artificial intelligence technology brings new opportunities for the reform and innovation of medical imaging teaching and training models. We took the lead in building an artificial intelligence neuroimaging education platform. The platform included four modules: imaging case library, intelligent interactive learning, self-test and exercise, and online exam. The platform enables a more flexible and convenient education mode, a precise and individualized training method, which can motivate the enthusiasm and initiative of medical imaging students and resident trainees in learning, promote the rapid integration of theoretical knowledge and clinical practice, and improve the efficiency and quality of residency training.
3.Effect of the thicknesses of different reconstruction layer and the ROI thicknesses on the measurement of BMD value of QCT
Jinlong LIU ; Danyang SU ; Haoran ZHANG ; Yuanbo MA ; Qiuju MIAO ; Zhen BAI ; Xiaopeng YANG
China Medical Equipment 2025;22(1):19-23
Objective:To assess the effect of using different thicknesses of reconstruction layer and different thicknesses of region of interest (ROI) on the results of vertebral bone mineral density (BMD) values that were measured by quantitative computed tomography (QCT). Methods:A total of 100 patients who underwent QCT screening for opportunistic osteoporosis between May and September 2021 at the First Affiliated Hospital of Zhengzhou University were retrospectively collected. Images that the thicknesses of QCT reconstruction layer were respectively 1 and 5 mm were transferred to the QCT Pro workstation,and ROI thicknesses were adjusted to 5,7,and 9 mm,respectively. The average BMD values of QCT measurements were recorded under different thicknesses of reconstruction layer and different ROI thicknesses. Then,the effects of the choose of different thicknesses of reconstruction layer and the different ROI thicknesses on BMD values that were measured by QCT were analyzed. Results:The average BMD values of 1 mm and 5 mm thicknesses of reconstruction layer were respectively (117.41±45.97) mg/cm3 and (118.77±44.84) mg/cm3 when ROI thickness was 5 mm,with a statistically significant difference (t=-2.283,P<0.05). The average BMD values of 1 mm and 5 mm thicknesses of reconstruction layer were respectively (116.38±46.06) mg/cm3 and (119.06±44.55) mg/cm3 when the ROI thickness was 7mm,and the difference was statistically significant (t=-3.280,P<0.05). The average BMD values of 1 mm and 5 mm thicknesses of reconstruction layer were respectively (116.25±45.36) mg/cm3 and (120.12±44.10) mg/cm3 when the ROI thickness was 9 mm,and the difference was statistically significant (t=-5.841,P<0.001). The differences in BMD measurement values among 5,7 and 9 mm ROI thicknesses were not statistically significant when the thicknesses of reconstruction layer were respectively 1 and 5 mm. Conclusion:There is an effect of the thickness of QCT reconstruction layer on average BMD measurement values,and 1 mm thickness of reconstruction layer is more suitable to clinical application,while there is not significant effect in ROI thickness on average BMD measurement value of QCT. In clinical application,it is feasible to adjust ROI thickness according to actual situation so as to avoid the effect caused by some factors such as fracture or vertebral implants.
4.A machine learning-based model for predicting the risk of diabetic kidney disease in type 2 diabetes mellitus
Tingting LI ; Peng SU ; Jinbo CHEN ; Xiaoyan HE ; Yi CAO ; Xin ZHANG ; Qingling TANG ; Xubin MIAO ; Xiaohua LIANG ; Dong MA
Chinese Journal of Diabetes 2025;33(4):241-247
Objective To compare and find an optimal model for predicting the risk of DKD occurrence in patients with type 2 diabetes mellitus(T2DM).Methods A total of 2005 patients with T2DM were enrolled in this study from The Second Hospital of Shijiazhuang City during December 2017 to December 2022.All the subjects were divided into a training set(n=1403)and a validation set(n=602)according to the ratio of 3∶1 by simple random sampling.With the occurrence of DKD as the outcome variablein the training set,important feature variables were screened by LASSO regression.Six different machine learning models were established according to the feature variables,thenthe optimal model was determined by comparison,and anonlinerisk predictor for DKD occurrence was constructed in patients with T2DM.Results Taking the occurrence of DKD as the outcome variable in the training set,the results of LASSO regression analysis showed that the optimal value of the model was 10-fold cross validation lambda.1se=0.01662473,and 15 characteristic variables with nonzero coefficient were screened out to be related to the occurrence of DKD.The data included sex,age,family history of DM,DM duration,LDL-C,HbA1c,WBC,PDW,Scr,urine α1-microglobulin,urine β2-microglobulin,urine microalbumin,hypertension,hypokalemia,and DR.In the training set and validation set,the prediction performance of XGBoost model was better than that of other models(AUC=0.872,0.893,95%CI 0.853~0.891,0.865~0.921),the sensitivity was 0.779,0.863,and the specificity was 0.721,0.758,respectively.The F1 scores were 0.774 and 0.787.DCA analysis showed that the XGBoost model had a greater net benefit and threshold probability.According to the XGBoost model,the online predictor of DKD risk in T2DM patients was laid out,and two patients were selected for application,the results showed that the predictive value of the model was 0.185 in non-DKD patients,and the predictive value was 0.510 in DKD patients.Conclusions The XGBoost model is the best model for predicting the occurrence of DKD in T2DM patients,and an online predictor was successfully built.
5.Correlations of artificial intelligence measured parameters on anteroposterior and lateral spinal X-ray films with severity of adolescent idiopathic scoliosis
Jinlong LIU ; Danyang SU ; Zhen BAI ; Wenhao GENG ; Fei LI ; Qiuju MIAO ; Xiaopeng YANG
Chinese Journal of Medical Imaging Technology 2025;41(5):778-782
Objective To observe the correlations of artificial intelligence(AI)measured parameters on anteroposterior and lateral spinal X-ray films with the severity of adolescent idiopathic scoliosis(AIS).Methods Totally 1 786 AIS patients were retrospectively enrolled.Parameters including Cobb angle(CA),coronal balance distance(CBD),T1 slope(T1S),pelvic tilt(PT),sacral slope(SS),apical vertebral translation(AVT),thoracic trunk shift(TTS),thoracic kyphosis(TK)and sagittal vertical axis(SVA)on anteroposterior and lateral spinal X-ray films were measured using uAI DR scoliosis analysis system.The severity of AIS was evaluated according to CA,and the correlations between other parameters and the severity of AIS were explored.The above parameters were compared under different severity levels and coronal/sagittal equilibrium states.Multivariate logistic regression analysis was performed to screen the independent impact factors on the severity of AIS.Results Significant differences of the above parameters were found among different severity levels except for SVA(all P<0.001).With the aggravation of AIS,CA,CBD,AVT and TTS increased successively(all P<0.001).T1S of severe AIS was higher than that of mild and moderate AIS(both P<0.001),PT and SS of moderate and severe AIS were all bigger,while their TK were smaller than those of mild AIS(all P<0.001).Significant differences of CA,T1S,PT,SS,AVT,TTS and TK were found between coronal balanced and imbalanced AIS(all P<0.05),while of TK were found between sagittal balanced and unbalanced AIS(P=0.026).CBD,T1S,PT,SS,AVT and TTS were all positively correlated(r,=0.136-0.606,all P<0.001),while TK was negatively correlated(r,=—0.404,P<0.001)with the severity of AIS.T1S,AVT and TTS were all independent impact factors of the severity of AIS(all P<0.001).Conclusion Among AI measured parameters on anteroposterior and lateral spinal X-ray films,CBD,T1S,PT,SS,AVT and TTS were positively correlated,while TK was negatively correlated with the severity of AIS.
6.Relationships among empathy,meaning in life and altruistic behavior in medical students
Yingjuan HE ; Yujie LIU ; Kai DONG ; Junpeng SU ; Hailong ZHANG ; Miao MIAO
Chinese Mental Health Journal 2025;39(11):1007-1012
Objective:To investigate the relationship between empathy and meaning in life among medical students,and explore the mediating role of altruistic behavior.Methods:A total of 581 medical students were recrui-ted.They were assessed with the Interpersonal Reactivity Index-C(IRI-C),Altruistic Behavior Questionnaire of College Students(ABQ-CS),and Quadripartite Existential Meaning Scale(QEMS).The bootstrap method was used to test the hypothesized mediating effect.Results:The scores of IRI-C were positively correlated with the scores of ABQ-CS and QEMS(r=0.45,0.21,Ps<0.001).The scores of ABQ-CS were positively correlated with the QEMS scores(r=0.46,P<0.001).Altruism was a complete mediator between empathy and meaning in life,the indirect effect was 0.20(95%CI:0.15-0.26).Conclusion:This study reveals the underlying connections a-mong altruistic behavior,empathy,and meaning in life among medical students,suggesting that interventions targe-ting empathy and altruistic behavior may enhance their meaning in life.
7.Mid-and long-term effect of Kegel training combined with Pilates training on urinary control recovery in pa-tients with post-prostatectomy incontinence with different body mass index
Di AN ; Jianxia WANG ; Fan ZHANG ; Huafang JING ; Yi GAO ; Huiling CONG ; Guodong SU ; Miao YE ; Chunying HU ; Juan WU ; Limin LIAO
Chinese Journal of Rehabilitation Theory and Practice 2025;31(8):972-978
Objective To observe the mid-and long-term effects of Kegel training combined with Pilates training on urinary conti-nence recovery in different body mass index(BMI)male patients with urinary incontinence after prostatectomy.Methods From May,2023 to June,2024,48 patients in Beijing Bo'ai Hospital were recruited and divided into group A(<25 kg/m2,n=15),group B(25 to 30 kg/m2,n=18)and group C(>30 kg/m2,n=15)according to their BMI.All the groups performed Kegel training combined with Pilates training for two months,and followed up at six months from baseline.They were evaluated with one hour pad test,the number of daily urinary incontinence,In-ternational Consultation on Incontinence Questionnaire-Short Form(ICIQ-SF)and modified Oxford Rating Scale before treatment,and four weeks,eight weeks and six months after treatment.Results The intra-group effect,the inter-group effect and interaction effect were significant in the results of one hour pad test and the daily number of urinary incontinence(F>2.955,P<0.05).Post Hoc test showed that they were worse in group C than in groups A and B(P<0.05),and the number of daily urinary incontinence was more in group B than in group A(P<0.05).There was significant difference in the scores of ICIQ-SF and modified Ox-ford Rating Scale among groups in different time points after treatment(Z>10.476,P<0.05)except the score of ICIQ-SF four weeks after treatment(P>0.05),and they were the worst in group C.BMI(group A=1,group B=2,group C=3)was correlated with the results of one hour pad test(r=0.79,P<0.001),the number of daily uri-nary incontinence(r=0.68,P<0.001),and the scores of ICIQ-SF(r=0.68,P<0.001)and modified Oxford Rating Scale(r=-0.47,P=0.001)six months after treatment.Conclusion Kegel training combined with Pilates training could improve the urinary control in patients with urinary in-continence after prostatectomy.The decrease of BMI can promote the recovery of urinary control,and improve the symptoms of later urinary incontinence in mid-and long-term.
8.Research progress on NLRP3 inflammasome in microglia in ischemic stroke
Xin GAO ; Gang SU ; Miao CHAI ; Wei CHEN ; Minghui SHEN ; Yang AN ; Zhenzhen HU ; Zhenchang ZHANG
Chinese Journal of Immunology 2025;41(6):1504-1511
After ischemic stroke,intracranial cells experience stress due to ischemic and hypoxic injury,leading to a series of aseptic immune response processes.The oxidative stress process in microglias triggers the activation of the NLRP3 inflammasome,which promotes the release of inflammatory factors such as IL-1β and IL-18,contributing to the inflammatory reaction caused by isch-emic stroke.In addition,NLRP3 inflammasome is involved in the polarization,pyroptosis and autophagy of microglias,regulating the prognosis of ischemic stroke.This review summarizes the specific mechanisms of NLRP3 inflammasome in regulating microglial status and its involvement in ischemia-reperfusion injury.It also discusses the associated treatment strategies,identifies the current research focus and blanks,and provides some guidance and ideas for future research.
9.Effect of the thicknesses of different reconstruction layer and the ROI thicknesses on the measurement of BMD value of QCT
Jinlong LIU ; Danyang SU ; Haoran ZHANG ; Yuanbo MA ; Qiuju MIAO ; Zhen BAI ; Xiaopeng YANG
China Medical Equipment 2025;22(1):19-23
Objective:To assess the effect of using different thicknesses of reconstruction layer and different thicknesses of region of interest (ROI) on the results of vertebral bone mineral density (BMD) values that were measured by quantitative computed tomography (QCT). Methods:A total of 100 patients who underwent QCT screening for opportunistic osteoporosis between May and September 2021 at the First Affiliated Hospital of Zhengzhou University were retrospectively collected. Images that the thicknesses of QCT reconstruction layer were respectively 1 and 5 mm were transferred to the QCT Pro workstation,and ROI thicknesses were adjusted to 5,7,and 9 mm,respectively. The average BMD values of QCT measurements were recorded under different thicknesses of reconstruction layer and different ROI thicknesses. Then,the effects of the choose of different thicknesses of reconstruction layer and the different ROI thicknesses on BMD values that were measured by QCT were analyzed. Results:The average BMD values of 1 mm and 5 mm thicknesses of reconstruction layer were respectively (117.41±45.97) mg/cm3 and (118.77±44.84) mg/cm3 when ROI thickness was 5 mm,with a statistically significant difference (t=-2.283,P<0.05). The average BMD values of 1 mm and 5 mm thicknesses of reconstruction layer were respectively (116.38±46.06) mg/cm3 and (119.06±44.55) mg/cm3 when the ROI thickness was 7mm,and the difference was statistically significant (t=-3.280,P<0.05). The average BMD values of 1 mm and 5 mm thicknesses of reconstruction layer were respectively (116.25±45.36) mg/cm3 and (120.12±44.10) mg/cm3 when the ROI thickness was 9 mm,and the difference was statistically significant (t=-5.841,P<0.001). The differences in BMD measurement values among 5,7 and 9 mm ROI thicknesses were not statistically significant when the thicknesses of reconstruction layer were respectively 1 and 5 mm. Conclusion:There is an effect of the thickness of QCT reconstruction layer on average BMD measurement values,and 1 mm thickness of reconstruction layer is more suitable to clinical application,while there is not significant effect in ROI thickness on average BMD measurement value of QCT. In clinical application,it is feasible to adjust ROI thickness according to actual situation so as to avoid the effect caused by some factors such as fracture or vertebral implants.
10.Mid-and long-term effect of Kegel training combined with Pilates training on urinary control recovery in pa-tients with post-prostatectomy incontinence with different body mass index
Di AN ; Jianxia WANG ; Fan ZHANG ; Huafang JING ; Yi GAO ; Huiling CONG ; Guodong SU ; Miao YE ; Chunying HU ; Juan WU ; Limin LIAO
Chinese Journal of Rehabilitation Theory and Practice 2025;31(8):972-978
Objective To observe the mid-and long-term effects of Kegel training combined with Pilates training on urinary conti-nence recovery in different body mass index(BMI)male patients with urinary incontinence after prostatectomy.Methods From May,2023 to June,2024,48 patients in Beijing Bo'ai Hospital were recruited and divided into group A(<25 kg/m2,n=15),group B(25 to 30 kg/m2,n=18)and group C(>30 kg/m2,n=15)according to their BMI.All the groups performed Kegel training combined with Pilates training for two months,and followed up at six months from baseline.They were evaluated with one hour pad test,the number of daily urinary incontinence,In-ternational Consultation on Incontinence Questionnaire-Short Form(ICIQ-SF)and modified Oxford Rating Scale before treatment,and four weeks,eight weeks and six months after treatment.Results The intra-group effect,the inter-group effect and interaction effect were significant in the results of one hour pad test and the daily number of urinary incontinence(F>2.955,P<0.05).Post Hoc test showed that they were worse in group C than in groups A and B(P<0.05),and the number of daily urinary incontinence was more in group B than in group A(P<0.05).There was significant difference in the scores of ICIQ-SF and modified Ox-ford Rating Scale among groups in different time points after treatment(Z>10.476,P<0.05)except the score of ICIQ-SF four weeks after treatment(P>0.05),and they were the worst in group C.BMI(group A=1,group B=2,group C=3)was correlated with the results of one hour pad test(r=0.79,P<0.001),the number of daily uri-nary incontinence(r=0.68,P<0.001),and the scores of ICIQ-SF(r=0.68,P<0.001)and modified Oxford Rating Scale(r=-0.47,P=0.001)six months after treatment.Conclusion Kegel training combined with Pilates training could improve the urinary control in patients with urinary in-continence after prostatectomy.The decrease of BMI can promote the recovery of urinary control,and improve the symptoms of later urinary incontinence in mid-and long-term.

Result Analysis
Print
Save
E-mail