Objective To explore the value of MRI radiomics based on the frontal and temporal lobes combined with multiple machine learning algorithms in the diagnosis of mild cognitive impairment(MCI).Methods Patients who underwent cranial MR examination were retrospectively selected.According to the inclusion and exclusion criteria,a total of 173 subjects were finally included and randomly divided into training set and test set in a ratio of 7∶3.After delineating the regions of interest(ROI)of the frontal and temporal lobes on T2-fluid attenuated inversion recovery(FLAIR)images,radiomics features were extracted based on the Pyradiomics data package.Features were screened through inter-and intraclass correlation coefficient(ICC),independent samples t-test,and the LightGBM algorithm.Diagnostic models were constructed using support vector machine(SVM),random forest(RF),decision tree(DT),K-nearest neighbor(KNN),gradient boosting decision tree(GBDT),and extreme gradient boosting(XGBoost)combined with 10-fold cross-validation respectively.The training set was further divided into 9 training data sets and 1 validation data set through 10-fold cross-validation,and the hyperparameters were optimized through iterative cycles.The diagnostic efficacy of the model was evaluated by receiver operating characteristic(ROC)curve and area under the curve(AUC),and the DeLong test was applied to compare the differences between different models.Results The AUC of the radiomics models constructed by SVM,DT,RF,KNN,GBDT,XGBoost in the training set were 0.951,0.992,0.998,0.957,1.000,and 1.000 respectively,in the validation set were 0.890,0.843,0.934,0.878,0.930,and 0.945 respectively,and in the test set were 0.902,0.711,0.899,0.849,0.889,and 0.882 respectively.Conclusion MRI radiomics based on the frontal and temporal lobes combined with multiple machine learning algorithms can diagnose MCI,and the model constructed based on SVM shows the highest diagnostic value.

Objective To explore the value of MRI radiomics based on the frontal and temporal lobes combined with multiple machine learning algorithms in the diagnosis of mild cognitive impairment(MCI).Methods Patients who underwent cranial MR examination were retrospectively selected.According to the inclusion and exclusion criteria,a total of 173 subjects were finally included and randomly divided into training set and test set in a ratio of 7∶3.After delineating the regions of interest(ROI)of the frontal and temporal lobes on T2-fluid attenuated inversion recovery(FLAIR)images,radiomics features were extracted based on the Pyradiomics data package.Features were screened through inter-and intraclass correlation coefficient(ICC),independent samples t-test,and the LightGBM algorithm.Diagnostic models were constructed using support vector machine(SVM),random forest(RF),decision tree(DT),K-nearest neighbor(KNN),gradient boosting decision tree(GBDT),and extreme gradient boosting(XGBoost)combined with 10-fold cross-validation respectively.The training set was further divided into 9 training data sets and 1 validation data set through 10-fold cross-validation,and the hyperparameters were optimized through iterative cycles.The diagnostic efficacy of the model was evaluated by receiver operating characteristic(ROC)curve and area under the curve(AUC),and the DeLong test was applied to compare the differences between different models.Results The AUC of the radiomics models constructed by SVM,DT,RF,KNN,GBDT,XGBoost in the training set were 0.951,0.992,0.998,0.957,1.000,and 1.000 respectively,in the validation set were 0.890,0.843,0.934,0.878,0.930,and 0.945 respectively,and in the test set were 0.902,0.711,0.899,0.849,0.889,and 0.882 respectively.Conclusion MRI radiomics based on the frontal and temporal lobes combined with multiple machine learning algorithms can diagnose MCI,and the model constructed based on SVM shows the highest diagnostic value.

Objective:To analyze the changes of thyroid volume before and after supplementation with lipiodol pills in children with goiter, and to evaluate the recovery effect of lipiodol pills supplementation on children with goiter in the short term.Methods:In October 2018, 4 townships and towns in Linxia Hui Autonomous Prefecture with relatively serious historical conditions and high goiter rate of children aged 8 to 10 were selected for thyroid examination in 19 primary schools within the jurisdiction. Sixty children with goiter were selected as research subjects; at the same time, 138 children of the same age with normal thyroid B-ultrasound examination results were selected as control in the same period. Under the condition of normal diet, children with goiter were intervened by taking 200 mg lipiodol pills at one time. After 6 months, the thyroid volume of children with goiter and control children was measured by B-ultrasound.Results:Fifty-three children with goiter were finally included, with a sex ratio of 1.00 ∶ 1.04 (26 ∶ 27). There were 138 control children in the same period, with a sex ratio of 1.00 ∶ 1.30 (60 ∶ 78). Six months after taking lipiodol pills, the median thyroid volume of children with goiter was 3.7 ml, which was significantly different from that before supplementing with lipidol pills (5.8 ml, Z = - 7.95, P < 0.001), and not significantly different from that of control children (4.1 ml) in the same period ( Z = - 0.91, P = 0.365). Among them, 90.6% (48/53) of children with goiter recovered to the normal range, and 100.0% (15/15), 81.8% (18/22) and 93.8% (15/16) children's thyroid recovered returned to the normal range in the 8-, 9-, and 10-year-old age groups, respectively, and the highest proportion was in the 8-year-old age group. Stratified by age and gender, the thyroid volume of children with goiter in all age groups and gender after supplementation with lipiodol pills was lower than that before supplementation with lipiodol pills ( P < 0.001), but there was no difference compared with the control children in the same period ( P > 0.05). After supplementing with lipiodol pills, the diameters of thyroid in children with goiter were significantly lower than those before supplementing with lipiodol pills ( P < 0.001). Compared with the control children in the same period, there were significant differences in the right width, left length and right long diameter of the thyroid ( P < 0.05). Conclusion:Supplementing lipiodol pills can restore the thyroid volume of 8 - 10 year old children with goiter to normal range in a short term, and can effectively treat simple goiter.

Mesenchymal stem cells(MSCs)have a unique role in immune regulation and focus to T-cells.In the mixed lymphocyte reactions,MSCs inhibit T-cells proliferation by cycle arrest,but they do not increase T-cell apoptosis and the suppress T-cell activation.In addition,MSCs can reduce CD8~+T cells and Thl cells,and simultaneously increase Th2 cells in the reaction system to suppress the inflammatory response,which may play a therapeutic effect on the T-cells mediated autoimmune diseases.