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 detect changes of Foxp3 expression in the decidua in patients with preeclampsia and investigate the correlation of Foxp3-924 (rs2232365) polymorphisms with preeclampsia. Methods From October 2011 to December 2012, 252 normal pregnant women and 156 preeclampsia patients of Han nationality from the same geographic region were tested for Foxp3-924 genotypes by polymerase chain reaction with sequence-specific primer (PCR-SSP). Sixty-eight of the patients with preeclampsia (33 with mild and 35 with severe preeclampsia) and 30 of the normal pregnant women were also examined for Foxp3 expression in the decidua using immunohistochemical method. Results Foxp3 positive expression rates in the decidua was 51.52%in mild preeclampsia and 28.57%in severe preeclampsia cases, significantly lower than that in the control group (86.67%, P<0.05). In preeclampsia patients, the frequencies of Foxp3-924G/G, G/A, and A/A genotypes were 0.1346, 0.4615 and 0.4038, respectively, and the frequencies of Foxp3-924A and Foxp3-924 G were 0.6346 and 0.3654, respectively. The genotype frequencies of Foxp3-924G/G, G/A and A/A in the control group were 0.1508, 0.4087 and 0.4405, respectively, and the frequencies of Foxp3-924 A and Foxp3-924 G were 0.6448 and 0.3552, respectively. No significant differences were found in the gene frequencies of Foxp3-924G/A between preeclampsia patients and the control group (P>0.05). Conclusion The expression level of Foxp3 in the placental tissue of preeclampsia patients is significantly lower than that in normal pregnant women, suggesting that lowered Foxp3 expression decreases the immunosuppressive function and causes imbalance of immune tolerance between maternal-fetal to induce preeclampsia. Foxp3-924 polymorphisms is not significantly correlated with the occurrence of preeclampsia.

Objective To detect changes of Foxp3 expression in the decidua in patients with preeclampsia and investigate the correlation of Foxp3-924 (rs2232365) polymorphisms with preeclampsia. Methods From October 2011 to December 2012, 252 normal pregnant women and 156 preeclampsia patients of Han nationality from the same geographic region were tested for Foxp3-924 genotypes by polymerase chain reaction with sequence-specific primer (PCR-SSP). Sixty-eight of the patients with preeclampsia (33 with mild and 35 with severe preeclampsia) and 30 of the normal pregnant women were also examined for Foxp3 expression in the decidua using immunohistochemical method. Results Foxp3 positive expression rates in the decidua was 51.52%in mild preeclampsia and 28.57%in severe preeclampsia cases, significantly lower than that in the control group (86.67%, P<0.05). In preeclampsia patients, the frequencies of Foxp3-924G/G, G/A, and A/A genotypes were 0.1346, 0.4615 and 0.4038, respectively, and the frequencies of Foxp3-924A and Foxp3-924 G were 0.6346 and 0.3654, respectively. The genotype frequencies of Foxp3-924G/G, G/A and A/A in the control group were 0.1508, 0.4087 and 0.4405, respectively, and the frequencies of Foxp3-924 A and Foxp3-924 G were 0.6448 and 0.3552, respectively. No significant differences were found in the gene frequencies of Foxp3-924G/A between preeclampsia patients and the control group (P>0.05). Conclusion The expression level of Foxp3 in the placental tissue of preeclampsia patients is significantly lower than that in normal pregnant women, suggesting that lowered Foxp3 expression decreases the immunosuppressive function and causes imbalance of immune tolerance between maternal-fetal to induce preeclampsia. Foxp3-924 polymorphisms is not significantly correlated with the occurrence of preeclampsia.