Objective: To explore the value of amide proton transfer imaging (APT) and diffusion kurtosis imaging (DKI) in differentiating histological grade of cervical squamous cell carcinoma. Methods: APT and DKI data of 36 patients with cervical squamous cell carcinoma, including 11 with high differentiated tumor (high differentiated group), 16 with moderate differentiated tumor (moderate differentiated group)and 9 with poor differentiated tumor (poor differentiated group) were retrospectively analyzed. The magnetization transfer ratio asymmetry (MTRasym), mean kurtosis (MK) and mean diffusion (MD) values of tumors were measured on the corresponding pseudo color pictures, respectively. The differences of MTRasym, MK and MD values were compared among 3 groups. ROC curve was used to analyze the diagnostic efficiency of each parameter in differentiating histological grade of cervical squamous cell carcinoma, and the correlation of each parameter with histological grade was analyzed. Results: No statistical difference of MTRasym, MK nor MD value was found among 3 groups (F=25.82, 15.21, 15.35, all P<0.01). MTRasym had the best diagnostic efficacy of differentiating high and moderate, moderate and poor differentiated cervical squamous cell carcinoma (AUC=0.85, 0.90, both P<0.01), which was better than MD (AUC=0.83, 0.78, P<0.01) and MK (AUC=0.82, 0.82, P<0.01), respectively. MK and MTRasym values were positively correlated(r=0.78, 0.69, both P<0.01) and MD value was negatively correlated with pathological grade of cervical squamous cell carcinoma (r=-0.68, P<0.01). Conclusion: Both APT and DKI parameters are helpful to differentiating pathological grades of cervical squamous cell carcinoma. Compared with DKI, APT has higher diagnostic efficacy.

Objective ToevaluatethevalueofMRDKIandDWIindiagnosingendometrialcarcinomaandevaluatingitspathologicalgrade. Methods TheDKIandDWIdataof48patientswithendometrialcarcinomaand27patientswithnormalendometrium wereanalyzed retrospectively.Thevaluesofmeankurtosis (MK),meandiffusion (MD)andADCinendometrialcarcinomaandnormalendometrium were measuredrespectively.Thesimilaritiesanddifferencesoftheparametersbetweentheendometrialnormalgroup(G0)andtheendometrialcarcinoma group (G1,G2,G3)werecomparedandanalyzed.TheROCcurvewasemployedtoevaluatethediagnosticefficacyandthresholdof eachparameter.P earson correlation wasappliedtoanalyzethecorrelationbetweeneachparametervalueandpathologicalgrade.Results The MK valuesincreasedgradually,meanwhiletheMDandADCvaluesdecreasedgraduallyinG0,G1,G2andG3groups.ExceptforMDand ADCvaluesbetweenG0andG1groups,othervalueswerestatisticallysignificantdifferent(P<0.05)betweendifferentgroups.In differentiatingoftheG0/(G1+G2+G3),G0/G1,G1/G2,G2/G3,theMKvalueshadthehighestdiagnosticefficacy(AUC=09.2,07.6,09.0,0.96, P<0 .05 ).M oreover ,in the correlation of pathological grading ,M K>M D>A D C (r=0 .850 ,0 .781 ,0 .709 ,P<0 .05 ).Conclusion Both DKIandDWIcandiagnoseandevaluatepathologicalgradeofendometrialcarcinoma.ComparedwithDWI,DKIembracesmoreperfectmathematical modelandmoresensitiveparameters,andcanbeusedasaneffectivemethodtoevaluatethepathophysiologicalfeaturesofendometrialcarcinoma.

Purpose To explore the value of a prediction model based on diffusion weighted imaging(DWI)deep learning features in endometrial cancer microsatellite instability status assessment.Materials and Methods DWI data of 32 microsatellite instability and 55 microsatellite stability endometrial cancer patients were analysed from June 2020 to April 2023 in Xinxiang Central Hospital,retrospectively.Apparent diffusion coefficient(ADC)values of the primary lesions were measured,and deep learning features and imaging histological features of the primary lesions were extracted using multilayer convolutional neural networks and PyRadiomics,respectively.The least absolute shrinkage and selection operator and random forest were used for feature screening and model building,respectively.The area under the receiver operating characteristic curve(AUC)and net reclassification improvement were used to evaluate model performance.Bootstrap based on 1 000 resamples was used for internal validation of the model.Results For the deep learning model,a total of 6 features were included,the 7th,57th,77th,82nd,97th and 108th features,with an AUC of 0.905(95％CI 0.823-0.957);for the radiomics model,a total of 6 features were included,1 neighborhood grey level difference matrix,4 grey level region size matrices and 1 grey level tour length matrix feature,with an AUC was 0.844(95％CI 0.751-0.913);for ADC values,the microsatellite instability group had smaller ADC values than the microsatellite stability group(t=-4.123,P＜0.001),with an AUC of 0.810(95％CI 0.712-0.886).Compared with the radiomics model and ADC values,the deep learning model showed improved risk prediction,with net reclassification improvements of 0.856 and 0.486(P＜0.01,P=0.024),respectively.In Bootstrap-based internal validation,the deep learning model also demonstrated higher performance than the radiomics model,with AUCs of 0.897(95％CI0.889-0.905)and 0.829(95％CI0.812-0.839),respectively.Conclusion A prediction model based on deep learning features of DWI images can provide a better assessment of microsatellite instability status in endometrial cancer patients than radiomics model and ADC values.