Development And Validation Of Multivariate Models Integrating Preoperative Clinicopathological Features And Radiographic Findings Based On Late Arterial Phase CT Images For Staging In Gastric Cancer

Part ?: Development and validation of multivariate models integrating preoperative clinicopathological features and radiographic findings based on late arterial phase CT images for predicting subserosal invasion in gastric cancerObjectives: This study was conducted to develop and validate multivariate models integrating clinicopathological features and radiographic findings based on late arterial phase(LAP)computed tomography(CT)images to predict subserosal invasion in gastric cancer(GC).Methods: Preoperative differentiation degree based on biopsy,6 tumor markers,10 CT morphological characteristics based on LAP,18 CT value-related parameters,and 35 CT texture parameters of 145 patients with GC were analyzed retrospectively.The differences in parameters between T1-2 and T3-4 were analyzed by the Mann-Whitney U test.Multivariate models based on regression analysis and machine learning algorithms were performed to improve diagnostic efficacy.Results: The differentiation degree,carbohydrate antigen(CA)125,6 CT morphological characteristics,5 CT value-related parameters,and 19 texture parameters showed significant differences between T1-2 and T3-4 groups in the primary cohort(all p<0.05).The multivariate model integrating clinicopathological parameters and radiographic findings based on regression achieved an area under the curve(AUC)of 0.919 and 0.955 in the primary and validation cohort,respectively.The model generated by the support vector machine(SVM)algorithm showed better performance than those generated by other algorithms in the primary and validation cohorts,with AUCs of 0.870 and 0.938,respectively.Conclusions: We developed and validated multivariate models integrating endoscopic biopsy,CT morphological characteristics based on LAP,and CT value-related and texture parameters to predict subserosal invasion in GCs and achieved satisfactory performance.Part ?: Prediction of serosal invasion in gastric cancer: development and validation of multivariate models integrating preoperative clinicopathological features and radiographic findings based on late arterial phase CT imagesObjectives: To develop and validate multivariate models integrating endoscopic biopsy,tumor markers,and computed tomography(CT)findings based on late arterial phase(LAP)to predict serosal invasion in gastric cancers(GCs).Methods: The preoperative differentiation degree,tumor markers,CT morphological characteristics,and CT value-related and texture parameters of 190 patients with GC were analyzed retrospectively.Multivariate models based on the regression analysis and machine learning algorithm were performed to improve diagnostic efficacy.Results: The differentiation degree,5 tumor markers,3 CT value-related parameters,and 21 texture parameters differed significantly between T1-3 and T4 GCs in the primary cohort(all p<0.05).Multivariate models based on the regression analysis,support vector machine(SVM),naive bayes(NB),and decision tree(RF)algorithm showed better performance,with areas under the curve of 0.918,0.805,0.819,and 0.836 in the primary cohort,respectively.Conclusions: We developed and validated multivariate models integrating endoscopic biopsy,tumor markers,CT morphological characteristics,and CT value-related and texture parameters to predict serosal invasion in GCs and achieved favorable performance.Part ?: Development and validation of multivariate models integrating preoperative clinicopathological parameters and radiographic findings based on late arterial phase CT images for predicting lymph node metastasis in gastric cancerObjectives: To develop and validate multivariate models integrating endoscopic biopsy,tumor markers,computed tomography(CT)morphological characteristics based on late arterial phase(LAP),and CT value-related and texture parameters to predict lymph node(LN)metastasis in gastric cancers(GCs).Methods: The preoperative differentiation degree based on biopsy,6 tumor markers,8 CT morphological characteristics based on LAP,18 CT value-related parameters,and 35 CT texture parameters of 185 patients(127 men and 58 women)with GC were analyzed retrospectively.The differences in parameters between N(-)and N(+)GCs were analyzed by the Mann-Whitney U test.Diagnostic performance was obtained by receiver operating characteristic(ROC)curve analysis.Multivariate models based on regression analysis and machine learning algorithms were performed to improve diagnostic efficacy.Results: The differentiation degree,3 tumor markers,6 CT morphological characteristics,8 CT value-related parameters,and 26 CT texture parameters showed significant differences between N(-)and N(+)GCs in the primary cohort(all p<0.05).The multivariate model integrating clinicopathological parameters and radiographic findings based on regression analysis achieved areas under the ROC curve(AUCs)of 0.884 and 0.933 in the primary and validation cohorts,respectively.The model generated by the naive bayes algorithm achieved AUCs of 0.829 and 0.781,respectively.Conclusions: We developed and validated multivariate models integrating endoscopic biopsy,CT morphological characteristics based on LAP,CT value-related parameters,and texture parameters to predict LN metastasis in GCs and achieved satisfactory performance.Part ?: Gastric poorly cohesive carcinoma: differentiation from tubular adenocarcinoma using nomograms based on CT findings in the 40 s late arterial phaseObjectives: To summarize the computed tomography(CT)findings of gastric poorly cohesive carcinoma(PCC)in the 40 s late arterial phase(LAP)and differentiate it from tubular adenocarcinoma(TAC)using an integrative nomogram.Methods: A total of 241 patients including 59 PCCs,109 TACs,and 73 other type gastric cancers were enrolled.Thirteen CT morphological characteristics of each lesion based on LAP were evaluated.In addition,CT value-related parameters were extracted from regions of interest(ROIs)encompassing the area of greatest enhancement on four-phase CT images.Nomograms based on regression models were built to discriminate PCCs from TACs and from non-PCCs.Receiver operating characteristic(ROC)curve analysis was performed to assess the diagnostic efficiency.Results: Six morphological characteristics,10 CT value-related parameters,and the enhanced curve type differed significantly among the above three groups in the primary cohort(all p<0.05).The paired comparison revealed that 10 CT value-related parameters differed significantly between PCCs and TACs(all p<0.05).The area under the curve(AUC)of the nomogram based on the multivariate model for discriminating PCCs from TACs was 0.954,which was confirmed in the validation cohort(AUC=0.895).The AUC of another nomogram for discriminating PCCs from non-PCCs was 0.938,which was confirmed in the validation cohort(AUC=0.880).Conclusions: In the 40 s LAP,the morphological characteristics and CT value-related parameters were significantly different among PCCs,TACs,and other types.PCCs were prone to manifest mucosal line interruption,diffuse thickening,infiltrative growth,and slow-rising enhanced curve(Type A).Furthermore,multivariate models were useful in discriminating PCCs from TACs and other types.