Skip to main content
Fig. 2 | BMC Cancer

Fig. 2

From: 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 images

Fig. 2

The workflow of this study. a Endoscopic biopsy, laboratory tests, and CT images of patients with gastric cancer were collected. b Differentiation degree based on biopsy, tumor markers, CT morphological characteristics based on late arterial phase, CT value-related parameters, and texture parameters were extracted. c Multivariate models were built based on binomial logistic regression and machine learning algorithms. d Diagnostic performance for predicting serosal invasion was obtained by ROC curve analysis, and a nomogram was used to visualize the multivariate model. AFP, alpha fetoprotein; CEA, carcinoembryonic antigen; CA, carbohydrate antigen; CT, computed tomography; LASSO, least absolute shrinkage and selection operator; SVM, support vector machine; RF, random forest; ANN, artificial neural network; KNN, k nearest neighbors; ROC, receiver operating characteristic

Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us