Radiomics features were extracted through MRI images and different prediction models (clinical model, logistic regression [LR], random forest [RF], support vector machine [SVM], clinical-LR model, clinical-RF model, and clinical-SVM model) for extramural venous invasion (EMVI) were constructed on the basis of radiomics features and clinical factors, respectively. The optimal model, which had the best predictive efficiency, was screened out for predicting the EMVI status of rectal adenocarcinoma patients.
This abstract and the presentation materials are available to members only; a login is required.