Preoperative Noninvasive Prediction of Tumor Budding Based on Radiomics Model of T2WI Tumor and Peritumoral Regions...

To investigate the ability of a radiomics model of T2-weighted imaging (T2WI) tumor and peritumoral regions for predicting noninvasively tumor budding grading in rectal patients.

This retrospective study included 478 patients diagnosed with rectal cancer from three different institutions and randomly divided into a training cohort (n=309), an internal testing cohort (n=78), and an external validation cohort (n=91). The model that achieved the balance between discrimination and stability in the training and internal testing cohort was selected as the optimal peritumor model. A nomogram was constructed by an ensemble model combined peritumoral model with tumoral model and independent clinical predictor. The Receiver Operating Characteristic curve (ROC), the Area Under the ROC curve (AUC), decision curve analysis (DCA), calibration analysis, and the DeLong test were adopted to evaluate the performance of models. The Shapley Additive Explanations (SHAP) algorithm was used to visually interpret the weights of each feature that constructed the models.

The peritumoral model constructed by features extracted from the 5 mm extension distance achieved the balance between discrimination and stability in the training and internal test cohort, with AUC values of 0.841 and 0.761, respectively. The ensemble model showed certain discriminative ability in the external validation cohort, with AUC of 0.853.

The ensemble model that integrated radiomics features from tumor and peritumoral regions and independent clinical predictor can serve as a promising noninvasive assessment tool for clinicians to predict TB grading in rectal cancer patients preoperatively.