To establish and validate a machine learning based radiomics model for detection of perineural invasion (PNI) in gastric cancer (GC).
This retrospective study included a total of 955 patients with GC selected from two centers; they were separated into training (n=603), internal testing (n=259), and external testing (n=93) sets. Radiomic features were derived from three phases of contrast-enhanced computed tomography (CECT) scan images. Seven machine learning (ML) algorithms including least absolute shrinkage and selection operator (LASSO), naïve Bayes (NB), k-nearest neighbor (KNN), decision tree (DT), logistic regression (LR), random forest (RF), eXtreme gradient boosting (XGBoost) and support vector machine (SVM) were trained for development of optimal radiomics signature. A combined model was constructed by aggregating the radiomic signatures and important clinicopathological characteristics. The predictive ability of the radiomic model was then assessed with receiver operating characteristic (ROC) and calibration curve analyses in all three sets.
The PNI rates for the training, internal testing, and external testing sets were 22.1, 22.8, and 36.6%, respectively. LASSO algorithm was selected for signature establishment. The radiomics signature, consisting of 8 robust features, revealed good discrimination accuracy for the PNI in all three sets (training set: AUC = 0.86; internal testing set: AUC = 0.82; external testing set: AUC = 0.78). The risk of PNI was significantly associated with higher radiomics scores. A combined model that integrated radiomics and T stage demonstrated enhanced accuracy and excellent calibration in all three sets (training set: AUC = 0.89; internal testing set: AUC = 0.84; external testing set: AUC = 0.82).
The suggested radiomics model exhibited satisfactory prediction performance for the PNI in GC.