Segmentation-guided peritumoral radiomics and machine learning for ultrasound-based classification of salivary gland tumors

BACKGROUND: Preoperative differentiation of benign and malignant salivary gland tumors (SGTs) remains challenging because of overlapping ultrasonographic features. OBJECTIVES: To develop and validate a segmentation-guided machine learning model using peritumoral radiomic features for ultrasound-based classification of SGTs. MATERIALS AND METHODS: = 51; January-December 2025). RESULTS: The YOLOv8 model achieved Dice coefficients of 0.9485 and 0.8896 in the training and testing cohorts, respectively. Twelve radiomic features were retained for model development. Among the evaluated classifiers, the Support Vector Classifier (SVC) demonstrated the best performance, achieving AUCs of 0.8117 and 0.7951 in the testing and validation cohorts, respectively. The complete pipeline was implemented as both standalone and web-based applications. CONCLUSIONS: Segmentation-guided peritumoral radiomics combined with machine learning represents an interpretable and promising adjunctive approach for ultrasound-based classification of salivary gland tumors.