Diagnostic value of high-frequency ultrasound in preoperative evaluation of benign and malignant skin tumors

Objective To develop a High-frequency ultrasound (HFUS)-based predictive nomogram integrating clinical and ultrasound features for distinguishing malignant from benign skin tumors. Methods This retrospective study enrolled 185 patients who underwent preoperative HFUS examination for skin tumors. Patients were randomly divided into training (n=130; 73 malignant, 57 benign) and validation (n=55; 31 malignant, 24 benign) cohorts. Clinical characteristics and ultrasound features were systematically analyzed. Univariate and multivariate logistic regression analyses were used to identify independent predictors of malignancy, which were incorporated into a nomogram. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA). Results Malignant tumors demonstrated significantly greater multilayer involvement, irregular margins, heterogeneous echogenicity, raised surface morphology, and abundant intralesional vascularity compared to benign tumors (all P<0.001). Multivariate analysis identified five independent predictors of malignancy: advanced age (OR = 1.01, 95% CI: 1.00 - 1.01), multilayer involvement (OR = 1.19, 95% CI: 1.12 - 1.26), unclear margins (OR = 1.36, 95% CI: 1.21 - 1.54), raised surface morphology (OR = 1.10, 95% CI: 1.01 - 1.21), and heterogeneous echogenicity (OR = 1.09, 95% CI: 0.99 - 1.21). The nomogram achieved area under the curve (AUC) values of 0.98 (95% CI 0.95-1.00) in the training cohort and 0.98 (95% CI 0.95-1.00) in the validation cohort. Conclusions HFUS provides valuable information for preoperative evaluation of skin tumors. The nomogram demonstrates good diagnostic performance and clinical utility for distinguishing malignant from benign skin tumors.