Objective:To analyze the application value of breast ultrasound artificial intelligence S-Detect technology in the diag-nosis of BI-RADS 4 breast masses.Methods:Totally 102 patients diagnosed with BI-RADS 4 breast masses(102 masses)by conven-tional ultrasound were reviewed.All of them underwent detection using breast ultrasound S-Detect technology.Histopathological results were used as the gold standard to compare the diagnostic efficacy of conventional ultrasound and breast ultrasound S-Detect technology for BI-RADS 4 breast masses.Results:Among the 102 cases enrolled,62 cases were confirmed by pathology,including 33 cases with benign masses and 29 cases with malignant masses.The sensitivity,specificity,accuracy,positive and negative predictive values of breast ultrasound S-Detect technology for diagnosing benign and malignant BI-RADS 4 breast masses(93.10％,96.97％,95.16％,96.43％and 96.12％)were higher than those of conventional ultrasound(72.41％,78.79％,75.81％,75.00％and 76.47％)(P＜0.05).The AUC of breast ultrasound S-Detect technology was 0.874,which was larger than that of conventional ultrasound(0.718)(Z=2.274,P=0.023).Conclusion:Breast ultrasound S-Detect technology has high value in differential diagnosis of benign and malignant BI-RADS 4 breast masse and is worthy of clinical promotion.