Clinical application value of ultrasound artificial intelligence technology in the diagnosis of breast nodules

ObjectiveTo investigate the application value of ultrasound artificial intelligence S-Detect technology in the differential diagnosis of benign and malignant breast nodules.MethodsSuspicious breast nodules were examined using S-Detect technology, conventional ultrasound (US), and contrast-enhanced ultrasound (CEUS). The differential diagnoses were compared with final pathological results to analyze the diagnostic efficacy of these three techniques in distinguishing benign from malignant breast nodules.ResultsThe accuracy of S-Detect in diagnosing benign and malignant breast nodules was 0.859, with a sensitivity of 0.915, specificity of 0.839, and an area under the ROC curve (AUC) of 0.877. The value of AUC was significantly higher than that of US (0.727, <i>P</i> < 0.01), but lower than US + CEUS (0.908, <i>P</i> < 0.05). According to the final pathological classification, S-Detect demonstrated higher accuracy in distinguishing benign from malignant lesions in complex cysts, hyperplastic nodules, and adenomas compared to US (<i>P</i> < 0.05), with no significant difference when compared to US + CEUS. In differentiating malignant breast tumors, there was no significant difference in accuracy between S-Detect and US.ConclusionUltrasound artificial intelligence S-Detect technology exhibits high diagnostic efficacy in the differential diagnosis of benign and malignant breast nodules.