A non-invasive end-to-end intelligent assistance system for breast ultrasound

Although artificial intelligence enhances medical image classification to effectively improve lesion diagnosis accuracy and efficiency, it still faces generalization challenges in breast ultrasound and its clinical potential remains underutilized in complex real-world scenarios. Here, we develop and test an end-to-end breast intelligent recognition device (BIRD) for women across diverse institution/population datasets. The accuracy of BIRD in the internal test set is 0.837 (95% confidence interval: 0.827-0.846), which significantly improves radiologists' accuracy in 2 reader studies (P < 0.05). BIRD is applied in breast cancer screening for 6,817 individuals and shows high consistency (Cohen's kappa: 0.702 (95% confidence interval: 0.628-0.777)) with clinical assessments in real-world application across 107 hospitals. Pathological and molecular subtype models developed using data from five hospitals also exhibit satisfactory classification performance. These findings confirm BIRD's ability to improve diagnostic accuracy, assist screening, and characterize breast lesions, facilitating clinical adoption in breast health practice. The Chinese Clinical Trial Register: ChiCTR2300073777.