Knowledge Tensor-Aided Breast Ultrasound Image Assistant Inference Framework

Breast cancer is one of the most prevalent cancers in women nowadays, and medical intervention at an early stage can significantly improve prognosis patients. ultrasound (BUS) a widely used tool for screening breast primary care hospitals but it relies heavily on ability experience physicians. Accordingly, we propose knowledge tensor-based Imaging Reporting Data System (BI-RADS)-score-assisted generalized inference model, which uses BI-RADS score senior physicians as gold standard to construct tensor model infer benignity malignancy tumors axes diagnostic results against those junior provide aid diagnosis. The experimental showed that AUC constructed using characteristics labeled by radiologists achieved 0.983 (95% confidential interval (CI) = 0.975–0.992) benign malignant cancer, while performance was only 0.849 CI 0.823–0.876). With fusion, improved 0.887 0.864–0.909). Therefore, our proposed effectively help reduce misclassification and, thus, breast-ultrasound-assisted