Abstract
OBJECTIVES: Human epidermal growth factor receptor 2 (HER2)-positive breast cancer is an aggressive subtype; however, neoadjuvant therapy (NAT) can improve patient outcomes. Accurate prediction of pathological complete response (pCR) is crucial for guiding treatment adjustments. This study aimed to evaluate the predictive value of ultrasound elastography features for pCR in patients with HER2-positive breast cancer undergoing NAT. METHODS: This retrospective study included 80 patients with HER2-positive breast cancer who received NAT and were evaluated for pCR by histopathological examination. Ultrasound elastography features, including strain ratio and strain difference, were compared between patients achieving pCR (n = 36) and those without pCR (n = 44). Logistic regression and receiver operating characteristic curve analyses were performed. An external validation cohort of 72 patients was used to assess model robustness. RESULTS: Posterior shadowing on ultrasound and lower strain ratio and difference at six weeks were significantly associated with higher pCR rates. Logistic regression identified posterior shadowing (OR = 6.634, P = 0.008), strain ratio (OR = 0.064, P = 0.022), and strain difference (OR = 0.678, P < 0.001) as independent predictors of pCR. The combined predictive model demonstrated excellent performance, with an area under the curve of 0.871 in the primary cohort and 0.884 in the validation cohort. CONCLUSION: Ultrasound elastography features, particularly posterior shadowing and changes in strain metrics, are independent predictors of pCR in patients with HER2-positive breast cancer receiving NAT.