The Emergence of the Potential Therapeutic Targets: Ultrasound-Based Radiomics in the Prediction of Human Epidermal Growth Factor Receptor 2-Low Breast Cancer

Rationale and Objectives To evaluate whether ultrasound-based radiomics features can effectively predict HER2-low expression in patients with breast cancer (BC). Material and Methods Between January 2021 and June 2023, patients who received US scans with pathologically confirmed BC in this multicenter study were included. In total, 383 patients from institution 1 were comprised of training set, 233 patients from institution 2 were comprised of validation set and 149 patients from institution 3 were comprised of external validation set. Radiomics features were derived from conventional ultrasound (US) images. The minimum redundancy and maximum relevancy and the least absolute shrinkage and selector operation algorithm were used to generate an US-based radiomics score (RS). Multivariable logistic regression analysis was used to select variables associated with HER2 expressions. The diagnostic performance of the RS was evaluated through the area under the receiver operating characteristic curve (AUC). Results In the training set, the RS yield an AUC of 0.81 (95%CI: 0.76–0.84) for differentiation HER2-zero from HER2-low and -positive cases, and performed well in validation set (AUC 0.84, 95%CI: 0.78–0.88) and external validation set (AUC 0.82, 95%CI: 0.73–0.90). In the subgroups analysis, the RS showed good performance in distinguishing HER2-zero from HER2 1 + , HER2 2 + and HER2-low tumors (AUC range, 0.79–0.87). Conclusion The RS based on conventional US is proven effective for predicting HER2-low expression in BC.