Investigating the optimal timing for the ultrasound prediction of a pathologic complete response in neoadjuvant breast cancer treatment.

Background: Neoadjuvant therapy (NAT) for breast cancer requires effective monitoring to assess the treatment response. To optimize treatment strategies, the early prediction of the therapeutic response is crucial. This study evaluated the predictive performance of three ultrasound models-the longest axis model (LAM), the dual axes model (DAM), and the manual segment model (MSM)-with a focus on early treatment cycles, and the relationship between tumor shrinkage and the probability of a pathologic complete response (pCR). Methods: In total, 121 breast cancer patients (with 942 ultrasound images) at the Renmin Hospital of Wuhan University from December 2020 to July 2023 were enrolled in this prospective study. The ability of the three ultrasound models to predict the pCR across 6-8 NAT cycles was compared. Tumor response was measured as the tumor shrinkage ratio (TSR) relative to the baseline and the preceding cycle. Area under the curve (AUC) values were calculated for each model and cycle, and statistical significance was determined using the DeLong test. A logistic regression model based on the first-cycle MSM was used to quantify the relationship between the TSR and the probability of a pCR. Results: The models had the highest AUC values in the first cycle of NAT, indicating their superior early predictive performance (P<0.05). Tumor shrinkage was significantly greater in the pCR group than in the non-pCR group. The logistic regression analysis based on the first-cycle MSM revealed a strong correlation between tumor shrinkage and the probability of a pCR, such that patients with ≥50% shrinkage had a higher likelihood of achieving a pCR. Conclusions: Early cycle ultrasound assessments, particularly those that used the MSM, have strong predictive value for the pCR. Integrating a tumor shrinkage-based probability analysis enhances the predictive accuracy of the models. These findings support the use of early ultrasound evaluation in clinical practice to optimize NAT strategies and patient outcomes.