Abstract
Background
To investigate factors predicting calcifications without residual carcinoma (ypCalc_0) or with residual carcinoma (ypCalc_ca) and to develop a prediction model for patients exhibiting residual suspicious calcifications on mammography but complete response on MRI after neoadjuvant chemotherapy (NAC).
Methods
This retrospective study included breast cancer patients undergoing NAC, showing residual suspicious mammographic calcifications but complete response on MRI between January 2019 and December 2020 (development set) and between January 2021 and December 2022 (validation set). Multivariable logistic regression analysis identified significant factors associated with ypCalc_0. The prediction model, developed using a decision tree and factors from logistic regression analysis, was validated in the validation set.
Results
The development set included 134 women (mean age, 50.6 years; 91 with ypCalc_0 and 43 with ypCalc_ca) and validation set included 146 women (mean age, 51.0 years; 108 with ypCalc_0 and 38 with ypCalc_ca). Molecular subtype (P = .0002) and high Ki-67 (P = .02) emerged as significant independent factors associated with ypCalc_0 in the development set. The prediction model, incorporating hormone receptor (HR)−/human epidermal growth factor receptor 2 (HER2) + with high Ki-67 as ypCalc_0 predictors, and HR+/HER2 − cancers or HR+/HER2 + or triple negative (TN) cancers with low Ki-67, as ypCalc_ca predictors, achieved an area under receiver operating characteristic curve of 0.844 (95% CI, 0.774 − 0.914) in the validation set.
Conclusion
Minimized surgery may be considered for managing residual calcifications in HR−/HER2 + with high Ki-67 cancers, while complete excision is recommended for HR+/HER2 − breast cancers or for HR+/HER2 + or TN breast cancers with low Ki-67.