Objective:

To develop and validate a nomogram integrating DCE-MRI features and clinicopathological parameters for predicting pathological complete response (pCR) in HER2-positive breast cancer patients receiving neoadjuvant chemotherapy (NAC).

Approach:

• Study Design: Retrospective analysis of 183 HER2-positive breast cancer patients who received NAC followed by surgery, with 166 patients included after data exclusion.
• Data Collection: DCE-MRI imaging features and clinicopathological variables were analyzed to identify independent predictors of pCR.
• Nomogram Development: A nomogram was constructed and validated using ROC curves, calibration plots, and decision curve analysis.

Key Findings:

• The overall pCR rate was 44.6% (74/166 evaluable patients).
• Molecular subtype analysis revealed significantly higher pCR rates in HR-/HER2+ patients (52.2%) versus HR+/HER2+ patients (38.5%, P = 0.048).
• Independent predictors of pCR included ADCmin value, Ki-67 index, tumor size, clinical N stage, and HR status.
• The nomogram demonstrated excellent discrimination with AUC of 0.823 in the training cohort and 0.795 in the validation cohort.
• Calibration plots showed good agreement (Hosmer-Lemeshow P = 0.412).
• DCA confirmed clinical utility across threshold probabilities of 0.15-0.75.

Interpretation:

The developed nomogram integrates DCE-MRI features and clinicopathological parameters to predict pCR in HER2-positive breast cancer patients undergoing NAC.

Limitations:

• The study is retrospective, which may introduce bias.
• The sample size may limit the generalizability of the findings.

Conclusion:

The nomogram facilitates individualized treatment decision-making for HER2-positive breast cancer patients.