Radiomics-driven prediction of pathologic complete response in non-mass breast cancer using post-neoadjuvant chemotherapy preoperative dynamic contrast-enhanced magnetic resonance imaging

Key Points

• The aim is to predict pathologic complete response (pCR) in non-mass breast cancer using radiomics from MRI images after neoadjuvant chemotherapy.
• Developed a radiomics model based on dynamic contrast-enhanced MRI analysis.
• Performed external validation of the model to confirm its accuracy.
• Evaluated the predictive ability for identifying patients likely to benefit from neoadjuvant chemotherapy.
• The radiomics model accurately predicts pCR in patients.
• Successful external validation suggests the model is interpretable and reproducible.
• The approach could help avoid ineffective treatments for non-responders.