Diagnostic Accuracy of Post-Treatment ADC and MRI Response Assessment for Predicting Pathological Complete Response...

Background/Objectives: This study aimed to evaluate the diagnostic performance of post-neoadjuvant chemotherapy (NAC) contrast-enhanced MRI in breast cancer treatment response assessment and to determine whether apparent diffusion coefficient (ADC) parameters contribute to predicting and confirming pathologic complete response (pCR). Methods: This retrospective cohort study enrolled patients with histopathologically confirmed invasive breast cancer who underwent breast MRI before and after NAC, followed by surgical resection. Post-NAC MRI response was classified into four categories and subsequently dichotomised into complete response versus residual disease. On diffusion-weighted imaging (DWI), pre-treatment minimum and maximum ADC values, post-treatment ADC, and the percentage change in ADC (ΔADC) were calculated. Diagnostic performance was assessed by sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), receiver operating characteristic (ROC) curve analysis, and Cohen's kappa coefficient. Results: Of 188 patients, 19.7% achieved pCR. Post-NAC MRI complete response predicted pCR with 100% sensitivity and 90.1% specificity, with a Cohen's kappa of 0.781 and 15 false-positive cases. Post-treatment ADC achieved the highest predictive performance, with an area under the ROC curve (AUC) of 0.967 (optimism-corrected 0.958); at the derived threshold, sensitivity was 100.0% and specificity 96.7%. ΔADC was likewise a statistically significant predictor of pCR, and post-treatment ADC remained independent after adjustment. Pre-treatment ADC parameters carried no meaningful predictive value in the full-cohort analysis. Conclusions: Post-treatment ADC and ΔADC help identify true complete responders among cases that contrast-enhanced MRI alone misclassifies as positive. Incorporating quantitative diffusion parameters into standard post-NAC MRI assessment may support pCR confirmation and warrants prospective external validation.