68Ga-Labeled Fibroblast Activation Protein Inhibitor PET/CT for Monitoring Neoadjuvant Chemotherapy Responses in Breast Cancer Subtypes

Background ⁶⁸Ga-labeled fibroblast activation protein inhibitor (⁶⁸Ga-FAPI) PET/CT has shown promising potential in predicting pathological complete response (pCR) in patients with breast cancer (BC). However, current literature lacks comprehensive data addressing molecular subtype-specific variations. This study aims to evaluate the predictive value of ⁶⁸Ga-FAPI PET/CT across different BC molecular subtypes. Methods This prospective study enrolled 66 patients with clinical stage II-III BC scheduled for neoadjuvant chemotherapy (NAC). Patients underwent ⁶⁸Ga-FAPI PET/CT at baseline (PET1), after two NAC cycles (PET2), and presurgery (PET3). The maximum standardized uptake value (SUVmax) and its percentage change from baseline (ΔSUVmax) were calculated for the primary tumors. Pathological response was assessed postsurgery. Patients were stratified into three molecular subtypes: hormone receptor-positive/HER2-negative (HR+/HER2-), HER2-positive (HER2+), and triple-negative breast cancer (TNBC). Receiver operating characteristic (ROC) curve analysis was utilized to evaluate the predictive performance of FAPI parameters for pCR. Results Among the 66 patients, 21 (31.8%) achieved pCR, with rates varying significantly across molecular subtypes ( P  = 0.002). Baseline ⁶⁸Ga-FAPI uptake (SUVmax1) was significantly higher in HER2 + tumors (17.98 ± 6.34) compared to HR+/HER2- (14.37 ± 4.11) and TNBC tumors (15.00 ± 5.25) ( P  = 0.043). The predictive value of ⁶⁸Ga-FAPI parameters for pCR was highly dependent on molecular subtype. In HER2 + tumors, early response assessment was most effective, with ΔSUVmax1 (change after two cycles) being the strongest predictor (area under the curve [AUC] = 0.799). A cutoff of -69.49% yielded 85.7% sensitivity and 72.7% specificity. For TNBC, late-phase parameters demonstrated exceptional accuracy, with SUVmax3 (pre-surgery) achieving near-perfect discrimination (AUC = 0.967). A cutoff of ≤ 2.19 provided 100% sensitivity and 95.5% specificity. In HR+/HER2- tumors, late-phase parameters were most predictive, with SUVmax3 showing excellent performance (AUC = 0.948). A cutoff of ≤ 1.58 yielded 75.0% sensitivity and 91.7% specificity. Conclusion The predictive efficacy of ⁶⁸Ga-FAPI PET/CT for pCR demonstrates substantial variability across BC molecular subtypes. These findings underscore the potential of ⁶⁸Ga-FAPI PET/CT to inform subtype-specific, personalized treatment approaches.