Comparison between 18F-FDG PET image-derived indices for early prediction of response to neoadjuvant chemotherapy in breast cancer

Abstract

The goal of this study was to determine the best predictive factor among image-derived parameters extracted from sequential (18)F-FDG PET scans for early tumor response prediction after 2 cycles of neoadjuvant chemotherapy in breast cancer.

Methods: 51 breast cancer patients were included. Responder and nonresponder status was determined by histopathologic examination according to the tumor and node Sataloff scale. PET indices (maximum and mean standardized uptake value [SUV], metabolically active tumor volume, and total lesion glycolysis [TLG]), at baseline and their variation (Δ) after 2 cycles of neoadjuvant chemotherapy were extracted from the PET images. Their predictive value was investigated using Mann-Whitney U tests and receiver-operating-characteristic analysis. Subgroup analysis was also performed by considering estrogen receptor (ER)-positive/human epidermal growth factor receptor 2 (HER2)-negative, triple-negative, and HER2-positive tumors separately. The impact of partial-volume correction was also investigated using an iterative deconvolution algorithm.

Results: There were 24 pathologic nonresponders and 27 responders. None of the baseline PET parameters was correlated with response. After 2 neoadjuvant chemotherapy cycles, the reduction of each parameter was significantly associated with response, the best prediction of response being obtained with ΔTLG (96% sensitivity, 92% specificity, and 94% accuracy), which had a significantly higher area under the curve (0.91 vs. 0.82, P = 0.01) than did ΔSUVmax (63% sensitivity, 92% specificity, and 77% accuracy). Subgroup analysis confirmed a significantly higher accuracy for ΔTLG than ΔSUV for ER-positive/HER-negative but not for triple-negative and HER2-positive tumors. Partial-volume correction had no impact on the predictive value of any of the PET image-derived parameters despite significant changes in their absolute values.

Conclusion: Our results suggest that the reduction after 2 neoadjuvant chemotherapy cycles of the metabolically active volume of primary tumor measurements such as ΔTLG predicts histopathologic tumor response with higher accuracy than does ΔSUV measurements, especially for ER-positive/HER2-negative breast cancer. These results should be confirmed in a larger group of patients as they may potentially increase the clinical value and efficiency of (18)F-FDG PET for early prediction of response to neoadjuvant chemotherapy.