Although endocrine therapy is an effective method to treat estrogen receptor (ER)–positive breast cancer, approximately 30%–40% of all hormone receptor–positive tumors display de novo resistance. The aim of our current study was to analyze whether ¹⁸F-labeled fluoromisonidazole (1-(2-nitro-1-imidazolyl)-2-hydroxy-3-fluoropropane [¹⁸F-FMISO]) PET/CT could predict primary resistance to hormonal therapy in ER-positive breast cancer. Postmenopausal women who had ER-α–positive breast cancer, stages II–IV, and had never received prior endocrine therapy were prospectively enrolled in this study. Patients underwent both ¹⁸F-FDG and ¹⁸F-FMISO PET/CT scans before and after treatment. The hottest ¹⁸F-FDG standardized uptake value (SUV) in the tumor foci, the SUVs at 2 and 4 h, and the TBR2 h and TBR4 h for the target lesions were calculated (TBR2 h = SUV2 h_T/SUV2 h_B and TBR4 h = SUV4 h_T/SUV4 h_B [TBR is the tumor-to-background ratio]). Clinical outcomes of primary endocrine therapy with letrozole were evaluated according to the criteria of the World Health Organization after at least 3 mo of treatment. Immunohistochemistry for markers of proliferation (Ki67) and hypoxia-induced factor 1α was performed on a subset of tumors that had undergone biopsy or surgery. Pearson and Spearman analysis was used to determine the correlation between the parameters of ¹⁸F-FDG and ¹⁸F-FMISO uptake and clinical or immunohistochemistry outcomes with a 0.01 threshold for statistical significance. A total of 45 lesions (13 primary, 32 metastatic) from 20 patients met the inclusion criteria in this study. Baseline ¹⁸F-FDG and ¹⁸F-FMISO PET/CT scans were obtained for 33 lesions from 16 patients. The correlation between baseline ¹⁸F-FDG uptake and clinical outcome was weak and did not reach statistical significance (r = 0.37, P = 0.031). However, there was a significantly positive correlation between baseline ¹⁸F-FMISO uptake (SUV2 h_T, TBR2 h, SUV4 h_T, and TBR4 h) and clinical outcomes after ≥3 mo of primary endocrine therapy with letrozole (r = 0.77, 0.76, 0.71, and 0.78, respectively; P < 0.0001). The application of a TBR4 h cutoff of ≥1.2 allowed the prediction of 88% of the cases of progressive disease (15/17). Despite poor correlation between ¹⁸F-FMISO uptake and hypoxia-induced factor 1α expression, a marginal positive correlation between TBR4 h and Ki67 expression was measured (r = 0.51, P = 0.011) in a subset of malignant lesions acquired by biopsy or surgery. ¹⁸F-FMISO PET/CT can be used to predict primary endocrine resistance in ER-positive breast cancer.