To determine whether [18F]-fluorodeoxyglucose (FDG) positron emission tomography (PET) can predict complete pathological response (pCR) in patients achieving a good clinical response to neoadjuvant chemotherapy for primary breast cancer, 10 patients underwent FDG PET scanning prior to definitive breast surgery. Scan reports were compared with histopathological findings. No abnormal uptake at the primary tumour site was visualised in any patient. 9 of the 10 patients had residual invasive carcinoma at operation, ranging from 2 to 20 mm in maximum dimension. One patient achieved a complete pathological response. Of the 5 patients who underwent axillary surgery, no axillary FDG uptake was seen preoperatively although 3 of the 5 were histologically node-positive. FDG PET did not reliably identify residual disease in this series of good clinical responders to neoadjuvant chemotherapy, and its discriminatory power as a tool to predict complete pathological response therefore appears to be inadequate for clinical use in this setting.