Purpose Investigate whether 18F-FDG PET-CT has the potential to predict the major pathologic response (MPR) to neoadjuvant sintilimab in resectable NSCLC patients, and the potential of sifting patients who probably benefit from immunotherapy. Methods Treatment-naive patients with resectable NSCLC (stage IA–IIIB) received two cycles of sintilimab (200 mg, intravenously, day 1 and 22). Surgery was performed between day 29 and 43. PET-CT was obtained at baseline and prior to surgery. The following lean body mass–corrected metabolic parameters were calculated by PET VCAR: SULmax, SULpeak, MTV, TLG, ΔSULmax%, ΔSULpeak%, ΔMTV%, ΔTLG%. PET responses were classified using PERCIST. The above metabolic information on FDG-PET was correlated with the surgical pathology. (Registration Number: ChiCTR-OIC-17013726). Results Thirty-six patients received 2 doses of sintilimab, all of whom underwent PET-CT twice and had radical resection (35) or biopsy (1). MPR occurred in 13 of 36 resected tumors (36.1%, 13/36). The degree of pathological regression was positively correlated with SULmax (p = 0.036) of scan-1, and was negatively correlated with all metabolic parameters of scan-2, and the percentage changes of the metabolic parameters after neoadjuvant therapy (p peak% Conclusions 18F-FDG PET-CT can predict MPR to neoadjuvant sintilimab in resectable non-small cell lung cancer.