Background: Currently, only a fraction of patients with non-small cell lung cancer (NSCLC) treated with immune checkpoint inhibitors (ICIs) experience a durable clinical benefit (DCB). According to NCCN guidelines, Programmed death-ligand 1 (PD-L1) expression status determined by immunohistochemistry (IHC) of biopsies is the only clinically approved companion biomarker to trigger the use of ICI therapy. Based on prior work showing a relationship between quantitative imaging and gene expression, we hypothesize that quantitative imaging (radiomics) can provide an alternative surrogate for PD-L1 expression status in clinical decision support. Methods: ¹⁸F-FDG-PET/CT images and clinical data were curated from 697 patients with NSCLC from three institutions and these were analyzed using a small-residual-convolutional-network (SResCNN) to develop a deeply learned score (DLS) to predict the PD-L1 expression status. This developed model was further used to predict DCB, progression-free survival (PFS), and overall survival (OS) in two retrospective and one prospective test cohorts of ICI-treated patients with advanced stage NSCLC. Results: The PD-L1 DLS significantly discriminated between PD-L1 positive and negative patients (area under receiver operating characteristics curve ≥0.82 in the training, validation, and two external test cohorts). Importantly, the DLS was indistinguishable from IHC-derived PD-L1 status in predicting PFS and OS, suggesting the utility of DLS as a surrogate for IHC. A score generated by combining the DLS with clinical characteristics was able to accurately (C-indexes of 0.70–0.87) predict DCB, PFS, and OS in retrospective training, prospective testing and external validation cohorts. Conclusion: Hence, we propose DLS as a surrogate or substitute for IHC-determined PD-L1 measurement to guide individual pretherapy decisions pending in larger prospective trials.

Background: Immunotherapy targeting programmed cell death 1 (PD-1) or its ligand 1 (PD-L1) has shown promising results in non-small cell lung cancer (NSCLC) patients. Exploring PD-L1 expression could help to select NSCLC candidates for immunotherapy. Fluorine-18 fluorodeoxyglucose (FDG) PET/CT could provide phenotypic information on malignant tumors. Thus, this study investigated PD-L1 expression correlation with metabolic parameters of FDG PET/CT and clinicopathological characteristics in NSCLC. Methods: FDG PET/CT metabolic parameters including maximum standard uptake (SUVmax), metabolic tumor volume and total lesion glycolysis of primary lesion (MTV-P, TLG-P), and combination of primary lesion and metastases (MTV-C, TLG-C) were compared with PD-L1-positive expression in patients with NSCLC. Moreover, clinicopathological characteristics, including age, gender, smoking history, serum tumor markers, tumor location, size, TNM stage, and genetic mutation were also reviewed. Results: All 374 patients (215 men; 159 women; age 63 ± 9 years) included 283 adenocarcinomas (ACs) and 91 squamous cell carcinomas (SCCs). PD-L1 expression was positive in 27.8% (104/374) cases. SUVmax, TLG-P, and TLG-C of PD-L1 positivity were significantly higher than PD-L1 negativity. Moreover, PD-L1 expression was obviously correlated with man, smoking, and central NSCLC. If ACs and SCCs were separately analyzed, PD-L1 positivity in ACs and SCCs was 21.6% (61/283) and 47.5% (43/91), respectively, and only SUVmax was obviously associated with PD-L1 expression. Furthermore, multivariate analysis revealed that only SUVmax was an independent predictor of PD-L1 positive expression in overall NSCLC, AC, and SCC. Using a SUVmax cut-off value of 12.5, PD-L1 status of NSCLC was predicted by FDG PET/CT with sensitivity, specificity, and accuracy of 65.4%, 86.7%, and 80.7%, respectively. Conclusions: PD-L1 expression of NSCLC was related to SUVmax, TLG, man, smoking, and central location. However, only SUVmax was an independent predictor of PD-L1 positivity, which could help to explore the existence of immune checkpoints.