Abstract
Background: The advent of programmed cell death-1/programmed death-ligand 1 (PD-1/PD-L1) inhibitors has revolutionized lung cancer treatment, necessitating accurate PD-L1 immunohistochemical (IHC) assessment. While standardized for formalin-fixed paraffin-embedded histological samples, PD-L1 testing on cytology remains challenging. This review aims to address the complexities of PD-L1 IHC in cytology, focusing on validation guidelines, quality assessment, cytohistological correlation, and interobserver variability. Summary: This review synthesizes current guidelines and research on PD-L1 IHC in cytology; in particular, recent College of American Pathologists (CAP) guidelines emphasize the necessity for rigorous validation, particularly for non-formalin-fixed specimens. As far as cytohistological concordance studies are concerned, the review of 48 original articles revealed significant variability in PD-L1 expression, with concordance rates ranging from 54 to 100% at the 1% cutoff and 82–100% at the 50% cutoff. Finally, interobserver variability, particularly in the 1–49% PD-L1 expression range, further complicates accurate assessment. The review also discusses the challenges associated with quality assessment in cytology, including the lack of standardized control materials and external quality assessment (EQA) programs specifically tailored for cytological samples. Key Messages: PD-L1 testing in cytology is feasible but faces substantial challenges compared to histological specimens. Validation of PD-L1 IHC protocols for cytological preparations, especially non-formalin-fixed samples, is essential. Concordance between cytological and histological PD-L1 expression is variable, highlighting the need for caution in interpretation. Interobserver variability, particularly in cases with intermediate PD-L1 expression (1–49%), affects diagnostic reproducibility. The development of standardized quality control materials and EQA programs for cytology is urgently needed to support consistent and reliable PD-L1 testing.