Programmed death ligand 1 (PD-L1) expression is the standard biomarker in advanced non-small cell lung cancer (NSCLC). However, manual evaluation of PD-L1 tumor proportion score (TPS) by pathologists has practical limitations of interobserver bias, variation in subjectivity on the area of interest, and intensive labor. This study aimed to explore whether the artificial intelligence (AI)-powered TPS analyzer could reduce the human discrepancy.
AI-powered TPS analyzer, namely Lunit SCOPE PD-L1, was developed with a total of 393,565 tumor cells annotated by board-certified pathologists for PD-L1 expression in 802 whole-slide images (WSI) of NSCLC stained by 22C3 pharmDx immunohistochemistry. Three independent pathologists labeled PD-L1 TPS into 3 class categories: TPS < 1%, 1-49%, or ≥ 50%, of 479 NSCLC slides. For the cases of disagreement between each pathologist and AI model, the pathologists were asked to revise TPS class in assistance with AI model which not only detects PD-L1 positivity of tumor cells, but also calculates WSI-level TPS. Finally, we compared the concordance rate of three pathologists with or without AI assistance.
Without AI assistance, 3 pathologists concordantly labeled TPS in 81.4% of cases (n = 390 / 479, κ = 0.798), and the concordance rate between the consensus of pathologists and standalone AI model was 86.4% (n = 337 / 390). Afterward, pathologists revised their initial labeling with assistance of AI model for the cases of disagreement between the pathologist and AI model (n = 91, 93, and 107, respectively for each pathologist). Interestingly, the overall concordance rate of three pathologists with AI assistance was increased to 90.2% (n = 432 / 479, κ = 0.890). Subgroup analysis showed that the concordance rates without AI assistance according to PD-L1 TPS <1%, 1-49%, and ≥50% class were 67.9%, 72.2%, and 92.4%, respectively, which were increased with AI assistance to 89.6%, 86.2%, and 93.6%, respectively.
Assistance with AI-powered TPS analyzer substantially improved the pathologist’s consensus and could be regarded as a reference for the final labeling of TPS, especially in the subgroups of TPS <1% and 1-49%.
Clinical trial identification
Legal entity responsible for the study
S. Cho, M. Ma, S. Park, S. Pereira, B.J. Aum, S. Shin, K. Paeng, D. Yoo, W. Jung. C-Y. Ock: Financial Interests, Personal, Full or part-time Employment: Lunit Inc. T.S.K. Mok: Honoraria for Invited Speaker and/or Advisory Board roles for: AbbVie, ACEA Pharma, Alpha Biopharma, Amgen, Amoy Diagnostics, Beigene, Boehringer Ingelheim, Bristol Myers Squibb, Eli Lilly, Blueprint Medicines, Berry Oncology, CStone Pharma, Curio Science, Daiichi Sankyo, Eisai, Fishawack Facilitate, Gritstone Oncology, Guardant Health, G1 Therapeutics, Hengrui, Ignyta, IQVIA, Incyte Corporation, Inivata, InMed Medical Communication, Janssen, Loxo Oncology, Lunit USA, Inc., MD Health, Medscape/WebMD, Merck Serono, Mirati Therapeutics, MoreHealth, MSD, Novartis, OrigiMed, PeerVoice, PER, Permanyer SL, Prime Oncology, Puma Tech., Qiming Dev., Research to Practice, Roche, Sanofi-Aventis, Takeda, Touch Medical Media, Virtus Medical, Yuhan; Advisory role (non-financial interest): AstraZeneca, Aurora Tele-Oncology, geneDecode, Lunit USA, Inc., Sanomics Ltd.; Stocks/shares: Aurora Tele-Oncology, Biolidics Ltd., Hutchison Chi-Med, Loxo Oncology, Lunit USA, Inc., OrigiMed Co., Sanomics Ltd., Virtus Medical Group; Receipt of grants (institutional financial support for clinical trials): AstraZeneca, BMS, Clovis Oncology, G1 Therapeutics, Merck Serono, MSD, Novartis, Pfizer, Roche, SFJ Pharmaceuticals, Takeda, XCovery; Member of Board of Directors (remunerated): AstraZeneca, Hutchison Chi-Med. All other authors have declared no conflicts of interest.