Automated PD-L1 Scoring Using Artificial Intelligence in Head and Neck Squamous Cell Carcinoma

• Published in: Cancers Vol. 13; no. 17; p. 4409
• Main Authors: Puladi, Behrus, Ooms, Mark, Kintsler, Svetlana, Houschyar, Khosrow Siamak, Steib, Florian, Modabber, Ali, Hölzle, Frank, Knüchel-Clarke, Ruth, Braunschweig, Till
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 31.08.2021; MDPI
• Subjects: Antibodies; Artificial intelligence; Automation; Cancer therapies; Chemotherapy; Cognitive ability; Cytotoxicity; Exports; Head and neck carcinoma; Immune checkpoint inhibitors; Immunohistochemistry; Immunosuppressive agents; Immunotherapy; Medical prognosis; Metastases; Metastasis; Neural networks; Patients; PD-1 protein; PD-L1 protein; Squamous cell carcinoma; Tumors; Aachen Germany; United States > US; Switzerland; Germany; deep learning; PD-L1 scoring; open-source; tumor detection; medical image analysis; head and neck squamous cell carcinoma
• ISSN: 2072-6694; 2072-6694
• DOI: 10.3390/cancers13174409

Immune checkpoint inhibitors (ICI) represent a new therapeutic approach in recurrent and metastatic head and neck squamous cell carcinoma (HNSCC). The patient selection for the PD-1/PD-L1 inhibitor therapy is based on the degree of PD-L1 expression in immunohistochemistry reflected by manually determined PD-L1 scores. However, manual scoring shows variability between different investigators and is influenced by cognitive and visual traps and could therefore negatively influence treatment decisions. Automated PD-L1 scoring could facilitate reliable and reproducible results. Our novel approach uses three neural networks sequentially applied for fully automated PD-L1 scoring of all three established PD-L1 scores: tumor proportion score (TPS), combined positive score (CPS) and tumor-infiltrating immune cell score (ICS). Our approach was validated using WSIs of HNSCC cases and compared with manual PD-L1 scoring by human investigators. The inter-rater correlation (ICC) between human and machine was very similar to the human-human correlation. The ICC was slightly higher between human-machine compared to human-human for the CPS and ICS, but a slightly lower for the TPS. Our study provides deeper insights into automated PD-L1 scoring by neural networks and its limitations. This may serve as a basis to improve ICI patient selection in the future.