Dataset Information

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

ABSTRACT: 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.

SUBMITTER: Puladi B

PROVIDER: S-EPMC8431396 | biostudies-literature | 2021 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Puladi Behrus B Ooms Mark M Kintsler Svetlana S Houschyar Khosrow Siamak KS Steib Florian F Modabber Ali A Hölzle Frank F Knüchel-Clarke Ruth R Braunschweig Till T

Cancers 20210831 17

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 decisio ...[more]

PMID: 34503218

Similar Datasets

Project description:The PD-1 receptor and its ligands PD-L1 and PD-L2 are known to be significantly involved in T-cell regulation. Recent studies suggest that PD-L1 expression in malignant tumors contributes to an immunosuppressive microenvironment and disruption of antitumoral immune response. Drugs targeting this pathway are already tested in clinical trials against several tumor entities with promising results. However, until now comprehensive data with regard to PD-L1 and PD-L2 expression in head and neck squamous cell carcinoma (HNSCC) is still lacking.We assessed PD-L1 and PD-L2 expression via immunohistochemistry in two independent cohorts of 293 HNSCC patients.A significant subset of HNSCC showed high expression levels of PD-L1. Most remarkable, we detected a strong correlation between PD-L1 expression and overall survival time in both HNSCC cohorts. Further, in multivariate cox proportional hazard models, PD-L1 dominates as the strongest prognostic factor of patient's outcome in HNSCC, leaving even tumor stage and distant metastasis behind. Moreover, strong PD-L1 expression was associated with the presence of distant metastases in a subset of cases.In summary, while the significance of PD-L2 in HNSCC seems to minor, we show that PD-L1 expression is common in HNSCC and, more importantly, a both robust and strong prognostic biomarker. In this respect, our results provide hints on further application of therapies targeting the PD-1/PD-L1 pathway in HNSCC. Investigation of response and outcome of patients receiving anti-PD-1/PD-L1 containing therapies in correlation with PD-L1 expression analysis should be an important task for the future.In spite of improved treatment options and increasing knowledge of molecular alterations in HNSCC, the survival rate has not been dramatically changed in the past decades. Pies are missing in HNSCC. One promising candidate in cancer immune therapy is PD-L1. Drugs targeting PD-L1 or its receptor PD-1 are subject of several clinical studies in different cancer entities. However, comprehensive data about PD-L1 expression in HNSCC and therefore a rational basis for anti PD-L1/PD-1 therapy in HNSCC is lacking. Here, we provide wide-ranging data about PD-L1 expression in HNSCC of all major localizations. We observed a strong correlation between expression of PD-L1 and reduced overall survival time. Furthermore, high PD-L1 expression was identified as a strong prognostic factor of patient's outcome when verified together with recognized prognostic factors.

Project description:IntroductionImmune-checkpoint inhibitors have demonstrated a significant survival benefit in metastatic and non-resectable head and neck squamous cell carcinoma (HNSCC). Patients with a combined positivity score (CPS) of 20 and higher benefit the most from therapy. Inaccurate definition of the CPS category might lead to the incorrect stratification of patients to immunotherapy. This study's main aim was to investigate programmed death-ligand 1 (PD-L1) antigen expression in HNSCC in diverse clinical situations and histological settings.Materials and methodsThis is a prospective cohort study conducted in a tertiary referral medical center. Tissues were investigated for PD-L1 expression using the FDA-approved 22C3 immunohistochemistry assay (Dako). We analyzed potential associations between the CPS category and meaningful demographic, clinical, and outcome metrics. Furthermore, we investigated morphologically separate sites for CPS scores in whole surgical tissue specimens and matched preoperative biopsies.ResultsWe analyzed 36 patients, of whom 26 had oral cavity SCC and 10 had laryngeal SCC. The overall, disease-specific, and progression-free survival of the HNSCC group of patients were not associated with the CPS category (p = 0.45, p = 0.31, and p = 0.88, respectively). There was a significant (18%, 95% CI 0.65-0.9) inconsistency between the CPS category determined in biopsies versus whole carcinoma analyses. We also found an uneven distribution of whole-tumor CPS attributed to spatial carcinoma invasiveness, tumor differentiation, and inflammatory cell infiltration heterogeneity.Discussion and conclusionsOur data suggest that careful selection of tumor area for CPS analysis is important. PD-L1 antigen expression, clinically represented by CPS, may be up- or down-categorized in different clinical and pathological circumstances. The high whole-tissue CPS category scatter may clinically result in potential treatment modifications. We argue that CPS analysis requires not only adequacy (at least 100 viable tumor cells), but also correct representation of the tumor microenvironment.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets