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

Cancers ◽  
2021 ◽  
Vol 13 (17) ◽  
pp. 4409
Author(s):  
Behrus Puladi ◽  
Mark Ooms ◽  
Svetlana Kintsler ◽  
Khosrow Siamak Houschyar ◽  
Florian Steib ◽  
...  
Keyword(s):  
Neural Networks ◽  
Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Squamous Cell ◽  
Patient Selection ◽  
Immune Cell ◽  
Checkpoint Inhibitors ◽  
Neck Squamous Cell Carcinoma ◽  
Novel Approach

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.

scholarly journals Highly Multiplexed Digital Spatial Profiling of the Tumor Microenvironment of Head and Neck Squamous Cell Carcinoma Patients

2021 ◽  
Vol 10 ◽  
Author(s):  
Arutha Kulasinghe ◽  
Touraj Taheri ◽  
Ken O’Byrne ◽  
Brett G. M. Hughes ◽  
Liz Kenny ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
Tumor Microenvironment ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Squamous Cell ◽  
Immune Cell ◽  
Checkpoint Inhibitors ◽  
Neck Squamous Cell Carcinoma ◽  
Protein Markers ◽  
Spatial Profiling

BackgroundImmune checkpoint inhibitors (ICI) have shown durable and long-term benefits in a subset of head and neck squamous cell carcinoma (HNSCC) patients. To identify patient-responders from non-responders, biomarkers are needed which are predictive of outcome to ICI therapy. Cues in the tumor microenvironment (TME) have been informative in understanding the tumor-immune contexture.MethodsIn this preliminary study, the NanoString GeoMx™ Digital Spatial Profiling (DSP) technology was used to determine the immune marker and compartment specific measurements in a cohort of HNSCC tumors from patients receiving ICI therapy.ResultsOur data revealed that markers involved with immune cell infiltration (CD8 T-cells) were not predictive of outcome to ICI therapy. Rather, a number of immune cell types and protein markers (CD4, CD68, CD45, CD44, CD66b) were found to correlate with progressive disease. Cross platform comparison with the Opal Vectra (Perkin Elmer) for a number of markers across similar regions of interest demonstrated concordance for pan-cytokeratin, CD8, and PD-L1.ConclusionThis study, to our knowledge, represents the first digital spatial analysis of HNSCC tumors. A larger cohort of HNSCC will be required to orthogonally validate the findings.

scholarly journals Identification of Immune-Related LncRNA Pairs for Predicting Prognosis and Immunotherapeutic Response in Head and Neck Squamous Cell Carcinoma

2021 ◽  
Vol 12 ◽  
Author(s):  
Xueying Wang ◽  
Kui Cao ◽  
Erliang Guo ◽  
Xionghui Mao ◽  
Lunhua Guo ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
T Cells ◽  
Clinical Outcome ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Squamous Cell ◽  
Immune Cell ◽  
Cox Regression ◽  
Checkpoint Inhibitors ◽  
Neck Squamous Cell Carcinoma

Long noncoding RNAs (lncRNAs) have multiple functions with regard to the cancer immunity response and the tumor microenvironment. The prognosis of head and neck squamous cell carcinoma (HNSCC) is still poor currently, and it may be effective to predict the clinical outcome and immunotherapeutic response of HNSCC by immunogenic analysis. Therefore, by using univariate COX analysis and Lasso Cox regression, we identified a signature consisting of 21 immune-related lncRNA pairs (IRLPs) that predicted clinical outcome and Immunotherapeutic response in HNSCC. Specifically, it was associated with immune cell infiltration (i.e., T cells CD4 memory resting, CD8 T cells, macrophages M0, M2, and NK cells), and more importantly this signature was strongly related with immune checkpoint inhibitors (ICIs) [such as PDCD1 (r = -0.35, P < 0.001), CTLA4 (r = -0.26, P < 0.001), LAG3 (r = -0.22, P < 0.001) and HAVCR2 (r = -0.2, P < 0.001)] and immunotherapy-related biomarkers (MMR and HLA). The present study highlighted the value of the 21 IRLPs signature as a predictor of prognosis and immunotherapeutic response in HNSCC.

scholarly journals Bioinformatics analysis of DNMT1 expression and its role in head and neck squamous cell carcinoma prognosis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jili Cui ◽  
Lian Zheng ◽  
Yuanyuan Zhang ◽  
Miaomiao Xue
Keyword(s):  
Gene Expression ◽  
Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Squamous Cell ◽  
Immune Cell ◽  
Neck Squamous Cell Carcinoma ◽  
Hub Genes ◽  
Significant Difference ◽  
Dnmt1 Expression

AbstractHead and neck squamous cell carcinoma (HNSCC) is the sixth most common type of malignancy in the world. DNA cytosine-5-methyltransferase 1 (DNMT1) play key roles in carcinogenesis and regulation of the immune micro-environment, but the gene expression and the role of DNMT1 in HNSCC is unknown. In this study, we utilized online tools and databases for pan-cancer and HNSCC analysis of DNMT1 expression and its association with clinical cancer characteristics. We also identified genes that positively and negatively correlated with DNMT1 expression and identified eight hub genes based on protein–protein interaction (PPI) network analysis. Enrichment analyses were performed to explore the biological functions related with of DNMT1. The Tumor Immune Estimation Resource (TIMER) database was performed to explore the relationship between DNMT1 expression and immune-cell infiltration. We demonstrated that DNMT1 gene expression was upregulated in HNSCC and associated with poor prognosis. Based on analysis of the eight hub genes, we determined that DNMT1 may be involved in cell cycle, proliferation and metabolic related pathways. We also found that significant difference of B cells infiltration based on TP 53 mutation. These findings suggest that DNMT1 related epigenetic alterations have close relationship with HNSCC progression, and DNMT1 could be a novel diagnostic biomarker and a promising therapeutic target for HNSCC.

scholarly journals Characterization of the immune cell infiltration landscape in head and neck squamous cell carcinoma to aid immunotherapy

2020 ◽  
Author(s):  
Xinhai Zhang ◽  
Tielou Chen ◽  
Boxin Zhang
Keyword(s):  
Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Signaling Pathway ◽  
Squamous Cell ◽  
Immune Cell ◽  
Neck Squamous Cell Carcinoma ◽  
Cell Infiltration ◽  
Immune Cell Infiltration ◽  
Stromal Component

Abstract Background: The tumor microenvironment chiefly consists of tumor cells, and tumor-infiltrating immune cells admixed with the stromal component. The recent clinical trial has shown that the tumor immune cell infiltration is correlated with the sensitivity to immunotherapy and the prognosis of head and neck squamous cell carcinoma (HNSC). However, to date, the immune infiltrative landscape of HNSC has not yet been elucidated. Methods: We proposed two computational algorithms to unravel the immune infiltration landscape of 1029 HNSC patients. The Boruta algorithm and principal component algorithms (PCA) were employed to quantify three immune cell infiltration gene subtypes categorized as per the immune cell infiltrations pattern. Results: The high ICI score subtype was characterized by a higher tumor mutation burden (TMB) and the immune-activated signaling pathway. However, a low ICI score subtype was categorized as per the activation of immunosuppressive signaling pathways such as TGF-BETA, WNT signaling pathway, and lower TMB. Two immunotherapy cohorts confirmed patients with higher ICI score demonstrated significant therapeutic advantages and clinical benefits.Conclusions: This demonstrated that the ICI score could serve as an effective prognostic biomarker and predictive indicator for immunotherapy. A comprehensive understanding of the HNSC immune landscape might help in tailoring immunotherapeutic strategies for different patients.

Sign in / Sign up

Export Citation Format

Share Document