A Deep Learning Onion Peeling Approach to Measure Oral Epithelium Layer Number.

Simple Summary: Oral cavity and pharyngeal cancer affects 560,000 people worldwide on a yearly basis. Despite advances in treatment, the survival rate remains poor, while prognoses typically improve with early diagnosis. The epithelium of the oral cavity often exhibits abnormal cellular growth, or dysplasia, that predisposes the patient to cancer depending on severity. Our study aims to address the current lack of rigorous quantitative methods for analyzing histopathological features relevant to clinical diagnosis, such as cellular morphology and epithelial layer number. We developed a deep learning approach that segments the oral epithelium and counts epithelial layer number within H&E-stained whole slide images. Our results demonstrate the feasibility of this automated approach for segmenting oral epithelium and counting its layer number. We also show its clinical relevance by comparing oral epithelium layer numbers between dysplasia of different severities. Head and neck squamous cell carcinoma (HNSCC), specifically in the oral cavity (oral squamous cell carcinoma, OSCC), is a common, complex cancer that significantly affects patients' quality of life. Early diagnosis typically improves prognoses yet relies on pathologist examination of histology images that exhibit high inter- and intra-observer variation. The advent of deep learning has automated this analysis, notably with object segmentation. However, techniques for automated oral dysplasia diagnosis have been limited to shape or cell stain information, without addressing the diagnostic potential in counting the number of cell layers in the oral epithelium. Our study attempts to address this gap by combining the existing U-Net and HD-Staining architectures for segmenting the oral epithelium and introducing a novel algorithm that we call Onion Peeling for counting the epithelium layer number. Experimental results show a close correlation between our algorithmic and expert manual layer counts, demonstrating the feasibility of automated layer counting. We also show the clinical relevance of oral epithelial layer number to grading oral dysplasia severity through survival analysis. Overall, our study shows that automated counting of oral epithelium layers can represent a potential addition to the digital pathology toolbox. Model generalizability and accuracy could be improved further with a larger training dataset. [ABSTRACT FROM AUTHOR]