A digital score of peri-epithelial lymphocytic activity predicts malignant transformation in oral epithelial dysplasia

Abstract

Oral squamous cell carcinoma (OSCC) is amongst the most common cancers worldwide, with more than 377,000 new cases worldwide each year. OSCC prognosis remains poor, related to cancer presentation at a late stage indicating the need for early detection to improve patient prognosis. OSCC is often preceded by a premalignant state known as oral epithelial dysplasia (OED), which is diagnosed and graded using subjective histological criteria leading to variability and prognostic unreliability. In this work, we propose a deep learning approach for the development of prognostic models for malignant transformation and their association with clinical outcomes in histology whole slide images (WSIs) of OED tissue sections. We train a weakly supervised method on OED (n= 137) cases with transformation (n= 50) status and mean malignant transformation time of 6.51 years (±5.35 SD). Performing stratified 5-fold cross-validation achieves an average AUROC of ~0.78 for predicting malignant transformations in OED. Hotspot analysis reveals various features from nuclei in the epithelium and peri-epithelial tissue to be significant prognostic factors for malignant transformation, including the count of peri-epithelial lymphocytes (PELs) (p < 0.05), epithelial layer nuclei count (NC) (p < 0.05) and basal layer NC (p < 0.05). Progression free survival using the Epithelial layer NC (p < 0.05, C-index = 0.73), Basal layer NC (p < 0.05, C-index = 0.70) and PEL count (p < 0.05, C-index = 0.73) shown association of these features with a high risk of malignant transformation. Our work shows the application of deep learning for prognostication and progression free survival (PFS) prediction of OED for the first time and has a significant potential to aid patient management. Further evaluation and testing on multi-centric data is required for validation and translation to clinical practice.

A Novel AI-based Score for Assessing the Prognostic Value of Intra-Epithelial Lymphocytes in Oral Epithelial Dysplasia

“…Yet, despite this, OED lesions are often strongly infiltrated with CD8+ T lymphocytes, that may act to reverse this immunosuppressive microenvironment [42,43]. Recent evidence has suggested a higher density of PELs in cases undergoing malignant transformation [26]. This was further supported by Shephard et al [20], who additionally found a potential association between both PELs and IELs and malignant transformation.…”

“…In the context of OED, our previous work has used deep learning to segment dysplasia [19] and also the oral epithelium into sub-regions: the lower basal layer, the middle epithelial layer, and the superior keratin layer [20,21]. These methods have even been used to predict OED malignant transformation, based on either deep [26] or nuclear features [20,27]. Thus, deep learning tools offer a potential avenue for reducing grading variability while ensuring consistency across sites in informing treatment decisions [28,29].…”

“…Computational pathology has not only allowed researchers to replicate and automate pathology workflows, but also to aid in biomarker discovery. Bashir et al [26] developed a pipeline to predict malignant transformation in OED. In doing so they discovered a positive association between an increased presence of peri-epithelial lymphocytes (PELs) and transformation.…”