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

Abstract

Oral epithelial dysplasia (OED) poses a significant clinical challenge due to its potential for malignant transformation and the lack of reliable prognostic markers. Current grading systems for OED may not be reliable for prediction of malignant transformation and suffer from considerable inter- and intra-rater variability, potentially leading to suboptimal treatment decisions. Recent studies have highlighted the potential prognostic significance of peri-epithelial lymphocytes (PELs) in malignant transformation, with suggestions that intra-epithelial lymphocytes (IELs) may also play a role. In this study, we propose a novel artificial intelligence (AI) based IEL score from Haematoxylin and Eosin (H&E) stained Whole Slide Images (WSIs) of OED tissue slides. We further determine the prognostic value of our IEL score on a large digital dataset of 219 OED WSIs (acquired using three different scanners), compared to pathologist-led clinical grading. Notably, despite IELs not being incorporated into the current WHO grading system for OED, our findings suggest that IEL scores carry significant prognostic value that were shown to further improve both the Binary/WHO grading systems in multivariate analyses. This underscores the potential importance of IELs, and by extension our IEL score, as prognostic indicators in OED. Further validation through prospective multi-centric studies is warranted to confirm the clinical utility of the proposed IEL score and its integration into existing grading systems for OED.