An Optimal Architecture for Semantic Segmentation in Multi-Gigapixel Images of Oral Dysplasia

Oral epithelial dysplasia (OED) is a pre-cancerous histopathological diagnosis given to a range of head and neck lesions. OED is distinguished by architectural and cytological changes of the epithelium reflecting the loss of normal growth and stratification pattern. Therefore, segmentation of the epithelium layer into three distinct layers can be considered as a first step towards identification of OED by quantifying and comparing nuclear features between the different layers. However, semantic segmentation of regions of interest in large multi-gigapixel histology images remains a challenge due to the sheer size of the histology images and also due to the complexity and variety of histological patterns present in these images. We propose a solution for designing neural networks for effective semantic segmentation of epithelial layers in OED. Our preliminary results reveal that the model achieved using an optimal network architecture approach outperforms all other state-of-the-art models for the semantic segmentation task.