Keywords: Oral Epithelial Dysplasia, Histopathological Images, Neural Architecture Search, Deep Learning, Machine Learning
TL;DR: Automated Oral Epithelial Dysplasia Grading
Abstract: Oral epithelial dysplasia (OED) is a precancerous lesion, histologically graded as mild, moderate or severe. The manual histological diagnosis of OED is time-consuming and subjective. We explore a customised Neural Architecture Search (NAS) technique to optimise an efficient architecture for full epithelium and individual nuclei segmentation in pathology whole slide images (WSIs). Results show the NAS-derived model outperforms all state-of-the-art networks. Accurate nuclear segmentation allows us to extract morphometric features. We propose a random forest model, using these features, to differentiate between OED grades.
Registration: I acknowledge that acceptance of this work at MIDL requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
Paper Type: novel methodological ideas without extensive validation
Primary Subject Area: Application: Histopathology
Secondary Subject Area: Segmentation
Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.