Epithelial segmentation of oral OCT with deep learning to quantify thickness and degree of stratification

Chloe Hill; Catherine Poh; Calum MacAulay; Pierre Lane

doi:10.1117/12.2650484

17 March 2023 Epithelial segmentation of oral OCT with deep learning to quantify thickness and degree of stratification

Chloe Hill, Catherine Poh, Calum MacAulay, Pierre Lane

Proceedings Volume 12354, Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2023; 123540C (2023) https://doi.org/10.1117/12.2650484
Event: SPIE BiOS, 2023, San Francisco, California, United States

Abstract

Current practices for detection of oral cancers require invasive biopsy and costly histopathologic assessment. We hypothesize that applying deep learning (DL) to volumetric images (n = 320 images, 141 healthy) acquired using optical coherence tomography (OCT) could facilitate image-guided biopsy by (1) providing accurate and objective assessments of the state of subsurface oral tissues where changes in morphology indicate disease, and (2) allowing for non-invasive identification of biomarkers associated with oral mucosa health. Preliminary DL model implementations have demonstrated Jaccard Similarity Index of 81.3% in automated identification of the stromal-epithelial boundary in the oral mucosa

Conference Presentation

Citation Download Citation

Chloe Hill, Catherine Poh, Calum MacAulay, and Pierre Lane "Epithelial segmentation of oral OCT with deep learning to quantify thickness and degree of stratification", Proc. SPIE 12354, Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2023, 123540C (17 March 2023); https://doi.org/10.1117/12.2650484

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available