Abstract
This paper aims to simplify the application of optical coherence tomography (OCT) for the examination of subsurface morphology in the oral cavity and reduce barriers towards the adoption of OCT as a biopsy guidance device. The aim of this work was to develop automated software tools for the simplified analysis of the large volume of data collected during OCT. Imaging and corresponding histopathology were acquired in-clinic using a wide-field endoscopic OCT system. An annotated dataset (n = 294 images) from 60 patients (34 male and 26 female) was assembled to train four unique neural networks. A deep learning pipeline was built using convolutional and modified u-net models to detect the imaging field of view (network 1), detect artifacts (network 2), identify the tissue surface (network 3), and identify the presence and location of the epithelial-stromal boundary (network 4). The area under the curve of the image and artifact detection networks was 1.00 and 0.94, respectively. The Dice similarity score for the surface and epithelial-stromal boundary segmentation networks was 0.98 and 0.83, respectively. Deep learning (DL) techniques can identify the location and variations in the epithelial surface and epithelial-stromal boundary in OCT images of the oral mucosa. Segmentation results can be synthesized into accessible en face maps to allow easier visualization of changes.