New publication on endoscopic oral OCT segmentation with deep learning

Congratulations to Chloe, a recent Masters student in our lab for her first publication in MDPI Cancers.

OCT produces a large amount of 3-dimensional data which is hard to quantify manually. This study presents a neural network pipeline to simplify OCT interpretation by providing information about epithelial depth and stratification through simple en face maps. The pipeline’s predictions demonstrate as-good-as or better agreement than inter-rater agreement, suggesting strong predictive power.

Grade 2 dysplasia of the lateral tongue, with an epithelial depth heatmap in (b).
Contralateral image of the lateral tongue, with an epithelial depth heatmap in (b).

Double-Clad Fiber article in BioPhotonics

Castor Optics has published a new article on multimodal optical coherence tomography using double-clad fiber in BioPhotonics, citing one of our previous publications. Multimodal OCT often uses double-clad fiber couplers from Castor Optics.

In vivo OCT and autofluorescence imaging (AFI) of human peripheral airways using a double-clad fiber (DCF) coupler. AFI of an airway (a), magnified AFI region (b), and OCT cross sections corresponding to the dashed lines (c-e). 

SPIE Photonics West 2024

Left to right: Eric, Kimiya, Jeanie, Alicia, and Adrian

OCIL trainees presented work at SPIE Photonics West 2024 in San Francisco, California. You can read more about their presentations here:

Congratulations Mehar & Allan!

Attenuation coefficient of normal (left) and pathologic (right) oral tissue.

A segmented airway and example cross-sections (segmentations in green).

Congratulations to Mehar and Allan who successfully defended their undergraduate honours theses this fall!

Mehar’s work ‘Methods for the Estimation of Depth-resolved Attenuation in OCT‘ compared different approaches for calculating the attenuation coefficient from OCT data. This allows us to characterize optical properties of tissue as they change with respect to depth.

Allan developed an automated tool to segment the tissue surface in OCT of the small airways of the lung. This tool allow us to quantify image features in the small airways without requiring manual segmentation. You can read his thesis, ‘Lumen Segmentation in Endobronchial Optical Coherence Tomography with Deep Learning‘ online.

Multipath artifacts enable angular contrast in multimodal endoscopic optical coherence tomography

Congratulations to Adrian and Jeanie on their new publication in Optics Express.

This work quantifies and suggests that there is utility in multipath artifacts found in double-clad fiber based OCT systems. While these artifacts appear as a smear in the A-line direction, they can be projected into a high-quality (and unique) en face image when compared to the fundamental mode image.

The angular dependence of the fundamental image and higher order image generated by the multipath artifact lays the basis for multipath contrast, a ratiometric measurement of differential coupling which provides information regarding the angular diversity of a sample. ultipath contrast images can be generated from OCT data where multipath artifacts are present, meaning that a wealth of clinical data can be retrospectively examined.