Spectral Bandwidth Recovery of Optical Coherence Tomography Images using Deep Learning
This work addresses a domain-specific problem for clinicians using OCT in retinal disease screening, but it is incremental as it builds upon existing super-resolution techniques.
The study tackled the problem of reduced axial resolution in optical coherence tomography (OCT) images due to narrower spectral bandwidth, by using a deep learning approach to reconstruct lost features, resulting in improved image quality to aid clinical decision-making.
Optical coherence tomography (OCT) captures cross-sectional data and is used for the screening, monitoring, and treatment planning of retinal diseases. Technological developments to increase the speed of acquisition often results in systems with a narrower spectral bandwidth, and hence a lower axial resolution. Traditionally, image-processing-based techniques have been utilized to reconstruct subsampled OCT data and more recently, deep-learning-based methods have been explored. In this study, we simulate reduced axial scan (A-scan) resolution by Gaussian windowing in the spectral domain and investigate the use of a learning-based approach for image feature reconstruction. In anticipation of the reduced resolution that accompanies wide-field OCT systems, we build upon super-resolution techniques to explore methods to better aid clinicians in their decision-making to improve patient outcomes, by reconstructing lost features using a pixel-to-pixel approach with an altered super-resolution generative adversarial network (SRGAN) architecture.