According to project managers, Galahad, a Horizon 2020 research project creating an OCT platform for enhanced early glaucoma screening, has successfully finished its job. The three-year program to create ultra-high resolution polarization-sensitive optical coherence tomography, called Galahad, from Glaucoma Advanced, LAbel-free High resolution Automated OCT Diagnostics, has ended. (UHR-PS-OCT).
By utilizing only OCT volumes focused on the optic nerve head of the retina, an automated algorithm created by the Universitat Politècnica de Valènci (UPV) demonstrated its ability to differentiate between healthy and glaucomatous eyes with an accuracy of 0.81, the sensitivity of 0.79, and specificity of 0.82. Class Activation Maps, an image analysis technique, were used to pinpoint the areas the deep learning network kept an eye on for categorization.
The axial resolution was below the crucial 1-micron threshold in tissue, making the system capable of resolving single cells in the area of interest. This degree of sensitivity was found to be within the range of commercial supercontinuum-based systems. The project referred to this resolution as establishing “the new state-of-the-art for PS-OCT systems.” It claimed that it was made possible through careful resampling and correction of the unbalanced dispersion created within the Michelson interferometer of the OCT system.
Related Content: Adaptive Optics For Imaging Immune Cells In The Eye