Computational approach to correcting defocus and suppressing speckle noise in Line-Field Optical Coherence Tomography images

The trade-off between transverse resolution and depth-of-focus (DOF) typical for optical coherence tomography (OCT) systems based on conventional optics, prevents “single-shot” acquisition of volumetric OCT images with sustained high transverse resolution over the entire imaging depth. Computational approaches for correcting defocus and higher order aberrations in OCT images developed in the past require highly stable phase data, which poses a significant technological challenge. Here we present an alternative computational approach to sharpening OCT images and reducing speckle noise, based on intensity OCT data. The novel algorithm uses non-local priors to model correlated speckle noise and a maximum a posteriori framework to generate sharp and noise-free images. The performance of the algorithm was tested on images of plant tissue (cucumber) and in-vivo healthy human cornea, acquired with a Line-Field Spectral Domain OCT (LF-SD-OCT) system. The novel algorithm effectively suppressed speckle noise and sharpened or recovered morphological features in the OCT images for depths up to 13×DOF relative to the focal plane.