OCT noise despeckling using 3D nonlinear complex diffusion filter

Abstract

An improved despeckling method, based on complex diffusion filtering, is herein presented to enhance structure segmentation in high-definition spectral domain optical coherence tomography (OCT) data. We propose to extend the traditional nonlinear complex diffusion filter concept propose by Gilboa (IEEE Trans Pattern Anal Mach Intell 26:1020-1036, 2004) from 2-to 3-dimensions, taking into account the consistency of noise along the entire 3D data volume. Moreover we also propose the extension to 3D of an improved complex diffusion filter (Bernardes et al. Opt Express 18:24,048-24,059, 2010), that was specially built for retinal tissue signal preservation in OCT data and that takes into account an adaptive optimized time step for the finite difference discretization. The extension to 3D of the traditional method compares favorably to existing methods reducing speckle noise and preserving edges and features. As expected, the improved 3D version has better performance than the traditional one. Numerical simulations show the feasibility of the method.