Mitigation of Speckle Noise in Optical Coherence Tomograms

Optical Coherence Tomography (OCT) is a promising high-resolution imaging technique that works based on low coherent interferometry. However, like other low coherent imaging modalities, OCT suffers from an artifact called, speckle. Speckle reduces the detectability of diagnostically relevant features in the tissue. Retinal optical coherence tomograms are of a great importance in detecting and diagnosing eye diseases. Different hardware or software based techniques are devised in literatures to mitigate speckle noise. The ultimate aim of any software-based despeckling technique is to suppress the noise part of speckle while preserves the information carrying portion of that. In this chapter, we reviewed the most prominent speckle reduction methods for OCT images to date and then present a novel and intelligent speckle reduction algorithm to reduce speckle in OCT images of retina, based on an ensemble framework of Multi-Layer Perceptron (MLP) neural networks.