Speckle noise reduction in spectral domain optical coherence tomography retinal images using anisotropic diffusion filtering

In Ophthalmology, Optical Coherence Tomography (OCT) is well accepted as a clinical standard for diagnosing and monitoring the pathological changes in optic disc and retinal layers. In recent times, even though spectral domain detection technique has proved higher potential in terms of extremely high sensitivity and image acquisition speed, the major shortcomings is existence of speckle and its effect on interpretation and diagnosis. In this present paper, preprocessing for automated segmentation in the Spectral Domain Optical Coherence Tomography (SDOCT) retinal images is performed using anisotropic diffusion filtering method. The image enhancement is done initially by fuzzification technique which uses the maximum fuzzy entropy principle. For effective removal of speckles which of the order of 2–3μm anistropic diffusion filtering is performed. The performance of the filter is analyzed practically by measuring its quantitative parameters of structural similarity index measure and the results show that significant improvement in image quality is achieved by preserving the edges.