Speckle reduction with attenuation compensation for Skin OCT images enhancement

The enhancement of skin image in optical coherence tomography (OCT) imaging can help dermatologists to investigate tissue layers more accurately, hence the more efficient diagnosis. In this paper, we propose an image enhancement technique including speckle reduction, attenuation compensation and cleaning to improve the quality of OCT skin images. A weighted median filter is designed to reduce the level of speckle noise while preserving the contrast. A novel border detection technique is designed to outline the main skin layers, stratum corneum, epidermis and dermis. A model of the light attenuation is then used to estimate the absorption coefficient of epidermis and dermis layers and compensate the brightness of the structures at deeper levels. The undesired part of the image is removed using a simple cleaning algorithm. The performance of the algorithm has been evaluated visually and numerically using the commonly used no-reference quality metrics. The results shows an improvement in the quality of the images.