Inter-frame information based choroid segmentation in enhanced optical coherence tomography images

Optical coherence tomography (OCT) has become a famous ophthalmic diagnostic technique recent years. It is a non-invasive imaging method and causes no damage to the eyes. Among the information OCT is able to provide, the thickness of choroid, especially epichoroidal space can reflect many diseases of the retina, which makes it a very important basis for diagnosing. However, up to now, there are few researches on it. In this paper, an automatic segmentation algorithm to detect epichoroidal space and methods for enhancing the images are presented. Since original OCT images are normally with severe noise, a new sparsity-based image denoising method is proposed against it. To remove the vascular shadows and improve the visibility of OCT image, proposed a noise-estimation assisted compensating algorithm is proposed. This is the first time that the effects of noise are taken into consideration in compensation. With the pre-processed images, Inter-frame Information is first used in developing choroid segmentation method.