Automatic segmentation of accumulated fluid inside the retinal layers from optical coherence tomography images

Visual impairments are mostly associated with the retinal diseases such as glaucoma, age related macular degeneration, fluid accumulation inside the retinal layers and other diseases. To evaluate the visual loss associated with the sub-retinal fluid accumulation, OCT images are widely used. So long, the effected retinal segment is visually estimated from the images. In this paper, we have proposed a novel Retinal Fluid Automatic Detection (RFAD) algorithm for automatically extracting the affected retinal segment due to fluid accumulation and thereby noticeably increasing the visual impact of the affected area than earlier by proper edge detection. The proposed method is validated qualitatively and quantitatively against 25 OCT images including both normal and different types of abnormal conditions. Good sensitivity and specificity is achieved as indicated in the result section.