Early detection and categorization of cataract using slit-lamp images by hough circular transform

摘要

CATARACT is a loss of the normal transparency of human lens due to opacity. The lens is mostly made of water and protein. A cataract is formed when the protein clumps together, which clouds the lens and reduces the light that reaches the retina. Age-related cataract is the leading cause of visual loss globally. The age-related cataract can be classified into three types according to the location of opacity in the lens as nuclear cataract, cortical cataract and post sub-capsular cataract. Nuclear cataract is the most common of all cataract types. It starts off at the center of the lens and progresses towards the surface. The slit-lamp photography is the main means of nuclear cataract imaging. It is based on reflected light. The camera and slit are placed obliquely to the visual axis of the eye to capture an image of the cross-section of the eye. The ability to best capture anterior sections of the eye makes it an ideal approach for grading nuclear cataracts. Clinically, ophthalmologists evaluated the degree of cataract by comparing the picture observed through camera with a series of standard photographs, which is termed as clinical grading such as Lens Opacities Classification System III (LOCSIII). The manual grading system causes intra-grader and inter-grader variations. With the development of image processing techniques, efforts have been put in the development of automatic systems to improve grading objectivity. For nuclear cataract classification, automatic systems were proposed using slit-lamp images.