Detection and Characterisation of the Optic Disk in Glaucoma and Diabetic Retinopathy
نویسندگان
چکیده
The optic nerve head is that region of the retina where nerve fibres and blood vessels pass through the sclera. It is sensitive to changes associated with glaucoma that can occur without other symptoms. Diabetes can also be the cause of changes in the appearance of the retina. The changes from the normal appearance can be diagnostic of the diseases, tracking of the changes in sequential images can be used to assess treatment or the progress of the illness. We are concerned with developing automated techniques of generating quantitative descriptions of the retina that might be used in diagnosis and treatment. Normal and abnormal images were collected from a range of sources, to simulate the mass screening process. Although full colour images were collected, only the green channel was processed as it had the greatest contrast. Blood vessels were removed using morphological techniques. The boundary of the optic disk was estimated using a simple edge detector and the circular Hough transform. Heuristic methods were defined to identify true and false positives. Although we do not expect the optic disk to be circular, this technique identifies it with sufficient accuracy to identify its approximate centre, which is used as the origin of 24 uniformly distributed radial vectors. The images were resampled along these vectors. The resulting image was filtered using the Lee filter and thresholded. In one or other of these images, normal subjects had a region of maximum grey value that extended the full width of the image (at the centre of the optic disk) but did not extend the full height. Using a chi-squared test, the separation of normal and abnormal images using this test was found to be highly significant (p < 0.05, n = 60).
منابع مشابه
Morphological Exudate Detection in Retinal Images using PCA-based Optic Disc Removal
Diabetic retinopathy lesion detection such as exudate in fundus image of retina can lead to early diagnosis of the disease. Retinal image includes dark areas such as main blood vessels and retinal tissue and also bright areas such as optic disk, optical fibers and lesions e.g. exudate. In this paper, a multistage algorithm for the detection of exudate in foreground is proposed. The algorithm se...
متن کاملSegmentation and Detection of Optic Disc Using Kmeans Clustering
Diabetic retinopathy and glaucoma are one of the major cause of blindness. Early stage segmentation and detection of optic disc may be of great help to ophthalmologist for treatment of patient before any serious complications. In this paper new methodology is proposed for the detection of the optical disk from the retinal images. Input image is first preprocessed using spatial average filtering...
متن کاملDetection of Macular Edema and Glaucoma from Fundus Images
Diabetic macular edema (DME) is an eye disease that belongs to diabetic retinopathy which leads to vision loss. DME, which is a swelling in the macular region of eye is a common vision problem seen in diabetic patients.Hard exudates (bright lesions)in the fundus image indicates the presence of DME. When blood vessels in retina of diabetic patient is begin to leak into the macula region of eye l...
متن کاملAutomatic Detection of Optic disc in Eye Fundus Images
In the automatic analysis of retinal images for diagnosing various eye diseases such as diabetic retinopathy, glaucoma etc. the automatic detection of the optic disc is a crucial step. Before processing the fundus image for detecting any type of retinal disease it is necessary to mask out the anatomical features of eye so that they will not be mistaken as abnormality. Optic disc often considere...
متن کاملOnline Optic Disk Segmentation Using Fractals
Optic disk segmentation plays a key role in the mass screening of individuals with diabetic retinopathy and glaucoma ailments. An efficient hardware-based algorithm for optic disk localization and segmentation would aid for developing an automated retinal image analysis system for real time applications. Herein, TMS320C6416DSK DSP board pixel intensity based fractal analysis algorithm for an au...
متن کاملEarly Detection of Diabetic Retinopathy in Fluorescent Angiography Retinal Images Using Image Processing Methods
Introduction: Diabetic retinopathy (DR) is the single largest cause of sight loss and blindness in the working age population of Western countries; it is the most common cause of blindness in adults between 20 and 60 years of age. Early diagnosis of DR is critical for preventing vision loss so early detection of microaneurysms (MAs) as the first signs of DR is important. This paper addresses th...
متن کامل