Detection Of Diabetic Retinopathy Biology Essay

Published: Last Edited:

This essay has been submitted by a student. This is not an example of the work written by our professional essay writers.

Automated detection of lesions in retinal images can assist in early diagnosis and screening of a common disease: Diabetic Retinopathy. A robust and computationally efficient approach for the localization of the different features and lesions in a fundus retinal image is presented in this paper. Since many features have common intensity properties, geometric features and correlations are used to distinguish between them.

India ranks second in diabetes in the world. We show how to prevent the loss of vision in diabetes patients using the technique of Image Processing. Eye image processing will give us the status of the severity of diabetes in the patient.

This paper aims to develop a system which warns the patient about his vision and take some measures to prevent him from becoming blind. We propose a new constraint for optic disk detection where we first detect the major blood vessels first and use the intersection of these to find the approximate location of the optic disk. This is further localized using color properties.

1. Introduction

Diabetic retinopathy is retinopathy (damage to the retina) caused by complications of diabetes mellitus, which can eventually lead to blindness. It is an ocular manifestation of systemic disease which affects up to 80% of the patients who have had diabetes for 10 years or more. Despite these intimidating statistics, research indicates that at least 90% of these new cases could be reduced if there was proper and vigilant treatment and monitoring of the eyes.

Fig.1. Normal Vision

Fig.2. Same View with Retinopathy

Diabetic retinopathy (DR) is a common retinal complication associated with diabetes. It is a major cause of blindness in both middle and advanced age groups.

Diabetes screening is recommended for many people at various stages of life, and for those with any of several risk factors. The screening test varies according to the circumstances and local policy, and may be random glucose test or EYE SIGHT TEST.

Retinal damage makes it the most common cause of blindness among the non elderly adults in India.

1.1 Signs and Symptoms

Diabetic retinopathy often has no early warning signs. It causes vision loss more rapidly, and may not have any warning signs for some time. In general, however, a person with macular edema is likely to have blurred vision, making it hard to do things like read or drive as shown in Fig.2 where Fig.1 represents normal view. In some cases, the vision will get better or worse during the day.

As new blood vessels form at the back of the eye as a part of proliferative diabetic retinopathy, they can bleed and blur vision. The first time this happens, it may not be very severe. In most cases, it will leave just a few specks of blood or spots, floating in a person's visual field, though the spots often go away after a few hours.

These spots are often followed within a few days or weeks by a much greater leakage of blood, which blurs vision. In extreme cases, a person will only be able to tell light from dark in that eye. It may take the blood anywhere from a few days to months or even years to clear from the inside of the eye, and in some cases the blood will not clear. These types of large hemorrhages tend to happen more than once, often during sleep.

1.2 Diagnosis

Diabetic retinopathy is detected during an eye examination that includes:

Visual acuity test: This test uses an eye chart to measure how well a person sees at various distances.

Pupil dilation: The eye care professional places drops into the eye to widen the pupil. This allows him or her to see more of the retina and look for signs of diabetic retinopathy. After the examination, close-up vision may remain blurred for several hours.

Ophthalmoscopy: This is an examination of the retina in which the eye care professional: (1) looks through a device called ophthalmoscope (as shown in Fig.3) with a special magnifying lens that provides a narrow view of the retina, or (2) wearing a headset with a bright light, looks through a special magnifying glass and gains a wide view of the retina. Note that hand-held ophthalmoscopy (as shown in Fig.4) is insufficient to rule out significant and treatable diabetic retinopathy.

Optical coherence tomography (OCT): This is an optical imaging modality based upon interference, and analogous to ultrasound. It produces cross-sectional images of the retina (B-scans) which can be used to measure the thickness of the retina and to resolve its major layers, allowing the observation of swelling and or leakage.

Digital Retinal Screening Programs: Systematic programs for the early detection of eye disease including diabetic retinopathy are becoming more common, such as in the UK, where all people with diabetes mellitus are offered retinal screening at least annually. This involves digital image capture and transmission of the images to a digital reading center for evaluation and treatment referral. See Vanderbilt Ophthalmic Imaging Center and the English National Screening Programme for Diabetic Retinopathy

Slit Lamp Biomicroscopy Retinal Screening Program: Systematic programs for the early detection of diabetic retinopathy using slit-lamp biomicroscopy. These exist either as a standalone scheme or as part of the Digital program (above) where the digital photograph was considered to lack enough clarity for detection and/or diagnosis of any retinal abnormality.

The eye care professional will look at the retina for early signs of the disease, such as: (1) leaking blood vessels, (2) retinal swelling, such as macular edema, (3) pale, fatty deposits on the retina (exudates) - signs of leaking blood vessels, (4) damaged nerve tissue, and (5) any changes in the blood vessels.

Should the doctor suspect macular edema, he or she may perform a test called fluorescin angiography. In this test, a special dye is injected into the arm. Pictures are then taken as the dye passes through the blood vessels in the retina. This test allows the doctor to find the leaking blood vessels.

1.3 Management

There are three major treatments for diabetic retinopathy, which are very effective in reducing vision loss from this disease. In fact, even people with advanced retinopathy have a 90 percent chance of keeping their vision when they get treatment before the retina is severely damaged (as shown in Fig.5 and Fig.6). These three treatments are laser surgery, injection of triamcinolone into the eye and vitrectomy.

It is important to note that although these treatments are very successful, they do not cure diabetic retinopathy. Caution should be exercised in treatment with laser surgery since it causes a loss of retinal tissue. It is often more prudent to inject triamcinolone. In some patients it results in a marked increase of vision, especially if there is an edema of the macula.

Fig.3. Ophthalmoscope

Fig.4. Ophthalmoscopy being done

Fig.5. Mild DR

Avoiding tobacco use and correction of associated hypertension are important therapeutic measures in the management of diabetic retinopathy.

The best way of addressing diabetic retinopathy is to monitor it vigilantly.

In patients with dianetes mellitus, regular ophthalmoscopic eye examinations (once every 6 months to 1 year) are important to screen for diabetic retinopathy as visual loss due to diabetes can be prevented by retinal laser treatment if retinopathy is spotted early.

2 Diabetic Retinopathy detection using Image Processing

Image processing is any form of signal processing for which the input is an image, such as photographs or frames of video; the output of image processing can be either an image or a set of characteristics or parameters related to the image. Most image processing techniques involve treating the image as a two dimensional signal and applying standard signal-processing techniques to it.

Fig.6. Severe DR

Image processing usually refers to digital image processing, but optical and analogy image processing are also possible. This paper proposes an image processing techniques that apply to images taken from the diabetic retinopathy.

2.1 Image processing System

The major objective of this work is to design a system as shown in Fig.6, which captures the eye images from the patient and processes it using image processor.

Fig.6. Image Processing System

It compares the captured current image with the already available images in the database. Once image matching is done it is easy to find the stage or severity of the diabetic retinopathy. Once it identified the stage or severity of diabetic retinopathy it gives the list of nearest available doctors to consult. It also suggests the first aid for the patient in a printed slip.

Camera captures images of the patients it stores in digital forms and feed to Image processor block. Where image processor will first removes the noise presented in the images. DR image processor will perform the following list of steps to detect the diabetic retinopathy.

Image segmentation: segmentation subdivides an image into its constituent regions and objects. Image segmentation algorithms generally are based on one of two basic properties of intensity values: discontinuity and similarity. The first approach is to partition an image based on abrupt changes in intensity, such as edges in an image. The principal approaches in the second category are based on partitioning an image into regions that are similar according to a set of predefined criteria. Thresholding, region growing, and region splitting and merging are examples of methods in this category.

Detection of Discontinuties: There are several techniques for detecting the three basic types of gray-level discontinuities in a digital image: points, lines, and edges. The most common way to look for discontinuities is to run a mask through the image. For 3x3 mask as shown in Fig.7, this procedure involves computing the sum of products of the coefficients with.

R = w1z1 + w2z2 + … + w9z9

Where zi is gray level of the pixel associated with mask coefficient wi.

Fig.7. A general 3 x 3 mask

Point Detection: The detection of isolated points in an image is detected using 3x3 mask {-1,-1,-1; -1, 8, -1; -1, -1, -1}. The point is detected when ever |R| >= T. where T is a nonnegative threshold.

Line Detection: The line mask are used to detect the lines. It has four masks: horizontal, +45o, vertical and -45o.

Horizontal{-1,-1,-1; 2,2,2;-1,-1,-1}

+45o {-1,-1,2; -1,2,-1; 2,-1,-1}

Vertical {-1,2,-1; -1,2,-1; -1,2;-1}

-45o {2,-1,-1; -1,2,-1; -1,-1,2}

If the first mask moved around the image, it would respond more strongly to lines (one pixel thick) oriented horizontally. With a constant background, the maximum response would result when the line passed through the middle row of the mask.

Let R1, R2, R3 and R4 denote the responses of the masks. Suppose four masks are run individually through an image. If a certain point in the image |Ri| > |Rj|. for all j ≠ I, that point is said to be more likely associated with a line in the direction of mask i. for example, if at a point in the image, |R1| > |Rj| for j = 2, 3, 4, that particular point is said to be more likely associated with a horizontal line.

Edge Detection: The first and second order digital derivatives are used for the detection of edges in an image.

By using above image processing methodology for a given image we will get the details of edges, lines and points. These edges, lines and points are compared with healthy human eye with the help of comparator block of the system.

Comparator will compare all the extracted details of the given image using image processing techniques with the golden reference images. Based on the matching it will generate the printed report. The golden reference images will have all the stages of diabetic retinopathy.

3. Implementation Details

The complete system can be implemented using the MATLAB 7.1 and using the high level language (C, VC++ and Java) based software system. This completed process is demonstrated with a computer, camera and printer.

4. Conclusions and future scope

Early detection of diabetic retinopathy will certainly help the patient to get cured from going blind. Software system based image processing techniques detection diabetic retinopathy and gives the first aid details. The future scope for this work is to develop an ISOC (Image Processing based System on Chip), which will be faster when compared with the software based system.