Glaucoma Detection from Fundus Images Using MATLAB GUI

ABSTRACT:

A troublesome disease in which damages of the optic nerve of eye’s is nothing but the glaucoma, which causes irretrievable loss of vision. Glaucoma is a disease where if treatment is get late, the person can blind. Normally glaucoma detects when there is an increase in the fluid in the front of eye. When that extra fluid is increased, the pressure in your eye is also getting increased. Accordingly, the size of the optic disc and optic cup is increased as a result diameter also increased. The ratio of the cup and disc diameter is called cup-to-disc ratio (CDR). Threshold type segmentation method is used in this system for localizing the optic disc and optic cup. Another edge detection and ellipse fitting algorithm are also used. The proposed system for optic disc and optic cup localization and CDR calculation is MATLAB GUI software.

PROJECT OUTPUT VIDEO:

EXISTING SYSTEM

The ratio of the optic cup to disc (CDR) in retinal fundus images is one of the principal physiological characteristics in the diagnosis of glaucoma. Currently the CDR is manually determined which can be subjective and limits its use in mass screening. To automatically extract the disc, a variational level set method is presented in this paper.

DISADVANTAGES

• Less accurate detection with high cost effectiveness,

• It may be beneficial to the rich people only.

• Sometimes it will predict wrongly.

• Segmentation and detection is based on boundary only.

PROPOSED SYSTEM

The image processing step is introduced to enhance the contrast of fundus image and convert that image into gray scale image. Further image processing is done for the localization of the boundary of cup and disc. First of all convert the fundus image into gray scale image. After that we compare the images with black image then we get the segmented disc. Again we compare that image with the black image then we get the optic cup boundary. The segmentation is used to detect the boundary of the optic disc and optic cup. Here, our main motto is glaucoma detection by CDR and disc and cup detection using MATLAB GUI. In this project, Concentrate on direct linear method for CDR finding. The combine approach for detection is segmentation, ellipse fitting on boundary, CDR for finding ratio is proposed.

ADVANTAGES OF PROPOSED SYSTEM

• Fit ellipse is used for boundary detection of optic cup and optic disc to improve accuracy.

• By using the CDR ratio of cup-to-disc, detect particular eye have glaucoma or normal which is almost correct to that of doctor’s result.

• This system is easy to use

• Hence its user friendly.

MODULES

• Image Preprocessing

• Segmentation Of Optic Disc

• Smoothing Of Optic Disc

• Segmentation Of Optic Cup

• Smoothing Of Optic Cup

• Cup-To-Disc Ratio(Cdr)

• Ellipse Fitting

MODULES DESCRIPTION:

IMAGE PREPROCESSING

The human visual system does not perceive the world in the same manner as digital detector; hence we need to convert the image into digital image, its nothing but the image processing. Here we are enhancing the contrast of an image for further process. We are also converting the image into gray scale image.

SEGMENTATION OF OPTIC DISC

From the fundus images, the optic disc is segmented. For the segmentation of optic disc we compare the fundus image with the threshold value of ‘0’ while a threshold value of our object pixel is ‘1’. After the comparison we get the optic disc boundary from fundus image. In this paper, we are localizing the optic disc boundary by comparison method. By using edge detection we localize the optic disc.

SMOOTHING OF OPTIC DISC

After doing the segmentation and edge detection of optic disc, we didn’t get the boundary of optic disc as desired. Hence we are using the ellipse fitting algorithm for boundary detection.

SEGMENTATION OF OPTIC CUP

After completing the localization of optic disc boundary, optic cup localization is also mandatory. To localize the optic cup boundary we use the segmentation method same as used for optic disc segmentation. The extraction of the cup boundary we compare the again optic disc with the blank black color image of the same size of the image. From comparing this we get the optic cup boundary.

SMOOTHING OF OPTIC CUP

After the localization of cup boundary, to get the boundary as desired, we use ellipse fitting algorithm. After the smoothing of cup and disc boundary we plot the ellipse using Cartesian coordinate system. We also find out the cup diameter and disc diameter using Cartesians method. The CDR is calculated using the optic dis and cup diameter.

CUP-TO-DISC RATIO(CDR)

As now we are with the disc and cup diameter, now the next step is to measure the cup-to-disc ratio (CDR). Fig 3 shows the normal calculation of the CDR. The optic cup region and optic disc region for normal eye is
shown. Earlier we localize the disc and cup boundaries, after that using Cartesians system we find out the diameter, height center, and width center, horizontal and
vertical center. From this using the calculated diameter now. we follow the cup-to disc ration which is nothing but the clinical indicator of glaucoma detection. The formula to calculate CDR is as follows, CDR= Cup diameter / Disc diameter When the ratio of cup-to-disc is more than 0.3, then we can say that patient have the glaucoma disease. Normal eye has the CDR is less than 0.3. We are comparing the CDR, if it’s greater than 0.3 then its glaucoma eye otherwise normal eye, which shown in output GUI result.

ELLIPSE FITTING

After the segmentation, disc and cup boundary is not as per the desire. Hence for smoothing the cup and disc boundary we are using here ellipse fitting algorithm. Least-square techniques center on finding the set of parameters that minimize some distance measure between the data points and ellipse.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

• System          : Pentium Dual Core.

• Hard Disk      : 120 GB.

• Monitor          : 15’’ LED

• Input Devices : Keyboard, Mouse

• Ram                : 1GB.

SOFTWARE REQUIREMENTS:

• Operating system : Windows 7.

• Coding Language : MATLAB.

• Tool                       : MATLAB R2013A

REFERENCE:

Shwetali M. Nikam, Dr. C. Y. Patil, “Glaucoma Detection from Fundus Images Using MATLAB GUI”, IEEE.