Glaucoma Detection From Fundus Image Using Opencv

This study proposes a semi automated method for glaucoma detection using CDR and ISNT ratio of a fundus image. CDR (Cup to Disc Ratio) is ratio of area of Optic Cup to area of Optic Disc. For a patient with glaucoma Optic Cup size increases while the Optic Disc size remains same and hence CDR will be high for glaucoma patient than normal fundus image. The ROI of green plane is taken and K-Means clustering technique is recursively applied and Optic Disc and Optic Cup is segmented. Through elliptic fiiting, area of Optic Disc and Cup is determined and hence CDR is calculated. ISNT is another parameter used for the diagnosis of glaucoma which is determined through the ratio of area of blood vessels in Inferior Superior to Nasal Temporal side. Blood vessels will shift to Nasal side for glaucoma patients, hence value will be less for glaucoma patient than normal fundus image. Matched filter and Local entropy thresholding is applied to extract blood vessels. The code is programmed in C++ using OpenCV library functions. OpenCV (Open Source Computer Vision Library) is a library of programming functions developed by Intel. Core, highgui, imgproc, ml are the main libraries used from OpenCV. The optimized functions in OpenCV increase the speed of operation and is very much suitable for real time mass screening purpose. A batch of 50 retinal images (25 normal set and 25 abnormal set) obtained from the Aravind Eye Hospital, is used to assess the performance of the proposed system.

[1]  Shijian Lu,et al.  Neuro-Retinal Optic Cup Detection in Glaucoma Diagnosis , 2009, 2009 2nd International Conference on Biomedical Engineering and Informatics.

[2]  Guoliang Fan,et al.  An efficient blood vessel detection algorithm for retinal images using local entropy thresholding , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[3]  Jaspreet Kaur,et al.  An Efficient Blood Vessel Detection Algorithm For Retinal Images Using Local Entropy Thresholding , 2012 .

[4]  Tien Yin Wong,et al.  Closed angle glaucoma detection in RetCam images , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[5]  Sh Gharibzadeh,et al.  The new approach to automatic detection of Optic Disc from non-dilated retinal images , 2010, 2010 17th Iranian Conference of Biomedical Engineering (ICBME).

[6]  U. Rajendra Acharya,et al.  Automated Diagnosis of Glaucoma Using Texture and Higher Order Spectra Features , 2011, IEEE Transactions on Information Technology in Biomedicine.

[7]  Ahmed Wasif Reza,et al.  Automatic Tracing of Optic Disc and Exudates from Color Fundus Images Using Fixed and Variable Thresholds , 2009, Journal of Medical Systems.

[8]  Jayanthi Sivaswamy,et al.  Optic Disk and Cup Segmentation From Monocular Color Retinal Images for Glaucoma Assessment , 2011, IEEE Transactions on Medical Imaging.

[9]  J. Liu,et al.  Optic cup and disk extraction from retinal fundus images for determination of cup-to-disc ratio , 2008, 2008 3rd IEEE Conference on Industrial Electronics and Applications.

[10]  K.S. Park,et al.  Three dimensional reconstruction of conventional stereo optic disc image , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[11]  Anurag Mittal,et al.  Automated feature extraction for early detection of diabetic retinopathy in fundus images , 2009, CVPR.

[12]  K. Narasimhan,et al.  AN EFFICIENT AUTOMATED SYSTEM FOR GLAUCOMA DETECTION USING FUNDUS IMAGE , 2011 .

[13]  Thomas Walter,et al.  Automatic Analysis of Color Fundus Photographs and Its Application to the Diagnosis of Diabetic Retinopathy , 2005 .

[14]  Frans Vos,et al.  Modeling of scanning laser polarimetry images of the human retina for progression detection of glaucoma , 2006, IEEE Transactions on Medical Imaging.

[15]  K. Duraiswamy,et al.  Early detection of glaucoma in retinal images using cup to disc ratio , 2010, 2010 Second International conference on Computing, Communication and Networking Technologies.

[16]  Manuel Emilio Gegúndez-Arias,et al.  Detecting the Optic Disc Boundary in Digital Fundus Images Using Morphological, Edge Detection, and Feature Extraction Techniques , 2010, IEEE Transactions on Medical Imaging.

[17]  Heinrich Niemann,et al.  Automated segmentation of the optic nerve head for diagnosis of glaucoma , 2005, Medical Image Anal..