Automated Localization of Optic Disk, Detection of Microaneurysms and Extraction of Blood Vessels to Bypass Angiography

Diabetic Retinopathy is considered as a root cause of vision loss for diabetic patients. For Diabetic patients, regular check-up and screening is required. At times lesions are not visible through fundus image, Dr. Recommends angiography. However Angiography is not advisable in certain conditions like if patient is of very old age, if patient is a pregnant woman, if patient is a child, if patient has some critical disease or if patient has undergone some major surgery. In this paper we propose a system Automated Diabetic Retinopathy Detection System (ADRDS) through which fundus image will be processed in such a way that it will have the similar quality to that of angiogram where lesions are clearly visible. It will also identify the Optic Disk (OD) and extract blood vessels because pattern of these blood vessels near optic disc region plays an important role in diagnosis for eye disease. We have passed 100 images in the system collected from Dr. Manoj Saswade and Dr. Neha Deshpande and got true positive rate of 100%, false positive rate of 3%, and accuracy score is 0.9902.

[1]  M. Usman Akram,et al.  Automated Detection of Dark and Bright Lesions in Retinal Images for Early Detection of Diabetic Retinopathy , 2012, Journal of Medical Systems.

[2]  Ahmed Wasif Reza,et al.  Diagnosis of Diabetic Retinopathy: Automatic Extraction of Optic Disc and Exudates from Retinal Images using Marker-controlled Watershed Transformation , 2009, Journal of Medical Systems.

[3]  R. C. Tripathi,et al.  Automated Early Detection of Diabetic Retinopathy Using Image Analysis Techniques , 2010 .

[4]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Ramesh R. Manza,et al.  A Critical Review of Expert Systems for Detection and Diagnosis of Diabetic Retinopathy , 2012 .

[6]  J. Kanski Clinical Ophthalmology: A Systematic Approach , 1989 .

[7]  Chandan Chakraborty,et al.  Quantitative clinical marker extraction from colour fundus images for non-proliferative Diabetic Retinopathy grading , 2011, 2011 International Conference on Image Information Processing.

[8]  Vipula Singh,et al.  Automatic Detection of Diabetic Retinopathy in Non- dilated RGB Retinal Fundus Images , 2012 .

[9]  Rangaraj M. Rangayyan,et al.  Detection of the Optic Nerve Head in Fundus Images of the Retina with Gabor Filters and Phase Portrait Analysis , 2010, Journal of Digital Imaging.

[10]  Lakshminarayanan Subramanian,et al.  Case for Automated Detection of Diabetic Retinopathy , 2010, AAAI Spring Symposium: Artificial Intelligence for Development.

[11]  [Automatic detection of vessels in color fundus images]. , 2010, Archivos de la Sociedad Espanola de Oftalmologia.

[12]  Ahmed Wasif Reza,et al.  Diabetic Retinopathy: A Quadtree Based Blood Vessel Detection Algorithm Using RGB Components in Fundus Images , 2007, Journal of Medical Systems.

[13]  Ramesh R. Manza,et al.  Review on Detection and Classification of Diabetic Retinopathy Lesions Using Image Processing Techniques , 2013 .

[14]  Hiroshi Fujita,et al.  Automated microaneurysm detection method based on double-ring filter and feature analysis in retinal fundus images , 2012, 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS).

[15]  ANALYSIS OF DIABETIC RETINOPATHY IMAGES USING BLOOD VESSEL EXTRACTION , 2012 .

[16]  Diego Marin,et al.  Automated Optic Disc Detection in Retinal Images of Patients with Diabetic Retinopathy and Risk of Macular Edema , 2009 .

[17]  Rangaraj M. Rangayyan,et al.  Digital Image Processing for Ophthalmology: Detection of the Optic Nerve Head , 2011, Digital Image Processing for Ophthalmology.