System for Diagnosis of Diabetic Retinopathy using Neural Network
Dipika Gadriye1, Gopichand Khandale2, Rahul Nawkhare3
1Dipika Gadriye, P.G. Student, Department of Electronics Engineering, Wainganga College of Engineering & Management, Nagpur, (Maharashtra), India.
2Prof. Gopichand Khandale, Assistant professor Department of Electronics Engineering, Wainganga College of Engineering& Management, R. T.M.U, Nagpur, (Maharashtra), India.
3Prof. Rahul Nawkhare, Assistant professor Department of Electronics Engineering, Wainganga College of Engineering & Management, R. T.M.U, Nagpur, (Maharashtra), India.
Manuscript received on 20 May 2014 | Revised Manuscript received on 25 May 2014 | Manuscript published on 30 May 2014 | PP: 81-86 | Volume-3 Issue-2, May 2014 | Retrieval Number: B1110053214/2014©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The main cause of blindness for the working age population in western countries is Diabetic Retinopathy – a complication of diabetes mellitus – is a severe and wide- spread eye disease. Digital color fundus images are becoming increasingly important for the diagnosis of Diabetic Retinopathy. In order to facilitate and improve diagnosis in different ways, this fact opens the possibility of applying image processing techniques. An algorithm able to automatically detect the microaneurysms in fundus image captured is a necessary preprocessing step for a correct diagnosis as microaneurysms are earliest sign of DR. The key for low cost widespread screening is a system usable by operators with little training. Some methods that address this problem can be found in the literature but they have some drawbacks like accuracy or speed. The aim of this thesis is to develop and test a new method for detecting the microaneurysms in retina images. To do so preprocessing, gray level 2D feature based vessel extraction is done using neural network by using extra neurons which is evaluated on DRIVE database which is superior than rule based methods. Morphological opening and image enhancement are performed to identify microaneurysms in an image. The complete algorithm is developed by using a MATLAB implementation and the diagnosis in an image can be estimated with the better accuracy and in shorter time than previous techniques.
Keywords: Contrast normalization, Fundus, Microaneurysms, Retina, Pixel Classification, Retina.
Scope of the Article: Classification