Diabetic Retinopathy Detection using Fundus Photography
Hritik Rao1, Pranjay Bajaj2, Kanmani Sivagar3
1Hritik Rao*, Student, Department of Computer Science & Engineering, SRM Institute of Science and Technology, Kattankulathur India.
2Pranjay Bajaj, Student, Department of Computer Science & Engineering, SRM Institute of Science and Technology, Kattankulathur India.
3Kanmani Sivagar, Assistant Professor, Department of Computer Science & Engineering, SRM Institute of Science and Technology, Chennai, India.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 31, 2020. | Manuscript published on April 10, 2020. | PP:1194-1198 | Volume-9 Issue-6, April 2020. | Retrieval Number: E2790039520/2020©BEIESP | DOI: 10.35940/ijitee.E2790.049620
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Patients suffering from prolonged diabetic conditions are prone to Diabetic Retinopathy (DR) which leads to vision impairment if left untreated. Diabetic Retinopathy has been on the rise across the globe due to an increase in the number of diabetic patients. Diabetic Retinopathy detection in early stages has become vital to prevent permanent vision impairment and avoid arduous medical treatment in the later stages. Diabetic Retinopathy (DR) causes damage to the retina and gradual loss of sight and in severe cases permanent vision impairment eventually leading to blindness. An early analysis of Diabetic Retinopathy helps in controlling the progress of the disease and increases the chances of recovery. An automated classification of Diabetic Retinopathy using images is a difficult job due to the microscopic variability of the appearance of different classes and the lack of a standard data infrastructure by medical professionals. One of the major deterrents in automated Diabetic Retinopathy (DR) detection is the identification of the essential features in the fundus image. Techniques like Gaussian Blur and auto-cropping has been used for feature extraction and noise removal. Through this paper, we aim to classify various fundus images of the eye into various classes of diabetic Retinopathy and automate the screening process.
Keywords: Diabetic Retinopathy, Retina, Fluorescein Angiography, Convolutional Neural Network, radial, Optical Coherence Tomography, Preprocessing.
Scope of the Article: Neural Information Processing