Diabetic Retinopathy using Lstm-Rnn
Ojaswi Sharma1, Himanshu Saxena2
1Ojaswi Sharma*, C.S(C.S.E), SSVIT, Bareilly, India.
2Himanshu Saxena, C.S(C.S.E), SSVIT, Bareilly, India.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 31, 2020. | Manuscript published on April 10, 2020. | PP: 1771-1774 | Volume-9 Issue-6, April 2020. | Retrieval Number: F4309049620/2020©BEIESP | DOI: 10.35940/ijitee.F4309.049620
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: Diabetic retinopathy is an significant cause of loss of vision and blindness in millions of people worldwide. While screening protocols-fluorescence and optical accuracy to the identification of the disease, in most cases-have been identified, the patients remain unaware, and they can’t perform these tests on time. The early diagnosis of the condition plays a vital role in preventing loss of vision which results in a prolonged period of untreated diabetes mellitus between patients. Different profound learning strategies were applied for classification and disease prediction in diabetic retinopathy datasets, but most of them ignoreddata pre-processing and dimension reduction and resulted in partial outcomes. The diagnostic analysis is carried out in this paper with the use of profound learning and the LSTM-RNN methodology in this manner and by segmentation through Fuzzy c. Output indicates that the whole system being tested is validated by the use of 400 MESSIDOR (database) retinal fundus images.
Keywords: Deep learning, FCM, RNN, LSTM etc.
Scope of the Article: Deep learning