INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
DR and other microvascular and macrovascular disorders of diabetes cause serious illness and death and have a significant economic impact. Retinopathy and other minor microvascular disorders are caused by chronic hyper-glycemia, vascular injury and leakage, edema, tightening of the capillary basement membrane, neovascularization, bleeding, and ischemia.
In this paper, the technology in the previous decade have been increasing at a tremendous pace especially in fields like medicine, military etc. The process comprises two main phases i.e. transfer the learning of the process and its localization and its classification. The launched task consists of two main components, the first being data set and the other is an advanced Dense-Net network specialized in eye disease detection. Following this, Dense-Net is trained to distinguish existing classification on the degree of Diabetic Retinopathy. Finally, accuracy is measured in all units as per the metrics used in the field of computer vision classification.
Various training and testing of data takes place and test results show that the proposed model detects all DR categories and works better compared to the standard ones in the same Kaggle database. Experimenting with Densenet-121 we got an accuracy of 97.3%, sensitivity of 97.6%, precision of 97.7% and f1 score of 97.6%. This shows that it is very capable of accurately detecting level of Diabetic Retinopathy. Our finding will help in detecting early stages of DR to tackle further damage in eye.
"DETECTION OF DIABETIC RETINOPATHY USING DENSENET", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 4, page no.a758-a770, April-2023, Available :http://www.ijnrd.org/papers/IJNRD2304098.pdf
Downloads:
000118752
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn