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)
Abstract–Diabetic Retinopathy (DR) is one of the complicationswhich affects the retina and may lead to blindness in diabetes mellitus patients which can be avoided if diagnosed and detected early. Though it is often asymptotic if detected early is very much treatable. A computer vision-based algorithm can help the doctors and the patients for a faster and more precise diagnosis for treatment. Such algorithms can potentially have better accuracy in detecting different stages of the disease. However, developing such algorithms can be computationally expensive and to some extent complex in terms of extracting highly non-linear features. Applying deep learning in such scenarios increases the problem-solving capacity of the system significantly. Deep Learning algorithms have their own challenges often being dependent on corpus of labelled data. In the medical imaging field getting such large amount of labelled data can be expensive and time consuming but once completed and optimised would give a robust system for diagnosis. With image level annotation most DR gradings task are considered as Deep Learning classification problems. The DR related lesions have not fully been explored with Deep Learning perspectives.In this study we have used image-level and patch-level annotations to build a robust framework for the classification of DR severity gradings. This framework using the feature map of AlexNet gives us promising results in the diagnosis when compared with the advanced modern technologies and 3 medical professional practicing ophthalmologists for over 9 years.
Keywords:
Diabetic Retinopathy, AlexNet
Cite Article:
"Prognostication of Diabetic Retinopathy using Transfer Learning of AlexNet ", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 7, page no.a207-a218, July-2023, Available :http://www.ijnrd.org/papers/IJNRD2307026.pdf
Downloads:
000118760
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