Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (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)
A gradual consequence of diabetes, diabetic retinopathy (DR) is one of the main causes of avoidable blindness. Vision impairment can be prevented by early identification, however manual diagnosis using retinal fundus image analysis is laborious, subjective, and necessitates specific knowledge. The automated DR detection system proposed in this study makes use of EfficientNet-B4, a high-performing deep learning architecture that provides better accuracy and feature extraction capabilities than previous iterations of EfficientNet. Retinal fundus imaging datasets are used to train the model, which is then refined by transfer learning to categorise various DR phases. The trained model is made accessible by deploying it as a Flask-based web application, which allows users to upload fundus photos and get real-time predictions. Grad-CAM heatmaps are also used to provide interpretability. In underprivileged healthcare settings, the suggested approach seeks to enhance early detection, expedite large-scale screening, and support ophthalmologists in clinical decision-making.
Keywords:
Diabetic Retinopathy, EfficientNet-B4, Deep Learning, Transfer Learning, Fundus Images, Medical Image Analysis, Web Deployment, Flask
Cite Article:
"Automated Diagnostic System for Diabetic Retinopathy using Deep Learning", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 11, page no.a106-a109, November-2025, Available :http://www.ijrti.org/papers/IJRTI2511013.pdf
Downloads:
000234
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator