Assessment of transfer learning models for grading of diabetic retinopathy
Downloads
Published
DOI:
https://doi.org/10.58414/SCIENTIFICTEMPER.2023.14.2.17Keywords:
Transfer learning, retinal image, diabetic retinopathy, VGG16, Inception v3, ResNet50Dimensions Badge
Issue
Section
License
Copyright (c) 2023 The Scientific Temper
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Diabetic retinopathy is a potentially mortal diabetic complication. The severity level of DR must be identified earlier to reduce the medical complications. Effective automated ways for identifying DR and classifying its severity stage are necessary to reduce the burden on ophthalmologists. Transfer learning methods are utilized to automatically grade the severity of diabetic retinopathy in this study. The stages of DR are diagnosed using pretrained VGG16, Inception v3, and ResNet50 models on pre-processed retinal images of DDR dataset. Out of three implemented models, Inception v3 achieved higher validation accuracy of 76.47% and testing accuracy of 67% compared to VGG16 and ResNet50 models. This research contributes to the analysis of deep learning architectures for the creation of automated diabetic retinopathy stage diagnosis and gradingAbstract
How to Cite
Downloads
Similar Articles
- Sanjeev Kumar, Saurabh Charaya, Rachna Mehta, Multi-Metric Evaluation Framework for Machine Learning-Based Load Prediction in e-Governance Systems , The Scientific Temper: Vol. 17 No. 01 (2026): The Scientific Temper
- Nisha Patil, Archana Bhise, Rajesh K. Tiwari, Fusion deep learning with pre-post harvest quality management of grapes within the realm of supply chain management , The Scientific Temper: Vol. 15 No. 01 (2024): The Scientific Temper
- Ashish Nagila, Abhishek K Mishra, The effectiveness of machine learning and image processing in detecting plant leaf disease , The Scientific Temper: Vol. 14 No. 01 (2023): The Scientific Temper
- Lakshminarayani A, A Shaik Abdul Khadir, A blockchain-integrated smart healthcare framework utilizing dynamic hunting leadership algorithm with deep learning-based disease detection and classification model , The Scientific Temper: Vol. 15 No. 04 (2024): The Scientific Temper
- Deepa Ramachandran VR VR, Kamalraj N, Hybrid deep segmentation architecture using dual attention U-Net and Mask-RCNN for accurate detection of pests, diseases, and weeds in crops , The Scientific Temper: Vol. 16 No. 07 (2025): The Scientific Temper
- Rajesh Kumar Singh, Abhishek Kumar Mishra, Ramapati Mishra, Hand Gesture Identification for Improving Accuracy Using Convolutional Neural Network(CNN) , The Scientific Temper: Vol. 13 No. 02 (2022): The Scientific Temper
- R. Prabhu, P. Archana, S. Anusooya, P. Anuradha, Improved Steganography for IoT Network Node Data Security Promoting Secure Data Transmission using Generative Adversarial Networks , The Scientific Temper: Vol. 14 No. 03 (2023): The Scientific Temper
- S. Munawara Banu, M. Mohamed Surputheen, M. Rajakumar, Bio-Inspired and Machine Learning-Driven Multipath Routing Protocol for MANETs Using Predictive Link Analytics , The Scientific Temper: Vol. 16 No. 10 (2025): The Scientific Temper
- P. Ananthi, A. Chandrabose, The socio-technical opportunities and threats of crowdsensing , The Scientific Temper: Vol. 15 No. spl-1 (2024): The Scientific Temper
- Temesgen A. Asfaw, Batch size impact on enset leaf disease detection , The Scientific Temper: Vol. 15 No. 01 (2024): The Scientific Temper
<< < 1 2 3 4 5 6 7 8 9 10 > >>
You may also start an advanced similarity search for this article.
Most read articles by the same author(s)
- Sowmiya M, Banu Rekha B, Malar E, Ensemble classifiers with hybrid feature selection approach for diagnosis of coronary artery disease , The Scientific Temper: Vol. 14 No. 03 (2023): The Scientific Temper
