Diabetic retinopathy stage detection using convolutional fine-tuned transfer Learning model
Journal Title: International Journal of Experimental Research and Review - Year 2023, Vol 31, Issue 2
Abstract
Diabetic Retinopathy (DR) is a prevalent eye condition that occurs as a frequent complication among individuals with diabetes, particularly those who have been living with the disease for an extended period of time. This study uses fundus images to diagnose DR at five stages from early to late with No DR, Mild, Moderate, Severe, and Proliferative DR, commonly known as Stage 0 to Stage 4, respectively. This will aid in the timely treatment of diabetic patients preventing them from developing DR as early as possible. We used two most popular open-source datasets, the DR Detection database, namely APTOS 2019 and EyePACS, and combined them to create a larger dataset to trade off the data-centric obstacle and shortfall for any Deep Learning-based prediction models. Data augmentation and preprocessing techniques are applied to the images before feeding them to the proposed model to get a more accurate and efficient one. In the modern age oriented to Artificial Intelligence (AI), it is necessary to thoroughly analyze the identification of DR based on the existing Deep Learning (DL) models. After learning about the limitations of existing models, we have fine-tuned the ResNet50, DenseNet201 and InceptionV3 to enhance the model performance of the detection and categorization of DR. We have since proposed three Deep Convolutional Neural Networks (DCNN) models with better outcome based on accuracy than the existing state-of-the-art (SOTA) models. The fine-tuned DenseNet201 model, among the other two, performed significantly better with a validation accuracy of 90.04% and a negligible amount of loss, irrespective of each class, under the best configurable test conditions.
Authors and Affiliations
Jahnabi Medhi, Mithun Karmakar, Anup Kumar Barman, Subhash Mondal, Amitava Nag
Keywords
Related Articles
- EP ID EP719461
- DOI https://doi.org/10.52756/10.52756/ijerr.2023.v31spl.004
- Views 49
- Downloads 0
Enhancing Sign Language Understanding through Machine Learning at the Sentence Level
The visual language of sign language is based on nonverbal communication, including hand and body gestures. When it comes to communicating, it is the main tool for those who are deaf or hard of hearing all around the glo...
Computational Thinking Processes in Solving the Corona Epidemic Model: Pre-service Maths Teachers
In the 21st century, pre-service mathematics teachers are expected to have problem-solving skills that are effective, efficient, and solutive and are in line with the mindset of computer experts. In learning mathematics,...
Study of rhizospheric bacterial population of Azadirachta indica (Neem) of North 24 Parganas district of West Bengal for bioprospective consideration
The rhizospheric microbial population has immense role in agriculture and crop improvement. This article deals with the preliminary information about the rhizospheric bacterial population of Azadirachta indica growing at...
Geo-spatial analysis of Watershed Characteristics Using Remote Sensing and GIS Techniques: A case study of Kassai watershed, West Bengal, India
Watershed is a natural hydrological entity which allows surface run-off to a defined channel, drainage, stream or river at a particular point. It is the basic unit of water supply, which evolves over time. Morphometric a...
ISM approach to model financial risks in Indian KPO organization
Globalization has entered a new phase due to significant advancements in technology. This progress has allowed organizations to reduce costs while enhancing their market responsiveness, thus gaining a competitive edge. N...