What question did this study set out to answer?

The study aims to evaluate deep learning architectures for the detection and classification of diabetic retinopathy.

June 19, 2023SHILAP Revista de lepidopterologíaOpen Access

Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy

View Full Paper

Ask AI

Bookmark

Authors

CMCheena MohantyBiju Patnaik University of Technology SMSakuntala MahapatraCreative Technology (Singapore)BABiswaranjan AcharyaJSS Academy of Higher Education and Research

Discussion

Member takes

Implication

Randomized trial demonstrates improved accuracy in diabetic retinopathy detection using deep learning models, suggesting enhanced diagnosis efficiency.

Key Points

The study aims to evaluate deep learning architectures for the detection and classification of diabetic retinopathy.
Proposed two deep learning architectures: hybrid network (VGG16 + XGBoost) and DenseNet 121.
Preprocessed retinal images from the APTOS 2019 dataset, addressing imbalanced image class distribution.
Assessed model performance based on accuracy.
Hybrid network achieved 79.50% accuracy.
DenseNet 121 model achieved 97.30% accuracy.
DenseNet 121 displayed superior performance compared to existing methods using the same dataset.

Cite This Study

Mohanty et al. (2023) studied this question.

synapsesocial.com/papers/69dbe6c9eb8801008ea3c308 https://doi.org/10.3390/s23125726

View Full Paper

Ask AI

Bookmark

Implication

Randomized trial demonstrates improved accuracy in diabetic retinopathy detection using deep learning models, suggesting enhanced diagnosis efficiency.

Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy

Discussion

Member takes

Implication

Key Points

Cite This Study

Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider