Fusion-Based CNN Approach for Diabetic Retinopathy Detection from Fundus Images

DOI

10.2991/978-94-6463-471-6_41How to use a DOI?

Keywords

Diabetic Retinopathy; concatenates; DiaNet model; Resnet50; Inceptionv3; CNN

Abstract

Diabetic Retinopathy is a state that causes vision impairment in diabetics. Usually, it is brought on by elevated blood sugar, which damages in the eyes and might cause blindness. Blindness may result from a delayed diagnosis. The chance of permanent loss of vision can be considerably reduced aside receiving primal diagnosis and care for DR. The time, effort, and cost associated with ophthalmologists manually diagnosing DR retina fundus photographs are significant when compared to computer-aided diagnosis procedures. Deep learning is becoming widely used in two domains: medical image analysis and categorization. Convolutional neural systems are the suggested deep learning algorithms for evaluating medical pictures. This research proposed a new method for detecting diabetic retinopathy (DR) using the Dia Net Model (DNM), a CNN model that concatenates features extracted from Resnet50 and Inceptionv3 to detect DR. The Gabor filter is utilized for feature extraction, texture analysis, object recognition, image compression, and blood vessel visibility enhancement during the retinal image pre-processing step. An openly accessible dataset of fundus photos is used to assess the suggested model. Compared to the most advanced techniques. The experimental findings show that the proposed CNN model and DiaNet model obtain greater accuracy, sensitivity, specificity, precision, and f1 score.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - P. Yogendra Prasad
AU  - M. Ramu
AU  - Gundluru Rahul
AU  - A. Pradeepthi Reddy
AU  - Bala Ramana
AU  - Yaswanth Yerukola
PY  - 2024
DA  - 2024/07/30
TI  - Fusion-Based CNN Approach for Diabetic Retinopathy Detection from Fundus Images
BT  - Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
PB  - Atlantis Press
SP  - 420
EP  - 429
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-471-6_41
DO  - 10.2991/978-94-6463-471-6_41
ID  - Prasad2024
ER  -