Authors :
Gokul BV; Divyashree S; Neelam Manoj Kumar; DV Sreekethan; Akash S
Volume/Issue :
Volume 9 - 2024, Issue 12 - December
Google Scholar :
https://tinyurl.com/jrey969r
Scribd :
https://tinyurl.com/4tdkzfs6
DOI :
https://doi.org/10.5281/zenodo.14511815
Abstract :
The main cause of vision loss worldwide is
diabetic retinopathy (DR). This project presents a frame
work for automatic DR detection using retina and retinal
images. To improve overall modeling and prevent
overshoot, the system uses regularization techniques and
VGG16 ,CNN trained on ImageNet. Binary cross-
entropy loss function trains the system for for the
project. More than 90% of tests pass when ADAM
optimizer is used. Achieve accuracy when developing
training programs. There is a short delay to maintain the
lustiness of the model. This approach will be taken to use
in real clinical settings. It is a authentic instrument for
early treatment.
References :
- "Automated treatment of diabetic retinopathy: an analysis of deep machine learning techniques" (Patel, R., Williams, D. and Garcia, E., 2023) Computing in Biology and Medicine, 45, 78 -92. "Deep CNN for retinopathy detection: a comprehensive survey" los ntawm Lee, S., Kim, H. and Park, M. (2023) IEEE Transactions on Medical Imaging, 28(3), 204-217.
- "Progress in Diabetic Retinopathy on Deep Learning: A Systematic Review" Wang, X., Li, Y. and Zhang, Z. (2023) Journal of Medical Systems, 51(2), 156-169.
- "Evaluation of depth learning models for treatment of DR" Chen, L., Liu, J. and Yang, Y. (2023) Pattern Recognition Letters, 39, 301-315.
- "Recent Advances in Intersection Studies for the treatment of DR: A Review of the Literature" Methods and Applications, 82, 124-137, Kumar, S., Sharma, M. and Gupta, A . (2023).
- "Application of Deep Learning in Diabetic Retinopathy Detection: A Review" Sau: Li, H., Zhang, G. and Wang, J. (2023) Medical Bioengineering Computer, 29(4), 416-429.
- Jiménez, S., Sarmiento, A., Fondon, I. thiab Abbas, Q. 2023. Comparison of DR sorting using fundus and OCT images using depth studies. Medical research in publications, 115, page 103700. . Medical Artificial Intelligence, 137, p. 102434 a. Involving many levels for treatment of DR. 243-253 Medical Physics, 50(2).
- Chen, W., Zhao, H., Yang, F. (2023). Overview of clinical impact of deep machine learning projects for DR diagnosis. Health Technology Letters, 10(1), 36-47.
- Ong, T., Tan, S., and Lim, J. (2023). Deep learning hybrid architecture leads to improved visualization of diabetic retinopathy. Access, IEEE 8, 89456-89467.
- 2023, Xu, J., Zhang, Q. and Wang, F. Overview of major developments and practical implementation of DR in diabetic retinopathy. 17, 155-167;
- Wang, X., Luo, Y., & Deng, S. (2023). Evaluating the effectiveness of deep learning-based diabetic retinopathy assessment methods. Medical Device Expert Review, 20(3), 210-223.
- Liu, Z., Shi, L., Ma, Y. (2023). Diabetic retinopathy research using deep communication and transfer learning. Medical Informatics International, 168, 104646. Comparison of combined criteria for diabetic retinopathy diagnosis. 21, 255-268; Journal of Computational and Structural Biotechnology.
The main cause of vision loss worldwide is
diabetic retinopathy (DR). This project presents a frame
work for automatic DR detection using retina and retinal
images. To improve overall modeling and prevent
overshoot, the system uses regularization techniques and
VGG16 ,CNN trained on ImageNet. Binary cross-
entropy loss function trains the system for for the
project. More than 90% of tests pass when ADAM
optimizer is used. Achieve accuracy when developing
training programs. There is a short delay to maintain the
lustiness of the model. This approach will be taken to use
in real clinical settings. It is a authentic instrument for
early treatment.