Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Apr 15:2022:8014979.
doi: 10.1155/2022/8014979. eCollection 2022.

Diagnosis of Retinal Diseases Based on Bayesian Optimization Deep Learning Network Using Optical Coherence Tomography Images

Malliga Subramanian  1 , M Sandeep Kumar  2 , V E Sathishkumar  3 , Jayagopal Prabhu  2 , Alagar Karthick  4 , S Sankar Ganesh  5 , Mahseena Akter Meem  6
Affiliations

Diagnosis of Retinal Diseases Based on Bayesian Optimization Deep Learning Network Using Optical Coherence Tomography Images

Malliga Subramanian et al. Comput Intell Neurosci. .

Abstract

Retinal abnormalities have emerged as a serious public health concern in recent years and can manifest gradually and without warning. These diseases can affect any part of the retina, causing vision impairment and indeed blindness in extreme cases. This necessitates the development of automated approaches to detect retinal diseases more precisely and, preferably, earlier. In this paper, we examine transfer learning of pretrained convolutional neural network (CNN) and then transfer it to detect retinal problems from Optical Coherence Tomography (OCT) images. In this study, pretrained CNN models, namely, VGG16, DenseNet201, InceptionV3, and Xception, are used to classify seven different retinal diseases from a dataset of images with and without retinal diseases. In addition, to choose optimum values for hyperparameters, Bayesian optimization is applied, and image augmentation is used to increase the generalization capabilities of the developed models. This research also provides a comparison of the proposed models as well as an analysis of them. The accuracy achieved using DenseNet201 on the Retinal OCT Image dataset is more than 99% and offers a good level of accuracy in classifying retinal diseases compared to other approaches, which only detect a small number of retinal diseases.

PubMed Disclaimer

Conflict of interest statement

The authors declare that there are no conflicts of interest regarding the publication of this article.

Figures

Figure 1
Figure 1
Sample OCT images. (a) AMD. (b) CNV. (c) CSR. (d) DME. (e) DR. (f) Drusen. (g) MH. (h) Normal.
Figure 2
Figure 2
VGG16 architecture.
Figure 3
Figure 3
A 5-layer dense block [43].
Figure 4
Figure 4
Workflow for the proposed classifiers.
Figure 5
Figure 5
Confusion matrix. (a) VGG16 (feature extractor). (b) VGG16 (fine tuner).
Figure 6
Figure 6
Error analysis. (a) An OCT image with CNV disease. (b) An OCT normal image.
See this image and copyright information in PMC

References

    1. Eddy N. FDA clears GE Healthcare’s AI platform for X-ray scans. 2019. https://www.healthcareitnews.com/news/
    1. Sathishkumar V. E., Cho Y. Cardiovascular disease analysis and risk assessment using correlation based intelligent system. Basic and Clinical Pharmacology and Toxicology . 2019;125(1):p. 61.
    1. Alzubaidi L. MedNet: pre-trained convolutional neural network model for the medical imaging tasks. 2021. https://arxiv.org/abs/2110.06512 .
    1. Islam M. S., Wang J.-K., Johnson S. S., Thurtell M. J., Kardon R. H., Garvin M. K. A deep-learning approach for automated OCT en-face retinal vessel segmentation in cases of optic disc swelling using multiple en-face images as input. Translational Vision Science & Technology . 2020;9(2):p. 17. doi: 10.1167/tvst.9.2.17. - DOI - PMC - PubMed
    1. Malliga S. Automated skin disease identification using deep learning algorithm. International Journal of Advanced Science and Technology . 2019;29(3):255–260.