A CAD Method for Early Detection of Glaucoma Employing CNN from Fundus Photographs
Keywords:
Glaucoma, CNN, Precision, F1 Score, Recall, Matthews correlation, Local binary patternAbstract
Early detection and diagnosis of glaucoma, a crippling eye illness that causes irreversible vision loss, are essential for effective care. In this study, convolutional neural networks are used to diagnose glaucoma in a novel way (CNNs). The methodology incorporates local binary pattern (LBP) for image preprocessing using a rigorously curated dataset of Fundus Photos, which includes 1450 images with 899 cases of glaucoma and 551 non-glaucomatous images. Ten layers make up the proposed CNN architecture, including a Conv2D layer for feature extraction, a MaxPooling2D layer for down sampling, a Flatten layer for vectorization, and seven Dense levels for classification. By detecting glaucoma with an accuracy of 99% during training and a loss of 4%, this CNN model has demonstrated outstanding performance. On the test dataset, the model achieves a test loss of 30% and an accuracy of 94%. Confusion matrix, precision, recall, F1-score, support, Matthew’s correlation coefficient (MCC), and Area Under the Receiver Operating Characteristic Curve are just a few of the metrics used to assess this model (AUC). The model’s strong performance in evaluation measures, along with its high accuracy and low loss, point to its potential for early glaucoma detection and, consequently, its critical role in maintaining vision and improving patient treatment. In order to achieve the goal of prompt diagnosis and treatment, this research advances automated glaucoma detection systems.
Downloads
References
Guangzhou An et al. “Glaucoma diagnosis with ma- chine learning based on optical coherence tomography and color fundus images”. In: Journal of healthcare engineering 2019 (2019).
Isaac Arias-Serrano et al. “Artificial intelligence based glaucoma and diabetic retinopathy detection using MATLAB—Retrained AlexNet convolutional neural network”. In: F1000Research 12 (2023), p. 14.
Federico Badala` et al. “Optic disk and nerve fiber layer imaging to detect glaucoma”. In: American journal of ophthalmology 144.5 (2007), pp. 724–732.
D. R. Parashar and D. K. Agarwal, "SVM based Supervised Machine Learning Framework for Glaucoma Classification using Retinal Fundus Images," 2021 10th IEEE International Conference on Communication Systems and Network Technologies (CSNT), Bhopal, India, 2021, pp. 660-663, doi: 10.1109/CSNT51715.2021.950970
Gabriel Garc´ıa et al. “Glaucoma detection from raw cir- cumpapillary oct images using fully convolutional neu- ral networks”. In: 2020 IEEE international conference on image processing (ICIP). IEEE. 2020, pp. 2526– 2530.
Hitendra Garg et al. “A real time cloud-based frame- work for glaucoma screening using EfficientNet”. In: Multimedia Tools and Applications (2022), pp. 1–22.
Juan J Go´mez-Valverde et al. “Automatic glaucoma classification using color fundus images based on con- volutional neural networks and transfer learning”. In: Biomedical optics express 10.2 (2019), pp. 892–913.
Mir Tanvir Islam et al. “Deep learning-based glaucoma detection with cropped optic cup and disc and blood vessel segmentation”. In: IEEE Access 10 (2021), pp. 2828–2841.
Michael A Kass et al. “The Ocular Hypertension Treatment Study: a randomized trial determines that topical ocular hypotensive medication delays or prevents the onset of primary open-angle glaucoma”. In: Archives of ophthalmology 120.6 (2002), pp. 701–713.
Young Kook Kim, Jin Wook Jeoung, and Ki Ho Park. “Inferior macular damage in glaucoma: its relationship to retinal nerve fiber layer defect in macular vulnerability zone”. In: Journal of glaucoma 26.2 (2017), pp. 126–132.
M Cristina Leske et al. “Predictors of long-term progression in the early manifest glaucoma trial”. In: Ophthalmology 114.11 (2007), pp. 1965–1972.
Renato Lisboa et al. “Comparison of different spectral domain OCT scanning protocols for diagnosing preperimetric glaucoma”. In: Investigative ophthalmology & visual science 54.5 (2013), pp. 3417–3425.
D. Parashar and D. Agrawal, "Improved Classification of Glaucoma in Retinal Fundus Images using 2D-DWT," 2021 International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), Bhilai, India, 2021, pp. 1-5, doi: 10.1109/ICAECT49130.2021.9392531.
Abhishek Pal, Manav Rajiv Moorthy, and A Shahina. “G-eyenet: A convolutional autoencoding classifier framework for the detection of glaucoma from retinal fundus images”. In: 2018 25th IEEE international conference on image processing (ICIP). IEEE. 2018, pp. 2775–2779.
Amer Sallam et al. “Early detection of glaucoma using transfer learning from pre-trained cnn models”. In: 2021 International Conference of Technology, Science and Administration (ICTSA). IEEE. 2021, pp. 1–5.
Ali Serener and Sertan Serte. “Transfer learning for early and advanced glaucoma detection with convolutional neural networks”. In: 2019 Medical technologies congress (TIPTEKNO). IEEE. 2019, pp. 1–4.
Rutuja Shinde. “Glaucoma detection in retinal fundus images using U-Net and supervised machine learning algorithms”. In: Intelligence-Based Medicine 5 (2021), p. 100038.
Daniel Shu Wei Ting et al. “Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes”. In: Jama 318.22 (2017), pp. 2211–2223.
Vijaya Kumar Velpula and Lakhan Dev Sharma. “Multi- stage glaucoma classification using pre-trained con- volutional neural networks and voting-based classifier fusion”. In: Frontiers in Physiology 14 (2023), p. 1175881.
D. Parashar and D. K. Agrawal, "Automatic Classification of Glaucoma Stages Using Two-Dimensional Tensor Empirical Wavelet Transform," in IEEE Signal Processing Letters, vol. 28, pp. 66-70, 2021, doi: 10.1109/LSP.2020.3045638
D. Parashar and D. Agrawal, "Automated Classification of Glaucoma Using Retinal Fundus Images," 2020 First IEEE International Conference on Measurement, Instrumentation, Control and Automation (ICMICA), Kurukshetra, India, 2020, pp. 1-6, doi: 10.1109/ICMICA48462.2020.9242702
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
