Glaucoma Disease Classification by using Fundus images
-
Published:2024-03-25
Issue:1
Volume:13
Page:
-
ISSN:2409-9368
-
Container-title:Bulletin of Business and Economics (BBE)
-
language:
-
Short-container-title:BBE
Author:
Rakha Allah,Masood Sohail,Akram Arslan,Sultan Muhammad Faseeh
Abstract
Optic Disc (OD) and Optic Cup (OC) damage is caused by the eye condition glaucoma. OD is the morphological structure that is apparent in the cross-sectional view of the optic nerve connecting to the retina, while OC is the core region of OD. The morphological changes in the optic disc (OD) and optic cup (OC) often happen before visual field issues when glaucoma begins. Optic nerve head damage caused by glaucoma is permanent. Glaucoma is the greatest global cause of irreversible blindness, according to data from the World Health Organization (WHO). Only 10 to 50 percent of glaucoma patients, according to population-level surveys, are aware that they have the condition. As a result, glaucoma early identification is crucial for preventing irreversible eye damage. Glaucoma is a vision disorder that frequently affects older people and renders them permanently blind. Glaucoma affects 2.5% of people of all ages and 4.8% of people over the age of 75. Using MobileNetV2, this study suggests a unique deep transfer learning model for categorizing glaucoma. With regard to the error, with the least amount of expense, MobileNetV2 is a framework that optimizes memory consumption and execution speed. To increase the dataset and MobileNetV2's precision, data augmentation techniques were used. Using the HRF dataset, the suggested deep learning model's effectiveness is assessed. Results from the suggested procedure are accurate to 98%. Medical professionals can find the optimum course of treatment for their patients with the help of automated glaucoma classification.
Publisher
Research for Humanity (Private) Limited
Reference32 articles.
1. Ajitha, S., & Judy, M. (2020). Faster R-CNN classification for the recognition of glaucoma. Journal of Physics: Conference Series, 2. Alghamdi, M., & Abdel-Mottaleb, M. (2021). A comparative study of deep learning models for diagnosing glaucoma from fundus images. IEEE Access, 9, 23894-23906. 3. Ansari, E., Pavicic-Astalos, J., Ayan, F., King, A. J., Kinsella, M., Ng, E., Nita, A., & Group, V. (2021). Treatment of open-angle glaucoma and ocular hypertension with preservative-free tafluprost/timolol fixed-dose combination therapy: UK and Ireland results from the VISIONARY Study. Advances in therapy, 38(6), 2990-3002. 4. Arbeiter, D., Reske, T., Teske, M., Bajer, D., Senz, V., Schmitz, K.-P., Grabow, N., & Oschatz, S. (2021). Influence of drug incorporation on the physico-chemical properties of poly (L-lactide) implant coating matrices—A systematic study. Polymers, 13(2), 292. 5. Camara, J., Neto, A., Pires, I. M., Villasana, M. V., Zdravevski, E., & Cunha, A. (2022). Literature review on artificial intelligence methods for glaucoma screening, segmentation, and classification. Journal of Imaging, 8(2), 19.
|
|