To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
A Comparative Study of Deep Learning Techniques for Ocular Diseases |
|
Author |
Amal AlShahrani, Ruba Hassan Balubaid, Rafaa Ismail Alowaybidi, Hadeel Abdulaziz Alnasiri, Jumanah Moqbel Alsehli, Sarah Saeed Alshehri |
| Citation |
Vol. 25 No. 5 pp. 21-30 |
|
Abstract |
This study conducts a comparative evaluation of two cutting-edge deep learning models, You Only Look Once (YOLO) and VGG16, utilizing fundus images for automated ocular disease classification. The research endeavors to discern between Normal (N), Diabetes (D), Glaucoma (G), and Cataract (C), prevalent in fundus imagery. Fundus images, being a cornerstone in ophthalmic diagnostics, pose unique challenges due to variations in image quality, pathology manifestation, and disease complexity. By rigorously comparing the performance, strengths, and limitations of YOLOv8, YOLOv5, and VGG16 on this specific dataset, this study aims to provide insights into their efficacy in accurately diagnosing ocular conditions. The outcomes of this investigation have the potential to advance the development of more precise and efficient automated diagnostic systems for ocular diseases, thereby facilitating early intervention and improving patient care in ophthalmology. |
|
Keywords |
Deep Learning, YOLO (You Only Look Once), VGG16, Fundus Images, Ocular Disease Classification |
|
URL |
