Ocular Disease Detection Using state of the art Machine Learning techniques based Clinical Decision Support System for Ophthalmologist

DOI

10.2991/978-94-6463-602-4_8How to use a DOI?

Keywords

Machine learning; Ocular diseases; Transfer learning Technique; Clinical Decision Support System; Convolutional Neural Network

Abstract

Machine learning is vital in enabling medical practitioners to detect diseases such as Ocular at an early stage. It is important to detect ocular disorder to overcome the eternal damage to eyes. Ophthalmic disorders are generally not fatal, but if progress over time, they can significantly affect the quality of life. Diabetic Eye Diseases such as Cataract, Glaucoma and Diabetic retinopathy are the main causes of vision loss. Traditional approaches with subjective clinical testing are worth developing and applying automated, fast, and accurate solutions. Therefore, this article proposed a system namely Ocular Disease Detection System using state-of-the-art machine learning techniques. This Clinical Decision Support System (CDSS) assists ophthalmologists in detecting cataract, glaucoma, and diabetic retinopathy effortlessly. The system is designed using five state of the art supervised machine learning algorithms that includes Convolutional Neural Network (CNN), Support vector machine (SVM), Decision Tree, Random Forest and K-Nearest Neighbour (KNN). These algorithms were implemented to evaluate the strengths and weaknesses of each one alone and a comparison among them showed that CNN is the most robust algorithm among all with accuracy of 80.875%. The system has been trained on the dataset containing 5000 instances of fundus images of 5 different eye diseases. The novelty of the proposed system is in the employment of transfer learning technique using VGG19 model which enabled it to produce an outstanding performance even with limited labelled data. As a result of extensive testing which included cross-validation demonstrated that the developed system exhibited strong robustness and outperforms its competitors. The friendly graphical user interface (GUI) makes it easier for doctors and patients to interact effortlessly. The successful implementation of this system will significantly impact public health by providing them with early detection thus reducing the percentage of blindness being caused.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sarmad Shams
AU  - Mishkaat Jamil
AU  - Aqsa Faheem
AU  - Afnan Qureshi
AU  - Zona Khan
AU  - Natasha Mukhtiar
PY  - 2024
DA  - 2024/12/24
TI  - Ocular Disease Detection Using state of the art Machine Learning techniques based Clinical Decision Support System for Ophthalmologist
BT  - Proceedings of the 4th International Conference on Key Enabling Technologies (KEYTECH 2024)
PB  - Atlantis Press
SP  - 56
EP  - 61
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-602-4_8
DO  - 10.2991/978-94-6463-602-4_8
ID  - Shams2024
ER  -