An intelligent mobile based decision support system for retinal disease diagnosis

  • Authors:

  • A. Bourouis;M. Feham;M. A. Hossain;L. Zhang

  • Affiliations:

  • STIC Laboratory, Abou-bekr Belkaid University of Tlemcen, Algeria;STIC Laboratory, Abou-bekr Belkaid University of Tlemcen, Algeria;Computational Intelligence Group, Department of Computer Science and Digital Technology, Faculty of Engineering and Environment, University of Northumbria at Newcastle, UK;Computational Intelligence Group, Department of Computer Science and Digital Technology, Faculty of Engineering and Environment, University of Northumbria at Newcastle, UK

  • Venue:
  • Decision Support Systems
  • Year:
  • 2014

Quantified Score

Hi-index 0.00

Visualization

Abstract

Diabetes and Cataract are the key causes of retinal blindness for millions of people. Current detection of diabetes and Cataract from retinal images using Fundus camera is expensive and inconvenient since such detection is not portable and requires specialists to perform an operation. This paper presents an innovative development of a low cost Smartphone based intelligent system integrated with microscopic lens that allows patients in remote and isolated areas for regular eye examinations and disease diagnosis. This mobile diagnosis system uses an artificial Neural Network algorithm to analyze the retinal images captured by the microscopic lens to identify retinal disease conditions. The algorithm is first of all trained with infected and normal retinal images using a personal computer and then further developed into a mobile-based diagnosis application for Android environments. The application is optimized by using the rooted method in order to increase battery lifetime and processing capacity. A duty cycle method is also proposed to greatly improve the energy efficiency of this retinal scan and diagnosis system in Smartphone environments. The proposed mobile-based system is tested and verified using two well-known medical ophthalmology databases to demonstrate its merits and capabilities. The evaluation results indicate that the system shows competitive retinal disease detection accuracy rates (87%). It also offers early detection of retinal diseases and shows great potential to be further developed to identify skin cancer.