Affiliations: [a]
Department of Computer Science and Engineering, SRM IST Delhi NCR Campus Ghaziabad, India
| [b]
Department of ECE, Indra Ganesan College of Engineering, Trichy, Tamilnadu, India
| [c]
Department of Electronics and Communication Engineering, Nehru Institute of Engineering and Technology, Coimbatore, Tamilnadu, India
| [d]
Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, Tamilnadu, India
| [e]
Department of ECE, Sona College of Technology, Salem, Tamilnadu, India
| [f]
Department of ECE, SR University, Warangal, Telangana, India
Correspondence:
[*]
Corresponding author. K. Vidhya, Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, Tamilnadu, India. E-mail: vidhyak@karunya.edu.
Abstract: Age-Related Macular Degeneration is a progressive, irreversible eye condition that causes vision loss and impairs quality of life. The lost potential of the optic nerve cannot be regained, but a patient with Age-Related Macular Degeneration must have early diagnosis and treatment in order to prevent visual loss. The diagnosis of Age-Related Macular Degeneration is based on visual field loss tests, a patient’s medical history, intraocular pressure, and a physical fundus evaluation. Age-Related Macular Degeneration must be diagnosed early in order to avoid irreparable structural damage and vision loss. The objective of the proposed study is to develop a new optimization-driven strategy-based recurrent neural network using the Internet of Things for the identification of age-related macular degeneration. The Recurrent Neural Network (RNN) classifier is trained using the Particle Swarm Optimization (PSO) technique included into the RNN-IoMT. Initially, the input picture is sent through pre-processing in order to remove noise and artefacts. The generated preprocessed picture is simultaneously sent to optical disc detection and blood vessel detection. In addition, picture level characteristics are extracted from the image that has been preprocessed. Finally, the image-level, optic disc-level, and blood vessel-level features are retrieved and compiled into a feature vector. The acquired feature vector is fed into the RNN classifier, with the suggested PSO used to train the RNN for Age-Related Macular Degeneration detection via the Internet of Medical Things. The suggested PSO+RNN exhibits better performance with enhanced precision of 97.194%, sensitivity of 97.184%, and specificity of 97.2044%, respectively.
Keywords: Wearables, internet of things, teleophthalmology, deep learning, fundus images
