Salp swarm optimisation with deep transfer learning enabled retinal fundus image classification model. (2nd December 2022)

• Record Type: Journal Article
• Authors: Gupta, Indresh Kumar; Choubey, Abha; Choubey, Siddhartha
• Is Part Of: International journal of networking and virtual organisations. Volume 27:Number 2(2022)
• Page Start: 163
• Page End: 180
• Publication Date: 2022-12-02
• Subjects: retinal fundus images -- image classification -- machine learning -- deep learning -- salp swarm algorithm -- cascade forward neural network -- CFNN; Computer networks -- Periodicals; Information networks -- Periodicals; Virtual corporations -- Periodicals; Electronic commerce -- Periodicals; Management information systems -- Periodicals; Management -- Data processing -- Periodicals; 004.65
• Languages: English
• ISSNs: 1470-9503

Abstract

Automated screening and diagnostic process in the healthcare sector improves services, reduces cost and labour. With the developments of machine learning (ML) and deep learning (DL) models, intelligent disease diagnosis models can be designed. Retinal fundus image classification using DL models becomes essential for the identification and classification of distinct retinal diseases. This article develops a salp swarm optimisation with deep transfer learning enabled retinal fundus image classification (SSODTL-RFIC) model. The proposed SSODTL-RFIC model examines the retinal fundus image for the existence of diseases. In addition, a median filtering (MF) approach is employed for the noise removal process and graph cut (GC) segmentation is applied. Besides, MobileNetv1 feature extractor is involved to produce feature vectors. Finally, SSO with cascade forward neural network (CFNN) model is applied for recognition and classification process. A widespread experimentation process is performed on benchmark datasets to examine the enhanced performance of the SSODTL-RFIC model, an extensive comparative examination pointed out the supremacy of the SSODTL-RFIC model over the recent approaches with maximum accuracy of 98.71% and 99.12% on the test ARIA and STARE datasets respectively.