An Image Examination System for Retinal Optic Disc Mining and Analysis With Social Group Optimization Algorithm | IGI Global Scientific Publishing
Welcome to the InfoSci Platform
An Image Examination System for Retinal Optic Disc Mining and Analysis With Social Group Optimization Algorithm

An Image Examination System for Retinal Optic Disc Mining and Analysis With Social Group Optimization Algorithm

Pradipta Kumar Mishra, Suresh Chandra Satapathy
Copyright: © 2022 |Volume: 13 |Issue: 1 |Pages: 17
ISSN: 1947-9263|EISSN: 1947-9271|EISBN13: 9781683181514|DOI: 10.4018/IJSIR.300370
Cite Article Cite Article

MLA

Mishra, Pradipta Kumar, and Suresh Chandra Satapathy. "An Image Examination System for Retinal Optic Disc Mining and Analysis With Social Group Optimization Algorithm." IJSIR vol.13, no.1 2022: pp.1-17. https://doi.org/10.4018/IJSIR.300370

APA

Mishra, P. K. & Satapathy, S. C. (2022). An Image Examination System for Retinal Optic Disc Mining and Analysis With Social Group Optimization Algorithm. International Journal of Swarm Intelligence Research (IJSIR), 13(1), 1-17. https://doi.org/10.4018/IJSIR.300370

Chicago

Mishra, Pradipta Kumar, and Suresh Chandra Satapathy. "An Image Examination System for Retinal Optic Disc Mining and Analysis With Social Group Optimization Algorithm," International Journal of Swarm Intelligence Research (IJSIR) 13, no.1: 1-17. https://doi.org/10.4018/IJSIR.300370

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

This work aims to develop a hybrid image examination system to extract and evaluate the Optic Disc (OD) from the Age-related Macular Degeneration (AMD) and Non-AMD class Digital Fundus Retinal Image (DFRI). This work implements an image pre-processing through Shannon’s Entropy and Social Group Optimization (SE+SGO) based thresholding and image post-processing with Level Set Segmentation (LSS). A relative study among the extracted OD and the ground-truth is then executed to compute the vital Picture Similarity Parameters (PSP). This study also presents a detailed pixel level data analysis practice on the extracted OD. Finally, the performance of the LSS is then validated against the existing segmentation techniques, such as Chan-Vese, Active-Contour and k-means clustering. The proposed work is executed on the iChallenge-AMD-2018 DFRI (400 images) and the results confirm that, proposed hybrid tool helps to achieve better values of Jaccard (86.82%), Dice (91.78%), Accuracy (98.94%), Precision (92.86%), Sensitivity (94.06%), and Specificity (99.46%).

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global Scientific Publishing bookstore.