Document Type : Original Article
Authors
1
Professor of IT & Head Research Data Science Research Lab BlueCrest University,Monrovia, Liberia-1000
2
Associate Professor, Faculty of Engineering, Sohar University, Oman - 311
3
Dept.of Biotechnology, Prathyusha Engineering College, Thiruvallur-Chennai High Way, Aranvoyal, Chennai
4
Assistant Professor - ECE, Department of Research & Development, Sree Dattha Institute of Engineering & Science, Sheriguda, Greater Hyderabad -501 510
Abstract
Retinal disorders like diabetic retinopathy pose a significant threat to global vision. Early diagnosis is crucial, and fundus images provide vital insights into retinal conditions, focusing on blood vessel characteristics. Manual retinal vessel segmentation, though precise, is time-consuming and dependent on skilled professionals. Addressing this, an automatic and efficient retinal vessel segmentation method is urgently needed, utilizing computer vision techniques. Existing approaches include machine learning, filtering-based, and model-based methods. Our research aims to evaluate automated segmentation and classification techniques for diabetic retinopathy and glaucoma using diverse retinal image datasets, including DRIVE, REVIEW, STARE, HRF, and DRION. The methodologies under consideration encompass machine learning, filtering-based, and model-based approaches, with performance assessment based on a range of metrics, including true positive rate, true negative rate, positive predictive value, negative predictive value, false discovery rate, Matthews's correlation coefficient, and accuracy. The primary objective of this research is to scrutinize, assess, and compare the design and performance of different segmentation and classification techniques, encompassing both supervised and unsupervised learning methods. To attain this objective, we will refine existing techniques and develop new ones, ensuring a more streamlined and computationally efficient approach.
Keywords