Identification of retinal diseases based on retinal blood vessel segmentation using Dagum PDF and feature-based machine learning

ABSTRACT

Retinal diseases is one of the major cause of vision impairments worldwide and the variations in fundus images help to identify these retinal diseases. Manual identification and segmentation of these fundus images is a tedious task and is highly prone to errors. Thus, a Dagum probability distribution function (PDF) based on matched filter (MF) for retinal blood vessel segmentation is proposed in this work. Initially, different features are extracted from the fundus images and these features are provided to the ensemble classifier to perform the task of disease classification. The overall performance of the proposed work is evaluated using different popular datasets such as DRIVE, STARE, HRF, IRDiD, Kaggle retinal, ORIGA and RFI. It is found that the specificity of 0.9802 and 0.9838 is achieved on DRIVE and STARE datasets respectively. In addition, the input image is predicted with HRF-glaucoma image ‘10_g.jpg’, having a higher prediction accuracy of 95.45%.

KEYWORDS:

• Segmentation
• retinal blood vessels
• matched filter
• dagum PDF
• Length filtering
• texture features
• entropy thresholding
• Ensemble classifier

Disclosure statement

No potential conflict of interest was reported by the author(s).

Correction Statement

This article has been republished with minor changes. These changes do not impact the academic content of the article.

Additional information

Notes on contributors

K. Susheel Kumar

Dr. K. Susheel Kumar is an Assistant Professor in the Department of Computer Science and Engineering at the Gandhi Institute of Technology and Management, Bengaluru, India. Recently he was awarded Ph.D. in Computer Science and Engineering from NIT Hamirpur, India. He completed his MTech in Information Technology from IIIT Allahabad, India, and his BE in Computer Science and Engineering from Osmania University, Hyderabad, India. He has around fifteen research publications, reputed SCI, Scopus-indexed journals, and conferences. His research interests include image processing, computer vision, and machine learning.

Nagendra Pratap Singh

Dr. Nagendra Pratap Singh is an Assistant Professor in the Computer Science and Engineering Department at the NIT Jalandhar, India. He completed his Ph.D. in Computer Science and Engineering from the IIT (BHU), Varanasi, India. He completed his MTech in Computer Science and Engineering from the MNNIT Allahabad, India, and his BTech in Computer Science and Engineering from the IET, Kanpur, India. He has around 17 years of teaching research experience and approximated 35 research publications in reputed SCI, Scopus indexed journals and conferences. His research interests include image processing, computer vision, pattern recognition, algorithms, machine learning, and medical image analysis.