Modified curvature-based trigonometric identities for retinal blood vessel tortuosity measurement in diabetic retinopathy fundus images

N. Badariah A. Mustafa, Mimi Diyana W. Zaki, Aini Hussain, Jemaima Che Hamzah

Research output: Contribution to journalArticle

Abstract

In current clinical practice, there is no specific standard and grading system that can be used to measure the behaviour of the retinal blood vessel curvature. The retinal blood vessel curvature is measured based on clinical experiences. It is very subjective and inconsistent to describe the presence of tortuosity in fundus images. Thus, this paper aims to measure the tortuosity of retinal blood vessel using curvature- based method and investigate its relationship with diabetic retinopathy (DR) disease. The proposed tortuosity measures have been tested on 43 fundus images belonging to patients who have been diagnosed with DR disease and validated by two clinical experts from our collaborative hospital. On average, the proposed algorithm achieved 90.7% (accuracy), 98.72% (sensitivity) and 9.3% (false negative rate), that shows significant tortuosity presence in diabetic retinopathy fundus images.

Original languageEnglish
Pages (from-to)133-139
Number of pages7
JournalInternational Journal of Engineering and Technology(UAE)
Volume7
Issue number4
DOIs
Publication statusPublished - 01 Jan 2018

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Computer Science (miscellaneous)
  • Environmental Engineering
  • Chemical Engineering(all)
  • Engineering(all)
  • Hardware and Architecture

Cite this