Robust methodology for fractal analysis of the retinal vasculature

Robust methodology for fractal analysis of the retinal vasculature

We have developed a robust method to perform retinal vascular fractal analysis from digital retina images. The technique preprocesses the green channel retina images with Gabor wavelet transforms to enhance the retinal images. Fourier Fractal dimension is computed on these preprocessed images and do...

Full description

Bibliographic Details
Main Authors: Che Azemin, Mohd. Zulfaezal, Kumar, Dinesh Kant, Wong, Tien Y., Kawasaki, Ryo, Mitchell, Paul, Wang, Jie Jin
Format: Article
Language:English
Published: IEEE Engineering in Medicine and Biology Society 2011
Subjects:
RE Ophthalmology
Online Access:http://irep.iium.edu.my/24911/
http://irep.iium.edu.my/24911/
http://irep.iium.edu.my/24911/
http://irep.iium.edu.my/24911/1/IEEE_TMI.pdf
id iium-24911
recordtype eprints
spelling iium-249112013-01-11T00:46:25Z http://irep.iium.edu.my/24911/ Robust methodology for fractal analysis of the retinal vasculature Che Azemin, Mohd. Zulfaezal Kumar, Dinesh Kant Wong, Tien Y. Kawasaki, Ryo Mitchell, Paul Wang, Jie Jin RE Ophthalmology We have developed a robust method to perform retinal vascular fractal analysis from digital retina images. The technique preprocesses the green channel retina images with Gabor wavelet transforms to enhance the retinal images. Fourier Fractal dimension is computed on these preprocessed images and does not require any segmentation of the vessels. This novel technique requires human input only at a single step; the allocation of the optic disk center. We have tested this technique on 380 retina images from healthy individuals aged 50+ years, randomly selected from the Blue Mountains Eye Study population. To assess its reliability in assessing retinal vascular fractals from different allocation of optic center, we performed pair-wise Pearson correlation between the fractal dimension estimates with 100 simulated region of interest for each of the 380 images. There was Gaussian distribution variation in the optic center allocation in each simulation. The resulting mean correlation coefficient (standard deviation) was 0.93 (0.005). The repeatability of this method was found to be better than the earlier box-counting method. Using this method to assess retinal vascular fractals, we have also confirmed a reduction in the retinal vasculature complexity with aging, consistent with observations from other human organ systems. IEEE Engineering in Medicine and Biology Society 2011-02 Article PeerReviewed application/pdf en http://irep.iium.edu.my/24911/1/IEEE_TMI.pdf Che Azemin, Mohd. Zulfaezal and Kumar, Dinesh Kant and Wong, Tien Y. and Kawasaki, Ryo and Mitchell, Paul and Wang, Jie Jin (2011) Robust methodology for fractal analysis of the retinal vasculature. IEEE Transactions on Medical Imaging, 30 (2). pp. 243-250. ISSN 0278-0062 http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=42 10.1109/TMI.2010.2076322
repository_type Digital Repository
institution_category Local University
institution International Islamic University Malaysia
building IIUM Repository
collection Online Access
language English
topic RE Ophthalmology
spellingShingle RE Ophthalmology
Che Azemin, Mohd. Zulfaezal
Kumar, Dinesh Kant
Wong, Tien Y.
Kawasaki, Ryo
Mitchell, Paul
Wang, Jie Jin
Robust methodology for fractal analysis of the retinal vasculature
description We have developed a robust method to perform retinal vascular fractal analysis from digital retina images. The technique preprocesses the green channel retina images with Gabor wavelet transforms to enhance the retinal images. Fourier Fractal dimension is computed on these preprocessed images and does not require any segmentation of the vessels. This novel technique requires human input only at a single step; the allocation of the optic disk center. We have tested this technique on 380 retina images from healthy individuals aged 50+ years, randomly selected from the Blue Mountains Eye Study population. To assess its reliability in assessing retinal vascular fractals from different allocation of optic center, we performed pair-wise Pearson correlation between the fractal dimension estimates with 100 simulated region of interest for each of the 380 images. There was Gaussian distribution variation in the optic center allocation in each simulation. The resulting mean correlation coefficient (standard deviation) was 0.93 (0.005). The repeatability of this method was found to be better than the earlier box-counting method. Using this method to assess retinal vascular fractals, we have also confirmed a reduction in the retinal vasculature complexity with aging, consistent with observations from other human organ systems.
format Article
author Che Azemin, Mohd. Zulfaezal
Kumar, Dinesh Kant
Wong, Tien Y.
Kawasaki, Ryo
Mitchell, Paul
Wang, Jie Jin
author_facet Che Azemin, Mohd. Zulfaezal
Kumar, Dinesh Kant
Wong, Tien Y.
Kawasaki, Ryo
Mitchell, Paul
Wang, Jie Jin
author_sort Che Azemin, Mohd. Zulfaezal
title Robust methodology for fractal analysis of the retinal vasculature
title_short Robust methodology for fractal analysis of the retinal vasculature
title_full Robust methodology for fractal analysis of the retinal vasculature
title_fullStr Robust methodology for fractal analysis of the retinal vasculature
title_full_unstemmed Robust methodology for fractal analysis of the retinal vasculature
title_sort robust methodology for fractal analysis of the retinal vasculature
publisher IEEE Engineering in Medicine and Biology Society
publishDate 2011
url http://irep.iium.edu.my/24911/
http://irep.iium.edu.my/24911/
http://irep.iium.edu.my/24911/
http://irep.iium.edu.my/24911/1/IEEE_TMI.pdf
first_indexed 2023-09-18T20:37:15Z
last_indexed 2023-09-18T20:37:15Z
_version_ 1777409128179695616

Similar Items