You are on page 1of 14

Retinal Blood Vessels Segmentation

Presented By
Mithilesh kumar Singh Yadav
About me
 I am Mithilesh Kumar Singh Yadav, I am from Ghazipur
 I have completed my 10th and 12th from H.S.I.C. Ghazipur in 2000 & 2002
 I have completed my B.Tech from V.I.E.T, Ghaziabad in 2010 with an
aggregate of 70.60%
 I have completed my M.Tech from MNNIT Allahabad in 2012 with an
aggregate of 74%
 Working as an Assistant Professor in Department of CSE at BNCET
Lucknow since 11 February 2019
Introduction
 The human eye is one of the most important organs in the human
body.
 The cross-sectional view of human eye.
Introduction
 According to WHO report, blindness is a major issue world wide
 The major cause of blindness are:
1. Age-related macular degeneration (AMD)
2. Diabetic retinopathy (DR)
3. Hypertension
4. Glaucoma

 According to the Ophthalmologist most of the Retinal diseases


(including blindness) are diagnosed by the analyzing the retinal
blood vessels structure.
 Therefore retinal blood vessels segmentation is prominent task.
Literature survey
According to author M. M. Fraz et al., the retinal blood vessel
segmentation approaches are mainly classified into seven categories:-
 Intensity based pattern recognition technique

 Matched filter based approach

 Mathematical morphological based approach

 Tracking based approach

 Multi-scale based approach

 Vessel profile model based approach

 Parallel/hardware based approach

Our concentration on matched filter based segmentation because it


provides the best retinal vessel structure w.r.t. other segmentation
approaches.
Literature survey
 First time Chaudhuri et al. [7] in 1989, compare the intensity level of
the cross-section profile of the retinal image with Gaussian curve and
stated that the cross-sectional profile of retinal blood vessels has an
approximate Gaussian shape and proposed a Gaussian shaped
matched filter based approach to segment the retinal blood vessels.

 After that various authors Al- Rawi et al. [8], Xiaoyi and Mojon [9]
and Amin and Yan [11] improved the performance of matched filter
based approach by improving the thresholding techniques rather than
changing the Gaussian shaped matched filter kernel.
Literature survey
 In 2010 author Zhang et al. [10] proposed a matched filter approach
with first-order derivative of Gaussian and improve the performance.

 1n 2014 author Singh et al., proposed SDOG based matched filter


based approach and improve the performance .

 In 2014 author H. Zolfagharnasa et al. [7] first time replace the


Gaussian function based matched filter by Cauchy probability
distribution function (pdf) and reported that the accuracy of retinal
blood vessel detection was substantially improved.
 First time Singh et al.,[] in 2016 compare the intensity level of the
cross-section profile of the retinal image with Gumbel Pdf and stated
that the cross-sectional profile of retinal blood vessels matched better
with Gumbel Pdf rather than Gaussian distribution function and
proposed a Gumbel Pdf based matched filter approach to segment the
retinal blood vessels.

 In 2020 Saroj et al.,[] proposed a Frechet Pdf based matched filter


approach to segment the retinal blood vessels.

 Author Singh et al.,[] and Saroj et al.,[] stated that the intensity
profile of retinal blood vessel match better with extreme valued pdf
rather than Gaussian and Cauchy distribution function.
Research Objective
 There are various type of skewed pdf are exist in a Literature
that indicate it may be possible the intensity profile of retinal
blood vessel are matched better with other existing skewed pdf.

 Therefore the research objective is to identify the suitable


probability distribution function (pdf) as a kernel to design a new
matched filter approach that perform better for retinal blood
vessels segmentation.
Methodology
RGB COLOR IMAGE

PRE-PROCESSING

APPLY MATCHED FILTER BASED APPROCH


& GENERATE MATCH FILTER RESPONCE
IMAGE

APPLY POST-PROCESSING

EVALUTE THE PERFORMANCE


References:
1. A. Foster and S. Resniko , \The impact of vision 2020 on global blindness,"
Eye, vol. 19, no. 10, pp. 1133{1135, 2005).
2. A. Hoover, V. Kouznetsova, and M. Goldbaum, \Locating blood vessels in
retinal images by piecewise threshold probing of a matched filter response,"
Medical Imaging, IEEE Transactions on, vol. 19, no. 3, pp.203{210, 2000.
3. B. G. M. L. M. A. M. Niemeijer, J.J. Staal, \Drive: digital retinal images for
vessel extraction," Methods for Evaluating Segmentation and Indexing
techniques Dedicated to Retinal Ophthalmology, 2004.
4. J. Staal, M. D. Abramo, M. Niemeijer, M. A. Viergever, and B. Van
Ginneken, \Ridge-based vessel segmentation in color images of the retina,"
Medical Imaging, IEEE Transactions on, vol. 23, no. 4, pp. 501{509, 2004.
5. S. Chaudhuri, S. Chatterjee, N. Katz, M. Nelson, and M. Goldbaum,\
Detection of blood vessels in retinal images using two-dimensional matched
filters," IEEE Transactions on medical imaging, vol. 8, no. 3,pp. 263{269,
1989.

11
References:
6. M. M. Fraz, P. Remagnino, A. Hoppe, B. Uyyanonvara, A. R. Rudnicka,C.
G. Owen, and S. A. Barman, \Blood vessel segmentation methodologies in
retinal images{a survey," Computer methods and programsin biomedicine,
vol. 108, no. 1, pp. 407{433, 2012.
7. Al-Rawi, M., Qutaishat, M., Arrar., M., 2007. An improved matched filter
for blood vessel detection of digital retinal images. Computers in Biology
and Medicine 37, 262–267.
8. Xiaoyi Jiang, Mojon, D., 2003. Adaptive local thresholding by
verification-based multithreshold probing with application to vessel
detection
9. M. G. Cinsdikici and D. Aydn, \Detection of blood vessels in
ophthalmoscope images using mf/ant (matched filter/ant colony)
algorithm,"Computer methods and programs in biomedicine, vol. 96, no.
2, pp.85{95, 2009.
10. B. Zhang, L. Zhang, L. Zhang, and F. Karray, \Retinal vessel extraction
by matched filter with rst-order derivative of gaussian," Computers in
List of Publication
 Paper on "Route Optimization for Reverse AODV in MANETs by
Shrinking Mechanism" IEEE Sponsored 7th International Conference on
Advanced Computing and Communication Technologies (ICACCT™-
2013).
 Paper on "Cleaved reflector domain based DDOS attack "IEEE
Sponsored 7th International Conference on Advanced Computing and
Communication Technologies (ICACCT™-2013).
 Paper on "A SERVEY ON TRANSPORT LAYER PROTOCOLS"
published in VSRD International Journal of Computer Science &
Information Technology, Vol. 3 No. 3 March 2013.
 Paper on “Design And Implementation of Energy Efficient Protocol of
Heterogeneous WSN based on Node Energy” UGC Care I Journal in 2020
 Paper on “A Review on Stable election Protocol for Clustered
Heterogonous WSN” UGC Care I Journal in 2020
 Paper on “Enhancement in Homomorphism Encryption Scheme of
Cloud Computing Using PSO Algorithms” UGC Care I Journal in 2021.
.

THANK YOU

You might also like