Central Retinal Artery Occlusion: The Identification and Segmentation of Retinal Blood Vessels

 

B. S. Sathish¹, R. Murugesan², L.M.I. Leo Joseph³, V. Kalist⁴, Ganesan P^5*

¹Department of  Electronics and Communication Engineering, Ramachandra College of Engineering, Eluru, India.

²Department of Electronics and Communication Engineering, Malla Reddy College of Engineering and Technology, Secunderabad, Telangana, India.

³Department of  Electronics and Communication Engineering, S.R.Engineering College, Warangal, India.

⁴Department of  Electronics and Communication Engineering, Sathyabama Institute of Science and Technology.

^5*Department of Electronics and Communication Engineering, Vidya Jyothi Institute of Technology, Hyderabad.

 

ABSTRACT:

The Central Retinal Artery Occlusion is a retinal disorder in which blood flow through the major artery of retina gets blocked resulting in sudden vision loss without any pain in the affected eye. This blockage generally comes from a blood clot or cholesterol deposit in the blood vessel. The segmentation of retinal blood vessels and optical disc is the most vital and challenging task to investigate the rigorousness of the various retinal diseases such as branch retinal vein occlusion. There is lot of methods and algorithms are developed to address this issue. The proposed method enlightens the central retinal artery occluded retinal blood vessels identification and extraction based on simple image processing techniques.

 

 

1. INTRODUCTION:

The segmentation and identification is the most important task in image processing. The segmentation is the process of partitioning of a complete image into number of sub images called clusters^9-12. In color based segmentation, the image in RGB color model is transformed into other color models such as CIELab, HSV or YCbCr^13-14. The color model is the representation of color using color components or channels in three dimensional way^15-16.

 

Central Retinal Artery Occlusion is a retinal disorder in which one of the arteries that bring blood to the eye’s retina gets blocked resulting in sudden vision loss without any pain in the affected eye.

 

 

 

The retina is a very thin film of nerves at the back side of the inner eye that senses light falling on it^1-4. The retina converts the scene into electrical impulses^5-6. These electrical signals are transmitted to brain (neurons) through the optic nerves and we are capable to perceive the illustration^7-8. Therefore, an obstruction (blockage) in the retina’s arteries is a very severe problem. This blockage generally comes from a blood clot or cholesterol deposit in the blood vessel. This is a very serious state which needs instant and prompt medical attention.  Figure 1 illustrated the blocked artery of CRAO. The image is obtained from https://www.epainassist.com/eye-pain/central-retinal- artery-occlusion.

 

Central Retinal Artery Occlusion (CRAO) generally arises amongst the people at the age group between 50 and 70. Hardening of the arteries and atherosclerosis is the most general crisis linked with CRAO. An abnormal blood clot formation, thrombosis, is main cause of CRAO. The loss of blood flow through the major artery of retina is referred to as Central retinal artery occlusion (CRAO).

 

Figure 1: Central Retinal Artery Occlusion

 

The outcome of CRAO can appear rapidly and be extremely harsh such as loss of eyesight. Eyesight may not acquire well again even after treatment. In case of BRAO, resurgence is more liable and can get good eyesight even after treatment. The symptom of CRAO includes sudden blurring or blindness in anyone of our eyes, the steady loss of vision over a period. If one maintains good health, it is easier to stay away from Central retinal artery occlusion. CRAO is regularly related to heart problems or diabetes.

 

2. METHODOLOGY:

The proposed scheme for the detection and segmentation of the blood vessels from the central retinal artery occluded image is explained as follows. The proposed method is based on the basic digital image processing techniques and mathematical morphology. The outcome of the discrete wavelet transform for the segmentation of the blood vessels also discussed.  The proposed approach is elucidated as follows. The input test image is acquired from the DRIVE database. The Digital Retinal Images for Vessel Extraction (DRIVE) database is freely available to make possible investigations on the detection and segmentation of retina’s blood vessels in retinal fundus images for our research and experiments ²³ (https://www.isi.uu.nl/Research/Databases/DRIVE/). The pre-processing is the low level preliminary process in image processing to improve the quality of the image by suppressing the unnecessary disturbances (distortion) and / or enhance the necessary image features significant for further analysis and processing. The example for the pre-processing includes filtering, intensity adjustment, rotation, scaling, and translation. In our work image is resized to [400 700] for rapid processing. In our work contra harmonic mean filter of mask size 3 is utilized to remove the unnecessary distortion. We know that RGB color space is nothing but it is mixture of red, green and blue color components. The proposed work concentrates only on green channel of the test image because our eye is very sensitive to green component as compared to others. The CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm partitions the images into contextual regions and applies the histogram equalization to each one. The principle of median filter is arranging the pixels, according to their grey value, of a NxN mask in ascending order and median is computed. This median is now replacing the center pixel. In the next step, the median filtered out image is transformed into binary image using a global threshold method (otsu). The major advantage of the otsu method is the selection of the threshold level to reduce the intra-class difference of the 0 and 1 i.e., black and white pixels. It is necessary to remove all connected objects (components) the unnecessary small pixels to improve the appearance of the segmented output image. For this, ‘area opening’ operation is performed to eliminate all the associated objects in the threshold image that have lesser than 50 pixels.

 

 

(a) input image                                      (b) red channel

(c) green channel                                    (d) blue channel

Figure 2: Test image and its three different components

 

The assessment of the proposed method of retinal blood vessels segmentation of Central Retinal Artery Occluded fundus images is explained as follows. Figure 2 illustrates the test image and its components.

 

The proposed work concentrates only on green channel of the test image because our eye is very sensitive to green component as compared to others. The green channel is complemented for more visualization which is shown in fig 3. Image after CLAHE process is illustrated in Fig 4.

 

 

Figure 3: The complement of the green channel

Figure 4: Enhancement of the green channel

Figure 5: Morphological opening

 

Morphological opening operation softens the interior of the object contour and remove thin segment of the image as shown in fig 5. In our work, optical disk is removed. The outcome of this operation is shown in Fig 6.

 

 

Figure 6: The Optical disk removal

 

A straightforward edge-preserving median filter is used to lessen the amount of noise in the images¹⁹. The principle of this filter is arranging the pixels, according to their grey value, of a NxN mask in ascending order and median is computed. This median is now replacing the center pixel. The outcome of the median filtering is illustrated in Fig 7. In the next step, the median filtered out image is transformed into binary image using a global threshold method (otsu) as illustrated in fig 8(a). The major advantage of the otsu method is the selection of the threshold level to reduce the intra-class difference of the 0 and 1 i.e., black and white pixels. It is necessary to remove all connected objects (components) the unnecessary small pixels to improve the appearance of the segmented output image. For this, ‘area opening’ operation is performed to eliminate all the associated objects in the threshold image that have lesser than 50 pixels. Figure 8(b) is the end result of the proposed approach.

 

 

Figure 7: The outcome of the median filtering

 

 (a)                                                (b)

Figure 8: Result of the retinal blood vessel segmentation

 

4. CONCLUSION:

The image processing based detection of optical disc and retinal blood vessels of central retinal artery occluded fundus images is proposed and explained. The work is based on the simple image processing operations such as preprocessing, filtering, morphological operations and thresholding. The proposed method is tested with the images acquired from the DRIVE database. The experimental analysis demonstrated the competence of the proposed method for detection of optical disc and retinal blood vessels of central retinal artery occluded fundus images.

 

5. ACKOWLEDGMENT:

The authors would like to thank the Image Sciences Institute for the utilization of the image (DRIVE database) for our research work.

 

6. ETHICS AND CONSENT:

This article does not contain any studies with human participants or animals performed by any of the authors. No direct participation of human entertains in this article.

 

7. CONFLICT OF INTEREST:

We are declaring that, there is no conflict of interest regarding the publication of this paper.

 

8. REFERENCES:

1.        Li H, Chutatape,O. Automated feature extraction in color retinal  images by a model based approach.. IEEE Trans. Biomed. Eng. 51; 2004; 246–254.

2.        Jelinek HF, Cree MJ, Leandro JJG, Soares JVB, Cesar RM, and Luckie A, "Automated segmentation of retinal blood vessels and identification of proliferative diabetic retinopathy", JOSA A 24(5): 1448-1456, 2007.

3.        Rossant F, Badellino M, Chavillon A, Bloch I, and   Paques M. A morphological approach for vessel segmentation in eye fundus images, with quantitative evaluation. J. Med. Imaging. Health. Inf.  1(2); 2011; 42–49.

4.        Soares J and Cree M. Retinal vessel segmentation using the 2D Gabor wavelet and supervised classification.  IEEE Trans. Med. Imag.  25; 2006; 1214–1222.

5.        Luo, C. Opas, and Shankar M. Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter. IEEE Trans. Biomed. Eng. 49(1); 2008; 168–172.

6.        Zhang B, Zhang L, Zhang L, and Karray F. Retinal vessel extraction by matched filter with first-order derivative of Gaussian. Comput. Biol. Med.  40(1); 2010; 438–445.

7.        J.J. Staal, M.D. Abramoff, M. Niemeijer, M.A. Viergever, B. van Ginneken, "Ridge based vessel segmentation in color images of the retina", IEEE Transactions on Medical Imaging, 2004, vol. 23, pp. 501-509.

8.        Perfetti R, Ricci E, Casali D, et al., "Cellular neural networks with virtual template expansion for retinal vessel segmentation", IEEE Transactions on Circuits and Systems II 54(2): 141-145, 2007.

9.        Sajiv G. Unsupervised Clustering of Satellite Images in CIELab Color Space using Spatial Information Incorporated FCM Clustering Method.  International Journal of Applied Engineering Research. 10(20); 2015.

10.      Sathish BS, Ganesan P and Khamar Basha. Shaik. Color Image Segmentation based on Genetic Algorithm and Histogram Threshold. International Journal of Applied Engineering Research. 10(6); 2015; 123-127.

11.      Kalist V, Ganesan P,  Sathish BS, and Jenitha JMM. Possiblistic-Fuzzy C-Means Clustering Approach for the Segmentation of Satellite Images in HSL Color Space.  Procedia Computer Science. 57; 2015; 49-56.

12.      Shaik KB, Ganesan P, Kalist V, and Sathish BS. Comparative Study of Skin Color Detection and Segmentation in HSV and YCbCr Color Space.  Procedia Computer Science. 57; 2015; 41-48.

13.      Ganesan P and Shaik KB. HSV color space based segmentation of region of interest in satellite images.  2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT). 2014; 101-105.doi: 10.1109/ICCICCT.2014.6992938

14.      Sajiv G and Ganesan P.  Comparative Study of Possiblistic Fuzzy C-Means Clustering based Image Segmentation in RGB and CIELuv Color Space.  International Journal of Pharmacy & Technology. 8(1); 2016; 10899-10909.

15.      Thakur M, Raj I and Ganesan P. The cooperative approach of genetic algorithm and neural network for the identification of vehicle License Plate number. International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS). 2015; 1-6.

16.       Ganesan P and B. S. Sathish. Automatic Detection of Optic Disc and Blood Vessel in Retinal Images using Morphological Operations and Ipachi Model. Research J. Pharm. and Tech. 10(8): August 2017; 2602-2607.

17.      Adam Hoover and Michael Goldbaum, “Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels”, IEEE Transactions on Medical Imaging, Vol. 22, No. 8, August 2003, pp.951-957.

18.      Guillermo Ayala, Teresa León, and Victoria Zapater, “Different Averages of a Fuzzy Set with an application to Vessel Segmentation”, IEEE Transactions on Fuzzy Systems, Vol. 13, No. 3, June 2005, pp.384-393.

19.      Ganesan P, “Detection and Segmentation of Retinal Blood Vessel in Digital RGB and CIELUV color space Fundus Images”,   Research J. Pharm. and Tech. 11(6): 2018, 2326-2330.

20.      Meindert Niemeijer, Bram van Ginneken, Maria S. A. Suttorp-Schulten, and Michael D. Abràmoff, ” Automatic Detection of Red Lesions in  Digital Color Fundus Photographs, IEEE Transactions on Medical Imaging, Vol. 24, No. 5, May 2005, pp.584-592.

21.      Ana Maria Mendonça, and Aurélio Campilho,” Segmentation of Retinal Blood Vessels by Combining the Detection of Centerlines and Morphological Reconstruction”, IEEE Transactions on Medical Imaging, Vol. 25, No. 9, September 2006, pp.1200-1213.

22.      Tatijana Stoˇsic´ and Borko D. Stoˇsic´, “Multifractal Analysis of Human Retinal Vessels”, IEEE Transactions on Medical Imaging, Vol. 25, No. 8, August 2006. pp.1101-1108.

23.      https://www.isi.uu.nl/Research/Databases/DRIVE/

 

 

 

 

 

Received on 23.04.2019           Modified on 26.05.2019

Accepted on 29.06.2019         © RJPT All right reserved