Retinal fundus image is an indicative tool utilized in detection of risk factors of many diseases like

cardiovascular diseases. Fundus images mainly comprise of Retina and optic nerve. Retina is a sensible
membrane that ensures interior lining of back of the eyeball. Optic nerve conveys the image captured by
the eye to the brain. Optic nerve also plays a vital role in detection of diseases like hypertension,
Diabetic Retinopathy, glaucoma[19].A healthy retinal fundus image has arteriole, venule, optic
disc(based on superior and inferior position) and macular center. Retinal fundus image of infected
people pictures the general parts along with hemorrhage, micro aneurysms and exudates. Diabetic
Retinopathy is identified by micro aneurysms, hard exudates, soft exudates, hemorrhages[20].
Hemorrhage is condition at which blood (pointedly red blood cells) leaks out from blood vessels like
arteries and veins. Major forms of hemorrhage are retinal and vitreous hemorrhage. In former blood
leaks into retina and in latter blood escapes into vitreous humor of eye. The presence of hemorrhages
indicates diabetic retinopathy which leads to CVD. [21].If diabetic retinopathy caused due to
hemorrhages is left untreated, it results in vision loss and blindness[22],[23].Micro aneurysm specifies
the outward bulging of blood vessels which is due to wall weakness. As an aneurysm increases in size,
the risk of the rupture increases, leading to uncontrolled bleeding. Aneurysm sizes vary from 14 µm to
136 µm. As a result of ventricular[24] and atrial septal aneurysm there occurs myocardial infraction.
Aneurysms can be saccular, fusiform and focal bulges[25].Exudates are fluids that ooze out from cuts or
infected areas affecting the surrounding tissues. The fluid is mainly composed of serum,pus,whit blood
cells and dead cells. Exudates are one of the preliminary symptoms of diabetic retinopathy and
cardiovascular disease[26].Exudates are further divided into soft and hard exudates[27].Hard exudates
help to detect disease in early stage[28].Optic disc is a collection of axons from all nerves that are
leaving from eye to brain. The mean vertical and horizontal disc diameters were 1.88 mm and 1.77 mm,
respectively [29]

[19] Pal, S. and Chatterjee, S. (2017). Mathematical morphology aided optic disk segmentation from
retinal images. 2017 3rd International Conference on Condition Assessment Techniques in Electrical
Systems (CATCON).

[20] Rajput, G. and Patil, P. (2014). Detection and Classification of Exudates Using K-Means Clustering in
Color Retinal Images. 2014 Fifth International Conference on Signal and Image Processing.

[21] Kaur, N., Chatterjee, S., Acharyya, M., Kaur, J., Kapoor, N. and Gupta, S. (2016). A supervised
approach for automated detection of hemorrhages in retinal fundus images. 2016 5th International
Conference on Wireless Networks and Embedded Systems (WECON).

[22] Nimbarte, N. and Mushrif, M. (2018). An Effective Algorithm for Hemorrhages Detection in Retinal
Images. 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN).

[23] Xiao, D., Yu, S., Vignarajan, J., An, D., Tay-Kearney, M. and Kanagasingam, Y. (2017). Retinal
hemorrhage detection by rule-based and machine learning approach. 2017 39th Annual International
Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[24] Mahmood, R. and Syeda-Mahmood, T. (2015). Automatic detection of left ventricular aneurysms in
echocardiograms. 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).
[25] Wankhade, M. (2016). Analysis of Disease using Retinal Blood Vessels Detection. International
Journal of Engineering and Computer Science, 5(12), pp.19644- 19647.

[26] Yu, S., Xiao, D. and Kanagasingam, Y. (2017). Exudate detection for diabetic retinopathy with
convolutional neural networks. 2017 39th Annual International Conference of the IEEE Engineering in
Medicine and Biology Society (EMBC).

[27] Anitha, G. and Maria, K. (2018). Detecting Hard Exudates In Retinal Fundus Images Using
Convolutinal Neural Networks. 2018 International Conference on Current Trends towards Converging
Technologies (ICCTCT).

[28] Benzamin, A. and Chakraborty, C. (2018). Detection of Hard Exudates in Retinal Fundus Images
Using Deep Learning. 2018 IEEE International Conference on System, Computation, Automation and
Networking (ICSCA).

[29] Quigley HA, e. (2019). The size and shape of the optic disc in normal human eyes. - PubMed - NCBI.
[online] Ncbi.nlm.nih.gov. Available at: https://www.ncbi.nlm.nih.gov/pubmed/2297333 [Accessed 8
May 2019

[30] Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning

Ryan Poplin et al. utilized deep learning for feature extraction from retinal fundus image. They
developed deep-learning modals using features like optic disc and blood vessel for each prediction.

[31] Early detection of diabetic retinopathy from retinal fundus images using Eigen value analysis

R Manjula Sri and V Rajesh proposed a method for detection of micro-aneurysm via Eigen value analysis
by means of hessian matrix.It was implemented by LABVIEW software.

[32] A New Approach of Detection and Segmentation of Blood Vessels for the Classification of Healthy
and Diseased Retinal Images

Bithi Barua and Md. Mehedi Hasan proposed a new approach for retinal image analysis. The features
extracted from High Resolution Fundus (HRF) dataset are given for training of Artificial Neural
Network(ANN) classifier by backpropagation algorithm.
[33]. Diagnosis Of Ophthalmologic Disordersin retinal fundus images:

V Krishna Sree and P Sudhakar Rao concentrates mainly on age-related macular degeneration, diabetic
retinopathy, and glaucoma which causes blindness in industrial world. The Authors says that age-related
macular degeneration cannot be cured completely, but can be identified in its early stages. Their
algorithm captures the affected pixels and report their location so that it can be treated.

[34] Retinal Imaging and Image Analysis

Michael D. Abràmoff, Mona K. Garvin, Member and Milan Sonka employed quantitative techniques for
2-D fundus imaging and 3-D optical coherence tomography (OCT) imaging. Fundus images are analysed
for clinical evaluation retinal vasculature, identification of retinal lesions, assessment of optic nerve
head (ONH) shape, building retinal atlases, and to automated methods for population screening for
retinal diseases.

[35] A MULTI-ANATOMICAL RETINAL STRUCTURE SEGMENTATION SYSTEM FOR AUTOMATIC EYE SCREENING
USING MORPHOLOGICAL ADAPTIVE FUZZY THRESHOLDING:

Dr.R Satish Kumar,Preetha K, Rasika M, Suhashini M and Veerapreetha V focuses on automatic retina
screening using a robust hybrid segmentation algorithm. The algorithm is a combination of adaptive
fuzzy thresholding and mathematical morphology. The author extracts retinal structures and develops
computer-assisted diagnostic systems.