open access
www.bioinformation.net
Hypothesis
Volume 10(9)
A computational modeling for the detection of
diabetic retinopathy severity
Pavan Kumar Mishra1, Abhijit Sinha1, Kaveti Ravi Teja1, Nitin Bhojwani1, Sagar Sahu1 &
Awanish Kumar2*
1Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh, India; 2Department of
Biotechnology, National Institute of Technology, Raipur, Chhattisgarh, India; Awanish Kumar - Email: drawanishkr@gmail.com;
*Corresponding author
Received June 17, 2014; Revised August 06, 2014; Accepted August 07, 2014; Published September 30, 2014
Abstract:
Prolonged diabetes ultimately leads to Diabetic Retinopathy (DR) which is one of the leading causes of preventable blindness in the
world. Through advanced image analysis techniques are used for abnormalities detection in retina that define and correlate the
severity of DR. A thorough study is done in this area in recent past years and on the basis of these studies we have developed a
computer based prediction model that is used to determine the severity of DR. To identify severity DR, we have analyzed the
human eye image. We have extracted some important features from human eye image i.e. Blood Artery, Optical disc, Exudates.
Based on these image and data we have designed an automated system for the determination of DR severity. This automated DR
severity assessment methods can be used to predict the clinical case and conditions when young clinicians would agree or disagree
with their more experienced fellow members. The algorithms described in this study may be used in clinical practice to validate or
invalidate the diagnoses. Algorithms or method developed here may also be used for pooling diagnostic knowledge for serving
mankind. Here we have described a computational based low cost retinal diagnostic approach which can aid an ophthalmologist to
quickly diagnose the various stages of DR. This system can accept retinal images and can successfully detect any pathological
condition associated with DR.
Keywords: Diabetic retinopathy, fundus, blood vessel, optic disc, exudates, image processing.
Background:
Diabetic retinopathy (DR) is one of the leading chronic diseases,
caused by complications of diabetes that eventually leads to the
blindness. It is estimated that diabetes mellitus type 2 affects 4
percent of the world’s population and almost half of whom
have some degree of DR at any given time [1]. In India, there
has been epidemic increase in type 2 diabetes and DR as
reported by World Health Organization (WHO) [2]. Visual
disability from diabetes is thus a substantial public health
problem; however this morbidity is largely preventable and
treatable. Taking effective precautionary steps at right time, the
quality of life may be preserved [3]. DR is broadly classified in
two categories: i) Nonproliferative DR (NPDR) and ii)
ISSN 0973-2063 (online) 0973-8894 (print)
Bioinformation 10(9): 556-561 (2014)
Proliferative DR (PDR). NPDR happens when the blood vessels
leak and then close. PDR is the advanced stage of DR where the
new abnormal blood vessels grow. Due to lack of oxygen, it
causes fragile new blood vessel grow along retina and filled the
eye with clear gel like vitreous humour. If treatment is delayed
this can cause vessel to bleed and cause cloud vision and
destroy retina.
Therefore, an automated DR diagnostic system is required and
will have to be implemented [2, 3]. Ophthalmologists use color
fundus images of eye, optic disk (bright circular regions of eye
where blood vessels emanate) and other features (exudates,
microaneurysms, hemorrhages, fovea etc) to study the diseases
556
© 2014 Biomedical Informatics
BIOINFORMATION
open access
like DR. Exudates are yellow lipid deposits which appear as
bright yellow lesions. Microaneurysms are small occular
pouches in eye caused by local distension of capillary walls and
appear as small red dots. DR may lead to bigger blood clots
called hemorrhages. The fovea is defined as center of retina and
is region of highest visual acuity. The thicknesses of blood
vessels in optic disk, spatial distribution of exudates, micro
aneurysms and hemorrhages, especially in relation to the fovea
can be used to determine the severity of DR [4]. The present
research work is the use of DR patient’s eye images to extract
various discussed features and develop a computer based
algorithm and model for quick and reliable detection of DR
severity.
which is going to be used as training data. Now training data
were used to train kNN classifier.
Optic Disc Detection
It is mostly circular or elliptical in shape and its color is bright
yellowish or white [8]. Its intensity range lie in red color range
hence it is good to do analysis on red channel (Please see
supplementary material further explanation and equation).
Exudates detection
Exudates are the darkest spots in the retinal images which have
sharp boundaries with black background. For finding the
boundary of each exudate we have applied the morphological
operation on the retinal image. Exudates respond when dilation
is applied on the image because exudates have brighter edges
and dark yellow color. It occupies most of the part of the green
channel we apply dilation on the green channel of the eye
image to extract exudates [13]. In order to perform dilation we
have built-in Mat lab function Imdilate. We have selected
rectangle with height and width as 25 and 25 using this we
have developed a matrix which stores information of this object
and traverse over the input image and dilate it. We have dilated
the image to remove the blood vessels. After applying dilation
on the image with SE as rectangle then we got an image with no
blood vessels in it [14]. We had applied dilation again with SE
as disc on the original image then we will get an image with
highlighted bright exudates with no blood vessels. Then we
had subtracted the both outputs in order to get exudates with
sharp edges with no blood vessels in it [15]. Exudates are bright
yellow or white in color and have high intensity in the green
channel. We have localize the exudate patches more accurately
by taking all the candidate regions whose mean intensities in
the green channel are greater than a fraction (obtained by
training) of the maximum intensity in the channel [16]. After
this the contours which satisfy both conditions remain in the
output while other may be discarded [17]. We have extracted
optical disc object from the original image then we subtracted
both the outputs and the resultant output contain exudates only
[18].
Methodology:
Blood vessel detection
Automated detection of blood vessel is difficult task as the
diameter of blood vessel can vary from very small to large.
Most blood vessel detection algorithms are window based and
emphasis the surrounding window around a given pixel that
matches with a predefined model. The detection of blood
vessels using Gabor filters and scheme production is in
frequent use. The proposed method is beneficiary for both the
detection of large and small vessels but also good for removing
the noise and enhancement of responses of line filters. The
stated method for vessels detection involves the following
steps:
Inverted Green Channel
The analysis of RGB components of fundus images show that
Green channel has best background contrast whereas Blue and
Red Channel are very noisy. Therefore the input image to our
system has green channel extracted only. An iterative algorithm
proposed in is used to remove the strong contrast between the
retinal fundus and image outside the aperture [5]. The Gabor
wavelet transform is implemented using the fast fourier
transformation algorithm. 2-D Gabor wavelet has directional
selectiveness capability of detecting oriented features and fine
tuning to specific frequency [6].
Line Operators
We are focused on calculating two features at each pixel of
image using orthogonal line operators. The first feature
includes calculation of difference S= L – N where L denotes the
maximum gray level obtained when the line operator is
convoluted up to 360⁰ for each pixel and N denotes average
gray level. S is calculated for squared window Centered on
each pixel [7]. The second feature of line operator is evaluated
along gray level of line orthogonal to the first feature. This line
has three pixels length centered at the midpoint of the basic line
operator and perpendicular to it. Its average value is denoted
by L0 and its strength is obtained by S0= L0-N. This L0
separates the pixels of thin vessels as it would be very low and
pixels in background will have high L0 value. On the basis of
the pixel density of blood vessel to the pixel density is used to
estimate level of diabetes (normal, mild, moderate and severe).
In this case number of pixels occupied by the blood vessel was
calculated and then the number of pixels in eye of the fundus
image was calculated. After that the ratio of blood vessel by eye
pixels count was obtained and store in a text file as ‘data.txt’
ISSN 0973-2063 (online) 0973-8894 (print)
Bioinformation 10(9): 556-561 (2014)
Figure 1: Automated blood vessel detection: a) Input Image b)
Green channel of Image c) Mask eye of image d) Blood vessel
after Gabor Filter e) Final Output Image.
557
© 2014 Biomedical Informatics
BIOINFORMATION
open access
different algorithms as discussed in methadology. Hemorrhage
is mainly caused due to clotting of blood these clotting of blood
in eye is identified as dark spots. In diseased eye there is huge
percentage of dark spots. So we have identified these dark
spots in Figure 3 as output image. The output image was
binary threshold to a particular value such that image contains
clear boundaries of the exudates. After getting the boundaries
we have two types of exudates present in it soft exudates and
hard exudates. Hard exudates have closed boundaries in the
threshold image while the soft exudates breaks in the contours
are connected by smoothing spines.
The complete flow chart of this study was given in to Figure 4
in which the overall steps from pre processing of image to
result and analyses have been shown. The total area occupied
and the area occupied in the fovea region is calculated
corresponding to the exudates, based on the number of pixels
and the severity level was determined as none, mild, moderate
and severe. Figures 1, 2, 3 show the results of DR severity of a
typical patient, based on the fundus image. Table 1 & 2 show
the pixel count of blood vessel and optic disc. Pixel density and
eye ratio are listed in Table 1 & 2 to know about the severity of
DR. From the above datasets and results we may observe that
the severity of disease on the basis of available image/data in
the case of blood vessel vary as per the pixel density of the
blood vessel. It confirms the hypothesis that increasing
thickness of blood with severity leads to increase in the blood
vessel density in the images. While in the case of optic disc the
severity seems to be dependent on the ratio of area covered by
optic disc on the eye image. More severity leads to lesser
coverage of brighter optic disc area because we know that with
severity the brightness of eye become lesser as compared to
mild or moderate in which case the optic disc is bright and that
are covered more than 2%. This study shows the feasibility of
the computational model of the analysis of DR.
Figure 2: Set of multimodal photographs of eye analysed for
optic disc detection a) Input Image b) Applying Adaptive
Histogram Equalization c) After Closing Morphological
Operation d) After Image Segmentation e) After removing
small regions f) Optic Disc Mapped.
Results & Discussion:
The results were obtained from fundus images which were
used for detection and diagnosis of DR. The individual
segmentation modules were developed using MATLAB, later
integrated with other computational approaches as mentioned
in methodology. We have to determine the thickness of the
blood vessels because diseased eye have more thick blood
vessels when compared to normal eye. In order to determine
the thickness of the blood vessels we had applied the edge
detection algorithms like sobel operator, Morphological edge
detector etc, through this we had calculated the thickness of the
diseased blood vessels and compared with normal eye image
data. In this way we have estimate the disease level and
severity of DR (Figure 1). Image enhancement process has been
applied on filtered image (Figure 1a) by using adaptive
threshold as shown in figure 1b. The output image is a brighter
and contains blood vessel and exudates that has to be removed.
It is done by applying closing morphological operation (erosion
and dilation) so that the blood vessel is removed from the
image. The erosion operation narrows and remove blood vessel
while the dilation operation restore the image without blood
vessel as shown in Figure 1c. The image as shown in figure 1d
consists of small bright spots that are mostly exudates or fats
etc. Such small bright spots (that covers less than 1% pixels of
image) are removed from the image by bwareaopen built-in
method in Matlab as shown in Figure 1e. After that we have
identified the size of the optical disc in eye because diseased
eye have expanded optical disc size compare with standard eye
data (Figure 2). In order to find boundaries and the border of
the optical disc in the eye image, we have implemented
ISSN 0973-2063 (online) 0973-8894 (print)
Bioinformation 10(9): 556-561 (2014)
Figure 3: Set of multimodal photographs of eye for the
detection of exudates a) Input Image b) Image enhancement c)
558
© 2014 Biomedical Informatics
BIOINFORMATION
open access
Image Segmentation d) Optic Disc segmentation e) Image
Subtraction f) Output image.
condition based on features value. A major advantage of this
algorithm is that the accuracy achieved for detection is very
high which implies greater accuracy of DR detection. Therefore,
computational modelling and analyses done here can serve as
foundation chunks for the advance research in DR and
eventually help in their better management.
Conflict of Interest:
The authors have declared no conflict of interest.
Acknowledgement:
Authors are thankful to Dept. of Information Technology and
Dept. of Biotechnology, NIT, Raipur, India for providing
facility, space and resources for this work.
References:
[1] Shaw JE et al. Diabetes Res Clin Pract. 2010 87: 4 [PMID:
19896746]
[2] Raman R et al. Ophthalmology. 2009 116: 311 [PMID:
19084275]
[3] Chobanian AV N Engl J Med. 2001 16: 534 [PMID:
11519509]
[4] Thomas RL et al. BMJ. 2012 22: e874 [PMID: 22362115]
[5] Jiménez S et al. Arch Soc Esp Oftalmol 2011 86: 277 [PMID:
21893260]
[6] Heng LZ et al. Diabet Med. 2013 30: 640 [PMID: 23205608]
[7] Rema M et al. Invest Ophthalmol Vis Sci. 2005 46: 2328
[PMID:15980218]
[8] Rema M & Pradeepa R, Indian J Med Res. 2007 125: 297
[PMID: 17496357]
[9] Choudhari KS et al. Microsc Microanal. 2013 19: 1061 [PMID:
23702082]
[10] Kirbas C & Quek FKH, Third IEEE Symposium on
Bioinformatics and Bioengineering Proceedings, 2003 vol. 1,
pp.238-245
[11] Lazar I & Hajdu A, Conf Proc IEEE Eng Med Biol Soc. 2012
1458-1461 [PMID: 23366176]
[12] Abràmoff MD et al. Invest Ophthalmol Vis Sci 2007 48: 1665
[PMID: 17389498]
[13] Ward NP et al. Ophthalmology. 1989 96: 80 [PMID: 2919052]
[14] Walter T et al. IEEE Trans Med Imaging. 2002 21:1236
[PMID: 12585705]
[15] Sánchez Gutiérrez CI et al. Arch Soc Esp Oftalmol. 2004 79:
623 [PMID: 15627932]
[16] Rahebi J et al. J Med Syst. 2014 38: 85 [PMID: 24957399]
[17] Sinthanayothin C et al. Br J Ophthalmol. 1999 83: 902 [PMID:
10413690]
[18] Yip HM et al. Scientific World Journal. 2014 60: 81 [PMID:
25133248]
[19] McGavin DD, Community Eye Health. 1999 12: 32 [PMID:
17491991]
Figure 4: A flow chart for the detection of DR on the basis of
computational approach.
Conclusion:
We implemented algorithms to extract features like blood
vessels, exudates, optic disc and to find level of severity of
these mentioned features in the input eye image. The algorithm
implemented is automated so that every image diagnosis is not
depends on human value for features. These generalized
algorithms are independent of camera used ophthalmologist
because the calculation doesn’t depend on the size of pixels or
dimension of image or format of image. Our techniques or
algorithms are combined with some learning methods (KNN
classification) for possibly even better results. We have mainly
focused on adaptability and accuracy in this work and may
implement these finding in new features extraction such as
macula, fats and color of fundus image. We automate these
features detection technique and increase the efficiency of the
proposed algorithms.
Automation is where there is a room for improvement because
the learning algorithm used are slower and much simpler
method by introducing more new methods such as Neural
networks, Support Vector Machine or Principal components
Analysis. Further speed of the system can be enhance by
introducing parallelism through CUDA, OpenCL libraries such
that it can take advantage of hardware with the massive level of
parallelism. Such a model/system can be of significant benefit
for mass diagnosis in rural areas especially in India where
patient to ophthalmologist ratio is high [19]. In this paper we
have identified and concentrated on some features such as
thickness of blood vessels, fovea region, and blood clotting
area. On the basis of these feature we have estimated the
condition of the DR patient and applied several images
processing algorithm for finding the best result. For automatic
classification we use KNN classifier that predict the severity
Edited by P Kangueane
Citation: Mishra et al. Bioinformation 10(9): 556-561 (2014)
License statement: This is an open-access article, which permits unrestricted use, distribution, and reproduction in any medium, for
non-commercial purposes, provided the original author and source are credited
ISSN 0973-2063 (online) 0973-8894 (print)
Bioinformation 10(9): 556-561 (2014)
559
© 2014 Biomedical Informatics
BIOINFORMATION
open access
Supplementary material:
Methodology:
Optic Disc Detection
It is mostly circular or elliptical in shape and its color is bright yellowish or white [8]. Its intensity range lie in red color range hence
it is good to do analysis on red channel. On the red channel of image median filter is applied for reduction of noise image is
smoothened. There is a built in method enclose in Matlab which is fast and better compared to other implementation, it takes disk
type structural element as parameter [9]. After that image undergoes segmentation process and so for automatic determining the
threshold value for the segmentation Otsu Algorithm [10] is used. Otsu shows that minimizing the intra-class variance is the same
as maximizing inter-class variance between a segmented foreground object and background:
b2 t 2 2 t 1 t 2 t 1 t 2 t
2
which is expressed in terms of class probabilities
histogram as
t
i
and class means.
i
The class probability
1 (t )
is computed from the
:
1 (t ) p(i)
t
0
While the class mean
1 (t )
is:
1 (t ) p(i) x(i) / 1
Where
x(i)
t
0
is the value at the centre of the
i th
histogram bin & compute
2 (t ) and 2 (t )
on the right-hand side of the
histogram for bins greater than . Finally a binary image consist of the desired optic disc image was obtained. Then this binary
image was used to map the optic disc back to original image [11]. In this case number of pixels occupied by the optic disc was
calculated and then the number of pixels in eye of the fundus image was also calculated. After that a ratio of optic disc by eye
pixels count was obtained and store in a text file as ‘data.txt’ which going to be used as training data for kNN classifier [12].
Table 1: Numerical values obtained from blood vessel analysis.
Pixel Count
373378
199213
180585
134585
379916
227490
483927
169689
220901
22382
41458
13952
93254
19033
176488
165971
132726
122399
122399
124730
217409
153911
231684
337484
Pixel Density of vessels
25.78689542
13.62358148
12.45912158
9.2105513
25.98302523
15.57941537
33.13858056
11.6101289
15.10684161
33.86952772
21.97428259
25.9779917
16.03216955
32.8251384
12.62021302
15.81185182
10.23572254
12.94393349
12.94393349
8.93953967
17.5617625
13.40142991
16.58566547
24.91129314
ISSN 0973-2063 (online) 0973-8894 (print)
Bioinformation 10(9): 556-561 (2014)
Severity of DR
severe
mild
mild
normal
moderate
mild
severe
normal
mild
severe
severe
Moderate
moderate
sever
normal
mild
normal
normal
normal
normal
normal
normal
moderate
moderate
560
© 2014 Biomedical Informatics
BIOINFORMATION
open access
Table 2: Numerical values obtained from eye ratio.
Pixel Count
27202
37801
22149
31649
12104
35973
11587
38290
44648
35288
30995
10228
35973
9233
56821
123600
18621
160416
0
35869
0
0
82100
28156
37493
0
42831
17765
OD/Eye Ratio
2.67884137
2.79027092
1.58559031
2.75576051
0.86750732
3.4271032
0.82948372
3.1955761
4.72161327
2.72138222
2.22071285
0.74789481
3.4271032
0.72907454
4.10149765
8.83832515
1.51176385
2.29313835
0
2.45297367
0
0
5.61494217
1.92823429
2.56470769
0
2.93049892
1.21652002
ISSN 0973-2063 (online) 0973-8894 (print)
Bioinformation 10(9): 556-561 (2014)
Severity of DR
normal
mild
moderate
normal
moderate
mild
severe
normal
normal
mild
mild
Severe
mild
moderate
normal
normal
moderate
moderate
severe
mild
normal
mild
severe
normal
normal
moderate
normal
severe
561
© 2014 Biomedical Informatics