retinal vessel segmentation employing neural network · pdf fileretinal vessel segmentation...
TRANSCRIPT
INTERNATIONAL JOURNAL OF TECHNOLOGY AND COMPUTING (IJTC)
ISSN-2455-099X,
Volume 2, Issue 9 September 2016
IJTC201609007 www. ijtc.org 467
Retinal Vessel Segmentation employing Neural
Network and Feature ExtractionNavpreet Kaur
Department of Computer Science and Engineering
Shaheed Udham Singh College of Engineering and Technology, Mohali, India.
Abstract: Diabetic retinopathy, Glaucoma, Hypertension are the most common sight threatening eye diseases due to the changes in
the blood vessel structure. The retinal blood vessel segmentation helps to identify the successive stages of a these diseases and thus
helps to treat them at early stages. Blood vessel segmentation by making use of multilayer perceptron neural network is one such
technique used for the segmentation of retinal blood vessels. As it provides the ability to identify and classify the image pixels as
vessels or non vessels automatically, but it fails to achieve high accuracies. It is unable to segment the vessels of varying width and
small size. Thus this research work provides the blood vessel segmentation with neural network, which gives more efficient results
on fundus images.
Keywords: Retinal blood vessel segmentation, Diabetic Retinopathy, Neural Network, Fundus Images.
I. INTRODUCTION
Diabetic Retinopathy, Glaucoma, Hypertension are the most
common sight threatening eye diseases. Diabetic
retinopathy (DR) is a result of long-term diabetes [1]. Major
vision loss due to DR is highly preventable with proper
screening and timely diagnosis at the earlier stages. The
various features of retinal vessels such as length, width,
length and branching pattern provide new techniques to
diagnose various diseases like diabetes, glaucoma, hyper-
tension, cardiovascular disease and stroke. Retinal images
provide valuable information related to human eye, by
which the vascular condition can be
accurately observed and analyzed. The only part of the
central circulation that can be viewed directly and analyzed
is the retinal vessel. Changes in blood vessel structure and
vessel distribution, caused by diabetic retinopathy can lead
to new vessel growth, which in turn instigates vision
impairment.
In human retina, one of the most important organs is the
optic nerve which acts as the convergent point of the blood
vessel net-work. The central retinal artery and central retinal
vein flow out through the optic nerve that supplies blood to
the upper layers of the retina. Besides, the optic nerve acts
as a channel to convey the information from the eye to the
brain. In early stages, most of the retinal pathologies affects
locally and does not distress the entire retina. But retinal
pathology on or near the optic nerve may severely affect the
vision even at the early stages because optic nerve is the
most essential part for vision. A few observations found in
several important retinopathies are attenuation changes,
focal narrowing and occlusion of retinal arteries. The
diameter and shape of a retinal vessel plays a key role as
indicators in ophthalmologic studies. These changes give
valuable information to identify the successive stages of
diseases and their response to various therapies. The optic
nerve can be observed in a close view of the retinal fundus,
where the optic disc is the portion of the nerve that is visible
or perceivable by the eye. Fundus imaging is one of the
popular clinical procedures available to record this close
view observations of the retina. This fundus imaging
procedure is also used for the diagnosis and evaluation of
the healthy and non-healthy retinas of human eye. In a
healthy retina the optic nerve has a standard identifiable
size, shape, color and location relative to the blood vessels.
Nevertheless, in a retina containing lesions, any one or more
of these properties may be deviated from its standard level
and show a large variance. At various stages of the disease,
the vascular network in retina is very much affected and
hence various morphological changes occurring retinal
vessels.
We can substantially observe enough geometrical changes
in diameter, branching angle, length in the retinal blood
vessels due to diseases. The segmentation and measurement
of retinal blood vessels can be used to grade the severity of
certain diseases. The sign of risk level for diabetic
retinopathy is the variation in width of retinal vessels within
the fundus. One of the most important tools for the
prediction of proliferate diabetic retinopathy is the abnormal
variation in diameter along the vein. Moreover, the various
retinal micro vascular abnormalities predicted are seen to be
the early symptoms for the risk of stroke. In all these cases,
the desired focus is on the variation in diameter of the
vessel and not in the exact diameter of the vessel. An
alternative application of retinal vessel segmentation is
biometric identification using distinctive retinal vascular
network for each individual. The rest of the paper is
structured as: In Section 2 Related Work is described. In
section 3 Methodology of Proposed work is defined. In
Section 4 we give Comparative study between existing and
proposed approach and finally in Section 5 we give
Conclusion to paper.
II. RELATED WORK
Blood vessel segmentation in retinal images is attained by
classifying image pixels as vessel or non vessel based on
the local image features. In general there are two basic
approaches for blood vessel segmentation in retinal images.
The algorithms used for the segmentation of blood vessels
are broadly classified as pixel processing based methods
and vessel tracking methods.
Pixel processing-based methods normally consist of two
phases. In the first phase, an enhancement procedure is
implied and it selects an initial set of pixels, which is further
ensured as vessels in the second phase [9]. The retinal
vessel segmentation method presented in Ref. [2] consists
IJTC.O
RG
INTERNATIONAL JOURNAL OF TECHNOLOGY AND COMPUTING (IJTC)
ISSN-2455-099X,
Volume 2, Issue 9 September 2016
IJTC201609007 www. ijtc.org 468
of three processing phases. In the first phase, background
normalization of monochromatic input image is performed
and later thin vessel enhancement procedures are used. In
the second phase, the vessel centerline candidate points are
selected and subsequently these points are connected and
based on vessel length, the validation of centerline segment
candidates is achieved. In the third phase, vessels with
different widths are enhanced and processed using binary
morphological reconstruction technique and vessel filling is
achieved using region growing process. Soares et al. have
proposed an algorithm, where retinal blood vessels are
detected using Gabor wavelets by representing each pixel
by a feature vector and then by using Bayesian classifier
with Gaussian mixtures, each pixel is classified as either a
vessel or non vessel pixel and thus segmentation is
achieved. The concept of matched filter detection was
proposed by Chaudhuri et al. [10], where twelve rotated
versions of 2-D Gaussian shaped templates are used to
search vessel segments along all possible directions. The
resultant image produced is the binary representation of the
retinal vasculature. Likewise, segmentation of retinal
vessels are also obtained by matched filtering approaches
using global [11] orlocal thresholding strategies [12]. Also
for the purpose of vessel borders extraction, differential
filters based on either first-or-second order derivatives are
used. A two stage region growing procedure was proposed
by Martinez-Perez et al. where features derived from image
derivatives are used in the segmentation of retinal vessels
[13,14]. As stated in Ref. [15], the edge detection, matched
filtering and region growing procedures can also be
collectively used for the automated detection of retinal
blood vessels. Jiang et al. have proposed a technique of
adaptive local thresholding based on the use of verification-
based multithreshold scheme combined with classification
procedures in Ref. [16], used for the detection of vessels in
retinal images. A technique used for the segmentation of
vessel like patterns in retinal images that combines
morphological filters and cross-curvature evaluation was
proposed by Zana et al.in Ref. [17]. In this approach, vessel
segments alone are considered as image feature and hence
using morphological filters simplifies the computation of
cross-curvature. An algorithm for retinal vessel
segmentation based on the classification of pixels using
simple feature vector was proposed by Niemeijer et al. in
Ref. [18]. A new method of segmentation of blood vessels
in retinal images was pro-posed by Staal et al. in Ref. [19].
This supervised method is called primitive-based method
and this algorithm is based on the extraction of image ridges
used to compose primitives that describe the linear
segments called line elements. The pixels those are assigned
to the closest line element partitions the image in the form
of image patches and are classified using a set of features
from the corresponding line and image patch. In addition, a
technique based on neural network is used to identify the
retinal blood vessels, where the inputs are obtained using
principal component analysis and then edge detection
technique is used.
The classifiers are trained by learning from manually
labeled images. The classifiers are the Bayesian classifier
[17], KNN method [18], support vector machines [19] and
neural networks [20]. This paper provides an approach
based on the supervised method of segmentation using
neural network.
III. PROPOSED METHOD
This research work proposes a retinal vessel segmentation
technique using Artificial Neural Networks (ANN). Retinal
vessels are identified by using a multilayer perceptron
neural network, for which the inputs are derived from
Gabor and moment invariants based features.
The technique used in this method is tested and evaluated
by making use of the retinal color images available on
DRIVE database. This database has been widely used as
ground truth for performance evaluation by other
researchers to test their vessel segmentation methodologies.
The retinal images available in this database were captured
using a Canon CR5 nonmydriatic3CCD camera with a
45◦Field-of-View (FOV), in digital form. The DRIVE
database consists of forty eye fundus color images which
are divided into training and test set, each set containing
twenty images. The color images of the retina available in
the database are of size768 × 584 pixels.
A. PREPROCESSING
The first step is the preprocessing of image for further
processing. The RGB features of the image are extracted in
this stage as shown in Figure 1. The true color RGB is
converted to the grayscale intensity image to evaluate its
adequate ability for the segmentation of the retinal blood
vessels. The conversion is done by eliminating the hue and
saturation information, while retaining the luminance.
In the next step, the retinal image is further processed and
smoothened using Gaussian filter and mean filter as shown
in figure 2. After that it is converted into grayscale image
for further processing.
Then the Gabor features are extracted at different
orientations as shown in figure 3. Gabor filtering is done
and as per the Gabor coefficient attained, the original image
is convolved. Next, the moment invariant features are
extracted as shown in figure 4. Now the samples are taken
from the vessel and non vessel regions and they are trained
using neural network.
B. NEURAL NETWORK TRAINING
Each pixel in the retinal image is classified as a vessel or a
non vessel pixel, using neural network. The computational
model of neural network has similarities with the human
visual system. In order to classify each pixel of the retinal
image as vessel or not, a multilayer perceptron neural
network is used. It can be described as a black box having
multiple inputs and multiple outputs which operates using a
large number of mostly parallel connected simple arithmetic
units.
The back propagation algorithm is used in layered feed-
forward ANNs. The network receives inputs by neurons in
the input layer, and the output of the network is given by the
neurons on an output layer. There may be one or more
intermediate hidden layers. The back propagation algorithm
uses supervised learning, which means that we provide the
algorithm with examples of the inputs and outputs we want
the network to compute, and then the error (difference
between actual and expected results) is calculated. The idea
IJTC.O
RG
INTERNATIONAL JOURNAL OF TECHNOLOGY AND COMPUTING (IJTC)
ISSN-2455-099X,
Volume 2, Issue 9 September 2016
IJTC201609007 www. ijtc.org 469
of the back propagation algorithm is to reduce this error,
until the ANN learns the training data. The training begins
with random.
FIGURE 1. RGB COMPONENTS OF A TRUE COLOR RETINAL IMAGE.
FIGURE 2. GRAY SCALE IMAGE OBTAINED AFTER APPLYING GAUSSIAN AND MEAN FILTER.
FIGURE 3. EXTRACTION OF GABOR FEATURES
FIGURE 4. EXTRACTION OF MOMENT INVARIANT BASED
FEATURES.
Weights , and the goal is to adjust them so that the error will
be minimal.
A. ALGORITHM
Neural network using back propagation algorithm is
applied, using 5/6th of the data for training and 1/6th of the
data for validation. The training algorithm used in the back
propagation network is as follows:
Step 1 – Read the input image.
Step 2 – Separate the RGB components in R, G, and B
different planes.
Step 3 – Morphological opening operation is performed to
fill the vessel discontinuities.
Step 4 – Preprocessing steps like mean filtering and
Gaussian filtering are performed.
Step 5 – RGB features are extracted for the preprocessed
image and its mean is calculated.
IJTC.O
RG
INTERNATIONAL JOURNAL OF TECHNOLOGY AND COMPUTING (IJTC)
ISSN-2455-099X,
Volume 2, Issue 9 September 2016
IJTC201609007 www. ijtc.org 470
Step 6 – Gray scale image is obtained for further
processing.
Step 7 – Gabor features are extracted at different
orientations.
Step 8 – Moment invariants-based features are extracted.
Step 9 – Samples are taken from vessel and non vessel
regions and they are trained using neural networks.
Step10 – Segmentation of blood vessels is obtained as
output.
For each training pair, the neural network performs the
following tasks. At the first stage, during the initialization
of weights, a few small random variables are assigned. In
the next stage, i.e. feed forward stage, each input unit (Xi)
receives an input signal and transmits this signal to all the
units in the layer above i.e. hidden units, Each
hidden unit calculates the activation function,
( ) ∑
(1)
is the bias on hidden unit j. Each hidden unit sends this
signal to all output units. Each output unit then sums its weighted input signals and applies
its activation function to calculate the output signals.
∑ (2)
is the bias on output unit k.
During back propagation of errors, each output unit
compares its calculated activation with its target value , to
find out the related errors for that pattern. Error information
term is given as,
(3)
It is used to distribute the error at the output unit back to
all units in the previous layer. Then each hidden unit
( ) sums its delta inputs from units in the
above layer as:
∑ (4)
Similarly the error information term is
computed for each hidden unit. During the final stage, the
weights and biases are updated using the factor and the
activation function is updated, using as the learning rate.
Each output unit updates its weights and biases by using
theweight correction term and bias correction
term ,
Where,
Therefore,
(5)
Similarly the weights and biases are updated for each
hidden unit. Finally, the stopping condition is tested. The
stopping condition may be minimization of the errors,
number of epochs etc.
FIGURE 5. SEGMENTED IMAGE.
IV. RESULT ANALYSIS
The automatic vessel segmentation approach used in this
paper was tested on images from DRIVE database. This
technique has been proved as one of the most valuable tools
for the segmentation of blood vessels in retinal images.
The proposed algorithm is tested for various images having
the size 768 × 584 pixels are used for experimentation. The
results of different matrices of performance that is accuracy,
sensitivity and specificity on these images are used to verify
the performance of proposed algorithm.
A. PERFORMANCE EVALUATION
The accuracy was estimated by determining the true
positive fraction, which is the ratio of the number of true
positives to the total number of vessel pixels in the ground
truth segmentations. The ratio of the number of false
positives to the total number of non vessel pixels in the
ground truth segmentations determines the false positive
fraction. A pair formed by a true positive fraction and a
false positive fraction is plotted on the graph, which
produces a curve as shown in Fig In our experiments, these
fractions are calculated over all test images, considering
only pixels inside the field of view. The manual
segmentation result provided along with each database
image seems to be the best standard for evaluating the
performance measures. To exhibit the performance by
employing Gabor features and moment invariants-based
features using neural networks, we present the results
obtained by our method and compared them with the results
obtained by other existing methods, involving matched
filters and adaptive local thresholding techniques. The
Gabor feature extraction at different orientations used in
this method increases the accuracy of the segmentation of
vessels with different diameters. This method proves itself
to be efficient in enhancing the vessel contrast, thereby
filtering the noise. We have used a straight forward
MATLAB implementation for testing the images from
DRIVE database and we have obtained the best per-formed
vessel segmentation results.
IJTC.O
RG
INTERNATIONAL JOURNAL OF TECHNOLOGY AND COMPUTING (IJTC)
ISSN-2455-099X,
Volume 2, Issue 9 September 2016
IJTC201609007 www. ijtc.org 471
FIGURE 6. ROC CURVE FOR THE CLASSIFICATION ON THE
DRIVE DATABASE USING FEATURE EXTRACTION
V. CONCLUSION
This thesis has overviewed the method for retinal Image
segmentation using neural network. It automatically tracks
and segments the vessels in fundus images. One of the
highlights of this proposed technique is its adaptability to
particular image intensity properties. It assigns a precise
classification result as vessel or non-vessel to each pixel,
compared to other vessel segmentation algorithms. This
retinal vessel segmentation technique gives knowledge
about the location of vessels which paves a way for the
screening of diabetic retinopathy. One of the practical
applications of this method is to apply the results of this
segmentation algorithm for providing better performance
analysis in computer-aided diagnosis system for retinal
images. This allows us to analyze large number of images
and to characterize many more properties of the retinal
vasculature. The demonstrated effectiveness, together with
its simplicity, makes this automated blood vessel
segmentation method a suitable tool for the complete
prescreening system for early diabetic retinopathy detection.
While assessing the obtained segmentation results, a few
limitations like partial missing of very thin vessel branches
are noticed. These can be obviously noticed only in very
few image as a consequence of the variability of intensity
and contrast among vessels and the other regions. It can be
compensated by using vessel enhancement procedure. Such
misdetections can be minimized by using more flexible
classification process for every image point and thereby, the
overall performance of this method can be improved
REFERENCES
[1] M. Garcia, C.I. Sanchez, M.I. Lopez, D. Abasolo, R.
Hornero, Neural network based detection of hard
exudates in retinal images, Computer Methods
Programs Biomed. 93 (2009) 9–19.
[2] A.M. Mendonc¸ a, Aurélio Campilho, Segmentation of
retinal blood vessels by combining the detection of
centerlines and morphological reconstruction, IEEE
Med. Imaging 25 (9) (2006) 1200–1213.
[3] A.J. Frame, P.E. Undrill, M.J. Cree, J.A. Olson, K.C.
McHardy, P.F. Sharp, J.V. Forrester, A comparison of
computer based classification methods applied to the
detection of microaneurysms in ophthalmic fluorescein
angiograms, Computer Biol. Med. 28 (3) (1998) 225–
238.
[4] M. Larsen, J. Godt, N. Larsen, H. Lund-Andersen, A.K.
Sjølie, E. Agardh, H.Kalm, M. Grunkin, D.R. Owens,
Automated detection of fundus photographic red
lesions in diabetic retinopathy, Invest. Ophthalmic. Vis.
Sci. 44 (2) (2003)761–766.
[5] C. Oyster, The Human Eye: Structure and Function,
Sinauer Associates, Sunder-land, MA, 1999.
[6] A. Hoover, M. Goldbaum, Locating the optic nerve in a
retinal image using the fuzzy convergence of the blood
vessels, IEEE Trans. Med. Imaging 22 (8) (2003)951–
958.
[7] C. Sinthanayothin, J.F. Boyce, H.L. Cook, T.H.
Williamson, Automated localization of the optic disc,
fovea, and retinal blood vessels from digital color
fundus images, Br. J. Ophthalmol. 83 (8) (1999) 902–
910.
[8] C. Sinthanayothin, J.F. Boyce, T.H. Williamson, H.L.
Cook, E. Mensah, S. Lal, D.Usher, Automated
detection of diabetic retinopathy on digital fundus
images, Diabet. Med. 19 (2) (2002) 105–112.
[9] K.A. Vermeer, F.M. Vos, H.G. Lemij, A.M. Vossepoel,
model based method for retinal blood vessel detection,
Comput. Biol. Med. 34 (2004) 209–219.
[10] S. Chaudhuri, S. Chateterjee, N. Katz, M. Nelson, M.
Goldbaum, Detection of blood vessels in retinal images
using two-dimensional matched filters, IEEETrans.
Med. Imaging 8 (3) (1989) 263–269.
[11] T. Chanwimaluang, G. Fan, An efficient algorithm for
extraction of anatomicalstructures in retinal images, in:
Proc. ICIP, 2003, pp. 1193–1196.
[12] A. Hoover, V. Kouznetsova, M. Goldbaum, Locating
blood vessels in retinal images by piecewise threshold
probing of a matched filter response, IEEE Trans. Med.
Imaging 19 (3) (2000) 203–211.
[13] M.E. Martinez-Perez, A.D. Hughes, A.V. Stanton, S.A.
Thom, A.A. Bharath, K.H.Parker, Segmentation of
retinal blood vessels based on the second directional
derivative and region growing, in: Proc. ICIP, 1999, pp.
173–176.
[14] M.E. Martinez-Perez, A.D. Hughes, A.V. Stanton, S.A.
Thom, A.A. Bharath, K.H.Parker, Scale-space analysis
for the characterization of retinal blood vessels, in
Medical Image Computing and Computer- Assisted
Intervention—MICCAI’99,C. Taylor and A.
Colchester, (Eds.), Springer: New York, Lect. Notes
Comput. Sci.16794 (1999) 90–97.
[15] Y. Wang, S.C. Lee, A fast method for automated
detection of blood vessels in retinal images, in: IEEE
Comput. Soc. Proc. Asilomar Conf., 1998, pp.1700–
1704.
IJTC.O
RG
INTERNATIONAL JOURNAL OF TECHNOLOGY AND COMPUTING (IJTC)
ISSN-2455-099X,
Volume 2, Issue 9 September 2016
IJTC201609007 www. ijtc.org 472
[16] X. Jiang, D. Mojon, Adaptive local thresholding by
verification based multi-threshold probing with
application to vessel detection in retinal images,
IEEETrans. Pattern Anal. Mach. Intell. 254 (1) (2003)
131–137.
[17] F. Zana, J.-C. Klein, Segmentation of vessel-like
patterns using mathematical morphology and curvature
evaluation, IEEE Trans. Med. Imaging 11 (7)
(2001)1111–1119.
[18] M. Niemeijer, J. Staal, B. van Ginneken, M. Loog,
M.D. Abràmoff, Comparative study of retinal vessel
segmentation methods on a new publicly available
database, in: M. Fitzpatrick, M. Sonka (Eds.), Proc
SPIE Med. Image., vol. 5370,2004, pp. 648–656.
[19] J. Staal, M.D. Abramoff, M. Niemeijer, M.A.
Viergever, B. van Ginneken, Ridge-based vessel
segmentation in color images of the retina, IEEE Trans.
Med. Imaging 23 (4) (2004) 501–509.
[20] L. Zhou, M.S. Rzeszotarski, L.J. Singerman, J.M.
Chokreff, The detection and quantification of
retinopathy using digital angiograms, IEEE Trans.
Med. Imaging 13(4) (1994) 619–626.
[21] Y. Tolias, S.M. Panas, A fuzzy vessel tracking
algorithm for retinal images based on fuzzy clustering,
IEEE Trans. Med. Imaging 17 (2) (1998) 263–273.
[22] A. Can, H. Shen, J.N. Turner, H.L. Tanenbaum, B.
Roysam, Rapid automated tracing and feature
extraction from retinal fundus images using direct
exploratory algorithms, IEEE Trans. Inf. Technol.
Biomed. 3 (2) (1999) 125–138.
[23] O. Chutatape, L. Zheng, S.M. Krishnan, Retinal blood
vessel detection and tracking by matched Gaussian and
Kalman filters, in: Proc. 20th Annu. Int. Conf.
IEEEEng. Med. Biol., 1998, pp. 3144–3149.
[24] V.S. Lee, R.M. Kingsley, E.T. Lee, et al., The
diagnosis of diabetic retinopathy. Ophthalmoscopy
versus fundus photography, Ophthalmology 100
(1993)1504–1512.
[25] Research Section, Digital Retinal Image for Vessel
Extraction (DRIVE) Database, Univ. Med. Center
Utrecht, Image Sci. Inst., Utrecht, The Netherlands,
2014.
[26] R.C. Gonzalez, R.E. Woods, Digital Image Processing,
229–237, Addison-Wesley, Reading, 1993, pp. 583–
586.
[27] D.L. Toulson, J.F. Boyce, Segmentation of MR images
using neural nets, in: Proc.Br. Mach. Vision Conf.,
1991, pp. 284–292.
[28] D.L. Toulson, J.F. Boyce, Segmentation of MR images
using neural nets(expanded version), Image Vis.
Comput. 10 (1992) 324–328.
[29] S.C. Lo, M.T. Freedman, J.S. Lin, et al., Automatic
lung nodule detection using profile matching and back-
propagation neural network techniques, J. Digit.
Imaging 6 (1993) 48–54.
[30] M.L. Astion, P. Wilding, The application of back
propagation neural networks to problems in pathology
and laboratory medicine, Arch. Pathol. Lab. Med.
116(1992) 995–1001.
IJTC.O
RG