Efficient Brain Tumor Detection Using Wavelet Transform

Ku. Mayuri R. Khode et al. Int. Journal of Engineering Research and Application www.ijera.com
ISSN : 2248-9622, Vol. 7, Issue 1, ( Part -4) January 2017, pp.55-60
www.ijera.com 55 | P a g e
Efficient Brain Tumor Detection Using Wavelet Transform
Ku. Mayuri R. Khode*, Prof. S. R. Salwe**, Prof. A.P. Bagade***,
Dr. R. D. Raut****
*(M.Tech.VLSI student, B.D.C.E, Sewagram.)
**(EXTC Department, B.D.C.E, Sewagram.)
***(EXTC Department, B.D.C.E, Sewagram.)
****(Electronics Deapartment, B.D.C.E., Sewagram.)
ABSTRACT
Brain tumor detection is a challenging task and its very important to analyze the structure of the tumor correctly
so a automatic method is used now a days for the detection of the tumor. This method saves time as well as it
reduces the error which occurs in the method of manual detection. In this paper the tumor is detected using
wavelet transform. MRI is an important tool used in many fields of medicine and is capable of generating a
detailed image of any part of the human body. The tumor is segmented from the MRI images, features are
extracted and then the area of the tumor is determined. PNN can successfully handle the process of brain tumor
classification.
Keywords: Brain tumor, detection, MRI, segment, wavelet.
I. INTRODUCTION
The buildup of extra cells often forms a
mass of tissue called a growth or tumor. Brain tumor
is one of the major causes of death among people.
The symptoms of a brain tumor depend on tumor
size, type and location. Symptoms may be caused
when a tumor presses on a nerve or harms a part of a
brain. Also they may be caused when a tumor blocks
the fluid that flows through and around the or when
the brain swells because build up of fluid.
Headaches, nausea and vomiting, Changes in speech,
vision or hearing, problem balancing or walking,
changes in mood, personality or ability to
concentrate, problems with memory, muscle jerking
or itching, numbness or tingling in the arms or legs.
Accurate detection of the type of brain
abnormality is highly essential for treatment
planning which can minimize the fatal results.
Manual detection of brain tumor is a tedious job and
takes a lot of time and not accurate, varies from one
doctor to another. Accurate results can be obtained
only through computer aided automated systems.
Besides being accurate, these techniques must
coverage quickly in order to apply them for real time
applications. Brain tumor can be diagnosed by using
magnetic resonance imaging (MRI), ultrasonic, CT
images and X-rays. Magnetic Resonance Imaging is
an important tool used in many fields of medicine
and is capable of generating a detailed image of any
part of the human body.
MRI stands for Magnetic Resonance
Imaging. A MRI scanner uses powerful magnets to
polarise and excite hydrogen nuclei (single proton)
in human tissue, which produces a signal that can be
detected and it is encoded spatially, resulting in
images of the body. The MRI machine emits radio
frequency (RF) pulse that specifically binds only to
hydrogen. The system sends the pulse to that specific
area of the body that needs to be examined. Due to
the RF pulse, protons in that area absorb the energy
needed to make them spin in a different direction.
This is meant by the resonance of MRI. The RF
pulse makes the protons spin at the larmour
frequency, in a specific direction. This frequency is
found based on the particular tissue being imaged
and the strength of the main magnetic field.
Classification of the brain tumor is also a
important task for treatment planning. There are two
types of tumor which are- benign (non-cancerous)
and malignant (cancerous) tumors. Conventional
methods involve invasive techniques such as biopsy,
lumbar puncture and signal tap method, to detect and
classify brain tumor into benign and malignant
which are very painful and time consuming.
Wavelet analysis is an effective
methodology capable of revealing aspects of data
which other signal analysis techniques. Analyzing
the images at multiple levels, the method is able to
extract finer details from them and in turn improves
the quality of the image. In addition, wavelet
analysis is capable of compressing or de-noising a
signal without appreciable degradation. Wavelet
analysis is of at most importance in case of delicate
information, such as in case of medical imaging.
RESEARCH ARTICLE OPEN ACCESS

II. IMPLIMENTED WORK
2.1 MR image to gray scale image:
MRI images are magnetic resonance images
which can be acquired on computer when a patient is
scanned by MRI machine. We can acquire MRI
images of the part of the body which is under test or
desired. Generally when we see MRI images on
computer they looks like black and white images. In
analog practice, gray scale imaging is sometimes
called "black and white," but technically this is a
misnomer. In true black and white, also known as
halftone, the only possible shades are pure black and
pure white. The illusion of gray shading in a halftone
image is obtained by rendering the image as a grid of
black dots on a white background (or vice versa),
with the sizes of the individual dots determining the
apparent lightness of the gray in their vicinity. The
lightness of the gray is directly proportional to the
number representing the brightness levels of the
primary colors. Black is represented by R = G = B =
0 or R = G = B = 00000000, and white is represented
by R = G = B = 255 or R = G = B = 11111111.
Grayscale is a range of shades of gray
without apparent color. The darkest possible shade is
black, which is the total absence of transmitted or
reflected light. The lightest possible shade is white,
the total transmission or reflection of light at all
visible wavelengths. So because of the above
reasons first we convert our MRI image to be pre-
processed in grayscale image.
2.2 Image segmentation:
In image segmentation the level to which
the subdivision of an image into its constituent
regions or objects is carried depends on the problem
being solved. In other words, when the object of
focus is separated, image segmentation should stop
the main goal of segmentation is to divide an image
into parts having strong correlation with areas of
interest in the image. In medical imaging for
analyzing anatomical structures such as bones,
muscles blood vessels, tissue types, pathological
regions such as cancer, multiple sclerosis lesions and
for dividing an entire image into sub regions such as
the white matter (WM), gray matter (GM) and
cerebrospinal fluid (CSF) spaces of the brain
automated delineation of different image
components are used. In the field of medical image
processing segmentation of MR brain image is
significant as MRI is particularly suitable for brain
studies because of its excellent contrast of soft
issues, non invasive characteristic and a high spatial
resolution Segmentation is the process of splitting an
observed image into its homogeneous or constituent
regions. The goal of segmentation is to simplify or
change the representation of an image into
something that is more meaningful and easier to
analyze. It is important in many computer vision and
image processing application.
Fuzzy C-means clustering is the
overlapping clustering technique. One pixel value
depending upon the two or more clusters centers. It
is also known as soft clustering method. Most widely
used the fuzzy clustering algorithms is the Fuzzy C-
means (FCM) algorithm. The FCM algorithm is the
partition of the n element X={x1,...,xn} into a
collection of the c fuzzy clustering with respect to
the below given criteria. It is based on the
minimization of the following objective function:
(1)
Where, m = level of the fuzziness and real number
greater than 1.
uij= degree of the membership of xi in the cluster cj
x = data value
Fuzzy C-means is the popular method for
medical image segmentation but only consider the
image intensity thereby producing unsatisfactory
results in noisy images. A bunch of the algorithms
are proposed to make the FCM robust against noise
and in homogeneity but it’s still not perfect. fuzzy c-
mean is slower than the K-means in efficiency but
gives the accurate prediction of tumor cells which
are not predicted by the K-means algorithm.
Original image Skull stripped image
White matter Gray matter
CSF matter Segmented image

Fig: Extended Histogram and Edge map
2.3 Create database:
A database is an organized collection of
data and here it’s a collection of images. The
database is created using a number of images that are
selected and divided into two groups that are
healthy and disease image.
2.4 Feature extraction:
Texture analysis makes differentiation of
normal and abnormal tissue easy. It even provides
contrast between malignant and normal tissue, which
may be below the threshold of human perception.
Texture analysis using computer aided diagnosis can
be used to replace biopsy techniques and plays an
important role in early diagnosis and tracking of
diseases.
The wavelet is a powerful mathematical
tool for feature extraction, and has been used to
extract the wavelet coefficients from MR images.
Discrete Wavelet Transform is an implementation of
the WT using the dyadic scales and positions.
Two dimensional DWT results in four sub
bands LL (low-low), LH (low-high), HL (high-low),
HH (high-high) at each scale. Sub band LL, is the
approximation component of the image, which is
used for next two dimensional DWT. Whereas, LH,
HL, HH are the detailed components of the image
along the horizontal, vertical and diagonal axis,
respectively, as shown in the figure:
Lo_D: low pass filter
Hi_D: high pass filter
- Down sampling columns: keeps
the even indexed columns.
- Down sampling rows: keeps the
even indexed rows.
2.4 Classification:
Classification is done using probabilistic
neural network. Probabilistic Neural Network (PNN)
is a Radial Basis Neural Network, which provides a
general solution to pattern classification problems by
following an approach developed in statistics, called
Bayesian classifiers.
Probabilistic Neural Network has three
layers, as shown in fig., the Input layer, Radial Basis
Layer and the Competitive Layer. Radial Basis
Layer evaluates vector distances between input
vector and row weight vectors in weight matrix.
These distances are scaled by Radial Basis Function
nonlinearly. Then the Competitive Layer finds the
shortest distance among them, and thus finds the
training pattern closest to the input pattern based on
their distance.

Fig: Architecture of a probabilistic neural network
A PNN is predominantly a classifier since it
can map any input pattern to a number of
classifications. The main advantages that
discriminate PNN are, its fast training process, an
inherently parallel structure, guaranteed to converge
to an optimal classifier as the size of the
representative training set increases and training
samples can be added or removed without extensive
retraining.
Table: Comparison of four different methods based on time required for the image processing:
Images Neural
network
Algorithm
SVM Linear
(Time in sec)
SVM Radial
Basis (Time
in sec)
SVM
Quadratic
(Time in sec)
Tumor %
1. 0.0573s 1.4350s 1.6368s 0.4680s 0.8001%
2. 0.0035s 0.1483s 0.5657s 0.5095s 2.032%
3. 0.0050s 0.1528s 0.5787s 0.5339s 1.1444%
4. 0.1178s 0.1528s 1.5465s 0.5393s 1.6780%
5. 0.0867s 1.1615s 1.0087s 0.4699s 0.8713%
6. 0.0374s 0.1424s 0.4937s 0.4622s 1.5935%
7. 0.0039s 0.1545s 0.5315s 0.4689s 1.3418%
8. 0.0040s 0.1439s 0.5119s 0.5073s 1.8031%
9. 0.0036s 0.1456s 0.4946s 0.4599s 1.5274%
10. 0.0040s 0.1444s 0.4965s 0.4665s 2.0335%
11. 0.0035s 0.1438s 0.5232s 0.4738s 1.5340%
12. 0.0035s 0.1487s 0.5099s 0.4625s 2.4760%
13. 0.0035s 0.1476s 0.6110s 0.5326s 1.5869%
14. 0.0047s 0.1471s 0.5136s 0.4611s 2.2949%
15. 0.0037s 0.1562s 0.5153s 0.4796s 1.5406%
16. 0.0036s 0.1416s 0.5275s 0.4639s 2.1851%
17. 0.0035s 0.1445s 0.5248s 0.4561s 0.2218%
18. 0.0044s 0.1423s 0.4995s 0.4730s 1.7431%
19. 0.0038s 0.1672s 0.4922s 0.4752s 1.5630%
20. 0.0037s 0.1438s 0.5139s 0.4666s 1.6469%
21. 0.0036s 0.1448s 0.5164s 0.4746s 0.6470%
22. 0.0035s 0.1425s 0.4978s 0.4629s 1.6713%
23. 0.0048s 0.1442s 0.5077s 0.4729s 1.3667%
24. 0.0035s 0.1587s 0.5056s 0.4892s 1.6795%
25. 0.0036s 0.1444s 0.5189s 0.4584s 0.1221%

Graph:
Fig: Time taken by four methods
Fig: Cummulative time comparison of the four
methods
Fig: Comparison of efficiency of PNN with the
other three methods
III. FUTURE SCOPE
The goal is to detect, to segment, and to
identify most types of pathological tissue that occur
within pediatric brain tumors. Future research in the
segmentation of medical images will lead towards
improving the accuracy, exactness, and
computational speed of segmentation approaches, as
well as minimizing the amount of time taken for the
process.
IV. CONCLUSION
In this project fuzzy c-mean clustering
algorithm is used for segmentation methods,
classification of brain tumor and its feature
extraction is done using probabilistic neural network
algorithm. Many algorithms have been proposed in
the literature for each processing stage. So this
method used gives the better result. The results are
given and the graph showing the comparison in
terms of time given by various methods that is neural
network, SVM linear, SVM radial basis, SVM
quadratic is given.
REFERENCES
[1]. Ahmed Kharrat, Nacéra Benamrane, Abid
Mariem “Detection of Brain Tumor
Medical Images” International Conference
on Signals, Circuits and Systems 2009.
[2]. Dr. M. Karnan, K. Selvanayaki “Improved
Implementation of Brain MR Image
Segmentation Using Meta Heuristic
Algorithms” 2: Research Scholar 978-1-
4244-5967-4/10/$26.00 ©2010 IEEE.
[3]. P. Padilla, J. M. Gorriz, J. Ramirez, R.
Chaves “ Alzheimer’s disease detection in
functional images using 2D Gabor Wavelet
analysis” Electronics letter , vol. 46 no.
815th
April 2010.
[4]. Sudipta Roy, Atanu Saha, Samir K.
Bandyopadhyay “Brain tumor
segmentation and quantification from MRI
of brain” Journal of global research in
computer science, volume 2, No. 4, April
2011.
[5]. Sudipta Roy, Samir K. Bandyopadhyay
“Detection and Quantification of Brain
Tumor from MRI of brain and its
Symmetric Analysis” International Journal
of Information and Communication
Technology Research Volume 2 No. 6,
June 2012.
[6]. Arati Kothari “Detection and classification
of brain cancer using artificial neural
network in MRI image” World journal of
science and technology 2012.
[7]. S. Karpagam and S. Gowri “Brain Tumor
Growth and Volume Detection by
Ellipsoid-Diameter Technique Using MRI
Data” IJCSI International Journal of
Computer Science Issues, Vol. 9, Issue 2,
No 1, March 2012.
[8]. Pauline John “Brain Tumor Classification
Using Wavelet and Texture Based Neural
Network” International Journal of
Scientific & Engineering Research Volume
3, Issue 10, October-2012.
[9]. Kailash Sinha, G. R. Sinha “Efficient
Segmentation Methods for Tumor

Detection in MRI Images” IJCSI
International Journal of Computer Science
Issues, Vol. 9, Issue 2, No 1, March 2012.
[10]. Smita Haribhau Zol “Analytical study of
segmentation and quantification of brain
tumor and its importance in radiology” Vol.
1No.Jan 2012.
[11]. Snehalatha and Dr. Narendra Mustare
“Computer Based Detection and
Classification Technique for Brain Cancer”
International Journal of Research in
Engineering and Technology (IJRET) Vol.
1, No. 5, 2012.
[12]. Prof. B. K. Saptalakar, Miss. Rajeshwari. H
“Segmentation Based Detection of Brain
Tumor” International Journal of Computer
and Electronics Research [Volume 2, Issue
1, February 2013] .
[13]. Vivek Angoth, CYN Dwith, Amarjot Singh
“A Novel Wavelet Based Image Fusion for
Brain Tumor Detection” International
Journal of Computer Vision and Signal
Processing, 2(1), 1-7(2013).
[14]. Kimmi Verma, Aru Mehrotra, Vijayeta
Pandey, Shardendu Singh ”Image
Processing Techniques For The
Enhancement Of Brain Tumor Patterns”
International Journal of Advanced
Research in Electrical, Electronics and
Instrumentation Engineering Vol. 2, Issue
4, April 2013.
[15]. Jay Patel and Kaushal Doshi “A Study of
Segmentation Methods for Detection of
Tumor in Brain MRI” Advance in
Electronic and Electric Engineering
,Volume 4, Number 3 (2014).
[16]. Tarun Kumar Agarwal, Mayank Tiwari,
Subir Singh Lamba “Modified Histogram
Based Contrast Enhancement using
Homomorphic Filtering for Medical
Images” IEEE International Advance
Computing Conference (IACC) 2014.
[17]. Rohini Paul Joseph, C. Senthil Singh,
M.Manikandan “Brain Tumor MRI Image
Segmentation And Detection In Image
Processing” IJRET International Journal of
Research in Engineering and Technology
Mar-2014.
[18]. Ed-Edily Mohd. Azhari, Muhd. Mudzakkir
Mohd. Hatta, Zaw Zaw Htike and Shoon
Lei Win “Brain Tumor Detection And
Localization In Magnetic Resonance
Imaging” International Journal of
Information Technology Convergence and
Services (IJITCS) Vol.4, No.1, February
2014.
[19]. CH. Rambabu, B. Siva Ayyappa “Brain
Tumor Classification Using Multi Wavelet
Transform and Neural Network”
International Journal of Advanced
Research in Computer Science and
Software Engineering Volume 4, Issue 9,
September 2014.
[20]. Anisha M. Lal, M. Balaji, D. Aju “Multi-
Level Fusion of CT and MRI Brain Images
for Classifying Tumor”International
Journal of Enhanced Research in
Management & Computer Applications Vol.
3 Issue 8, August 2014.

Efficient Brain Tumor Detection Using Wavelet Transform

Recommended

More Related Content

What's hot (19)

Viewers also liked (14)

Similar to Efficient Brain Tumor Detection Using Wavelet Transform (20)

Recently uploaded (20)

Efficient Brain Tumor Detection Using Wavelet Transform