Multiple Analysis of Brain Tumor Detection based on FCM

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 04 Issue: 11 | Nov -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 1682
MULTIPLE ANALYSIS OF BRAIN TUMOR DETECTION BASED ON FCM
Parul Parmar 1, Vinay Thakur2
1M.Tech (ECE), SSU Palampur, Himachal Pradesh, India.
2Assistant Professor (ECE), SSU Palampur, Himachal Pradesh, India.
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - A Tumor is an abnormal mass of a tissue which
can be solid or fluid filled in any part of the body.Thetumors
are of different types and have different treatment. In this
paper it is used to detect the brain tumor from MR images
based on fuzzy rules. The Brain images can be seen by the
MRI scan or CT scan. It is important to find out the tumor
from MRI images but it is time consuming although, the MRI
scan is more comfortable than any other scans for diagnosis.
It do not affect the human body, as it is centered on the
magnetic field and radio waves. There are various types of
algorithm for brain tumor detection. But they may have
some drawback in detection and extraction.Accordingtothe
previous approaches brain tumor detection is done by
preprocessing which is first step and then segmentation is
done by fuzzy c-means algorithms the brain tumor is
detected and it is identified. Comparing with the other
algorithms the performance of fuzzy c-means plays a major
role.
Key Words: Tumor, MRI Scan, Preprocessing,
Segmentation, Fuzzy c-means.
1.INTRODUCTION
Doctors use many tests to find, or diagnose a brain tumor
and learn the type of a brain tumor. They also do the tests to
learn if it has spread to another part of body from where it
started, doctors may also do tests to learn which treatment
could work best For most of the types of tumor, taking the
sample of the possible tumor is the only sure way for the
doctor to know whether the area of the body has a tumor or
not. Most brain tumors are not diagnosed until after
symptoms appear. Often a brain tumor is initially diagnosed
by an internist or a neurologist. An internist is a doctor who
specializes in treating adults. A neurologist is a doctor who
specializes in problems with the brain and central nervous
system. In general, diagnosing a brain tumor usually begins
with magnetic resonance imaging (MRI). Once MRI shows
that there is a tumor in the brain, the most common way to
determine the type of brain tumor.
TUMOR
The tumor are generally of two types i.e. primary or
secondary. The primary brain tumor do not spread to
another body parts and can be malignant or benign and
secondary tumors if the part of the tumorspreadstoanother
place and grows on its own, then it is known as secondary.
The secondary brain tumors are always malignant. The
malignant tumor is more dangerous and life threatening
than benign tumor whereas malignant means the cells
which are cancerous and benign means which are non-
cancerous. The main aim of this system is to make a system
for detecting and identifying the tumor from MRI For
detection and segmentation of brain tumor is that if we
obtained the three dimensional image of brain tumor then
we can also find out its tumor size and also can evaluate its
tumor type.
1.2 MAGNETIC RESONANCE IMAGING
The MRI uses a large magnet and radio waves to look at
organs and structures inside your body. Health care
professionals use MRI scans to diagnose a variety of
conditions. MRI are very useful for examining the brain and
spinal cord . the MRI having better qualities then other
medical imaging techniques. In this a special dye is used to
enhance the likelihood of detecting the brain tumor.
2 PROPOSED SYSTEM
The proposed system it consists of four types named as Pre-
processing, segmentation, segmentation using fuzzy c-
means, Feature extraction, According to the need the pre-
processing step converts the image. It performs filtering of
noise and other artifacts in the image and sharpening the
edges in the image. RGB to gray conversion. The feature
extraction is extracting the cluster which is based upon
entropy using fuzzy rules which shows the predicted tumor
at the FCM (Fuzzy C-means). output. The extracted cluster is
given to the process. It applies a binary mask over the entire
image. In the approximate reasoning step the tumor area is
calculated using the method making the dark pixel darker
and white brighter. In the approximate reasoning step the
tumor area is calculated using the binarizationmethod.That
is the image having only two values either black or white (0
or 1). Here 256x256 JPEG image is a maximum image size.
The binary image can be representedasa summationoftotal
number of white and black pixels. The Pre-processing is
done by filtering. Segmentation which is done by Fuzzy C-
means algorithm. The feature extraction is done by fuzzy
rules and finally, approximating the methodtorecognizethe
tumor size in MRI image using FCM detection method.

2.1 Flow Diagram For Proposed Method
Fig.1 Flow diagram of Proposed Method with all
processing steps.
2.2 Pre-processing
The pre-processing plays a very important role it is used for
processing the gray scale image by using different
techniques like brightness, filtering and many others. In this
process the white objects are defined from gray and light
items from dark objects. The RGB (red green and blue) to
grey conversion also takes place here. It includes a median
filter for noise deduction. In this process it changes the
brightness of the image and the tumor detection in the MRI
image got easier to identify.
Fig 2 pre-processing
3. Segmentation
In this process the clustering is the set of objects in the same
group which are similar then to the other groups. These are
basically unsupervised method of learning, the algorithm
Fcm are used to define the numberofclusters.Theclustering
are based on the features into k number of groupswhere k is
a positive integer. The clustering is done byentropybyusing
the fuzzy rules.
3.1 Fuzzy c-means
Fuzzy c-means (FCM) it is a method of clustering which
allows one piece of data to belong two or more clusters. In
this the number of clusters are found by the entropy it is
based on the fuzzy rules in this the median value should be
the same as near to the pixels, one cluster value and
secondly the cluster value should be subtracted the result
should come zero and then the rules in this themedianvalue
should be the same as near to the pixels .one cluster value
and are found then the objective function will be zero and
then maximum value get morphed and the result when we
get one we will get a color of a tumor which is detected in
this we get tumor region and tumor size.
Fig. 3 FCM resulted image
4.RESULT
Process Accuracy
Initial Variance
Previous
Work
Proposed
Work
Filteration
0.2 0.2 .012
Precision Value
Previous
Work
Proposed
Work
Filteration
0.81 0.96 0.15
Recall Value
Previous
Work
Proposed
Work
Filteration
0.86 0.90 0.04
4. CONCLUSION
There are different types of tumors available. They may be
mass in the brain or malignant over the brain. The brain
image dataset is divided into two sets. Training dataset and
testing dataset. Thus, the pre-processing is done by filtering.
Segmentation is done by fuzzy c means algorithm and then
Feature extractions is done and finally the method scans the
RGB or grayscale, converts the image into binary image by
binarization technique and detects the edge of tumor pixels
in the binary image. Also, it calculates the size of the tumor
Pre-processing Segmentation Segmentation
using fuzzy
Feature
extraction

by calculating the number of white pixels (digit 0) in binary
image. The region of the tumor is based on thearea oftumor.
REFERENCES
[1] A.R. Kavitha, Dr. C.Chellamuthu, Ms. Kavin Rupa, ‟An
Efficient Approach for Brain Tumor Detection Based on
Modified Region Growing and Network in MRI Images”,
Information Forensics and Security, IEEE Transactions on,
Vol.9 (2), May 2012.
[2] R.B.Dubey, M.Hanmandlu, Sr. Member, Shantaram
Vasikarla, ‟ Evaluation of Three Methods for MRI Brain
Tumor segmentation”, IEEE Digital Object Identifier:
10.1109/ITNG.2011.92,2011.
[3] Shaheen Ahmed, Khan M. Iftekharuddin, ‟Efficacy of
Texture, Shape and Intensity Feature Fusion for Posterior
Fossa Tumor Segmentation In MRI”, IEEE Vol (2), pag: 206-
13, Mar 2011.
[4] David Rivest-Henault, Mohamed Cheriet,‟ Unsupervised
MRI segmentation of brain tissues Using a local linearmodel
and set”, Elsevier,Vol 29, Issue 2, pag.243-259, Mar2011.
[5] Vida Harati, Rasoul Khayati, Abdolreza Farzan, ‟Fully
automated tumor segmentation based onan improvedfuzzy
connectedness Algorithm in BrainMR Images”, Elsevier
Ltd,Vol 7, pag: 483-92, May 2011.
[6] Ali Gooya, George Biros Christos Davatzikos, ‟An EM
Algorithm for Brain Tumor Images Registration: A Tumor
Growth Modling Based Approach”, IEEE, Vol 2, pag. 375-90,
May 2010.

Multiple Analysis of Brain Tumor Detection based on FCM

More Related Content

What's hot (19)

Similar to Multiple Analysis of Brain Tumor Detection based on FCM (20)

More from IRJET Journal (20)

Recently uploaded (20)

Multiple Analysis of Brain Tumor Detection based on FCM