SUMALATHA 470 ECE-2 (4) (Asla) (LA)
SUMALATHA 470 ECE-2 (4) (Asla) (LA)
A Project Report
Submitted in partial fulfillment of Requirements for the Award of
the Degree of
BACHELOR OF TECHNOLOGY
IN
ELECTRONICS AND COMMUNICATION ENGINEERING
By
\
CERTIFICATE
This is to certify that this project titled “BRAIN TUMOR DETECTION BY USING MATLAB”is
a bonafide record of work done by K.VEDA SAI SRI (168A1A04A6 ) , M.HARISH
KUMAR(168A1A04A9), Y.LINGARAJU(178A5A0404 ) under my guidance and supervision and is
submitted in partial fulfillment of the requirements for the award of the degree of Bachelor of Technology in
Electronics &Communication Engineering by Jawaharlal Nehru Technological University, Kakinada during
the academic year 2016-2020.
EXTERNAL EXAMINER
ACKNOWLEDGEMENT
We owe our gratitude to our Principal, A.V.BHASKAR RAO garu, for his kind
attention in the valuable guidance to us throughout the course.
We sincerely thank our Guide MR.A.BENJAMIN PAUL, Assoc. professor for his
Guidance and valuable suggestions and support in the completion of the project.
Finally we thank all our faculty members, supporting staff of ECE Department and
friends for their kind co-operation and valuable help for the completion of the project.
Submitted By
K.VEDA SAI SRI (168A1A04A6)
M.HARISH KUMAR (168A1A04A9)
Y.LINGARAJU (178A5A0404)
RISE KRISHNA SAI PRAKASAM GROUP OF INSTITUTIONS::ONGOLE
(APPROVED BY AICTE-NEW DELHI, AFFILIATED TO JNTUK
KAKINADA)
AN ISO 9001:2015 CERTIFIED INSTITUTE
PEO4: Professional and ethical attitude, effective communication skills, and sense
Professionalism of responsibility towards society.
Name of the Course : Project & Seminar Year & Semester : IV Year II
Academic Year : 2019-20 Regulation : R16
Course Outcomes
Course Outcomes(COs)
Work in team to carry out analysis and cost-effective, environmental friendly designs
C426.4
of engineering systems.
Write Technical / Project reports and oral presentation of the work done to an
C426.5
audience.
Name of the Course : Project & Seminar Year & Semester : IV Year II
Academic Year : 2019-20 Regulation : R16
CO Vs PO Mapping
Course
Outcome PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12
s(COs)
C426.1 3 2 3 2 3 2 2 3 3 2 3 3
C426.2 3 3 3 2 3 2 2 3 3 2 3 3
C426.3 3 2 3 2 3 2 2 3 3 3 3 3
C426.4 3 2 3 2 3 2 2 3 3 3 3 3
C426.5 2 2 3 2 3 2 2 3 3 3 3 3
C426.6 2 2 3 2 3 2 2 3 3 3 3 3
C426 3 3 3 2 3 2 2 3 3 3 3 3
CO Vs PSO Mapping
Course
PSO1 PSO2 PSO3
Outcomes(COs)
C426.1 3 3 2
C426.2 3 3 2
C426.3 3 3 2
C426.4 3 3 2
C426.5 3 3 2
C426.6 3 3 2
C426 3 3 2
CONTENTS
Page no
ACKNOWLEDGEMENT I
DECLARATION II
LIST OF TABLES III
LIST OF FIGURES IV
ABSTRACT V
CHAPTER-1: INTRODUCTION 1-5
1.1 image processing 1
1.2 fundamental of image processing 1
1.3 Biomedical Image Processing 3
1.4 Neurological Disorders 4
1.5 Brain Tumors 5
CHAPTER-2: LITERATURE SURVEY 6-9
CHAPTER-3: EXISTING METHODS 10-14
3.1 image segmentation 10
3.2 image segmentation techniques 11
3.2.1 Threshold Based segmentation 11
3.2.2 Drawbacks os Thresholding 14
3.2.3 Region Based Segmentation 15
(i) Region Growing Segmentation 15
(ii) Speeded Region Growing 15
3.2.4 Drawbacks 16
3.2.5 Watershed Algoritham 16
3.2.6 Water Segmentation Methods 16
(i) Distance Transform Method 16
(ii) Gradient Magnitude 17
(iii) Marker Controller Method 17
3.2.7 Drawbacks Of Watershed Algorithm 18
CHAPTER-4: PROPOSED METHOD 19-29
4.1 Clustering 19
4.2 Image Classification 20
4.3 K-Mean Clustering 21
4.4 Initialization Methods 22
4.5 Strengths And Weakness 24
4.6 Fuzzy C-Mean Algorithm 25
4.7 Feature Extraction 26
4.8 Area Calculation 27
CHAPTER-5: RESULTS 30-45
CHAPTER-6: CONCLUSION 46
CHAPTER-7: BIBLIOGRAPHY 47
CHAPTER-8: BIODATA 48
LIST OF FIGURES
FIG.N DESCRIPTION PAGE No
o
1.1 Basic Block Diagram of Image Processing 4
3.1 Thresholding Based Segmentation Flow 12
3.2 Separation of Image and Histogram of two sides 13
3.3 Difference in the intensity of the two side brain 14
3.4 Flowchart of watershed Algorithm 18
4.1 Different ways of clustering the same set of points 23
4.2 Flowchart for K-mean clustering 24
4.3 Proposed Methodology 27
4.4 Output Image of Thresholding 28
5.1 Original gray level image 30
5.2 Original colormap image 31
5.3 Color space translated image 32
5.4 Image labelled by cluster index 33
5.5 Objects in cluster 1 34
5.6 Objects in cluster 2 35
5.7 Objects in cluster 3 36
5.8 Truly segmented image using k-mean 37
5.9 Original gray level image 38
5.10 Original colormap image 39
5.11 Color space translated image 40
5.12 Image labelled by cluster index 41
5.13 Objects in cluster 1 42
5.14 Objects in cluster 2 43
5.15 Objects in cluster 3 44
5.16 Truly segmented image using FCM 45
LIST OF TABLES
Table No Description Page No
5.1 Comparison between K-mean and FCM 45
ABSTRACT
This project deals with the implementation of Simple Algorithm for
detection of range and shape of tumor in brain MR images. Tumor is an
uncontrolled growth of tissues in any part of the body. Tumors are of different
types and they have different Characteristics and different treatment. As it is
known, brain tumor is inherently serious and life-threatening because of its
character in the limited space of the intracranial cavity (space formed inside the
skull). Most Research in developed countries show that the number of people
who have brain tumors were died due to the fact of inaccurate detection.
Generally, CT scan or MRI that is directed into intracranial cavity produces a
complete image of brain. This image is visually examined by the physician for
detection & diagnosis of brain tumor. However this method of detection resists
the accurate determination of stage & size of tumor. To avoid that, this project
uses computer aided method for segmentation (detection) of brain tumor based
on the combination of two algorithms. This method allows the segmentation of
tumor tissue with accuracy and reproducibility comparable to manual
segmentation. In addition, it also reduces the time for analysis. At the end of the
process the tumor is extracted from the MR image and its exact position and the
shape also determined. The stage of the tumor is displayed based on the amount
of area calculated from the cluster.
.