Download as pdf or txt
Download as pdf or txt
You are on page 1of 8

VISVESVARAYA TECHNOLOGICAL UNIVERSITY

Jnana Sangama, Belagavi-590014

2016-2017
A Dissertation Report
on
Breast Cancer Detection Using Statistical
Features and SVM

Submitted in partial fulfillment of the requirements for the award of degree


of

MASTER OF TECHNOLOGY
In
DIGITAL ELECTRONICS AND COMMUNICATION
SYSTEMS
By

NISHA V
(1VW15LDS10)

Under the guidance


of
Dr. Sarika Tale
Chairperson & Associate Professor

Department of Digital Electronics & Communication Systems


VTU CPGSB VIAT, Muddenahalli
Chickballapur-562101

VTU-Center for Post Graduate Studies, Bangalore Region


DEPARTMENT OF DIGITAL ELECTRONICS AND COMMUNICATION SYSTEMS
M uddenahalli, Chic kball apur-562101
ACKNOWLEDGEMENT
Any achievement, be it scholastic or otherwise does not depend solely on the individual
efforts but on the guidance, encouragement and cooperation of intellectuals, elders and friends.

It is a pleasure to acknowledge all those who have provided help inspiration and
encouragement as I proceed with this project work and made it a good Success. I am grateful to my
guide Dr. Sarika Tale, Chairperson & Associate professor, Department of Digital Electronics and
Communication system for her constant support, invaluable advice and encouragement throughout
the work. Without her guidance and invaluable time spent with us in this project, this report would
not have been completed successfully.

I would like to express my sincere thanks to all the faculty Ms. Reshma M, Mr. Dileep K T,
Mr. Manjunath M and non-teaching staff members of Digital Electronics and Communication
system for their valuable guidance and support.

Last but not the least I would like to say a word of thanks to my family members for their
moral support and encouragement throughout all these semester. Without their support, I would
never have gotten this far. I am grateful to my friends for their support and assistance during my
work towards this goal.

NISHA V

i
ABSTRACT
In human body certain organ and tissue cells divides each other and increases. Some
of the cells get increased due to duplication and some are prone to death of cells to maintain
the equilibrium state concerning the organs integrity. DNA or genetic defects balances the
creation and death of the cells. The propagation and replication of the cells take place which
results in new emerging changes.

This can result in uncontrolled growth of cells which turns in to tumor. These cancer
cells grab all the nutrients from healthy cells and start encroach the nearby tissue cells. Some
of the cancer cells remain obscure doesn’t get replicated but some cancer cells also enters
into other parts of the body via glands or the body parts.

The proposed work is to present an approach for classification of the breast cancer
using mammograms. The preprocessing of mammograms is a very important step to segment
the region of interest and enhancing the quality of the image in order to detect the
calcifications. The wavelets based artifacts removal is performed. Pectoral muscles are
detected using k-means clustering and are removed. Segmentation is performed using region
growing algorithm and extract shape vectors. Classification of cancer is performed using
artificial neural networks or support vector machine. After applying SVM classifying
technique to the images of database, will come to know the tumor is either Benign or
Malignant.

ii
TABLE OF CONTENTS
Details Page no
ACKNOWLEDGEMENT i
ABSTRACT ii
LIST OF FIGURES iii
LIST OF TABLE iv
LIST OF CHART v
CHAPTER 1 INTRODUCTION 1
1.1 Introduction of project 1
1.2 Motivation 2
1.3 Project Objective 3
1.4 Existing & Proposed system 3
1.5 Project Description 4
1.6 Project Outcome 5
1.7 Advantages & Applications 5

CHAPTER 2 LITERATURE SURVEY 7


2.1 Problem Statement 9

CHAPTER 3 METHODOLOGY 11
3.1 Data Collection 11
3.2 Block Diagram 11
3.2.1 Image Acquisition 12
3.2.2 Image Preprocessing 12
3.2.3 Image Segmentation 12
3.2.4 Feature Extraction 12
3.2.5 Feature Database 12
3.2.6 Image Recognition & Classification 12

IV
3.3 Methodology 13
3.4 Requirements 14
3.4.1 Hardware Requirements 14
3.4.2 Software Requirements 14

CHAPTER 4 IMPLEMENTATION 16
4.1 Input Data 16
4.2 Preprocessing 16
4.2.1 Low-Level Designs 17
4.2.2 Pectoral Muscle Removal 18
4.3 Segmentation 18
4.3.1 Region Growing Based Segmentation 19
4.3.2 Selection of Appropriate Seed Points for
Region Growing Segmentation 20
4.4 K-means Clustering 21
4.4.1 K-means Clustering Algorithm 22
4.5 Feature Extraction 23
4.6 Classification 24

CHAPTER 5 RESULT ANALYSIS 25


5.1 Snapshots 28

CHAPTER 6 CONCLUSIONS & FUTURE SCOPE 30


REFERENCES 31

V
LIST OF FIGURES

Figure Details Page no

3.1 Original Mammogram Image 11


3.2 Block diagram of mammogram
Cancer classification 11
3.3 Training of mammogram images 13
3.4 Testing of mammogram images 14
4.1 Representing Low-level designs 17
4.2 Mammogram Image with Pectoral Muscle
Suppressed 18
4.3 K-Means Clustering Algorithm 22
5.1 Snapshot of K-Means Segmentation 28
5.2 Snapshot of Feature Extraction Output 28

LIST OF TABLE
Figure Details Page no

1 Result Analysis for Mammogram


Classification Using SVM Classifier. 27

LIST OF CHART
Figure Details Page no
1 Represents the Total Number of Image
with Classification of Malignant and Benign. 27
2 Represents the classification rate of SVM
Classifier in classifying the mammogram images. 27

VI

You might also like