Brain Tumor Classification using MRI Images

Industrial/In-house Training REPORT

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

of

BACHELOR OF TECHNOLOGY

in

ELECTRONICS & COMMUNICATION ENGINEERING

by

Shivam Kapur Shrey Goel Nikita Tewary

08711502819 21011502819 35211502819

Guided by

Mr. Adgaonker Shashank

Mentor

DEPARTMENT OF ELECTRONICS & COMMUNICATION ENGINEERING

BHARATI VIDYAPEETH’S COLLEGE OF ENGINEERING
(AFFILIATED TO GURU GOBIND SINGH INDRAPRASTHA UNIVERSITY, DELHI)
NEW DELHI – 110063
March 2021
 CANDIDATE’S DECLARATION

It is hereby certified that the work which is being presented in the B. Tech Industrial/In-house
training Report entitled "Brain Tumor Classification using MRI Images " in partial fulfilment
of the requirements for the award of the degree of Bachelor of Technology and submitted in the
Department of Electronics & Communication Engineering of BHARATI
VIDYAPEETH’S COLLEGE OF ENGINEERING, New Delhi (Affiliated to Guru Gobind
Singh Indraprastha University, Delhi) is an authentic record of our own work carried out
during a period from February2021 to March 2021 under the guidance of Mr. Adgaonker
Shashank.

The matter presented in the B. Tech Industrial/In-house training Report has not been submitted
by me for the award of any other degree of this or any other Institute.

Shivam Kapur Shrey Goel Nikita Tewary

08711502819 21011502819 35211502819

This is to certify that the above statement made by the candidate is correct to the best of my
knowledge. He/She/They are permitted to appear in the External Industrial/In-house training
Examination

Mr. Adgaonker Shashank Prof. Kriti Gupta

Mentor Head, ECE

The B. Tech Industrial/In-house training Viva-Voce Examination of Shivam Kapur

(08711502819), Shrey Goel (21011502819), Nikita Tewary (35211502819) has been held on
5th March, 2022.

Dr. S B Kumar
Industrial/In-house training Coordinator (Signature of External Examiner)
 ABSTRACT

A brain tumor arises due to an abnormal growth of cells that have proliferated in an
uncontrolled manner. When normal cells grow old or get injured, they either undergo cell
death or get repaired by themselves. Research shows that people affected by brain tumors
die due to their inaccurate detection. In this project, there has been proposed an intelligent
classification technique to recognize normal and abnormal MRI brain images. Medical
images like ECG, MRI and CT-scan images are important ways to diagnose disease of
human beings efficiently. To avoid manual errors, an automated intelligent classification
technique is proposed which caters the need for classification of images. In this project
work, classification techniques based on Support Vector Machines (SVM) are proposed
and applied to brain image classification. Here feature extraction from MRI Images will
be carried out by gray scale, symmetrical and texture features. This intelligent system
improves accuracy rate and reduces error rate of MRI brain tumor classification using
SVM.
 ACKNOWLEDGEMENT

We express our deep gratitude to Mr. Adgaonker Shashank, Mentor for his valuable guidance
and suggestion throughout my project work. We are thankful to Industrial/In-house
Coordinator, Dr S B Kumar for their valuable guidance.

We would like to extend my sincere thanks to Head of the Department, Prof, Kriti Gupta for
her time to time suggestions to complete my project work. I am also thankful to Prof.
Dharmender Saini, Principal, for providing me the facilities to carry out my project work.

Shivam Kapur Shrey Goel Nikita Tewary

08711502819 21011502819 35211502819
 TABLE OF CONTENTS

CANDIDATE DECLARATION Iii

ABSTRACT Iv
ACKNOWLEDGEMENT Vii
TABLE OF CONTENTS ix – xiv
LIST OF FIGURES xv – xvi
LIST OF TABLES xvii - xviii

Chapter 1: Introduction 5

1.0 Introduction 5
1.1 Motivation 5
1.2 Objective 5

Chapter 2: Description of the project 7

Chapter 3: Result and Description 9-13

Chapter 4: Conclusion 13
 LIST OF FIGURES

Figure 2.1 Project Architecture

Figure 3.1 All the libraries and files were uploaded
Figure 3.2 Testing of the project
Figure 3.3 Model Training
Figure 3.4 Prediction
Figure 3.5 Output Result 1
Figure 3.6 Output Result 2
CHAPTER 1: INTRODUCTION

1.0 INTRODUCTION
Brain tumors are the most common and aggressive disease, leading to a very short life
expectancy in their highest grade. Thus, treatment planning is a key stage to improve the
quality of life of patients. Generally, various image techniques such as Computed
Tomography (CT), Magnetic Resonance Imaging (MRI)and ultrasound image are used to
evaluate the tumor in a brain, lung, liver, breast, prostate…etc. Especially in this work
MRI images are used to diagnose tumors in the brain. However the huge amount of data
generated by MRI scans thwarts manual classification of tumor vs non-tumor in a
particular time. But it has some limitations (i.e) accurate quantitative measurements are
provided for a limited number of images. Hence trusted and automatic classification
schemes are essential to prevent the death rate of humans. The automatic brain tumor
classification is a very challenging task in large spatial and structural variability of the
surrounding region of brain tumor. In this work, automatic brain tumor detection is
proposed by using Support Vector Machine (SVM) classification. The deeper architecture
design is performed by using small kernels.

1.1 MOTIVATION
Brain tumor is one of the vital organs in the human body, which consists of billions of
cells. The abnormal group of cells is formed from the uncontrolled division of cells,
which is also called a tumor. Brain tumors are divided into two types such as low grade
(grade1 and grade2) and high grade (grade3 and grade4) tumors. Low grade brain tumors
are called benign. Similarly, the high grade tumor is also called malignant. Benign tumor
is not a cancerous tumor. Hence it doesn’t spread to other parts of the brain. However the
malignant tumor is a cancerous tumor. So it spreads rapidly with indefinite boundaries to
other regions of the body easily. It leads to immediate death.

Brain MRI image is mainly used to detect the tumor and tumor progress modeling
process. This information is mainly used for tumor detection and treatment
processes.MRI image gives more information about a given medical image than the CT or
ultrasound image. MRI image provides detailed information about brain structure and
anomaly detection in brain tissue.

1.2 OBJECTIVE

The Objective of this Project is to avoid manual errors, while detecting Brain Tumors. To
do so, an automated intelligent classification technique is proposed and created, which
caters the need for classification of images. In this project, classification techniques based
on Support Vector Machines (SVM) are proposed and applied to brain image
classification.
Chapter 2: DESCRIPTION OF THE PROJECT

Classification techniques based on Support Vector Machines (SVM) are proposed and applied
to brain image classification. The feature extraction from MRI Images will be carried out by
gray scale, symmetrical and texture features. The main objective of this system is to give an
excellent outcome (i.e. higher accuracy rate and lower error rate) of MRI brain cancer
classification using SVM. Medical images are corrupted by different types of noises like
Rician noise etc. It is very important to have good quality of images for accurate observations
for the given application. Median filter is used to remove noises while retaining as much as
possible the important signal features. Skull masking is used to remove non-brain tissue like
scalp, skull, fat, eyes, neck, etc., from MRI brain image. For skull masking morphological
operations such as erosion and dilation is used. It helps to improve the speed and accuracy of
diagnostic and predictive procedures in medical applications. Segmentation is the process of
partitioning an image into multiple segments. It used to locate objects and boundaries in
images. Based on image representation, a visual image is constructed by splitting the edges of
sub images into equal-sized bins. For each bin, the number of points from the edge that fall
into each bin is counted. Feature extraction refers to various quantitative measurements of
medical images typically used for decision making. In this work 28 features are calculated for
each image. Extracted feature sets are applied to PCA. PCA is used to reduce the feature set
which is extracted from images. The reduced features are submitted to a support vector
machine for training and testing. Therefore this method will decrease the computation time
and complexity. The classification process is divided into two parts i.e. the training and the
testing part. Firstly, in the training part known data are given to the classifier for training.
Secondly, in the testing part, unknown data are given to the classifier and the classification is
performed after the training part. The accuracy rate and error rate of the classification depends
on the efficiency of the training.

The proposed automatic intelligent classification technique architectural diagram (fig. 2) is

shown below: Image pre-processing is used to improve the quality of images. Medical images
are corrupted by different type of noises like Rician noise etc. It is very important to have
good quality of images for accurate observations for the given application. Median filter is
simple to understand. It preserves brightness differences resulting in minimal blurring of
regional boundaries. It also preserves the positions of boundaries in an image, making this
method useful for visual examination and measurement. MRI brain image is an RGB image.
This image is first converted into a gray scale image. Gray scale image is also known as an
intensity image. Array of class pixel values specify intensity values. For single and double
arrays, values range from [0, 1]. For uint8, values range from [0,255]. For uinta6, values range
from [0, 65535]. For intl6, values range from [-32768, 32767]. Intensity or brightness of an
image as two dimensional continuous function F(x, y) where (x, y) denotes the spatial
coordinates when only the brightness of light is considered. Filtering is the process of
removing noise from MRI images. Medical images are corrupted with different kinds of noise
while image acquisition. Here the median filter is used to remove noise from the MRI images.
The median filter is a nonlinear digital filtering technique, often used to remove noise. Such
noise reduction is a typical preprocessing step to improve the results of later processing (for
example, edge detection on an image). Median filtering is very widely used in digital image
processing because, under certain conditions, it preserves edges while removing noise. The
purpose of edge detection in general is to significantly reduce the amount of data in an image,
while preserving the structural properties to be used for further image processing. Edges are
significant local changes of intensity in an image. Edges typically occur on the boundary
between two different regions in an image. The goal of edge detection is to produce a line
drawing of a scene from an image of that scene and to extract important features from the
edges of an image. These features are used by higher-level computer vision algorithms. Canny
Edge Detector Algorithm is used for Edge Detection. Segmentation is the process which
divides an image into its constituent regions or objects. Segmenting non trivial images is one
of the difficult tasks in image processing. Segmentation accuracy determines the eventual
success or failure of a computerized analysis procedure. Segmentation algorithms are based on
one of two basic properties of intensity values: discontinuity and similarity. First category is to
partition an image based on abrupt changes in intensity, such as edges in an image. Second
category is based on partitioning an image into regions that are similar according to predefined
criteria. Image Thresholding approach falls under this category. Visual Image is constructed
by splitting the range of the data into equal sized bins (called classes). Then for each bin, the
number of points from the data set that fall into each bin is counted.

Feature extraction calculates features on the basis of which image can be easily classified as
normal or abnormal. The feature extraction is the process to represent raw images to facilitate
decision making such as pattern classification. Features will be extracted from the tumor
regions from MRI images. Feature extraction involves reducing the amount of data required to
describe a large set of data accurately. Features are used as inputs to classifiers that assign
them to the class that they represent. The intention of feature extraction is to reduce the
original data by measuring positive properties, or features, that discriminate one input sample
from another sample. Excessive features used for classification not only increase computation
time but also increase storage memory. They sometimes make classification more
complicated. It is required to reduce the number of features. PCA is a proficient tool to reduce
the dimension of a data set consisting of a large number of interconnected variables while
retaining most of the variations. Reduce dimension means reduced feature set which acts as an
input to the SVM during the training part as well as testing part. The SVM algorithm was first
developed in 1963 by Vapnik and Lerner. SVM is a binary classifier based on supervised
learning which gives better results than other classifiers. SVM classifies between two classes
by constructing a hyper plane in high-dimensional feature space which can be used for
classification. SVM is a classification algorithm, which is based on different kernel methods.

Preprocessing
Input Image Segmentation
(Median Filter)

Feature Vector Feature Extraction

Multi SVM Classifier

Identify Tumor

Fig 2.1: Project Architecture

CHAPTER 3: RESULT and DISCUSSION

Fig 3.1: All the required libraries and files were uploaded.

Fig 3.2: Testing of the dataset

Figure 3.3: Model Training.

Fig 3.4: Prediction

 Fig 3.5: Output Result 1

Fig 3.6: Output Result 2

CHAPTER 4: CONCLUSION

Brain tumors are caused by abnormal and uncontrolled growing of the cells inside the
brain.Treatment of a brain tumor depends on its size and location. Although benign tumors do
not tend to spread, they can cause damage by pressing on areas of the brain if they are not
treated early. To avoid manual errors, an automated intelligent classification technique is
proposed which caters the need for classification of images. In this project, classification
techniques based on Support Vector Machines (SVM) are proposed and applied to brain
image classification. This automated intelligent system results in the improvement of accuracy
rate and reduces the error rate of MRI brain tumor.
 REFERENCES

[1] Detection of brain tumor in MRI images, using combination of fuzzy c-means and SVM
[2] MRI Brain Tumor Classification Using SVM and Histogram Based Image Segmentation
[3] MRI brain tumor classification using Support Vector Machines and meta-heuristic method
[4] Brain Tumor Classification Using Hybrid Model Of PSO And SVM Classifier
[5] Detection of brain tumor from MRI images by using segmentation & SVM