BRAIN TUMOR DETECTION USING

MACHINE LEARNING

40EC8P1-PROJECT WORK PHASE II

ZEROTH REVIEW REPORT

Submitted by

PUNITHA.S 1513209

RANJINI.G 1513213

RANJITH.C. K 1513214

SHALINI.M 1513227

THENMOZHI.S 1213265

in partial fulfilment of the requirement

for the award of the degree

of

BACHELOR OF ENGINEERING

in

ELECTRONICS AND COMMUNICATION ENGINEERING,

TIRUCHENGODE – 637 215
K.S. RANGASAMY COLLEGE OF TECHNOLOGY
(An Autonomous Institution, affiliated to Anna University Chennai and Approved by AICTE, New Delhi)

DECEMBER-2018

PROJECT GUIDE PROJECT COORDINATOR

Mrs. D.SUJATHA, M.E Mrs.D.SUJATHA, M.E
i
ABSTRACT

One of the challenging tasks in the medical area is brain tumor segmentation
which consists on the extraction process of tumor regions from images. Generally, this
task is done manually by medical experts which is not always obvious due to the
similarity between tumor and normal tissues and the high diversity in tumors appearance.
Thus, automating medical image segmentation remains a real challenge which has
attracted the attention of several researchers in last years. Our idea is to consider this
problem as a classification problem where the aim is to distinguish between normal and
abnormal pixels on the basis of several features, namely intensities and texture. More
precisely, we propose to use Support Vector Machine (SVM) which is within popular
and well motivating classification methods. Support Vector Machines (SVM) is a fast
and dependable classification algorithm that performs very well with a limited amount
of data.

1
BLOCK DIAGRAM

Figure 1 : Block diagram of brain tumor

2
DESCRIPTION DETAILS

PREPROCESSING

There are two stages in pre-processing

 Binarization

 Median Filter

I. BINARIZATION
It is a mapping of a multi-class learning problem to several two-class learning
problems in a way that allows a sensible decoding of the prediction, i.e., it allows the derivation
of a prediction for the multi-class problem from the predictions of the set of two-class
classifiers. The learning algorithm used for solving the two-class problems is called the base
learner.

II. MEDIAN FILTER

It is a nonlinear digital filtering technique, often used to remove noise from
an image or signal. Such noise reduction is a typical pre-processing 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 (but see discussion below), also having
applications in signal processing.

Figure 2. Example for median filter.

3
EXTRACTION AND SEGMENTATION OF BRAIN MRI IMAGE

I. EXTRACTION

When the input data to an algorithm is too large to be processed and it is

suspected to be redundant then it can be transformed into a reduced set of features .
Determining a subset of the initial features is called feature selection. The selected features are
expected to contain the relevant information from the input data, so that the desired task can be
performed by using this reduced representation instead of the complete initial data. In which
algorithms are used to detect and isolate various desired portions or shapes (features) of a
digitized image or video stream. It is particularly important in the area of optical character
recognition. In this project shape based extraction was used.

II. SEGMENTATION
Image segmentation is the process of partitioning a digital image into multiple
segments .The goal of segmentation is to simplify and/or change the representation of an image
into something that is more meaningful and easier to analyze. Image segmentation is typically
used to locate objects and boundaries in images. image segmentation is the process of assigning
a label to every pixel in an image such that pixels with the same label share certain
characteristics

Figure 3: Segmentation images

4
TRAINING AND TESTING
Most approaches that search through training data for empirical relationships tend to
over fit the data, meaning that they can identify apparent relationships in the training data that
do not hold in general.

A test dataset is a dataset that is independent of the training dataset, but that follows
the same probability distribution as the training dataset. If a model fit to the training dataset
also fits the test dataset well, minimal over fitting has taken place (see figure above). A better
fitting of the training dataset as opposed to the test dataset usually points to over fitting.

CLASSIFICATION

Types of classification algorithms

 Linear Classifiers: Logistic Regression, Naive Bayes Classifier

 Support Vector Machines

 Decision

 Random Forest

 Neural Networks

 Nearest Neighbor

i) Naive Bayes Classifier (Generative Learning Model)

It is a classification technique based on Bayes Theorem with an assumption of

independence among predictors. In simple terms, a Naive Bayes classifier assumes that the
presence of a particular feature in a class is unrelated to the presence of any other feature.
Even if these features depend on each other or upon the existence of the other features, all of
these properties independently contribute to the probability. Naive Bayes model is easy to
build and particularly useful for very large data sets. Along with simplicity, Naive Bayes is
known to outperform even highly sophisticated classification methods.

5
ii) Logistic Regression (Predictive Learning Model)
It is a statistical method for analysing a data set in which there are one or more
independent variables that determine an outcome. The outcome is measured with a
dichotomous variable The goal of logistic regression is to find the best fitting model to describe
the relationship between the dichotomous characteristic of interest and a set of independent
variables.

iii) Support Vector Machine

SVM is a supervised machine learning algorithm which can be used for both
classification or regression challenges. However, it is mostly used in classification problems.
In this algorithm, we plot each data item as a point in n-dimensional space with the value of
each feature being the value of a particular coordinate. Then, we perform classification by
finding the hyper-plane that differentiate the two classes very well.

iv) Decision Trees

Decision tree builds classification or regression models in the form of a tree
structure. It breaks down a data set into smaller and smaller subsets while at the same time an
associated decision tree is incrementally developed. The final result is a tree with decision
nodes and leaf nodes. A decision node has two or more branches and a leaf node represents a
classification or decision. The topmost decision node in a tree which corresponds to the best
predictor called root node. Decision trees can handle both categorical and numerical data.

v) Random Forest
Random forests or random decision forests are an ensemble learning method for
classification, regression and other tasks, that operate by constructing a multitude of decision
trees at training time and outputting the class that is the mode of the classes (classification) or
mean prediction (regression) of the individual trees. Random decision forests correct for
decision trees’ habit of over fitting to their training set.

6
vi) Neural Network
A neural network consists of units (neurons), arranged in layers, which convert an
input vector into some output. Each unit takes an input, applies a (often nonlinear) function to
it and then passes the output on to the next layer. Generally, the networks are defined to be
feed-forward: a unit feeds its output to all the units on the next layer, but there is no feedback
to the previous layer. Weightings are applied to the signals passing from one unit to another,
and it is these weightings which are tuned in the training phase to adapt a neural network to the
particular problem at hand.

vii) Nearest Neighbor

The k-nearest-neighbors algorithm is a classification algorithm, and it is
supervised: it takes a bunch of labelled points and uses them to learn how to label other points.
Viii) SVM Importance

 Works well with even unstructured and semi structured data like text, Images and
trees.
 The kernel trick is real strength of SVM. With an appropriate kernel function, we can
solve any complex problem.

7
DISCUSSION

The chapter deals with the half of the result of this project. The data set use in this work consists
of few MRI images of human brain. Few of those images are normal human brain images, and
the remaining show brains suffering from tumors. The images were mainly acquired by
searching the Internet as it appears that acquiring such images from local hospitals is harder
task that initially anticipated. The data set is converted from RGB images into gray-scale
images using MATLAB image processing tools. The collected MRI images fed as input. Then
the input images are filtered to remove noise by using median filter. After the filtration process,
the MR images will be extracted. Algorithms for analyzing and classifying medical images
have gained a great level of attention recently. The experiments we present in this work show
that after pre-processing MRI images, support vector machine algorithm was the best. Compare
to another method the MATLAB is provide its user accurate solution of the problems and
produce code easily. Then MATLAB is a interpreted language, so the errors are easier to fix.

8
SUMMARY
Normal brain image and tumor images are mainly acquired by searching the
Internet as it appears that acquiring such images from local hospitals. The MRI images are fed
as input. Input given to the process is called image acquisition. Using MATLAB the images
are converted from GRB to gray scale image. After converting gray scale image noise are
removed from the image using median filter. Those are all the part of the pre-processing. Other
processes are extraction, segmentation and classification are continuing in the MODULE II
and MODULE III.
 9
REFERENCES

[1] K.S.Angel Viji and Dr. J. Jayakumari, “Automatic Detection of Brain Tumor based on
Magnetic Resonance Image using CAD system with watershed segmentation”, international
conference on Signal processing, Communication, Computing and Networking Technologies,
IEEE, 2017,PP.145-150.

[2] M.UsmanAkram and AnamUsman, “computer Aided System for BrainTumor Detection
and Segmentation”, IEEE, International conference oncomputer networks & information
Technologies (ICCNIT), 2016, pp.299-302.
[3] Ehab F. Badran, EsraaGalal Mahmoud and NadderHamdy, “Analgorithm for Detecting
Brain Tumors in MRI images”, International conference on computer Engg& systems, IEEE
systems (ICCES), 2016,pp. 368-373.
[4] Ainy Sachdeva, Vinod Kumar, Indra Gupta, Niranjan Khandelwal and Chirag Kamal
Ahuja, “Multiclass Brain Tumor Classification using GASVM”,IEEE 2015 Devlopments in E
systems Engineering, 2015,PP.182-187.
[5] Huilin Gao, Wenjie Chen, and Lihua Dou, “Image Classification Based on Support
Vector Machine and the Fusion of Complementary Features”, arXiv, 2015.
[6] U.Aswathy, G. Glan Deva Dhas, S.S. Kumar, “A Survey on Detectionof Brain Tumor
From MRI Brain Images”, 2014 internationalconference on control, Instrumentation,
Communication andComputational Technologies(ICCICCT), pp. 871-877, 2014.
[7] S.Anbumozhi, P. S. Manoharan, “Performance Analysis of Brain Tumor Detection Based
On Image Fusion”, International Journal of Computer, Electrical, Automation, Control and
Information Engineering, Vol. 08, No. 03, 2014.
[8] S.L.Jany Shabu, Dr.C. Jayakumar, T. Surya, “Survey of Image Fusion Techniques for
Brain Tumor Detection”, International Journal of Engineering and Advanced Technology, Vol.
03, No. 02, pp. 2249 – 8958, 2013.
[9] Zhenhua Guo, Lei Zhang and David Zhang, “A Completed Modelling of Local Binary
Pattern Operator for Texture Classification”, IEEE, Vol. 19, No. 6, pp. 1657 - 1663, 2010.
[10] Emmanuel J. Candes, Xiaodong Li, Yi Ma, and John Wright, “Robust Principal
Component Analysis”, Journal of the ACM, Vol. 58, No. 3, pp. 11, 2011.
10