OVERVIEW
• Introduction
• Objective
• Problem Statement
• Proposed System
• Methodology
• Applications
• Advantages
• Technical Specifications
• Result
• Conclusion
• References
INTRODUCTION
• The human body is composed of numerous types of cells. Each
cell has a specific function. These cells in the body grow and
divide in an arranged manner and form some new cells. These
new cells help to keep the human body healthy and ensures
proper functioning. When some of the cells lose their ability to
control their growth, they grow without any order. The extra
cells formed form a mass of tissue which is called tumor . A
brain tumor is a collection of abnormal cells in the brain.
Tumors can be benign or malignant. Malignant tumors lead to
cancer while benign tumors are not cancerous.
• The conventional method for tumor detection in magnetic
resonance brain images is human inspection. The observation
from human in predicting the tumor may mislead due to noise
and distortions found in the images. This method is impractical
for large amount of data and also very time consuming.
• So, automated tumor detection methods are developed as it
would save radiologist time. TheMRI brain tumor detection is
complex task due to complexity and variant of tumors. Tumor is
identified in brain MRI using Machine Learning algorithms. The
proposed work is divided into three sections: Preprocessing
steps are applied on the brain MRI images, then texture
features are extracted using Gray Level Co-occurrence Matrix
(GLCM) and finally classification is performed using machine
learning algorithm.
SYMPTOMS
Symptoms vary depending on the location of the brain tumor, but
the following may accompany different types of brain tumors:
• Headaches that may be more severe in the morning or awaken
the patient at night
• Seizures or convulsions
• Difficulty thinking, speaking or articulating
• Personality changes
• Weakness or paralysis in one part or one side of the body
• Loss of balance or dizziness
• Vision changes
• Hearing changes
• Facial numbness or tingling
• Nausea or vomiting, swallowing difficulties
• Confusion and disorientation
OBJECTIVE
• To capture MRI images to analyse the presence of tumor using
machine learning techniques.
• To perform segmentation process on MRI images to separate
the tumor from normal brain tissues.
• To extract features from captured images to find the tumor.
• To detect the presence of tumor.
PROBLEM STATEMENT
In the medical field, Tumor is detected by Doctors by referring the
MRI images which is very time consuming. Therefore, to overcome
this problem, an alternative way is to design the system that will
automatically identify the presence of Tumor in MRI images using
machine learning technique and also provide faster and accurate
solutions.
PROPOSED SYSTEM
System Architecture:
MODULE 1:- Image Acquisition
Firstly, the MRI images are acquired and then these images are given
as input to the pre-processing stage.
MODULE 2:- Pre-processing
Pre-processing is required as it improvises the image data which
enhances some of the image features that are important for the
further processing. The RGB MRI image is converted to gray scale
image and the median filter is applied to brain MRI images for noise
removal. The noise has to be removed for further processing as high
accuracy is required.The edges are detected from filtered image
using canny edge detection. The detected image of the edges are
required for segmentation of the image. Further, Watershed
segmentation is performed for finding the location of the tumor in
the brain image.
MODULE 3:- Segmentation
• Segmentation is the process of dividing an image into multiple
segments.
• The aim of segmentation is to change the representation of a
image into something which is easier to analyse.
• Segmentation is the process of separating the tumor from
normal brain tissues.
• Watershed segmentation is performed for finding the location
of the tumor in the MRI images.
• The result of watershed segmentation is label image. In label
image, the different objects that are identified will have
different pixel values.
For better understanding let’s look at the image on next page.
=
MODULE 4:- Feature Extraction
• When a input to an algorithm is very large and redundant to be
processed, it is transformed into reduced representative set
features called feature vector.
• Transformation of this input data into a set of features is called
feature extraction. In this step, the important features required
for image classification are extracted.
• The segmented brain MRI image is used and texture features
are extracted from the segmented image which shows the
texture property of the image.
• These features are extracted using Gray Level Co-occurrence
Matrix (GLCM) as it is robust method with high performance.
• This texture feature extraction method is very competitive as
using smaller number of gray levels shrinks the size of GLCM
which reduce the computational cost of the algorithm and also
maintains the high classification rates. These features are used
to differentiate between normal and abnormal brain.
The GLCM texture features that are extracted are as follows:
➢ Energy : It gives a measure of textural uniformity, that is,
measure of pixel pair repetitions.
Range=[0,1]
➢ Contrast : It gives a measure of intensity contrast
between a pixel and its neighbor over the whole image.
Range=[0,1]
➢ Correlation : It gives a measure of how correlated a pixel
to its neighbour over the whole image.
Range=[-1,1]
➢ Homogeneity : It gives a measure of closeness of
distribution of elements in GLCM to GLCM diagonal.
Range=[0,1]
MODULE 5:- Classification
❖ Classification of MR brain image either as normal or abnormal.
❖ In MLP, each node is a neuron with a nonlinear activation
function.
❖ With the help of above modules we can detect weather the
Tumor is present or not.
❖ This process helps in identifying the size, shape and position of
the tumor.
TECHNICAL SPECIFICATIONS
➢ Python Language
➢ Library’s used
➢ Tkinter:
➢ Tkinter commonly comes bundled with Python, using Tk and is
Python's standard GUI framework. It is famous for its simplicity
and graphical user interface. It is open-source and available
under the Python License.
➢ Initialize the window manager with the tkinter.Tk() method and
assign it to a variable. This method creates a blank window with
close, maximize, and minimize buttons on the top as a usual
GUI should have.
➢ Python Imaging Library Pillow (PIL) :
• Python Imaging Library (abbreviated as PIL) (in newer versions
known as Pillow) is a free and open source, additional library
for the Python Programming language that adds support for
opening, manipulating, and saving many different image file
formats.
• It is available for Windows, Mac OS X and Linux. Pillow offers
several standard procedures for image manipulation.
➢ NumPy:
• NumPy stands for Numerical Python. It is an open source
project and you can use it freely. NumPy is a python library
used for working with arrays. It also has functions for working
in domain of linear algebra, fourier transform, and matrices. In
Python we have lists that serve the purpose of arrays, but they
are slow to process.
• NumPy aims to provide an array object that is up to 50x faster
that traditional Python lists.
➢ Skimage:
➢ Scikit-image, or skimage, is an open source Python package
designed for image pre-processing. Skimage provides easy-to-
use functions for reading, displaying, and saving images. All of
the popular image formats, such as BMP, PNG, JPEG, and TIFF
are supported, along with several more esoteric formats.
➢ We import the io module of skimage (skimage.io) so we can
read and write images. Then, we use the skimage.io.imread()
function to read a JPEG image. Skimage reads the image,
converts it from JPEG into a NumPy array, and returns the
array; we save the array in a variable named image.
➢ Pandas:
• Pandas is an open-source, BSD-licensed Python library
providing high-performance, easy-to- use data structures and
data analysis tools for the Python programming language.
• Python with Pandas is used in a wide range of fields including
academic and commercial domains including finance,
economics, Statistics, analytics, etc.
TECHNIQUE USED
• Multilayer Perceptron (MLP) Classification:
• A multilayer perceptron (MLP) is a deep, artificial neural
network.
• It is composed of more than one perception.
• They are composed of an input layer to receive the signal, an
output layer that makes a decision or prediction about the
input, and in between those two, an arbitrary number of
hidden layers that are the true computational engine of the
MLP.
• MLPs with one hidden layer are capable of approximating any
continuous function.
• An MLP consists of at least three layers of nodes: an input
layer, a hidden layer and an output layer.
• Except for the input nodes, each node is a neuron that uses a
nonlinear activation function.
• MLP utilizes a supervised learning technique called back
propagation for training.
• Its multiple layers and non-linear activation distinguish MLP
from a linear perception.
• It can distinguish data that is not linearly separable.
• Multilayer perceptions are often applied to supervised learning
problems they train on a set of input-output pairs and learn to
model the correlation (or dependencies) between those inputs
and outputs.
ADVANTAGES
➢ Combination of various function in one application :
• This application provides features that would be used for
various tasks. Other application could consume
• more memory from the computer but this application can bring
images from server and useless memory of computer.
• + Also this application can generate better and accurate
outputs.
➢ User friendly interface:
• Many other application can have a complex interface but this
application has a graphical represented user friendly interface
which can reduce the time of the operator and a new user who
wants to use this software.
• A user can perform scans as well as comparisons on the
software at ease.
➢ Accuracy:
• As the base of this program is a machine learning, a large
number of data is collected from various hospitals or the CT
scan of brain.
• A huge library is generated over servers and it’s regularly
updated. This can guarantee accurate data reading and perfect
representation of the sports or the whites which are reflected
on the images to the image which is been uploaded by a user,
thus giving an accurate result.
➢ Time consumption:
• + The main objective of the software was to reduce the time
consumed for this process of detecting tumor via CT scan. The
software reduces the time of the user and doctors drastically by
using machine learning technology.
APPLICATION
• The main aim of the application is to identify tumor and
diagnosis.
• The main reason behind the development of this
application is to provide proper treatment as soon as
possible and protect the human life in danger.
• This application is used for drug discovery and
manufacturing.
• This application is helpful for doctors as well as patients.
• This application is used to do smart health care records.
• The manual identification is not so fast, accurate and
efficient, therefore to overcome these problems this
application is designed.
• This application is used to provide better Radiotherapy.
• It is user friendly application.
