A project report on

Brain Tumor Detection Using Machine Learning

Submitted By
Mr. Purva Prasad Ghade
M.Sc. (Computer Science) Semester-IV

Submitted to
Savitribai Phule Pune University
for partial fulfillment of the requirement of M.Sc(Computer Science)
K.S.K.W. Art’s, Commerce & Science College Cidco, Nashik

Guided by :
Smt.A.S.Bachhav
 Acknowledgement

We are happy to present the project “Brain Tumor Detection Using Machine
Learning”in Python ML. A project titled “Brain Tumor Detection Using Machine
Learning” would not have been completed without the valuable guidance and
encouragement of Smt A S Bachhav and all staff members. We acknowledge them
for their moral support.

This project is substantially upgrading our skill of software development

which we intend to good use in developing better system in future. In conclusion,
we would like to express our thanks to management for providing us all facilities for
completion of our project. Finally we extend our thanks our all M.sc. (Computer
Science) staff, Classmates and also thank to our parents to help us all time.

And special thanks to my friends who helped us for successful completion of

this project. They pointed out errors and suggested changes, helped in many ways,
give us the idea of this project.
 INDEX

Sr No Contents

1 Abstract
2 Introduction
 Motivation
 Problem Statement
 Purpose/Objective and Goals
 Literature Survey
 Project Scope and Limitations
3 System Analysis
 Comparative Study of Existing Systems
 Scope and Limitation of Existing System
 Project Perspective and Features
 Requirement Analysis
4 System Design
 Design Constraints
 System Model: UML Diagrams
 Data Model
 User Interface
5 Implementation Details
 Hardware and Software Specifications
6 Outputs and Reports

7 Testing
 Test Cases
8 Conclusion and Recommendations
 9 Future Scope

10 Bibliography/References

Abstract

A brain tumor is a disease caused due to the growth of abnormal cells in the brain.
There are two main categories of brain tumor; they are non-cancerous (benign)
brain tumor and cancerous (malignant) brain tumor.
Manual method of visual inspection of MRI images is tedious and inaccurate.
Histological grading, based on a stereotactic biopsy test, is the gold standard and
the convention for detecting the grade of a brain tumor.
The biopsy procedure requires the neurosurgeon to drill a small hole into the skull
from which the tissue is collected. There are many risk factors involving the biopsy
test, including bleeding from the tumor and brain causing infection, seizures,
severe migraine, stroke, coma and even death.
But the main concern with the stereotactic biopsy is that it is not 100% accurate
which may result in a serious diagnostic error followed by a wrong clinical
management of the disease. Tumor biopsy being challenging for brain tumor
patients, non-invasive imaging techniques like Magnetic Resonance Imaging
(MRI) have been extensively employed in diagnosing brain tumors.
Therefore, automatic classification methods are essential to prevent the death rate
of human. It saves radiologist time and provides better accuracy.
Automated detection of tumor in MRI is very important as it provides information
about abnormal tissues which is necessary for planning treatment.
With the growth of Artificial Intelligence, Deep learning models are used to
diagnose the brain tumor by taking the images of magnetic resonance
imaging(MRI). MRI is a type of scanning method that uses strong magnetic fields
and radio waves to produce detailed images of the inner body.
Machine Learning algorithm based on Neural Network(CNN) is used to detect
brain tumor.

Introduction
Brain tumor is one of the most rigorous diseases in the medical science. An
effective and efficient analysis is always a key concern for the radiologist in the
premature phase of tumor growth. Histological grading, based on a stereotactic
biopsy test, is the gold standard and the convention for detecting the grade of a
brain tumor. The biopsy procedure requires the neurosurgeon to drill a small hole
into the skull from which the tissue is collected. There are many risk factors
involving the biopsy test, including bleeding from the tumor and brain causing
infection, seizures, severe migraine, stroke, coma and even death. But the main
concern with the stereotactic biopsy is that it is not 100% accurate which may
result in a serious diagnostic error followed by a wrong clinical management of the
disease. Tumor biopsy being challenging for brain tumor patients, non-invasive
imaging techniques like Magnetic Resonance Imaging (MRI) have been
extensively employed in diagnosing brain tumors. Therefore, development of
systems for the detection and prediction of the grade of tumors based on MRI data
has become necessary.
 Motivation
The main motivation behind Brain tumor detection is to not only detect tumor but
it can also classify types of tumor. So it can be useful in cases such as we have to
sure the tumor is positive or negative, it can detect tumor from image and return
the result tumor is positive or not. This project deals with such a system, which
uses computer, based procedures to detect tumor blocks and classify the type of
tumor using Convolution Neural Network Algorithm for MRI images of different
patients.
 Problem Statement
But at first sight of the imaging modality like in Magnetic Resonance Imaging
(MRI), the proper visualisation of the tumor cells and its differentiation with its
nearby soft tissues is somewhat difficult task which may be due to the presence of
low illumination in imaging modalities or its large presence of data or several
complexity and variance of tumors-like unstructured shape, viable size and
unpredictable locations of the tumor. Automated defect detection in medical
imaging using machine learning has become the emergent field in several medical
diagnostic applications. Its application in the detection of brain tumor in MRI is
very crucial as it provides information about abnormal tissues which is necessary
for planning treatment.Studies in the recent literature have also reported that
automatic computerized detection and diagnosis of the disease, based on medical
image analysis, could be a good alternative as it would save radiologist time and
also obtain a tested accuracy. Furthermore, if computer algorithms can provide
robust and quantitative measurements of tumor depiction, these automated
measurements will greatly aid in the clinical management of brain tumors by
freeing physicians from the burden of the manual depiction of tumors. The
machine learning based approaches like Deep ConvNets in radiology and other
medical science fields plays an important role to diagnose the disease in much
simpler way as never done before and hence providing a feasible alternative to
surgical biopsy for brain tumors . In this project, we attempted at detecting and
classifying the brain tumor and comparing the results of binary and multi class
classification of brain tumor with and without Transfer Learning (use of pre-
trained Keras models like VGG16, ResNet50 and Inception v3) using
Convolutional Neural Network (CNN) architecture.
 Purpose/Objectives and Goals

Automated defect detection in medical imaging using machine learning has

become the emergent field in several medical diagnostic applications. Its
application in the detection of brain tumor in MRI is very crucial as it provides
information about abnormal tissues which is necessary for planning treatment.For
easy use of the system, the project also provides Front End and Back end so that
Doctor can conveniently interact with the patient and also store his history.
• The main aim of the applications is tumor identification.
• The main reason behind the development of this application is to provide proper
treatment as soon as possible and protect the human life which is in danger.
• This application is helpful to doctors as well as patient.
• The manual identification is not so fast, more accurate and efficient for user. To
overcome those problem this application is design.
• It is user friendly application
 Literature Survey
Paper-1: Image Analysis for MRI Based Brain Tumor Detection and Feature
Extraction Using Biologically Inspired BWT and SVM
• Publication Year: 6 March 2017
• Author: Nilesh Bhaskarrao Bahadure, Arun Kumar Ray, and Har Pal Thethi
• Journal Name: Hindawi International Journal of Biomedical Imaging
• Summary: In this paper using MR images of the brain, we segmented brain
tissues into normal tissues such as white matter, gray matter, cerebrospinal fluid
(background), and tumor-infected tissues. We used pre-processing to improve the
signal-to-noise ratio and to eliminate the effect of unwanted noise. We can used the
skull stripping algorithm its based on threshold technique for improve the skull
stripping performance.

Paper-2: A Survey on Brain Tumor Detection Using Image Processing

Techniques
• Publication Year: 2017
• Author: Luxit Kapoor, Sanjeev Thakur
• Journal Name: IEEE 7th International Conference on Cloud Computing, Data
Science & Engineering
• Summary: This paper surveys the various techniques that are part of Medical
Image Processing and are prominently used in discovering brain tumors from MRI
Images. Based on that research this Paper was written listing the various
techniques in use. A brief description of each technique is also provided. Also of
All the various steps involved in the process of detecting Tumors, Segmentation is
the most significant.
Paper-3: Identification of Brain Tumor using Image Processing Techniques
• Publication Year: 11 September 2017
• Author: Praveen Gamage
• Journal Name: Research gate
• Summary: This paper survey of Identifying brain tumors through MRI images
can be categorized into four different sections; pre-processing, image
segmentation, Feature extraction and image classification.

Paper-4: Review of Brain Tumor Detection from MRI Images

• Publication Year: 2016
• Author: Deepa, Akansha Singh
• Journal Name: IEEE International Conference on Computing for Sustainable
Global Development
• Summary: In this paper, some of the recent research work done on the Brain
tumor detection and segmentation is reviewed. Different Techniques used by
various researchers to detect the brain Tumor from the MRI images are described.
By this review we found that automation of brain tumor detection and
Segmentation from the MRI images is one of the most active Research areas.

Paper-5: An efficient Brain Tumor Detection from MRI Images using Entropy
Measures
• Publication Year: December 23-25, 2016
• Author: Devendra Somwanshi , Ashutosh Kumar, Pratima Sharma, Deepika Joshi
• Journal Name: IEEE International Conference on Recent Advances and
Innovations in Engineering
• Summary: In this paper, we have investigated the different Entropy functions for
tumor segmentation and its detection from various MRI images. The different
threshold values are obtained depend on the particular definition of the entropy.
 Project Scope and Limitations
Project Scope
1. It is considered as the best ml technique for image classification due to high
accuracy.
2. Image pre-processing required is much less compared to other algorithms.
3. It is used over feed forward neural networks as it can be trained better in case of
complex images to have higher accuracies.
4. It reduces images to a form which is easier to process without losing features
which are critical for a good prediction by applying relevant filters and reusability
of weights
5. It can automatically learn to perform any task just by going through the training
data i.e. there no need for prior knowledge
6. There is no need for specialised hand-crafted image features like that in case of
SVM, Random Forest etc.

Limitations:
1. It requires a large training data.
2. It requires appropriate model.
3. It is time consuming.
4. It is a tedious and exhaustive procedure.
5. While convolutional networks have already existed for a long time, their success
was limited due to the size of the considered network.
Solution-Transfer Learning for inadequate data which will replace the last fully
connected layer with pre-trained ConvNet with new fully connected layer.
 Existing System and Limitations

There are several existing of techniques are available for brain tumor segmentation
and classification to detect the brain tumor. There are many techniques available
presents a study of existing techniques for brain tumor detection and their
advantages and limitations. To overcome these limitations, propose a Convolution
Neural Network (CNN) based classifier. CNN based classifier does the comparison
between trained and test data, from this to get the simplest result.
 Project Perspective

• To provide doctors good software to identify tumor and their causes.

• Save patient’s time.
• Provide a solution appropriately at early stages.
• Get timely consultation.

Features
• The website reduces the manual work to maintain record efficiency
• Save patient’s time.
• This web application is fully functional and flexible
• Easy to use because of the friendly Graphical User Interface.
 Requirement Analysis
Software Requirements:
 Windows: Python 3.6.2 or above, PIP and NumPy 1.13.1
 Python
 PIP: It is the package management system used to install and manage
software packages written in Python.
 NumPy: NumPy is a general-purpose array-processing package. It provides
a high performance multidimensional array object, and tools for working
with these arrays
 Anaconda: Anaconda is a free and open-source distribution of the Python
and R programming languages for scientific computing that aims to simplify
package management and deployment. Package versions are managed by the
package management system conda. The Anaconda distribution includes
data-science packages suitable for Windows, Linux, and macOS. Anaconda
distribution comes with 1,500 packages selected from PyPI as well as the
conda package and virtual environment manager. It also includes a GUI,
Anaconda Navigator, as a graphical alternative to the command-line
interface (CLI).
 Jupyter Notebook: Anaconda distribution comes with 1,500 packages
selected from PyPI as well as the conda package and virtual environment
manager. It also includes a GUI, Anaconda Navigator, as a graphical
alternative to the command line interface (CLI). A Jupyter Notebook
document is a JSON document, following a versioned schema, and
containing an ordered list of input/output cells which can contain code, text
mathematics, plots and rich media, usually ending with the “. Ipynb”
extension.
 Tensor Flow: Tensor flow is a free and open-source software library for
dataflow and differentiable programming across a range of tasks. It is a
symbolic math library, and is also used for machine learning applications
such as neural networks. It is used for both research and production at
Google. 31
 Keras: Keras is an open-source neural-network library written in Python. It
is capable of running on top of TensorFlow, Microsoft Cognitive Toolkit, R,
 Theano, or Plaid ML. Designed to enable fast experimentation with deep
neural networks, it focuses on being user-friendly, modular, and extensible.
Keras contains numerous implementations of commonly used neural-
network building blocks such as layers, objectives, activation functions,
optimizers, and a host of tools to make working with image and text data
easier to simplify the coding necessary for writing deep neural network
code.
 OpenCV: OpenCV (Open source computer vision) is a library of
programming functions mainly aimed at real-time computer vision.
Originally developed by Intel, it was later supported by willow garage then
Itseez (which was later acquired by Intel). The library is cross platform and
free for use under the open source BSD license. OpenCV supports some
models from deep learning frameworks like TensorFlow, Torch, PyTorch
(after converting to an ONNX model) and Caffe according to a defined list
of supported layers. It promotes Open Vision Capsules. Which is a portable
format, compatible with all other formats.

Hardware Requirements:
 Processor: Intel core i5 or above.
 64-bit, quad-core, 2.5 GHz minimum per core
 Ram: 4 GB or more
 Hard disk: 10 GB of available space or more.
 Display: Dual XGA (1024 x 768) or higher resolution monitors
 Operating system: Windows
 System Model : UML Diagrams

 Entity Relationship Diagram

 Class Diagram
 Use Case Diagram
 Activity Diagram :

Activity Diagram of System

 Activity Diagram

Activity Diagram of Doctor

 Sequence Diagram
 Deployment Diagram
 Data Model

Table Name : MRI Dataset

Sr.no Attribute Datatype Constraints Description
1 id int Primary key Image
Identifier
2 name Varchar(20) Not null MRI name
3 type Varchar(20) Not null Tumor type

Table Name : Training Dataset

Sr.no Attribute Datatype Constraints Description
1 id int Primary key Image
identifier
2 name Varchar(20) Not null MRI name
3 type Varchar(20) Not null Tumor type

Table Name : Testing Dataset

Sr.no Attribute Datatype Constraints Description
1 id int Primary key Image
identifier
2 name Varchar(20) Not null MRI name
3 type Varchar(20) Not null Tumor type
Table Name : CNN Model
Sr.no Attribute Datatype Constraints Description
1 id int Primary key Image
identifier
2 trainingimgid int Foreign key Training img
id identifier
3 testingimgid int Foreign key Testing img id
identifier
4 type Varchar(20) Not null Tumor type

Table Name : Database

Sr.no Attribute Datatype Constraints Description
1 Patient_id int Primary key Patient
identifier
2 name Varchar(20) Not null Patient name
3 email Varchar(20) Not null Patient email
4 contact Int(11) Not null Patient
contact no
5 type Varchar(20) Not null Tumor type
Table Name : Doctor
Sr.no Attribute Datatype Constraints Description
1 id int Primary key Dr identifier
2 name Varchar(20) Not null Dr name
3 email Varchar(20) Not null Dr email id
4 contact Int(11) Not null Dr contact no
 User Interface
Home page
Image Input by doctor:
Input Image:
Image Processing and Classified Result :
Image Processing and Classified Result :
 Implementation Details

Hardware Specifications:

 Hard Disk : 500GB and Above

 RAM : 4GB and Above
 Processor : I3 and Above
 Output Devices : Monitor,Printer

Software Requirements:

 Operating System : Windows 10 (64 bit)

 Software : Python
 Tools : Anaconda (Jupyter Note Book IDE)
 Web Browser : Chrome or any
 Outputs and Reports

The image data are added to the variable named data which is of ndarray datatype.
The class labels of the images are also generated and stored in the variable
data_target which is also an ndarray. The images are then added inside the
dataframe. The image dataset is divided into training, validation and testing
dataset. Figure 3 represents the accuracy and loss obtained when the CNN model is
applied on the training and validation dataset When CNN model is applied on the
training data for fifty epochs training accuracy obtained is 97.13% and a validation
accuracy of 71.51 %. The same when applied on the testing data gives 80.77%
accuracy.
 Testing
SYSTEM TESTING:
Web application should sustain to heavy load Web performance testing should
include web load testing
1. Web Application Testing Checklist
2. Functionality Testing
3. Usability Testing
4. Interface Testing
5. Compatibility Testing
6. Performance Testing
7. Security Testing

Web testing is software testing practice to test websites. By performing website

testing an organization can make sure that web-based system is functioning properly
and can be accepted by real-time users.

The UI design and functionality are the captions of website testing

1) Functional Testing:
Test for-all the links in web pages, database connection, forms used for
submitting or getting information from the user through web pages, cookies testing
etc.
a) Links
b) Internal Links
c) External Links
d) Mail Links
e) Forms
f) :Field validation
g) :Error message or wrong input
h) :Optional and mandatory fields
Database:
Testing will be done on database integrity.
2) Usability Testing:
It is process by which the human-computer interaction characteristics of a system
are measure, and weakness are identified for correction.
It included the following:
a) The website should be easy to use.
b) The instructions provided should be very clear.

3) Interface Testing:
In web testing, the server-side interface should be tested. This is done by that
communication is done properly. Compatibility of server with software, hardware,
network and database should be tested.
a) Web server and application server interface.
b) Application server and database server interface.

4) Compatibility Testing:
The compatibility of website is very important testing aspect. See which
compatibility test to be executed.
a) Browser compatibility.
b) Operating system compatibility.

5) Performance Testing:
The web application should sustain to heavy load. Web performance testing
should include.
Web load testing.
 Conclusion and Recommendation

Without pre-trained Keras model, the train accuracy is 97.5% and

validation accuracy is 90.0%.The validation result had a best figure of
91.09% as accuracy.It is observed that without using pre-trained Keras
model, although the training accuracy is >90%, the overall accuracy is low
unlike where pre-trained model is used.
Also, when we trained our dataset without Transfer learning, the
computation time was 40 min whereas when we used Transfer Learning, the
computation time was 20min. Hence, training and computation time with
pre-trained Keras model was 50% lesser than without.
Chances over over-fitting the dataset is higher when training the
model from scratch rather than using pre-trained Keras.Keras also provides
an easy interface for data augmentation.
Amongst the Keras models, it is seen that ResNet 50 has the best
overall accuracy as well as F1 score.ResNet is a powerful backbone model
that is used very frequently in many computer vision tasks.
Precision and Recall both cannot be improved as one comes at the
cost of the other .So, we use F1 score too.
Transfer learning can only be applied if low-level features from Task
1(image recognition) can be helpful for Task 2(radiology diagnosis).
For a large dataset, Dice loss is preferred over Accuracy.
For small size of data, we should use simple models, pool data, clean
up data, limit experimentation, use regularisation/model averaging
,confidence intervals and single number evaluation metric.
To avoid overfitting, we need to ensure we have plenty of testing and
validation of data i.e. dataset is not generalised. This is solved by Data
Augmentation. If the training accuracy too high, we can conclude that it the
model might be over fitting the dataset. To avoid this, we can monitor
testing accuracy, use outliers and noise, train longer, compare variance
(=train performance-test performance).
 Future Scope
Build an app-based user interface in hospitals which allows doctors to easily
determine the impact of tumor and suggest treatment accordingly
Since performance and complexity of ConvNets depend on the input data
representation we can try to predict the location as well as stage of the tumor from
Volume based 3D images. By creating three dimensional (3D) anatomical models
from individual patients, training, planning and computer guidance during surgery
is improved.
Using VolumeNet with LOPO (Leave-One-Patient-Out) scheme has proved to
give a high training as well as validation accuracy(>95%).In LOPO test scheme, in
each iteration, one patient is used for testing and remaining patients are used for
training the ConvNets, this iterates for each patient. Although LOPO test scheme is
computationally expensive, using this we can have more training data which is
required for ConvNets training. LOPO testing is robust and most applicable to our
application, where we get test result for each individual patient. So, if classifier
misclassifies a patient then we can further investigate it separately.
Improve testing accuracy and computation time by using classifier boosting
techniques like using more number images with more data augmentation, fine-
tuning hyper parameters, training for a longer time i.e. using more epochs, adding
more appropriate layers etc.. Classifier boosting is done by building a model from
the training data then creating a second model that attempts to correct the errors
from the first model for faster prognosis. Such techniques can be used to raise the
accuracy even higher and reach a level that will allow this tool to be a significant
asset to any medical facility dealing with brain tumors.
For more complex datasets, we can use U-Net architecture rather than CNN where
the max pooling layers are just replaced by upsampling ones.
Ultimately we would like to use very large and deep convolutional nets on video
sequences where the temporal structure provides very helpful information that is
missing or far less obvious in static images.
Unsupervised transfer learning may attract more and more attention in the future.
 Bibliography/References

Reference Books:
1. The hundred page Machine learning Book - Andriy Burkov
2. Machine learning for hackers - Drew Conway and John Myles White

Youtube Videos

Websites:
1. www.w3schools.com
2. www.geeksforgeeks.org