See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/341788500

Brain Tumor Detection Using Convolutional Neural Networks

Thesis · June 2020

DOI: 10.13140/RG.2.2.11250.12482/1

CITATION READS
1 1,054

1 author:

Varun Totakura
Guru Nanak Institutions
8 PUBLICATIONS   6 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

BRAIN TUMOR DETECTION USING CONVOLUTIONAL NEURAL NETWORKS View project

Deep Neural Networks View project

All content following this page was uploaded by Varun Totakura on 01 June 2020.

The user has requested enhancement of the downloaded file.

 A Major Project Report
on

BRAIN TUMOR DETECTION USING

CONVOLUTIONAL NEURAL NETWORKS

Submitted to the

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY - HYDERABAD

In partial fulfillment of the requirement for the award of the degree of

BACHELOR OF TECHNOLOGY

IN

COMPUTER SCIENCE AND ENGINEERING

BY

T. VARUN (16WJ1A05V2)

Under the Esteemed Guidance Of

Mr. V. Devasekhar

Associate Professor, HOD CSE-2

GURU NANAK INSTITUTIONS TECHNICAL CAMPUS (AUTONOMOUS)

School of Engineering and Technology

Ibrahimpatnam, R.R District 501506

2019-2020
 CERTIFICATE

This is to certify that this project report entitled “BRAIN TUMOR DETECTION USING
CONVOLUTIONAL NEURAL NETWORKS” by T. VARUN submitted in partial fulfillmentof
the requirements for the degree of Bachelor of Technology in Computer Science and
Engineering of the Jawaharlal Nehru Technological University Hyderabad during the
academic year 2019-2020, is a bonafide record of work carried out under our guidance and
supervision.

--------------------------- --------------------------

PROJECT CO-ORDINATOR INTERNAL GUIDE & HOD CSE

Mrs. V. Swathi Mr. V. Devasekhar

EXTERNAL EXAMINER
 ACKNOWLEDGEMENT

We wish to express our sincere thanks to Dr. Rishi Sayal, Associate Director, GNITC for
providing us with the conducive environment for carrying through our academic schedules and
Project with ease.

We have been truly blessed to have a wonderful adviser V. Devasekhar, Associate

Professor & HOD of CSE - 2, GNITC as our internal guide for guiding us to explore the
ramification of our work and we express our sincere gratitude towards him for leading me through
the completion of Project.

We especially thank our major project co-coordinator Mrs. V. Swathi, Associate

Professor, Department of CSE, for her suggestions and the constant guidance in every stage of the
project. Finally, we would like to thank our family members for their moral support and
encouragement to achieve goals.

T. VARUN (16WJ1A05V2)
 ABSTRACT

A human brain is centre of the nervous system; it is a collection of white mass of cells. A
tumor of brain is collection of uncontrolled increasing of these cells abnormally found in different
part of the brain namely Glial cells, neurons, lymphatic tissues, blood vessels, pituitary glands and
other part of brain which lead to the cancer. Cancer of Brain is of two types. Benign which is not
cancerous no danger at all, other one is Malignant which is cancerous tumor; it grows abnormally
by multiplying the cells rapidly, which leads to the death of the person if not detected. Manually
it is not so easily possible to detect and identify the tumor. Programming division method by MRI
is way to detect and identify the tumor. In order to give precise output a strong segmentation
method is needed.

Brain tumor identification is really challenging task in early stages of life. But now it
became advanced with various machine learning and deep learning algorithms. Now a day’s issue
of brain tumor automatic identification is of great interest. In Order to detect the brain tumor of a
patient we consider the data of patients like MRI images of a patient’s brain. Here our problem is
to identify whether tumor is present in patient’s brain or not. It is very important to detect the
tumors at starting level for a healthy life of a patient. There are many literatures on detecting these
kinds of brain tumors and improving the detection accuracies.

The segmentation, detection, and extraction of infected tumor area from magnetic
resonance (MR) images are a primary concern but a tedious and time taking task performed by
radiologists or clinical experts, and their accuracy depends on their experience only. So, the use of
computer aided technology becomes very necessary to overcome these limitations.

We estimate the brain tumor severity using Convolutional Neural Network algorithm
which gives us accurate results.

KEYWORDS:

Tumor Detection, Convolutional Neural Network, Gaussian Filters, MRI Images, Brain.

I
 TABLE OF CONTENTS

Contents Page No
Abstract……………………………………………………………………………. I
List of Figure………………………………………………………………………. V
List of Tables………………………………………………………………………. VI
1. INTRODUCTION 1
Introduction to Brain Tumor Detection Using Convolutional Neural
1.1 2
Networks

1.2 About the project 2

1.3 Problem Statement 4

1.4 Project Features 5

2. LITERATURE SURVEY 6
Brain Tumor Detection Based on Multimodal Information Fusion and
2.1 7
Convolutional Neural Network

2.2 Brain Tumor Detection Using Convolutional Neural Network 7

Classification of brain tumor types by deep learning with convolutional

2.3 neural network on magnetic resonance images using a developed web- 8
based interface
Brain Tumor Segmentation Using Deep Learning by Type Specific
2.4 9
Sorting of Images
High-Resolution Encoder–Decoder Networks for Low-Contrast
2.5 10
Medical Image Segmentation

3. SYSTEM ANALYSIS 11

3.1 Introduction 12
3.2 System Study 12

3.2.1 Existing system 12

II
 3.2.2 Proposed system 12

3.3 Feasibility Study 13

3.4 Objectives 14

3.5 Business System Options For Software 14

3.6 Business System Options For Hardware 14

3.7 Cost Benefit Analysis 14

4. SYSTEM REQUIREMENTS AND ANALYSIS 16

4.1 Introduction 17

4.2 Software Requirements 17

4.3 Hardware Requirements 17

5. SYSTEM DESIGN 19

5.1 Introduction 20
5.2 UML Diagrams 21
5.3 System Design 24

6. CODING 28

6.1 Introduction 29

6.2 Technologies used 29

6.3 Sample Code 33

7. TESTING 48

7.1 Introduction 49

7.2 Testing 50

7.3 Types of Testing 50

7.4 Software Maintenance 53

III
7.5 Test Cases and Results 54

8. IMPLEMENTATION 56

8.1 Introduction 57

8.2 Technologies used 57

8.3 Screen shots 58

9. CONCLUSION AND FUTURE ENHANCEMENT 62

9.1 Conclusion 63

9.2 Future scope and Enhancement 63

REFERENCES AND BIBLIOGRAPHY 64

IV
 LIST OF FIGURES

S.no. Fig. no. Title Page no.

Pre-processing Diagram for Brain Tumor Detection Using
1 5.a 20
Convolutional Neural Networks
System Architecture for Brain Tumor Detection Using
2 5.b 20
Convolutional Neural Networks
Use case Diagram for Brain Tumor Detection Using
3 5.1 21
Convolutional Neural Networks
Class Diagram for Brain Tumor Detection Using
4 5.2 22
Convolutional Neural Networks
Sequence Diagram for Brain Tumor Detection Using
5 5.3 22
Convolutional Neural Networks
Collaboration Diagram for Brain Tumor Detection Using
6 5.4 23
Convolutional Neural Networks

7 5.3.a Convolutional Neural Network 25

8 5.3.b Pooling in Convolutional Neural Network 25

9 5.3.c Pooling Concept 26

10 5.3.d Pooling Example 26

11 7.5.a CNN Model 54

12 7.5.b Dataset 55

13 7.5.c Result Graph 55

14 8.1 Screenshot of Index Page 58

15 8.2 Screenshot of Login Page 58
16 8.3 Screenshot of Signup Page 59
17 8.4 Screenshot of Home Page 59
18 8.5 Screenshot of Uploading and Predicting Page 60
19 8.6 Screenshot of Uploading 60
20 8.7 Screenshot of Upload Page 61
21 8.8 Screenshot of Prediction Page 61

V
 LIST OF TABLES

S.no Fig. no. Title Page no.

1 5.1 TABLE-NAME: Users 27
2 5.2 Table: Previous Methodologies Result 27

VI
 CHAPTER 1
INTRODUCTION

1
1.1 Introduction to Brain Tumor Detection using Convolutional Neural
Networks

With the improvement of modern medical standards, medical imaging technology plays
an increasingly important role in daily medical diagnosis and medical research. Therefore,
research on medical diagnostic image data is very important. As a tumor disease with frequent
occurrence and complexity, brain tumor has become a key research topic in the medical field.
The diagnosis of brain tumors is usually based on imaging data analysis of brain tumor images.
Accurate analysis of brain tumor images is a key step in determining a patient's condition.
However, the accumulation of doctors' personal medical knowledge, differences in experience
levels, and visual fatigue can affect the correct analysis of image results. Therefore, how to
accurately detect brain tumor images is very important. Magnetic Resonance Imaging (MRI) can
provide information on the shape, size, and position of human tissues and organs without high
ionizing radiation. The images obtained are very clear and precise. MRI greatly improves the
diagnostic efficiency, avoids the operation of thoracotomy or laparotomy exploration, and
provides a good guide for lesion localization and surgical treatment. Brain tumor MRI uses three-
dimensional multi-band imaging technology, and chest X-ray scanning, etc. Compared with 2D
images, 3D multiband MRI can provide the coordinate position of the lesion area to assist the
doctor to accurately locate the lesion area. In addition, MRI imaging can also obtain different
structures of the same tissue using the unused development sequence. That is, a multimodal MRI
image. Different modes can display different brain tumor features.

1.2 About the Project

A brain tumor is defined as abnormal growth of cells within the brain or central spinal
canal. Some tumors can be cancerous thus they need to be detected and cured in time. The exact
cause of brain tumors is not clear and neither is exact set of symptoms defined, thus, people may
be suffering from it without realizing the danger.Primary brain tumors can be either malignant
(contain cancer cells) or benign (do not contain cancer cells).

Brain tumor occurred when the cells were dividing and growing abnormally. It is appearing
to be a solid mass when it diagnosed with diagnostic medical imaging techniques. There are two
types of brain tumor which is primary brain tumor and metastatic brain tumor. Primary brain tumor
is the condition when the tumor is formed in the brain and tended to stay there while the metastatic
brain tumor is the tumor that is formed elsewhere in the body and spread through the brain.

2
 The symptom having of brain tumor depends on the location, size and type of the tumor. It
occurs when the tumor compressing the surrounding cells and gives out pressure. Besides, it is
also occurring when the tumor blocks the fluid that flows throughout the brain. The common
symptoms are having headache, nausea and vomiting, and having problem in balancing and
walking. Brain tumor can be detected by the diagnostic imaging modalities such as CT scan and
MRI. Both of the modalities have advantages in detecting depending on the location type and the
purpose of examination needed. In this paper, we prefer to use the CT images because it is easy to
examine and gives out accurate calcification and foreign mass location.

The CT image acquired from the CT machine give two-dimension cross sectional of brain.
However, the image acquired did not extract the tumor from the image. Thus, the image processing
is needed to determine the severity of the tumor depends on the size.

The reasons for selecting CT images upon MRI images are as follows:

1. CT is much faster than MRI, making it the study of choice in cases of trauma and other
acute neurological emergencies. CT can be obtained at considerably less cost than MRI.
2. CT can be obtained at considerably less cost than MRI.
3. CT is less sensitive to patient motion during the examination.
4. The imaging can be performed much more rapidly, so CT may be easier to perform in
claustrophobic or very heavy patients.
5. CT can be performed at no risk to the patient with implantable medical devices, such as
cardiac pacemakers, ferromagnetic vascular clips and nerve stimulators.

The focus of this project is CT brain images’ tumor extraction and its representation in
simpler form such that it is understandable by everyone. Humans tend to understand colored
images better than black and white images, thus, we are using colors to make the representation
simpler enough to be understood by the patient along with the medical staff. Contour plot and c-
label of tumor and its boundary is programmed to give 3D visualization from 2D image using
different colors for different levels of intensity. A user-friendly GUI is also created which helps
medical staff to attain the above objective without getting into the code.

What can you do in a Web Application integrated with Deep Learning Model?

● Analyse data collected from distributed users across country or world

● Display reports in Graphical Form

3
 ● Produce Estimates - You gain details of what they are interested. You are available
24/7

● Deliver News about the Tumor and nearest Hospital Information

● Provide information online

Advantages of Web Applications integrated with Deep Learning Model:

Web Applications integrated with Deep Learning Model deliver many hospital benefits
compared to hospital based solutions.

● Zero Install – all PCs have a browser

● Reduce Hospital costs – less money spent on consulting the doctors.

● It is easy to backup.

● Quick and easy updates.

● Reach anybody, anywhere in the world.

● Available 24 hours a day, 7 days a week.

● Direct access to latest information.

1.3 PROBLEM STATEMENT

The aim of the paper is tumor identification in brain CT images. The main reason for
detection of brain tumors is to provide aid to clinical diagnosis. The aim is to provide an algorithm
that guarantees the presence of a tumor by combining several procedures to provide a foolproof
method of tumor detection in CT brain images. The methods utilized are filtering, contrast
adjustment, negation of an image, image subtraction, erosion, dilation, threshold, and outlining of
the tumor.

The focus of this project is CT brain images’ tumor extraction and its representation in
simpler form such that it is understandable by everyone. Humans tend to understand colored
images better than black and white images, thus, we are using colors to make the representation
simpler enough to be understood by the patient along with the medical staff.

The objective of this work is to bring some useful information in simpler form in front of
the users, especially for the medical staff treating the patient. Aim of this paper is to define an
algorithm that will result in extracted image of the tumor from the CT brain image. The resultant
4
image will be able to provide information like size, dimension and position of the tumor, plotting
contour and c-label of the tumor and its boundary provides us with information related to the tumor
that can prove useful for various cases, which will provide a better base for the staff to decide the
curing procedure.

1.4 SCOPE

The website is developed for real life application. The aim of our project is to present an
optimized design, accurate results and experience to the users for their doubts on the brain tumor.
Through User Experience, we seek to engaging interactions between users and systems, thus we
provide accurate information. Through User Interface, easy and efficient interaction of the user
with the information device is achieved. This includes display screens, appearance of the desktop.
The growing dependence of many companies on when applications and mobile applications has
led many conferences to place increased priority on digital platform in an effort to improve the
user’s overall experience. The site will help to estimate the benefits and calculate the requirements
very easily. The benefits will be in terms of speedy query, smooth and faster operations at all
levels.

1.5 PROJECT FEATURES

Web Applicationintegrated with Deep Learning Model directs you to the homepage where
there is an option to upload the CT scan image to the website and the same image is given as feed
to the trained Convolutional Deep Learning Neural Network to predict the classification of the
image. New users can also use the website by providing appropriate information and already tumor
confirmed user will get the notifications from the hospital to get treatment. The user information
is collected to inform the nearest hospitals for the further treatment.

5
 CHAPTER 2

LITERATURE SURVEY

6
2.1 LITERATURE SURVEY

1. Paper Title: Brain Tumor Detection Based on Multimodal Information Fusion and
Convolutional Neural Network.
Authors: Ming Li, Lishan Kuang, Shuhua Xu, and Zhanguo Sha
About the paper:
In this paper, a method with three-dimensional MRI brain tumor detection
combining multimodal information fusion and CNN is proposed. Firstly, it is better to use
the improved multimodal 3D-CNNs to obtain the three-dimensional features of brain tumor
lesions under different modalities. Extract the difference information between the various
modes. Secondly, in order to solve the problem that the network convergence is slow and
the over-fitting is serious, the brain tumor characteristic data is normalized. Then,
according to the small volume of the lesion area and the large volume of the non-focal area,
a new weighted loss function is constructed to weaken the interference of the non-focal
area on the detection of brain tumors, and the loss function can be improved to reduce the
detection of brain tumors in non-focal areas. The experimental results show that the three
evaluation indexes of dice, SN and SE are optimized respectively, and the two-dimensional
brain tumor detection network and the original single-mode brain tumor detection method
are compared. There has been a big improvement.

2. Paper Title: Brain Tumor Detection Using Convolutional Neural Network

Authors: Tonmoy Hossain, Fairuz Shadmani Shishir, Mohsena Ashraf, MD Abdullah Al
Nasim, Faisal Muhammad Shah
About the paper:
Image segmentation plays a significant role in medical image processing as medical
images have different diversities. For brain tumor segmentation, they have used MRI and
CT scan images. MRI is most vastly used for brain tumor segmentation and classification.
In their work, they have used Fuzzy C-Means clustering for tumor segmentation which can
predict tumor cells accurately. The segmentation process was followed by classification
using traditional classifiers and Convolutional Neural Network. In the traditional classifier
part, they have applied and compared the results of different traditional classifiers such as
K-Nearest Neighbor, Logistic Regression, Multilayer Perceptron, Naïve Bayes, Random
Forest, and Support Vector Machine. Among these traditional ones, SVM gave us the
highest accuracy of 92.42%. Further, for better results, they have implemented CNN which
7
 brought in the accuracy 97.87% with a split ratio of 80:20 of 217 images, i.e. 80% of
training images and 20% of testing images. In the future, they have planned to work with
3D brain images, achieve more efficient brain tumor segmentation. Working with a larger
dataset will be more challenging in this aspect, and they have wanted to build a dataset
emphasizing the abstract with respect to their country which will accelerate the scope of
their work.

3. Paper Title:Classification of brain tumor types by deep learning with convolutional neural
network on magnetic resonance images using a developed web-based interface
Authors: Hasan Ucuzal, Şeyma YAŞAR, Cemil Çolak
About the paper:
The aim of this study is to develop web-based software that can classify brain
tumors (glioma, meningioma, pituitary) based on high-precision T1 contrast magnetic
resonance images using convolutional neural network from deep learning algorithm.
Thanks to the free web-based software developed, it is believed that medical professionals
and other health professionals can classify brain tumors faster and more accurately. In this
aspect, the software can be used as a clinical decision support system in the classification
of brain tumor types (i.e., glioma, meningioma, pituitary). According to the experimental
results, all the calculated performance metrics are higher than 98% for classifying the types
of brain tumors on the training dataset. Similarly, all the performance metrics are higher
than 91% except for sensitivity and MCC performance metrics for meningioma brain tumor
on the testing dataset. When considering the calculated performance metrics from the CNN
model on the training and testing stages, the proposed model is successfully capable of
classifying brain tumor types. A recent study has developed a deep learning system
established on CNN for classifying brain tumors on public data sets, containing 233 and
73 patients with a total of 3064 and 516 images on T1-weighted contrast-enhanced
magnetic resonance images. The developed system in the study realizes a important
performance with the best total accuracy rates of 96.13% and 98.7% for the two datasets,
respectively and can successfully classify for brain tumor multi-classification tasks. In
another article, a new deep learning algorithm has been constructed for classifying brain
tumors into grade I, grade II, grade III and grade IV on the CNN deep learning algorithm.
The new deep learning algorithm consists of three stages: tumor segmentation, data
augmentation and deep features extraction/classification. Experimental results in the

8
 studied paper point out that the proposed algorithm has better performance than the present
methods when it is applied to the augmented and original datasets. Machine learning and
deep learning algorithms have been reported to perform well in the classification and
prediction of T1-weighted magnetic resonance images of brain tumors in the previous
studies. However, when considering the machine learning/data mining applications of the
reported studies in recent years, the selection and creation of these algorithms may require
a lot of time and experience. Therefore, automatic machine learning and different modeling
systems have been commonly developed in recent years. In a nutshell, the current study
presents novel public web-based software for classifying the types of brain tumors based
on T1-weighted MR image scans by CNN algorithm of deep learning. In the following
stages, it is envisaged to develop a system that can classify data sets containing brain
images of healthy individuals in addition to the images of the brain tumors of patients
examined in this study.

4. Paper Title:Brain Tumor Segmentation Using Deep Learning by Type Specific Sorting of
Images
Authors: Zahra Sobhaninia, Safiyeh Rezaei, Alireza Noroozi, Mehdi Ahmadi, Hamidreza
Zarrabi, Nader Karimi, Ali Emami, Shadrokh Samavi
About the paper:
In this paper, they have introduced a new method for CNN to automatically
segmenting the most common types of brain tumor, i.e. the Glioma, Meningioma, and
Pituitary. This technique does not require preprocessing steps. The results show that the
separation of images based on angles improves segmentation accuracy. The best Dice score
that was obtained is 0.79. This relatively high score was obtained from segmentation of
tumors in sagittal view images. Sagittal images do not contain details of other organs and
tumor is more prominent than other images. The lowest Dice score in their experiments
was 0.71 which is related to the images from the axial view of the head. As compared to
other images, axial view contains fewer details. It is expected that by performing
preprocessing on this group of images better classification of tumor pixels could be
obtained and the Dice score will increase. Their proposed method may be implemented as
a simple and useful tool for doctors in segmenting of brain tumor in MR images.

9
5. Paper Title:High-Resolution Encoder–Decoder Networks for Low-Contrast Medical
Image Segmentation
Authors: Ming Sihang Zhou, Dong Nie, Ehsan Adeli , Member, IEEE, Jianping Yin
About the paper:
In this paper, they have proposed a high-resolution multi-scale encoder-decoder
network (HMEDN) to segment medical images, especially for the challenging cases with
blurry and vanishing boundaries caused by low tissue contrast. In this network, three
kinds of pathways (i.e., skip connections, distilling pathways, and high-resolution
pathways) were integrated to extract meaningful features that capture accurate location
and semantic information. Specifically, in the distilling pathway, both U-Net structure
and HED structure were utilized to capture comprehensive multi-scale information. In
the high resolution pathway, the densely connected residual dilated blocks were adopted
to extract location accurate semantic information for the vague boundary localization.
Moreover, to further improve the boundary localization accuracy and the performance of
the network on the relatively “hard” regions, they have added a contour regression task
and a difficulty-guided cross entropy loss to the network. Extensive experiments
indicated the superior performance and good generality of their designed network.
Through the experiments, they have made several observations: (1) Skip connections,
which are usually adopted in the encoder-decoder networks, are not enough for detecting
the blurry and vanishing boundaries in medical images. (2) Finding a good balance
between semantic feature resolution and the network complexity is an important factor
for the segmentation performance, especially when small and complicated structures are
being segmented in blurry images. Observing the failed samples of their algorithm, they
have found that the algorithm fails in cases where the boundaries are totally invisible due
to significant amounts of noise incurred by low dose, metal, and motion artifacts, and so
forth. To solve these problems, in the future they have will combine their algorithm with
shape-based segmentation methods and incorporate more robust shape and structural
information of target organs.

10
 CHAPTER 3
SYSTEM ANALYSIS

11
3.1 INTRODUCTION

System analysis refers to analyzing the project hardware and software requirements. It is
often done for Diagnostic or troubleshooting purposes. running a system analysis can also be
helpful when determining if the project means all the desired requirements.

3.2 SYSTEM STUDY

In system study we will go to existing system, proposed system and feasibility study of
the application.

3.2.1 EXISTING SYSTEM AND DRAWBACKS:

There are websites for the brain tumor detection applications which provide details about
the brain tumor, but in those the user cannot register his problem so that the nearby doctors would
approach him in some or the other way. A person who wants to attend the hospital for the brain
tumortreatment has to go and visit only that particular hospital place physically. This makes him
a main problem to travel again and again.

The existing applications mainly focus on information displaying about the brain tumor
and display the details of the hospitals. Most of the applications available provide information only
about the problem, there is no classified information about the detection without visiting the
hospital.

3.2.2 PROPOSED SYSTEM AND ADVANTAGES:

The developed application is very simple and easy to handle and the user can view all the
details about the hospitals and check whether he has brain tumor or not which makes it easy for
the user to make a quick decision. Scope limitations are restricted in some of the hospitals which
can be displayed clearly and the patients or the users can book the appointment date and time slots
as per their availability and can also provide their details prior. Everything is available at the
fingertips for the user with minimal selections.

The application gain popularity not only by the way it looks but also the way it feels and
our project makes the most use of it, since it is based on Convolutional Deep Learning Neural
Networks.

The proposed system has following advantages:

12
 ● Displaying of the information and highlighting the key points which makes the
huge difference with other websites.

● To serve the patient with best possible quality and maximum facilities with less price.

● Honour suggestions from doctors.

● Process complete backup services.

● Ensures safety of user data.

● Ensures user satisfaction.

3.3 FEASIBILITY STUDY

The feasibility study is a formal proposal for a new system. Before the project is to be
begin, the project is study to determine what exactly the user wants depending upon the result of
the initial investigation. The server is expanded to more detailed study. Feasibility study can be
understood by giving the answer solution of these their requirements.

What are the user’s demonstrable needs and how does the candidate system meet them?

A new system covers all the basic of the user for e.g, as mentioned earlier that our
database is MS Access, which does not have any limitation to store data. And one of the major
advantages of new system is that it avoids redundancy means there is no repetition of the data.

A feasibility analysis involves a detailed assessment of the need, value and practicality of
a proposed enterprise such as systems development. The process of designing and implementing
Record Keeping system has sufficient accountability and resource implications for an
organisation. Feasibility analysis will help you make inform and transparent decisions at crucial
points during the development process to determine whether it is operational economical and
technically realistic to produce with a particular course of action. What resources are available for
given candidate system? is a problem worth solving? in the existing system the Opera or has to
learn all the operations of the command whichever is coming in light while operating a particular
form then one help called tooltip will come if the mouse comes on corresponding field of particular
form.

The new system is well fitted in the office working condition, because it covers all basic
needs of the user working in the office full stop it is less tedious and less time consuming.

FEASIBILITY REPORT
13
 The feasibility report is a formal document for management use, brief enough and
sufficiently non-technical to be understandable, yet detailed enough to provide the basic for
system design. There is no standard format for preparing feasibility report. Analyst usually
decide on a format that shoots a particular user and the system.

3.4 OBJECTIVES

A web platform for the Brain tumor detection using Convolutional Neural Networks has the
following objectives:

A. To serve its users with best possible quality and provide the maximum facilities with
less price.

B. To serve and take well care of our user/patient.

C. Ensure user satisfaction.

D. Honour suggestions from doctors or users.

E. Possess complete backup services.

3.5 BUSINESS SYSTEM OPTIONS FOR SOFTWARE

● Windows 10 or above/ MAC OS X

● Tomcat server

● MySQL workbench/ phpMyAdmin

● Brackets/Sublime Text

3.6 BUSINESS SYSTEM OPTIONS FOR HARDWARE

● Intel core i3

● 50GB Hard Disk

● 4GB RAM

● Keyboard

● Mouse

3.7 COST BENEFIT ANALYSIS

14
 Cost Benefit Analysis can be explained as a procedure for estimating all costs involved and
possible profits to be derived from a business opportunity or proposal. It takes into account both
quantitative and qualitative factors for analysis of the value for money for a particular project or
investment opportunity. Benefits to costs ratio and other indicators are used to conduct such
analyses. The objective is to ascertain the soundness of any investment opportunity and provide a
basis for making comparisons with other such proposals. All positives and negatives of the project
are first quantified in monetary terms and then adjusted for their time-value to obtain correct
estimates for conduct of cost-benefit analysis. Most economists also account for opportunity costs
of the investment in the project to get the costs involved.

In the economic feasibility, the development cost of creating the system is evaluated
against the ultimate benefit derived from the new systems. Financial benefits must equal or exceed
the costs. The system is economically feasible because it does not require any addition hardware
or software resources. Since the interface for this system is developed using the existing resources
and technologies that are available, there is a nominal expenditure and it is economically feasible.

15
 CHAPTER 4
SYSTEM REQUIREMENTS

16
4.1 INTRODUCTION:

To be used efficiently, all computer software needs certain hardware components or other
software resources to be present on a computer. these prerequisites are known as(computer) system
requirements and are often used as a guideline as opposed to an absolute rule. Most software
defines two sets of system requirements: minimum and recommended. With increasing demand
for higher processing power and resources in newer versions of software. System requirements
tend to increase over time. Industry analysts suggest that this trend plays a bigger part in driving
upgrades to existing computer systems than technological advancements. A second meaning of the
term of System requirements, is a generalisation of this first definition, giving the requirements to
be met in the design of the system or subsystem. Typically, an organisation starts with a set of
business requirements and then derives the system requirements from there.

4.2 SOFTWARE REQUIREMENTS

1. Software requirements is a field within software engineering that deals with establishing
the needs of stakeholders that are to be solved by software. The IEEE standard Glossary of
software engineering Technology defines a software requirement as A condition or
capability needed by a user to solve a problem or achieve an objective.

2. A condition or capability that must be met or possessed by a system or system component

to satisfy a contract, standard, specification or other formally imposed document

3. A documented representation of a condition or capability as in 1 or 2

FRONT END : HTML, CSS, PHP, Python

BACK END : MySQL

OPERATING SYSTEM : WINDOWS 7 or above, MAC OS X

IDE : SUBLIME TEXT

4.3 HARDWARE REQUIREMENTS

The most common set of requirements defined by any operating system or software
application is the physical computer resources, also known as hardware. A hardware requirements
list is often accompanied by a hardware compatibility list (HCL), especially in case of operating
systems. An HCL list tested, compatible, and sometimes incompatible hardware devices for a
particular system or application.

17
PROCESSOR : Intel Core i5

RAM : 4 GB DD RAM

HARD DISK : 128 GB or above

18
 CHAPTER 5
SYSTEM DESIGN

19
5.1 INTRODUCTION

System design is the process of defining the architecture, components, modules,

interfaces, and data for a system to satisfy specifies requirements. System design could be as
seen as the application of systems theory to product development. It is about the physical
organisation of the system. It is demonstrated with the help of UML Diagram or block
Diagrams etc. it is explained in a pictorial representation.

Figure 5.a: Pre-processing

Figure 5.b: System Architecture

5.2 UML Diagrams

20
 The Unified Modelling Language (UML) is a general-purpose modelling language in the
field of software engineering, which is designed to provide a standard way to visualize the design
of a system. The Unified Modelling Language (UML) offers a way to visualize a system’s
architectural blueprints in a Diagram.

5.1 Use case Diagram for Brain Tumor Detection Using Convolutional Neural Networks

Fig 5.1 Use case Diagram for Brain Tumor Detection Using Convolutional Neural Networks

A use case Diagram at its simplest is a representation of a user’s interaction with the
system that shows the relationship between the user and the different use cases in which the
user is involved. A use case Diagram can identify the different types of users of a system and
the different use cases and will often be accompanied by other types of Diagrams as well.

5.2 Class Diagram for Brain Tumor Detection Using Convolutional Neural Networks

21
 Fig: 5.2 Class Diagram for Brain Tumor Detection Using Convolutional Neural Networks

A class Diagram in the Unified Modelling language(UML) is a type of static structure

Diagram that describes the structure of a system by showing the system’s classes, their
attributes, operations (or methods), and the relationships among objects.

5.3 Sequence Diagram for Brain Tumor Detection Using Convolutional Neural Networks

Fig: 5.3 Sequence Diagram for Brain Tumor Detection Using Convolutional Neural Networks

22
 A sequence Diagram shows object interactions arranged in time sequence. It depicts the
objects and classes involved in the scenario and the sequence of messages exchanged between
the objects needed to carry out the functionality of the scenario. Sequence Diagrams are
typically associated with use case realizations in the Logical View of the system under
development. Sequence Diagrams are sometimes called event Diagrams or event scenarios.

5.4 Collaboration Diagram for Brain Tumor Detection Using Convolutional Neural
Networks

Fig: 5.4Collaboration Diagram for Brain Tumor Detection Using Convolutional Neural
Networks

A Collaboration Diagram is also called as communication Diagram. A Communication

Diagram models the interactions between objects or parts in terms of sequenced messages.
Communication Diagrams represent a combination of information taken from Class, Sequence,
and Use Case Diagrams describing both the static structure and dynamic behavior of a system.

23
5.3 SYSTEM DESIGN

Database design is the organization of data according to the database model. The designer
determines what data must be stored and how the data elements interrelate. With this information
we can fit the data into the database. It involves classifying data and identifying the
interrelationships. It basically involves tables: lists of rows and columns. Each row is more
correctly called a record and each column a field. A record is a meaningful and consistent way to
combine information about something. A field is a single term of information- an item type that
appears in every record. A key is a set of columns that is used to uniquely identify a record in a
table. It is used to fetch or retrieve records/ data-rows from data table.

Certain principles guide the database design process. The design process consists of the
following steps:

● Determining the purpose of the database

● Find and organize the information required

● Divide the information into tables

● Turn information items into columns

● Specify primary keys

● Set up the table relationships

● Refine your design

● Apply the normalization rules

A good database design is therefore the one that,

● Divides the information into subject-based tables to reduce redundant data.

● Provides access with the information it requires to join the information in the tables
together as needed.

● Helps support and ensure the accuracy and integrity of the information.

● Accommodates the data processing and reporting needs.

24
 Figure 5.3.a: Convolutional Neural Network

Figure 5.3.b: Pooling in Convolutional Neural Network

Figure 5.3.c: Pooling Concept

25
 Figure 5.3.d: Pooling Example

MySQL:

MySQL is a freely available open source Relational Database management System

(RDBMS) that uses Structured Query Language (SQL). Its name is a combination of “My”, the
name of co-founder Michael Windenius’s daughter, and SQL. MySQL was owned and sponsored
by a single for-profit firm, the Swedish company MySQL AB, now owned by Oracle Corporation.
The first version of MySQL appeared on 23 May 1995. MySQL is written in C and C++.

SQL is the most popular language for adding, accessing and managing content in a
database. It is most noted for its quick processing, proven reliability, ease and flexibility of use.
MySQL is an essential part of almost every open source PHP application. Good examples for PHP
and MySQL-based scripts are WordPress, Joomla, Magento and Drupal.

The MySQL development project has made its source code available under the terms of
the GNU General Public License, as well as under a variety of proprietary agreements. MySQL
was owned and sponsored by a single for-profit firm, the Swedish company MySQL AB, now
owned by Oracle Corporation.

MySQL is a popular choice of database for use in web applications, and is a central
component of the widely used LAMP open source web application software stack. LAMP is an
acronym for "Linux, Apache, MySQL, Perl/PHP/Python." Free-software-open source projects
that require a full-featured database management system often use MySQL.

For proprietary use, several paid editions are available, and offer additional functionality.
Applications which use MySQL databases include: TYPO3, MODx, Joomla, WordPress,

26
phpBB, MyBB, Drupal and other software. MySQL is also used in many high-profile, large-
scale websites, including Google, Facebook, Twitter, Flickr, and YouTube.

5.1 TABLE-NAME: Users

5.1 Table - Users

In the Users table we have created 4 columns in the name of user_id, user_name,
user_email, user_password which is required for the admin to know and analyze the no. of users
and specific details.

5.2 TABLE: Previous Methodologies Result

Paper Model Name Accuracy

Gurbin et al. [1] Support Vector Machine Avg. 92%

Seetha et al. [8] Fuzzy C Means 97.5%

Detection using
Usman et al. [9] 97%
Segmentation

Convolutional Neural
Hossain et al. [5] 97.87%
Network

Table 5.2: Previous Methodologies Result

In the above mentioned table previous methodologies along with the accuracy of their
model has been displayed clearly.

27
CHAPTER 6
CODING

28
6.1 INTRODUCTION

Coding and Programming is used for solving problems in efficient manner. Every
human brain performs some kind of coding and programming inside brain, for doing day to
day tasks. Using same approach human developed programming.

Hence, coding is the primary method for allowing intercommunication between

humans and machines and professionals have established many more conventions and
strategies for computer coding in order to make finished products more stable and functional.

Some parts of code which is used in the development of the project are shown in the
next part of this chapter.

6.2 LANGUAGES USED

a. PYTHON

Python is an interpreted, high-level, general-purpose programming language. Created

by Guido van Rossum and first released in 1991, Python's design philosophy emphasizes code
readability with its notable use of significant whitespace. Its language constructs and object-
oriented approach aim to help programmers write clear, logical code for small and large-scale
projects. Python is dynamically typed and garbage-collected. It supports multiple programming
paradigms, including procedural, object-oriented, and functional programming. Python is often
described as a "batteries included" language due to its comprehensive standard library. Python
was conceived in the late 1980s as a successor to the ABC language. Python 2.0, released in
2000, introduced features like list comprehensions and a garbage collection system capable of
collecting reference cycles. Python 3.0, released in 2008, was a major revision of the language
that is not completely backward-compatible, and much Python 2 code does not run unmodified
on Python 3.

Machine learning is a type of artificial intelligence (AI) that provides computers with
the ability to learn without being explicitly programmed. Machine learning focuses on the
development of Computer Programs that can change when exposed to new data. In this article,
we’ll see basics of Machine Learning, and implementation of a simple machine learning
algorithm using python.Python community has developed many modules to help programmers
implement machine learning. In this article, we will be using numpy, scipy and scikit-learn

29
modules.Machine learning involves a computer to be trained using a given data set, and use
this training to predict the properties of a given new data. For example, we can train a computer
by feeding it 1000 images of cats and 1000 more images which are not of a cat, and tell each
time to the computer whether a picture is cat or not. Then if we show the computer a new
image, then from the above training, the computer should be able to tell whether this new image
is a cat or not. The process of training and prediction involves the use of specialized algorithms.
We feed the training data to an algorithm, and the algorithm uses this training data to give
predictions on a new test data. One such algorithm is K-Nearest-Neighbor classification (KNN
classification). It takes a test data, and finds k nearest data values to this data from test data set.
Then it selects the neighbor of maximum frequency and gives its properties as the prediction
result.

Deep structured learning or hierarchical learning or deep learning in short is part of the
family of machine learning methods which are themselves a subset of the broader field of
Artificial Intelligence.

Deep learning is a class of machine learning algorithms that use several layers of nonlinear
processing units for feature extraction and transformation. Each successive layer uses the
output from the previous layer as input.

Deep neural networks, deep belief networks and recurrent neural networks have been applied
to fields such as computer vision, speech recognition, natural language processing, audio
recognition, social network filtering, machine translation, and bioinformatics where they
produced results comparable to and in some cases better than human experts have.

Deep Learning Algorithms and Networks −

 are based on the unsupervised learning of multiple levels of features or representations

of the data. Higher-level features are derived from lower level features to form a
hierarchical representation.

 use some form of gradient descent for training.

b. HTML

Hypertext Markup Language is a markup language that web browsers use to interpret
and compose text, images and other material into visual or audible web pages. It is a standard
markup language used for creating web pages and web applications. HTML was created by
Berners-Lee in late 1991 but "HTML 2.0" was the first standard HTML specification which

30
was published in 1995. HTML 4.01 was a major version of HTML and it was published in late
1999. Though HTML 4.01 version is widely used but in 2004, development began on HTML%
in the Web Hypertext Application Technology Working Group(WHATWG), which became a
joint deliverable with the W3C in 2008, and completed and standardized on 28 October 2014.

HTML elements are the building blocks of HTML pages. With HTML constructs,
images and other objects such as interactive forms may be embedded. HTML elements are
delineated by tags, written using angle brackets. HTML can embed programs written in
scripting language such as JavaScript, which affects the behaviour and content of web pages.
Inclusion of CSS defines the look and layout of content.

HTML defines several data types for element content, such as script data and stylesheet
data, and a plethora of types for attribute values, including IDs, names, URIs, numbers and
many more. These datatypes are specializations of character data. HTML documents can be
delivered by the same means as any other computer file. They are most often delivered either
by HTTP from a web server or by an email.

HTML is widely used because it is easy to learn. Every browser supports HTML
language. So it can be said that it is because of HTML that web pages are interesting to look
at. But with HTML we can only create structure of the web page, to design it we need to learn
another language called “CSS” which stands for Cascading Style Sheets means to style and
design the web-page. With Cascading Style Sheets (CSS) and JavaScript, it forms a triad of
cornerstone technologies for the World Wide Web.

c. CSS

Cascading Style Sheets (CSS) are used to format the layout of the web pages. CSS was
first proposed by Hakon Wium Lie on October 10, 1994. CSS has various levels and profiles.
Each level of CSS builds upon the last, typically adding new features and denoted as CSS 1,
CSS 2, CSS 3 CSS 4.

CSS goes hand in hand with HTML to display the website the way it is intended to be
displayed. They can be used to define the text styles, table sizes, and other aspects of web pages
that previously could only be defined in a page’s HTML. CSS helps web developers create a
uniform look across several pages of a website. Instead of defining the style of each table
commonly used styles need to be defined only once in a CSS document. While CSS is great

31
forcreating text styles, it is helpful for formatting other aspects of web page layout like cell
padding of table cells, style, thickness.

CSS is designed to enable the separation of presentation and content, including layout,
colors, fonts. This separation can improve content accessibility, provide more flexibility and
control in the specification of presentation characteristics, enable multiple web pages to share
formatting by specifying the relevant CSS in a separate file and reduce complexity. This makes
it feasible to present the same markup page in different styles for different rendering methods,
such as on-screen, in print, by voice and on Braille-based tactile devices.

d. BOOTSTRAP

Bootstrap is a free and open-source front-end framework for designing websites and
web applications. It contains HTML and CSS based design templates for typography, forms,
buttons, navigation and other interface components. It concerns itself with front-end
development only. Bootstrap, originally named Twitter Blueprint, was developed by Nirav
Panchal and Jacob Thornton at Twitter as a framework to encourage consistency across internal
tools. It was released as an open source project n August 19,2011. The stable version of
Bootstrap 4 was released on January 18, 2018 basically improving print styles, border utilities
and provides more control over flexbox.

e. PHP

PHP (Hypertext Preprocessor) is a widely used open source general-purpose scripting

language that it especially suited for web development and can embedded into HTML. Instead
of lots of commands to output HTML, PHP pages contain HTML with embedded code that
does “something”. The PHP code is enclosed in special start and end processing instructions
that allow us to jump into and out of “PHP mode”.

PHP development began in 1994 when Rasmus Lerdorf wrote several Common
Gateway Interface (CGI) programs in C, which he used to maintain his personal homepage. He
extended them to work with web forms and to communicate with databases, and called the
implementation “Personal Home Page” or PHP.

PHP is a general-purpose scripting language that is especially suited to server-side web

development, in which case PHP generally runs on a web server. Any PHP code in a requested
file is executed by the PHP runtime, usually to create dynamic web page content. It can be used
for command-line scripting and client-side graphical user interface applications. PHP can be

32
deployed on most web servers, many operating systems and platforms and can be used with
many relational database management systems (RDBMS). It is available free of charge and the
PHP group provides the complete source code for users to build, customize and extend for their
own use.

PHP supports MySQL, Oracle, Sysbase etc. It is by far the compatible with servers like
Apache, IIS etc. It runs on platforms such as Windows, Linux. PHP can perform any task that
any CGI program can do but its strengths lies in its compatibility with many types of databases.
Also PHP can talk across networks using IMAP, SNMP, NNTP, POP3 or HTTP.

6.2 SAMPLE CODE

Header page

<!DOCTYPE html>

<html>

<head>

<title>First Website</title>

<link rel="stylesheet"
href="https://stackpath.bootstrapcdn.com/bootstrap/4.3.1/css/bootstrap.min.css"
integrity="sha384-
ggOyR0iXCbMQv3Xipma34MD+dH/1fQ784/j6cY/iJTQUOhcWr7x9JvoRxT2MZw1T"
crossorigin="anonymous">

<script
src="https://stackpath.bootstrapcdn.com/bootstrap/4.3.1/js/bootstrap.min.js"
integrity="sha384-
JjSmVgyd0p3pXB1rRibZUAYoIIy6OrQ6VrjIEaFf/nJGzIxFDsf4x0xIM+B07jRM"
crossorigin="anonymous"></script>

<script src="https://code.jquery.com/jquery-3.3.1.slim.min.js"
integrity="sha384-
q8i/X+965DzO0rT7abK41JStQIAqVgRVzpbzo5smXKp4YfRvH+8abtTE1Pi6jizo"
crossorigin="anonymous"></script>

33
 <script
src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.7/umd/popper.min.js"
integrity="sha384-
UO2eT0CpHqdSJQ6hJty5KVphtPhzWj9WO1clHTMGa3JDZwrnQq4sF86dIHNDz0W1"
crossorigin="anonymous"></script>

<script src="https://www.google.com/recaptcha/api.js" async defer></script>

<style>

#some{

position: fixed;

top: 30%;

left: 35%;

#footer{

position: fixed;

bottom: 0%;

left: 43%;

</style>

</head>

<body style="background-color: skyblue;">

<div style="background-color: white;">

<div class="container row" style="padding-top: 5px; padding-left: 55px; padding-bottom:

0px;">

<div class="col-md-7">

<h4 style="color: #000;">Brain Tumor</h4>

</div>

34
<div class="col-md-2">

<h5><a href="index.php" style="color: #000;">Home</a></h5>

</div>

<div class="col-md-2">

<h5><a href="Main.php" style="color: #000;">Process</a></h5>

</div>

<div class="col-md-1">

<?php

if (isset($_SESSION['uname'])) {

// echo'<h5><a href="#" style="color:

#000;">'.$_SESSION['uname'].'</a></h5>';

echo'<h5><a href="logout.php" style="color: #000;">Logout</a></h5>';

else {

echo '<h5><a href="login.php" style="color: #000;">Login</a></h5>';

?>

</div>

</div>

</div>

The above code is used for Header into the website.

Footer Page:

<div class="footer" id="footer">

35
 <h6>Copyright &copy; 2019. VARUN</h6>

</div>

</body>

</html>

The above code is used to create the Footer page for the website.

Login page:

<?php
session_start();
include 'header.php';
?>
<div class="container" id="some">
<form action="process.php" method="post" name="login">
<table>
<tr>
<td><h3>Username: </h3></td>
<td><input type="text" name="username"></td>
</tr>
<tr>
<td><h3>Password: </h3></td>
<td><input type="password" name="password"></td>
</tr>
</table>
<br/>
<span style="padding-left: 200px;"><input type="submit" name="submit"
value="Submit"></span>
</form>
<br/><br/>
<h5><span style="padding-left: 130px;">New?<a href="signup.php">
Signup</a></span></h5>
</div>

36
<?php
include 'footer.php';
?>
Signup Page:
<?php
session_start();
include 'header.php';
?>
<div class="container" id="some">
<form action="process_reg.php" method="post" name="signup"
enctype="multipart/form-data">
<table>
<tr>
<td><h3>Full Name: </h3></td>
<td><input type="text" name="name"></td>
</tr>
<tr>
<td><h3>Email: </h3></td>
<td><input type="text" name="email"></td>
</tr>
<tr>
<td><h3>Username: </h3></td>
<td><input type="text" name="username"></td>
</tr>
<tr>
<td><h3>Password: </h3></td>
<td><input type="password" name="password"></td>
</tr>
<tr>
<td><h3>Mobile Number: </h3></td>
<td><input type="text" name="num"></td>

37
</tr>
</table><br/>
<div class="g-recaptcha" style="padding-left: 30px;" data-
sitekey="6LcLu6wUAAAAAATnKvGgo2rVgj4I4aEi_aBnIbFa" data-
callback="correctCaptcha"></div><br/>
<span style="padding-left: 150px;"><input type="submit" name="submit"
value="Submit"></span>
</form>
<br/>
<h5><span style="padding-left: 100px;">Already member?<a
href="login.php">Login</a></span></h5>
</div>
<?php
include 'footer.php';
?>
Main page:
<?php
session_start();
include 'header.php';
function redirect($url) {
ob_start();
header('Location: '.$url);
ob_end_flush();
die();
}
?>
<style>
#some{
position: fixed;
top: 20%;
left: 30%;
}

38
</style>
<?php
if($_SESSION['uname'])
{
echo '
<!DOCTYPE html>
<html>
<head>
<title>File Upload</title>
<link rel="stylesheet"
href="https://stackpath.bootstrapcdn.com/bootstrap/4.4.1/css/bootstrap.min.css"
integrity="sha384-
Vkoo8x4CGsO3+Hhxv8T/Q5PaXtkKtu6ug5TOeNV6gBiFeWPGFN9MuhOf23Q9Ifjh"
crossorigin="anonymous">
<script src="https://code.jquery.com/jquery-3.4.1.slim.min.js" integrity="sha384-
J6qa4849blE2+poT4WnyKhv5vZF5SrPo0iEjwBvKU7imGFAV0wwj1yYfoRSJoZ+n"
crossorigin="anonymous"></script>
<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/umd/popper.min.js"
integrity="sha384-
Q6E9RHvbIyZFJoft+2mJbHaEWldlvI9IOYy5n3zV9zzTtmI3UksdQRVvoxMfooAo"
crossorigin="anonymous"></script>
<script src="https://stackpath.bootstrapcdn.com/bootstrap/4.4.1/js/bootstrap.min.js"
integrity="sha384-
wfSDF2E50Y2D1uUdj0O3uMBJnjuUD4Ih7YwaYd1iqfktj0Uod8GCExl3Og8ifwB6"
crossorigin="anonymous"></script>
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
<script>
var loadFile = function(event) {
var image = document.getElementById("output");
image.src = URL.createObjectURL(event.target.files[0]);
};
</script>
</head>
<body style="background-color: burlywood;">
<center>

39
<form action="upload.php" method="post" enctype="multipart/form-data">
<table>
<th style="font-size:26px; font-family: sans-serif;">Select image to Upload and Predict:</th>
<tr></tr>
<tr>
<td><input type="file" name="fileToUpload" id="fileUploaded"
onchange="loadFile(event)"></td>
</tr>
<tr></tr>
<tr>
<td><input type="submit" value="Upload File" name="submit">&nbsp;Click to
Upload</td>
</tr>
</table>
<img id="output" src="#" alt="Please Upload an Image" style="width: 25%;" />
</form>
</center>
</body>
</html>
';
}
else {
redirect('http://localhost/PythonWebsites/UI/login.php');
}
include 'footer.php';
?>
Python Home.py:
#!C:\Users\VARUN\Anaconda3\python36.exe
import cgitb
cgitb.enable()
print("Content-type:text/html\n\n")

40
print("""
<!DOCTYPE html>
<html>
<head>
<title>File Upload</title>
<link rel="stylesheet"
href="https://stackpath.bootstrapcdn.com/bootstrap/4.4.1/css/bootstrap.min.css"
integrity="sha384-
Vkoo8x4CGsO3+Hhxv8T/Q5PaXtkKtu6ug5TOeNV6gBiFeWPGFN9MuhOf23Q9Ifjh"
crossorigin="anonymous">
<script src="https://code.jquery.com/jquery-3.4.1.slim.min.js" integrity="sha384-
J6qa4849blE2+poT4WnyKhv5vZF5SrPo0iEjwBvKU7imGFAV0wwj1yYfoRSJoZ+n"
crossorigin="anonymous"></script>
<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/umd/popper.min.js"
integrity="sha384-
Q6E9RHvbIyZFJoft+2mJbHaEWldlvI9IOYy5n3zV9zzTtmI3UksdQRVvoxMfooAo"
crossorigin="anonymous"></script>
<script src="https://stackpath.bootstrapcdn.com/bootstrap/4.4.1/js/bootstrap.min.js"
integrity="sha384-
wfSDF2E50Y2D1uUdj0O3uMBJnjuUD4Ih7YwaYd1iqfktj0Uod8GCExl3Og8ifwB6"
crossorigin="anonymous"></script>
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
<style>
#some{
position: fixed;
top: 37%;
left: 45%;
}
.button {
background-color: #4CAF50;
border: none;
color: white;
padding: 15px 32px;
text-align: center;
text-decoration: none;

41
 display: inline-block;
font-size: 16px;
margin: 4px 2px;
cursor: pointer;
}
.button1 {
box-shadow: 0 8px 16px 0 rgba(0,0,0,0.2), 0 6px 20px 0 rgba(0,0,0,0.19);
}

.button2:hover {
box-shadow: 0 12px 16px 0 rgba(0,0,0,0.24), 0 17px 50px 0 rgba(0,0,0,0.19);
}
</style>
</head>
<body style="background-color: burlywood;">
<center>
<div class="container" id="some">
<h3>Prediction: """)
import Predict
try:
text = Predict.predict()
except:
text = ""
print(text+"""
</h3>
<a href="index.php"><button class="button">Back</button></a>
</div>
</center>
</body>
</html>""")

42
Python Predict.py:
import os
import cv2
import time
import numpy as np
import tensorflow as tf

def predict():
class_names = ['No', 'Yes']
path = "C:/Users/VARUN/Desktop/BrainTumor/Images/Uploads/Test.png"
model =
tf.keras.models.load_model('C:/Users/VARUN/Desktop/BrainTumor/Model/BrainTumorDet
ection-Tensorflow.model')
img = cv2.imread(path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img = cv2.resize(img, (30,30))
img = np.asarray(img)
img = img.reshape((-1, 30, 30, 1))
img = img / 255.0
prediction = model.predict([img])[0]
predicted_label = class_names[np.argmax(prediction)]
cv2.waitKey(0)
file = "C:/Users/VARUN/Desktop/BrainTumor/Images/Uploads/Class.txt"
return predicted_label
Deep Convolutional Neural Network Model.py:
###
# Copyright (2019). All Rights belongs to VARUN
# Use the code by mentioning the Credits
# Credit: github.com/varuntotakura
# Developer:

43
#
# T VARUN
#
###

# Import the required libraries

import numpy
import numpy as np
import tensorflow as tf
from tensorflow import keras
import matplotlib.pyplot as plt
import time

# Import th data
data_name = '../Data/training_data_cleaned.npy'
data = np.load(data_name)

# Declare the required arrays

img = []
label = []
test_imgs = []
test_labs = []

# Class names
class_names = ['No', 'Yes']

# Input to the arrays

for item, index in data:
img.append(item)
label.append(index)

44
# Train and Test data
train_images = img
train_labels = label

test_images = img[-100:]
test_labels = label[-100:]

train_images = np.asarray(train_images)
test_images = np.asarray(test_images)

train_images = train_images.reshape((-1, 30, 30, 1))

test_images = test_images.reshape((-1, 30, 30, 1))

# Image Processing
train_images = train_images / 255.0

test_images = test_images / 255.0

# Sequential Model
# Convolutional Neural Network
model = keras.Sequential([
keras.layers.Conv2D(32, (2, 2), activation='relu', input_shape=(30, 30, 1)),
keras.layers.MaxPooling2D((2, 2)),
keras.layers.Conv2D(64, (3, 3), activation='relu'),
keras.layers.MaxPooling2D((2, 2)),
keras.layers.Conv2D(64, (3, 3), activation='relu'),
keras.layers.Dropout(0.25),
keras.layers.Flatten(),
keras.layers.Dense(512, activation=tf.nn.relu),

45
 keras.layers.Dense(128, activation=tf.nn.relu),
keras.layers.Dense(128, activation=tf.nn.relu),
keras.layers.Dense(len(class_names), activation=tf.nn.softmax)
])

# Compile the model

model.compile(optimizer=tf.train.AdamOptimizer(),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])

# Train the Model

history = model.fit(train_images, train_labels, epochs = 12)

# Save Model
#model.save('../Model/BrainTumorDetection-Tensorflow.model')

# Print the Summary

model.summary()

# Accuracy of the Model

test_loss, test_acc = model.evaluate(test_images, test_labels)

# Print Test accuracy

print('Test accuracy:', test_acc*100)

# Make Predictions
predictions = model.predict([test_images])[0]
predicted_label = class_names[np.argmax(predictions)]

# Compare the predictions

46
print("Predictions : ",predicted_label)
print("Actual : ", class_names[test_labels[0]])

##print(history.history.keys())
# summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['loss'])
plt.title('Model')
plt.ylabel('Result')
plt.xlabel('Epochs')
plt.legend(['Accuracy', 'Loss'], loc='upper left')
plt.show()

47
CHAPTER 7
TESTING

48
7.1 INTRODUCTION

Software testing is a critical element of software quality assurance and represents the
ultimate review of specification, design and coding, testing presents an interesting anomaly
for the software engineer.

Testing Objectives include

Testing is a process of executing a program with the intent of finding an error. A good
test case is one that has a probability of finding an as yet undiscovered error. A successful test
is one that uncovers an undiscovered error

TESTING PRINCIPLES

1. Testing shows the presence of bugs

Testing an application can only reveal that one or more defects exist in the application,
however, testing alone cannot prove that the application is error free. Therefore, it is important
to design test cases which find as many defects as possible.

2. Exhaustive testing is impossible

Unless the application under test (AUT) has a very simple logical structure and
limited input, it is not possible to test all possible combinations of data and scenarios. For
this reason, risk and priorities are used to concentrate on the most important aspects to test.

3. Early testing

The sooner we start the testing activities the better we can utilize the available time.
As soon as the initial products, such the requirement or design documents are available, we
can start testing. Another important point about early testing is that when defects are found
earlier in the lifecycle, they are much easier and cheaper to fix. It is much cheaper to change
an incorrect requirement than having to change a functionality in a large system that is not
working as requested or as designed!

4. Defect clustering

During testing, it can be observed that most of the reported defects are related to small
number of modules within a system. i.e. small number of modules contain most of the defects
in the system. This is the application of the Pareto Principle to software testing: approximately
80% of the problems are found in 20% of the modules.

49
5. The pesticide paradox

If you keep running the same set of tests over and over again, chances are no newer
defects will be discovered by those test cases. Because as the system evolves, many of the
previously reported defects will have been fixed and the old test cases do not apply anymore.
Anytime a fault is fixed or a new functionality added, we need to do regression testing to
make sure the new changed software has not broken any other part of the software.

6. Testing is context dependent

Different methodologies, techniques and types of testing is related to the type and
nature of the application. For example, a software application in a medical device needs more
testing than a games software. More importantly a medical device software requires risk based
testing, be compliant with medical industry regulators and possibly specific test design
techniques.

7. Absence of errors fallacy

Just because testing didn’t find any defects in the software, it doesn’t mean that the
software is ready to be shipped. Were the executed tests really designed to catch the most
defects? or where they designed to see if the software matched the user’s requirements?
There are many other factors to be considered before making a decision to ship the software.

7.2 TESTING

Testing is a process of executing a program with a intent of finding an error. Testing

presents an interesting anomaly for the software engineering. The goal of the software testing
is to convince system developer and scholar that the software is good enough for operational
use. Testing is a process intended to build confidence in the software.

7.3 TYPES OF TESTING

Test methodologies used:

7.3.1 FUNCTIONAL TESTING

Functional testing is a type of testing which verifies that each function of the software
application operates in conformance with the requirement specification. This testing mainly
involves black box testing and it is not concerned about the source code of the application. This

50
testing involves checking of User Interface, APIs, Database security, client/server applications
and functionality of the Application Under Test.

Characteristics of functional testing: Mainline functions, Basic Usability, Accessibility,

Errorconditions.

Functional Testing Process: Identify test input, compute the expected outcomes with
theselected test input values, execute test cases, comparison of actual and computed expected
result.

7.3.2 NON-FUNCTIONAL TESTING

Non-functional testing to check non- functional aspects of a software application. It is

designed to test the readiness of a system as per non-functional parameters which are never
addressed by functional testing.

Characteristics of Non-Functional Testing: Non-functional testing should be

measurable,important to prioritize the requirements, ensure the quality attributes are identified
correctly.

Parameters of non-functional testing: Security, reliability, survivability, availability,

usability,scalability, interoperability, efficiency, flexibility, portability, reusability.

7.3.3 STRUCTURAL TESTING

Structural testing, also known as glass box testing or white box testing is an approach
where the tests are derived from the knowledge of the software’s structure or internal
implementation.

Techniques of Structural testing: Statement Coverage, Branch Coverage, Path Coverage.

7.3.4 REGRESSION TESTING

Regression testing is defined as a type of software testing to confirm that a recent

program or code change has not adversely affected existing features. Regression testing is
nothing but full or partial selection of already executed test cases which are re-executed to
ensure existing functionalities work fine.

Need of Regression testing: It is required when there is a change in requirements and code
ismodified according to the requirement, new feature is added to the software, defect fixing,
performance issue fix.

51
Techniques of Regression testing: Retest All, Regression Test Selection, Prioritization of
TestCases.

7.3.5 END-TO-END TESTING

End-to-End testing is a type of Software testing that not only validates the software
system under test but also check its integration with external interfaces. It uses actual
production like data and test environment to simulate real-time settings. End-to-End testing is
also called Chain testing.

End-to-End design framework consists of three parts:

Build User functions, Build conditions, Build test cases.

7.3.6 GUI TESTING APPROACHES

GUI stands for Graphical User Interface where we interact with the computer using
images rather than text. GUI Testing is the process of testing the system’s Graphical User
Interface of the Application under test. It involves checking the screens with the controls
likemenus, buttons, icons and all types of bars- toolbar, menu bar, dialog boxes and windows
and many more.

Approaches of GUI Testing:This can be done in three ways:

7.3.6.1 Manual Based Testing:Manual Testing is based on domain and application knowledge
of the tester. It is error-prone and there are chances of most of test scenarios left out. Heuristic
methods are used for manual testing in which a group of specialists studies the software to find
problems. It requires more efforts, provides weak coverage.

7.3.6.2 Record and replay: GUI testing can be done using automation tools. This is done in
two parts. During record, test steps are captured, during playback, the recorded test steps are
executed on Application Under Test.

7.3.6.3 Model Based Testing:A model is a graphical representation of system’s behaviour. It

helps us to understand and predict the system behaviour. Some of the needs to be considered
are build a model, determine inputs for the model, run the tests, calculate expected output for
the model, compare actual output with expected output, decision on further action. Some of the
modelling techniques are Charts, Decision Tables.

7.4 SOFTWARE MAINTENANCE

52
 It is the modification of a software product after delivery to correct faults, to improve
performance or other attributes.

A common perception of maintenance is that it merely involves fixing defects.

However, one study indicated that over 80% of maintenance effort is used for non-corrective
actions.[2] This perception is perpetuated by users submitting problem reports that in reality
are functionality enhancements to the system.

7.4.1 CORRECTIVE MAINTENANCE

It deals with the repair of faults or defects found in day-today system functions. A
defect can result due to errors in software design, logic and coding. Design errors occur when
changesmade to the software are incorrect, incomplete, wrongly communicated, or the change
request is misunderstood.

7.4.2 ADAPTIVE MAINTENANCE

It is the implementation of changes in a part of the system, which has been affected by
a change that occurred in some other part of the system. Adaptive maintenance consists of
adapting software to changes in the environment such as the hardware or the operating system.
The term environment in this context refers to the conditions and the influences which act
(from outside) on the system. For example, business rules, work patterns, and government
policies have a significant impact on the software system.

7.4.3 PERFECTIVE MAINTENANCE

TEST TEST TEST DATA EXPECTED SUCCESS /

SCENARI STEP RESULT FAILURE
O S

Check user 1. Enter [email protected] Successful user Success

login with mailid 2.varun123 login on valid
valid data data
2. Enter
password

53
 Check user 1. Enter [email protected] Unsuccessful Failure
login with mailid 2.Xyzop user login
invalid data
2. Enter
password

It mainly deals with implementing new or changed user requirements. Perfective

maintenance involves making functional enhancements to the system in addition to the
activities to increase the system's performance even when the changes have not been suggested
by faults.

7.4.4 PREVENTIVE MAINTENANCE

It involves performing activities to prevent the occurrence of errors. It tends to reduce

the software complexity thereby improving program understand ability and increasing
software maintainability.

7.5 TEST CASES AND RESULTS

Test cases for software help and guide the tester through a sequence of steps to validate
whether a software application is free of bugs and working as required by the end user.

Figure 7.5.a: Convolutional Neural Network Model

54
 Figure 7.5.b: Dataset

Figure 7.5.c: Result Graph

55
 CHAPTER 8

IMPLEMENTATION

56
8.1 INTRODUCTION

Implementation is the carrying out, execution, or practice of a plan, a method, or any

design for doing something. As such, implementation is the action that must follow any
preliminary thinking in order for something to actually happen. In an information technology
context, implementation encompasses all the processes involved in getting new software or
hardware operating properly in its environment, including installation, configuration, running,
testing, and making necessary changes. The word deployment is sometimes used to mean the
same thing.

So in our app we provide users a very good platform to go on with their publishing of
papers in the International Conference. It is easy to use and understand. By this the user will
find it friendly to use. He can just login and can enjoy the services. A new user has to register
his name to proceed through the application. By the next time he log in, he can go through the
details provided.

8.2 TECHNOLOGIES USED

The different technologies used in development of the adventure guide application are
as follows:

● HTML

● CSS

● PHP

● Python

● JavaScript

● MySQL

● Apache server

57
8.3 SCREENSHOTS

Fig: 8.1Screenshot of IndexPage

Fig: 8.1Screenshot of IndexPage.

The above screenshot is the Index page integrated in our project.

Fig: 8.2Screenshot of LoginPage

Fig: 8.2Screenshot of LoginPage.

58
 The above screenshot is the Login page integrated in our project.

Fig: 8.3Screenshot of SignupPage

Fig: 8.3Screenshot of Signup Sessions Page.

The above screenshot is the Signup page integrated in our project.

Fig: 8.4Screenshot of After LoginPage

Fig: 8.4Screenshot of After LoginPage.

59
 The above screenshot is the after login page integrated in our project.

Fig: 8.5Screenshot of Main Uploading and Predicting Page

Fig: 8.5Screenshot of Uploading and Predicting Page.

The above screenshot is the Uploading and Predicting Page integrated in our project.

Fig: 8.6Screenshot of UplaodingPage

Fig: 8.6Screenshot of UplaodingPage.

60
 The above screenshot is the Uploading page integrated in our project.

Fig: 8.7Screenshot of After UplaodPage

Fig: 8.7Screenshot of After UploadPage.

The above screenshot is the after Upload page integrated in our project.

Fig: 8.8Screenshot of PredictionPage

Fig: 8.8Screenshot of PredictionPage.

The above screenshot is the Prediction page integrated in our project.

61
 CHAPTER 9
CONCLUSION AND FUTURE ENHANCEMENT

62
9.1 CONCLUSION

This projects consists of the details about the model which was used for the detection
of brain tumor using the MRI images of the brain from the normal persons and the persons who
had a brain tumor. From the resultant graphs, it is proven that the accuracy of the model has
reached good level, if it is deployed in the real-time scenario then it will help many people in
diagnosing the brain tumor without wasting the money on check-up. If the brain tumor is
confirmed by the model, then the person can reach the nearest hospital to get the treatment. It
can be the best way of practice for people to save money. As we know that the data plays a
crucial role in every deep learning model, if the data is more specific and accurate about the
symptoms of the brain tumor then that can help in reaching greater accuracy with better results
in real-time applications.

1. “Brain Tumor Detection using Convolutional Neural Networks” simplifies the

management process of brain tumor check-up by deploying a web interface to the users.

2. Fast processing and immediate results with high security.

3. Minimizing human effort and cost efficient databases.

4. Navigation through the site is easy.

9.2 FUTURE SCOPE AND ENHANCEMENT

There is a wide scope for future implementation of “Brain Tumor Detection using
Convolutional Neural Networks” towards an interesting experience of modern technologies.
Digital Platform is a ‘one stop shops’ for all kinds of Hospitals to serve the domestic and
international users at any time, any moment and anywhere in any parts of the world. Not being
sticky to make packages within India only, it can be global - a “global platform” through a
comprehensive.

In present days, modern technologies have made treatment more pleasure comprising
speed with comfort. So, people are not willing to be bound within only a small geographical
area, so there is place to make them experience the taste of “Global Platform”.

It can be enhanced into a Mobile Application. And also in future we can create an
Artificial Intelligence Deep Neural Network Model for the evaluation for all other kind of
diseases and even we develop in such a way that all the small kind of diseases can be cured
without contacting a doctor and by spending lot of money.

63
References:

[1]. Mircea Gurbin, Mihaela Lascu, Dan Lascu, “Tumor Detection and Classification of MRI
Brain Image using Different Wavelet Transforms and Support Vector Machines”, 2019 42nd
International Conference on Telecommunications and Signal Processing (TSP), Budapest,
Hungary, 2019, pp. 505-508.

[2]. M. Rezaei, H. Yang, C. Meinel, “Instance Tumor Segmentation using Multitask

Convolutional Neural Network”, 2018 International Joint Conference on Neural Networks
(IJCNN), Rio de Janeiro, 2018, pp. 1-8.

[3]. Harshini Badisa, Madhavi Polireddy, Aslam Mohammed, “CNN Based Brain Tumor
Detection”, International Journal of Engineering and Advanced Technology (IJEAT), Volume-
8 Issue-4, April 2019, pp. 1731 – 1734.

[4]. MB Bramarambika, Seshashayee, “Brain Tumor Detection and Identification Using

Histogram Method”, International Journal of Innovative Technology and Exploring
Engineering (IJITEE), Volume-8 Issue-10, August 2019, pp. 3517 – 3521.

[5]. Tonmoy Hossain, Fairuz Shadmani Shishir, Mohsena Ashraf, MD Abdullah Al Nasim,
Faisal Muhammad Shah, “Brain Tumor Detection Using Convolutional Neural Network”, 1st
International Conference on Advances in Science, Engineering and Robotics Technology 2019
(ICASERT 2019), Dhaka, Bangladesh, 2019, pp. 1-6.

[6]. N. Varuna Shree, T.N.R. Kumar, “Identification and classification of brain tumor MRI
images with feature extraction using DWT and probabilistic neural network”, Brain Inf. 5, pp.
23–30 (2018), https://doi.org/10.1007/s40708-017-0075-5

[7]. M Malathi, P Sinthia, “Brain Tumour Segmentation Using Convolutional Neural Network
with Tensor Flow”, Asian Pacific journal of cancer prevention, APJCP (2019), DOI:
10.31557/APJCP.2019.20.7.2095

[8]. J. Seetha, S. Selvakumar Raja, “Brain Tumor Classification Using Convolutional Neural
Networks”, Biomedical & Pharmacology Journal, September 2018, Vol. 11(3), p. 1457-1461.

[9]. M. Usman Akram, Anam Usma, “Computer Aided System for Brain Tumor Detection and
Segmentation”, International Conference on Computer Networks and Information Technology,
Abbottabad, 2011, pp. 299-302.

64
[10]. Varun Totakura, Mohana Krishna Janmanchi, Durganath Rajesh, M.I. Thariq Hussan,
“Prediction of Animal Vocal Emotions Using Convolutional Neural Network”, International
Journal of Scientific & Technology Research, Volume 9, Issue 2, pp. 6007-6011.

[11]. H. Ucuzal, Ş. YAŞAR and C. Çolak, "Classification of brain tumor types by deep learning
with convolutional neural network on magnetic resonance images using a developed web-based
interface," 2019 3rd International Symposium on Multidisciplinary Studies and Innovative
Technologies (ISMSIT), Ankara, Turkey, 2019, pp. 1-5, doi: 10.1109/ISMSIT.2019.8932761.

[12]. M. Li, L. Kuang, S. Xu and Z. Sha, "Brain Tumor Detection Based on Multimodal
Information Fusion and Convolutional Neural Network," in IEEE Access, vol. 7, pp. 180134-
180146, 2019, doi: 10.1109/ACCESS.2019.2958370.

[13]. Alam, Md & Rahman, Md. Mahbubur & Hossain, Mohammad & Islam, Md & Ahmed,
Kazi & Ahmed, Khandaker & Singh, Bikash & Miah, Md Sipon. (2019). Automatic Human
Brain Tumor Detection in MRI Image Using Template-Based K Means and Improved Fuzzy
C Means Clustering Algorithm. Big Data and Cognitive Computing. 3. 27.
10.3390/bdcc3020027.

[14]. I. Maiti and M. Chakraborty, "A new method for brain tumor segmentation based on
watershed and edge detection algorithms in HSV colour model," 2012 NATIONAL
CONFERENCE ON COMPUTING AND COMMUNICATION SYSTEMS, Durgapur, 2012,
pp. 1-5, doi: 10.1109/NCCCS.2012.6413020.

[15]. Patil, Ms & Pawar, Ms & Patil, Ms & Nichal, Arjun. (2017). A Review Paper on Brain
Tumor Segmentation and Detection. IJIREEICE. 5. 12-15. 10.17148/IJIREEICE.2017.5103.

[16]. T. H. Teo, W. M. Tan and Y. S. Tan, "Tumour Detection using Convolutional Neural
Network on a Lightweight Multi-Core Device," 2019 IEEE 13th International Symposium on
Embedded Multicore/Many-core Systems-on-Chip (MCSoC), Singapore, Singapore, 2019, pp.
87-92, doi: 10.1109/MCSoC.2019.00020.

[17]. P. M. Krishnammal and S. S. Raja, "Convolutional Neural Network based Image

Classification and Detection of Abnormalities in MRI Brain Images," 2019 International
Conference on Communication and Signal Processing (ICCSP), Chennai, India, 2019, pp.
0548-0553, doi: 10.1109/ICCSP.2019.8697915.

65
[18]. R. Rulaningtyas and K. Ain, "Edge detection for brain tumor pattern recognition,"
International Conference on Instrumentation, Communication, Information Technology, and
Biomedical Engineering 2009, Bandung, 2009, pp. 1-3, doi: 10.1109/ICICI-
BME.2009.5417299.

[19]. H. S. Abdulbaqi, Mohd Zubir Mat, A. F. Omar, I. S. B. Mustafa and L. K. Abood,

"Detecting brain tumor in Magnetic Resonance Images using Hidden Markov Random Fields
and Threshold techniques," 2014 IEEE Student Conference on Research and Development,
Batu Ferringhi, 2014, pp. 1-5, doi: 10.1109/SCORED.2014.7072963.

[20]. Sobhaninia, Zahra & Rezaei, Safiyeh & Noroozi, Alireza & Ahmadi, Mahdi & Zarrabi,
Hamidreza & Karimi, Nader & Emami, Ali & Samavi, Shadrokh. (2018). Brain Tumor
Segmentation Using Deep Learning by Type Specific Sorting of Images.

[21]. M. R. Islam and N. Rishad, "Effects of Filter on the Classification of Brain MRI Image
using Convolutional Neural Network," 2018 4th International Conference on Electrical
Engineering and Information & Communication Technology (iCEEiCT), Dhaka, Bangladesh,
2018, pp. 489-494, doi: 10.1109/CEEICT.2018.8628056.

[22]. Bahadure, Nilesh & Ray, Arun & Thethi, H.Pal. (2017). Image Analysis for MRI Based
Brain Tumor Detection and Feature Extraction Using Biologically Inspired BWT and SVM.
International Journal of Biomedical Imaging. 2017. 1-12. 10.1155/2017/9749108.

[23]. S. Zhou, D. Nie, E. Adeli, J. Yin, J. Lian and D. Shen, "High-Resolution Encoder–
Decoder Networks for Low-Contrast Medical Image Segmentation," in IEEE Transactions on
Image Processing, vol. 29, pp. 461-475, 2020, doi: 10.1109/TIP.2019.2919937.

[24]. W.Gonzalez, “Digital Image Processing”, 2nd ed. Prentice Hall, Year of Publication
2008.

[25]. Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing, Second Edition.

[26]. Rafael C. Gonzalez, Richard E. Woods, Steve L. Eddins, Digital Image Processing Using
MATLAB, 2003.

[27]. Rania Hussien Al-Ashwal, Eko Supriyanto, et.al., “Digital Processing for Computed
Tomography Images: Brain Tumor Extraction and Histogram Analysis”, Mathematics and
Computers in Contemporary Science, 2013

66
 [28]. J. Selvakumar, A. Lakshmi and T. Arivoli, “Brain Tumor Segmentation and its area
calculation in Brain MR images using K-means clustering and fuzzy C-mean algorithm”,
Imternational Conference on Advances in Engineering, Science and Management, 2012

[29]. R. Rajeswari, P. Anadhakumar, “Image segmentation and identification of brain tumor

using FFT techniques of MRI images”, ACEEE International Journal on Communication, Vol.
02, No. 02, July 2011

[30]. Mustaqeem, Anam, Ali Javed, and Tehseen Fatima, “An efficient brain tumor detection
algorithm using watershed and thresholding based segmentation”, International Journal 4, 2012

[31]. P.Dhanalakshmi, T.Kanimozhi, “Automated Segmentation of Brain Tumor using K-

Means Clustering and its area calculation”, IJAEEE, 2013.

[32]. Q.Hu, G. Quian, A. Aziz, W.L.Nowinski,”Segmentation of Brain from Computed

Tomography head images,” Engineering in Medicine and Biology 27th Annual Conference,
2005.

[33]. Natrajan P. , Krishnan N. , Natasha Sandeep kenkre and et.al ,”Tumor Detection using
Threshold operation in MRI Brain Images,” IEEE International Conference on Computational
Intelligence and Computing Research, 2012.

[34]. P. Natrajan, Debsmita Ghosh, kenkre Natasha Sandeep, Sabiha Jilani, ”Detection of
Tumor in Mammogram Images using extended Local Minima Threshold,” International
Journal of Engineering and Technology, Vol. 5, No . 3, jun-jul 2013.

[35]. X. Zang, J.Yang, D.Weng, Y. Liu and Y. Wang, “A novel anatomical Structure
segmentation method of CT head images,” International Conferences on complex medical
Engineering, 2010.

[36]. A. Padma and R. Sukanesh, “Automatic Classification and segmentation of brain tumor
in CT images using optimal dominant gray level run length texture features,” International
journal of Advanced Computer Science and Applications, 2011.

[37]. R.C. Patil and Dr. A.S. Bhalachandra, “Brain tumour extraction from MRI images using
MATLAB,” International Journal of Electronics, Communication &Soft Computing Science
and Engineering,vol. 2, pp. 1-4.

67

View publication stats