Extraction of Tumor from CT Brain Images and its

Visualization using Contour plot in GUI

A PROJECT REPORT
Submitted by

Abha Pandey (10BCE0229)

Alisha Singla (10BCE0233)

Saloni Agarwal (10BCE0272)

in partial fulfillment for the award

of
B. Tech
degree in
Computer Science and Engineering
School of Computing Science and Engineering

May – 2014
 School of Computing Science and Engineering

DECLARATION

We hereby declare that the project entitled “Extraction of Tumor from CT Brain Images and
its Visualization using Contour plot in GUI” submitted by us to the School of Computing Science and
Engineering, VIT University, Vellore-14 in partial fulfillment of the requirements for the award of the
degree of Bachelor of Technology in Computer Science and Engineering is a record of bona-fide work
carried out by us under the supervision of Prof. Natarajan P, Assistant Professor (S.G.), SCSE. We
further declare that the work reported in this project has not been submitted and will not be submitted,
either in part or in full, for the award of any other degree or diploma of this institute or of any other
institute or university.

Abha Pandey(10BCE0229)

Alisha Singla(10BCE0233)

Saloni Agarwal(10BCE0272)

2
 School of Computing Science and Engineering

CERTIFICATE

The project report entitled “Extraction of Tumor from CT Brain Images and its Visualization using
Contour plot in GUI” is prepared and submitted by Abha Pandey (10BCE0229), Alisha Singla
(10BCE0233) and Saloni Agarwal (10BCE0272). It has been found satisfactory in terms of scope,
quality and presentation as partial fulfillment of the requirements for the award of the degree of Bachelor
of Technology in Computer Science and Engineering in VIT University, India.

(Name & Signature of the Internal Guide)

Internal Examiner(s) External Examiner(s)

3
 ACKNOWLEDGEMENT

First of all we would like to thank our project guide, Prof. Natarajan P., Assistant Professor
(S.G.) of SCSE, VIT U, for providing us his time and knowledge during the building and
completion of this project. We would also like to thank our Program Chair, Prof. Hari Seetha and
Dean, Dr. Venkateswaran S, for giving us this opportunity to implement our ideas and learning
into shaping this project. Next we would take the opportunity to pass our thanks to our
educational institute, Vellore Institute of Technology, Vellore campus, for providing ample
opportunities and guidance .

4
 CONTENTS

S.no. Page number

Title

Title Page 1

Declaration 2

Certificate 3

Acknowledgement 4

Table of Contents 5

List of Tables 7

List of Figures 8

List of Abbreviations 9

Abstract 10

1 INTRODUCTION

1.1 General 11

11
1.2 Motivation

12
1.3 Aim & Objective

13
1.4 Related Work

14
1.5 System Requirements

2
OVERVIEW OF PROPOSED SYSTEM

15
2.1 Introduction of problem

2.2 Gaps identified in existing system 15

16
2.3 Proposed Solution

5
3
ANALYSIS AND DESIGN

16
3.1 Requirement Analysis

17
3.1.1 Functional Requirements

17
3.1.2 Non-Functional Requirements

18
3.2 Design of Proposed System

18
3.2.1 System Architectural Design

19
3.2.2 System Interface Description

20
3.2.3 Considered Design Constraints

4
IMPLEMENTATION

21
4.1 Tools Used

23
4.2 Execution

23
4.2.1 User Interface Design

24
4.2.2 Test Cases

5 25
RESULTS AND DISCUSSION

6 CONCLUSION AND FUTURE 32

ENHANCEMENTS
7 33
REFERENCES

34
APPENDIX -I

39
APPENDIX -II

6
 LIST OF TABLES

TITLE PAGE No.

System requirements 14

Test Cases 24

Table to show accuracy of algorithm 32

7
 LIST OF FIGURES

TITLE PAGE No.

System Interface Design 18

System Interface Description 19

Prototyping 23

Original image 25

Pre-processed image 25

Background estimation 26

Contrast adjustment when background is subtracted 26

Contrast adjustment when negative of background is subtracted 27

Subtraction of images to result in tumor region 27

Threshold image 27

Boundary detection 27

Contour of original image 28

Contour of tumour region 28

Contour of tumour boundary 28

Interface to select an image. 29

Start screen of GUI 29

Contour of selected image in GUI 30

Contourf of selected image in GUI 30

C-label of selected image in GUI 31

Interface to print current display in GUI 31

8
 LIST OF ABBREVIATIONS

ABBREVIATIONS EXPANSION
CT Computerized Tomography
GUI Graphical User Interface
PSNR Peak to Signal Noise Ratio
CPU Central Processing Unit
MRI Magneticl Resonance Imaging

9
 ABSTRACT
The field of medical imaging is gaining importance with an increase in the demand for
automated, reliable, fast and efficient diagnosis which can provide insight to the image better
than human eyes. Brain tumor is the second leading cause for cancer-related deaths in men in age
20 to 39 and fifth leading cause cancer among women in same age group. Brain tumors are
painful and may result in various diseases if not cured properly. Diagnosis of tumor is a very
important part in its treatment. Identification plays an important part in the diagnosis of benign
and malignant tumors. A prime reason behind an increase in the number of cancer patients
worldwide is the ignorance towards treatment of a tumor in its early stages. This paper discusses
such an algorithm that can inform the user about details of tumor using basic image processing
techniques. These methods include noise removal and sharpening of the image along with basic
morphological functions, erosion and dilation, to obtain the background. Subtraction of
background and its negative from different sets of images results in extracted tumor image.
Plotting contour and c-label of the tumor and its boundary provides us with information related
to the tumor that can help in a better visualization in diagnosing cases. This process helps in
identifying the size, shape and position of the tumor. It helps the medical staff as well as the
patient to understand the seriousness of the tumor with the help of different color-labeling for
different levels of elevation . A GUI for the contour of tumor and its boundary can provide
information to the medical staff on click of user choice buttons.

Keyword- Brain, CT, Contrast Adjust, Structural Element, Erosion, Dilation, Negation,
Tumor Detection, Contour, C-label , GUI.

10
1 Introduction

1.1 General

The driving force of this project is to create a transparent environment where medical staff and
patient can work in complete cooperation to achieve better results. This transparent environment
will help the patient to feel secure as they will understand the treatment-process choice, which in
turn will help the medical staff to handle the situation in a calm order giving them more time to
think and work.

1.2 Motivation

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) [7].

Brain tumor oc11curred when the cells were dividing and growing abnormally. It is appear 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 [4].

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 occurs when the tumor block 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 [4].

11
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 [4].

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.

1.3 Aim & Objective – Problem Description

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.

12
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
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. Plotting contour-f plot and c-label plot of the tumor and its
boundary will give easy understanding to the medical staff because humans comprehend images
better with the help of different colors for different levels of intensity, giving 3D visualization
from a 2D image.

1.4 Related Work

According to Mustaqeem, Anam, et.al, in “An efficient brain tumor detection algorithm using
watershed and thresholding based segmentation” published in “International Journal 4” in 2012
[7]
, benign also can be growth as malignant which is consists of cancerous cells. Malignant is the
rapid growing tumor which is invasive and life threatening. It is also called as brain cancer since
the malignant contains cancerous cells that able to destroy any nearby cell.

The paper “Tumor Detection using Threshold operation in MRI Brain Images” by Natarajan P.
et.al, [10] states that Primary brain tumors include any tumor that starts in the brain. Primary brain
tumors can start from brain cells, the membranes around the brain (meninges), nerves, or glands.
Tumors can directly destroy brain cells. They can also damage cells by producing inflammation,
placing pressure on other parts of the brain, and increasing pressure within the skull. A metastatic
brain tumor is a cancer that has spread from elsewhere in the body to the brain.

13
According to R. Rajeswari, P. Anadhakumar, in “Image segmentation and identification of brain
tumor using FFT techniques of MRI images”, published in “ACEEE International Journal on
Communication, Vol. 02” [6]
the conventional definition of brain tumor includes neoplasms
originating from brain parenchyma as well as from meninges and even tumors of the pituitary
gland or of osseous intracranial structure that can indirectly affect brain tissues [4].

In the paper “A novel anatomical Structure segmentation method of CT head images” by X.

[12]
Zang et.al Histogram contains intensity value of 0-255. The zero value is the darkest part
while the 255 was the white or the brightest side. Using the histogram analysis approached used
the mixture Gaussian filter for the extracted part pixel intensity.

However, most of the technique used is more on MRI modality compared to CT images because
it is higher resolutions. CT images of human body parts help medical doctors in diagnosing
illness like brain tumor, colon cancer, lung cancer and so forth. However, it is quite difficult to
obtain the important features in the images because it is limited by the image processing level
and also doctor’s experience. This is expressed in “Automatic Classification and segmentation of
brain tumor in CT images using optimal dominant gray level run length texture features,” by A.
Padma and R. Sukanesh [13].

1.5 System Requirements

Table 1.5.1. System requirements

Operating System Processors Disk Space RAM

Windows XP Service Any Intel or AMD x86 1 GB for MATLAB 1024 MB

Pack 3 processor supporting only, (At least 2048 MB
SSE2 instruction se 3–4 GB for a typical recommended)
Windows Server 2003 R2 installation
with Service Pack 2

Windows Vista Service

Pack 1 or 2
Windows Server 2008
Service Pack 2 or R2

Windows 7

14
Mac OS X 10.5.5 All Intel-based Macs 1 GB for MATLAB 1024 MB
(Leopard) and above only, (At least 2048 MB
3–4 GB for a typical recommended)
Mac OS X 10.6.x (Snow installation
Leopard)

Ubuntu 8.04, 8.10, 9.04, Any Intel or AMD x86 1 GB for MATLAB 1024 MB
and 9.10 processor supporting only, (At least 2048 MB
Red Hat Enterprise Linux SSE2 instruction set 3–4 GB for a typical recommended)
5.x installation
SUSE Linux Enterprise
Desktop 11.x
Debian 5.x

2 Overview of the Proposed System

2.1 Introduction of problem

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 [4].

2.2 Gaps identified in existing system

In the existing solution of extraction of brain tumor from CT scan images tumor part is detected
from the CT scan of the brain. The proposed solution also do the same thing , inform the user
about details of tumor using basic image processing techniques. The methods include noise
removal and sharpening of the image along with basic morphological functions, erosion and
dilation, to obtain the background. Subtraction of background and its negative from different sets
of images results in extracted tumor image. The difference in the proposed solution with existing
solution is plotting contour and c-label of the tumor and its boundary which provides us with
information related to the tumor that can help in a better visualization in diagnosing cases. This

15
process helps in identifying the size, shape and position of the tumor. It helps the medical staff as
well as the patient to understand the seriousness of the tumor with the help of different color-
labeling for different levels of elevation

2.3 Proposed solution

The algorithm is a set of image processing fundamental procedures. A set of noise-removal
functions accompanied with morphological operations that result in clear image of tumor after
passing through high pass filter is the basic idea behind the proposed algorithm. The set of
morphological operations used will decide the clarity and quality of the tumor image.

A GUI is created in the MATLAB offering the proposed application of extracting the tumor from
selected brain image and its visualization using contour plot. Without having to deal with the
code, medical staff can select the CT image and study the extracted tumor along with its
boundary from contour and c-label options. The GUI also contains options for zoom-in, zoom-
out, data cursor for co-ordinates, and prints the selected image.

3 Analysis and Design

3.1 Requirement Analysis

System requirements set out what the system should do without specifying how it should be
done. The requirement set out in this document is complete and consistent. There are 2 types of
user of this software-

1. Patient

2. Doctor

1. Patient can use the software to see the size of the tumor. It’s easy for the laymen to
understand the size and position of the tumor.

16
 2. Doctor are using for extracting of tumor from CT scan images of brain and visualization of
tumor using contour plot.

3.1.1 Functional Requirements

 Selecting the CT scan images of brain.
 Extracting only tumor region from the scan images.
 Finding the boundary of the tumor.
 Plotting the contour of tumor and boundary of the tumor.
 Plotting the c-label of tumor and boundary of the tumor.
 Creating a GUI for easy access of the program.

3.1.2 Non Functional Requirements

 Availability- The software for Extraction of brain tumor from CT scan images can be
available in all the systems who have MATLAB installed.
 Reliability- This software attempts to insure appropriate content but assume no
responsibility for external manipulations.
 Performance- CPU time of the proposed software varies from 4seconds to 6seconds and
PSNR value from 25dB to 26dB.

3.2 Design of the proposed system

17
3.2.1 System Architectural Design

Fig 3.2.1.1.System Architectural Description

18
3.2.2 System Interface Description

CT Brain Image (with tumor) Contour and C-label

Pre-Processing
(Grey-scale; Noise Removal; Sharpening)

Background Estimation
(Erosion and Dilation)

Subtraction of background and negative

of background from eroded image

Contrast adjustment of resultant images.

Subtraction of boundary from contrast

adjusted image

Threshold Contour and C-label

Boundary Detection Contour and C-label

Fig 3.2.2.1.System Interface Description

19
3.2.3 Considered Design Constraints
3.2.3.1 User Interface Constraints
Using this system is fairly simple and intuitive. A user familiar with basic
computer operability skills should be able to understand all functionality provided
by the system.

3.2.3.2 Hardware Constraints

The system should work on most home desktop and laptop computers and can be
extended to mobile phone apps.

3.2.3.3 Software Constraints

The system is designed to run on MATLAB having GUIDE.

3.2.3.4 Communications Constraints

System must have access to the images of CT scan for brain tumour.

3.2.3.5 Data Management Constraints

System shall be able to interface with other components according to their
specifications.

3.2.3.6 Operational Constraints

The system is not limited to any Operating System. It works in equally good in
Windows , Mac and LINUX.

20
4 Implementation

4.1 Tools Used

A. Noise Removal and Sharpening

As a grayscale or colored image maybe the inputted image, the first step is to convert the
given image into a grayscale image [4]. On procuring the grayscale image, the aim then is
[4] [4]
to filter it so as to sharpen it and remove any noise , if present. In the algorithm,
unsharp [1] [14] filtering of fspecial [2] [14]
filter is applied in order to sharpen the image by
removing the low intensity values. For noise-removal ‘Gaussian’ [1] [9] filters is used from
fspecial filters.

B. Erosion and Dilation

After pre-processing, next step is to estimate the background [14]. In order to do so we
make use of the basic morphological operations, erosion and dilation. More erosion [14]
and less dilation [14] will result in decrease in skull bones’ image size. To accomplish this
we will keep the eroding structural element’s radius bigger than that of dilating structural
elements. The structuring element used is ‘diamond’.

C. Negation
The estimated background, obtained by the previous step, will contain the eroded tumor
region as our aim was to remove the skull boundary and radius of structuring element
was kept as such. Negative of the image can be calculated by subtracting [11] the image
from 255 which the highest value any pixel can have.

D. Subtraction
Subtracting background and negative of background from eroded image will result in
images with and without tumors [11]. These images will contain skull’s boundary along
with the tumor region and thus will be imperfect for use [6].

E. Contrast Adjustment

21
 In order to provide a clear and well-defined image to work upon, this operation is further
applied to the result of subtracting images in previous step. This operation involves
increasing the contrast of the filtered image, which is accomplished by performing
contrast adjustment techniques [6]. These contrast images will further be subtracted from
dilated image [6] [11].

F. Threshold
Next step in this algorithm is to calculate global image threshold using Otsu's method [10],
which chooses the threshold to minimize the intra-class variance of the black and white
pixels. Thus we will get a clear image of the tumor region [6].

G. Boundary Detection
In earlier times without aid of medical imaging tumors were identified manually and
boundaries were drawn around it by an expert which always contained issues related to
manual-error. Thus, to remove this error, the next step includes producing a clear
boundary of the identified tumor using the morphological operation ‘remove’, which
removes all the interior pixels, thus leaving only the boundary pixels on.

H. Contour and C-label

Contour is a curve along which the function has a constant value. A contour line (often
just called a "contour") joins points of equal elevation (height) above a given level. These
different levels are represented by different colored boundaries. Contour-f function gives
a better view of the system by each level with different colors. C-label adds height labels
to a 2-D contour plot, providing a better insight to the image.

22
4.2 Execution

4.2.1. User Interface Design

The prototyping of the GUI is done by pencil2.0.3 tool .

Fig 4.2.1.1. Prototyping

23
4.2.2 Test Cases
Initial image Expected Output Obtained Output

Table 4.2.2.1. Test cases

5 Results and Discussion

24
This paper focuses upon the detection and visualization of a tumour in the brain from CT
images. By developing the proposed architecture, the demarcation of the tumour in the CT
image is obtained. The following results showcase the outputs received after each step in the
algorithm.

After the original image undergoes pre-processing transformations we get figure 5.2 from
figure 5.1. These basic pre-processing transformations include:

1. Changing the image to greyscale, as we need to find contour of the final image which
works on greyscale images.
2. Applying low pass filter, to remove any noise, if present, in the image.
3. Applying high pass filter, to obtain sharpened image with clear-defined boundaries.

Fig. 5.1. Original image Fig. 5.2. Pre-processed image

Series of steps that lead to figure 5.3 from figure 5.2 are:

25
 1. Eroding with structural element of big radius, say 6, to erode more.
2. Dilating with structural element of small radius, say 3, to dilate lesser than erode.
3. Use morphological open to get same amount of erosion and dilation, to estimate
background

Fig. 5.3. Background estimation Fig. 5.4. Contrast adjustment when

background is subtracted

Transitions from figure 5.3 to figure 5.4 and figure 5.5 happens by following steps mentioned
below:
1. Negate background.
2. Delete background from eroded iamge.
3. Delete negative of background form eroded image.
4. Find contrast of both subtracted images.

26
Fig. 5.5. Contrast adjustment when negative Fig. 5.6. Subtraction of images to result in
of background is subtracted tumor region

Subtracting figure 5 from figure 6 results in figure 7.

Fig. 5.7. Threshold image Fig.5.8. Boundary detection

In order to obtain figure 5.7 from figure 5.6 we take threshold of tumor region image (figure
5.7), in this process we convert the image to binary.

For boundary detection we use an inbuilt MATLAB function, bwmorph.

27
Fig. 5.9. Contour of original image Fig. 5.10. Contour of tumour region

Fig. 5.11. Contour of tumour boundary

Finally, we find contour of grey image, tumor region (figure 5.10) and tumor boundary
(figure 5.11).

28
A GUI, programmed in MATLAB shows the following step by step user interfaces.

Fig 5.12. Interface to select an image.

Fig 5.13. Start screen of GUI

29
Fig 5.14. Contour of selected image in GUI

Fig 5.15. Contourf of selected image in GUI

30
Fig 5.16.C-label of selected image in GUI

Fig 5.17. Interface to print current display in GUI

31
6 Conclusion and Future Enhancements
The proposed algorithm is inputted with gray scale images of brain that contain tumour/s. The
image is processed through various stages of morphological operations like filtering, contra
adjustment, erosion, dilation etc. through MATLAB programming. Hence, the tumour is outlined
in the original image and clearly demarcated. Contour plot and c-label plot is created to provide
3D visualization from the 2D image. A GUI is also developed which enables the above
application with a user friendly interface.

Table 6.1. Table to show accuracy of algorithm

Image CPU time (in sec) PSNR

6.2656 +25.84 db

4.0156 +25.25 db

6.7344 +26.70 db

32
 4.7188 +25.73 db

Possible extension of the presented work could use more features. It would be beneficial to
connect the system to cloud storage of patient’s information in hospital. The application can be
extended to accessibility and usability through mobile phones.

7 References
[1] W.Gonzalez, “Digital Image Processing”, 2nd ed. Prentice Hall, Year of Publication 2008.
[2] Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing, Second Edition.
[3] Rafael C. Gonzalez, Richard E. Woods, Steve L. Eddins, Digital Image Processing Using MATLAB, 2003.
[4] 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
[5] 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
[6] 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
[7] Mustaqeem, Anam, Ali Javed, and Tehseen Fatima, “An efficient brain tumor detection algorithm using
watershed and thresholding based segmentation”, International Journal 4, 2012
[8] P.Dhanalakshmi, T.Kanimozhi, “Automated Segmentation of Brain Tumor using K-Means Clustering and
its area calculation”, IJAEEE, 2013.
[9] Q.Hu, G. Quian, A. Aziz, W.L.Nowinski,”Segmentation of Brain from Computed Tomography head
images,” Engineering in Medicine and Biology 27 th Annual Conference, 2005.
[10] 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.
[11] 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.
[12] 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.
[13] 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.
[14] 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.

33
 APPENDIX-I
MATLAB
MATLAB (matrix laboratory) is a multi-paradigm numerical computing environment
and fourth-generation programming language. It uses the L-shaped membrane logo. Developed
by MathWorks, MATLAB allows matrix manipulations, plotting of functions and data,
implementation of algorithms, creation of user interfaces, and interfacing with programs written
in other languages, including C, C++, Java, and FORTRAN.

MATLAB® is a high-level language and interactive environment for numerical computation,

visualization, and programming. Using MATLAB, we can analyze data, develop algorithms, and
create models and applications. The language, tools, and built-in math functions enable us to
explore multiple approaches and reach a solution faster than with spreadsheets or traditional
programming languages, such as C/C++ or Java™.
Although MATLAB is intended primarily for numerical computing, an optional toolbox uses
the MuPAD symbolic engine, allowing access to symbolic computing capabilities. An additional
package, Simulink, adds graphical multi-domain simulation and Model-Based
Design for dynamic and embedded systems.
In 2004, MATLAB had around one million users across industry and academia. MATLAB users
come from various backgrounds of engineering, science, and economics. We can use MATLAB
for a range of applications, including signal processing and communications, image and video
processing, control systems, test and measurement, computational finance, and computational
biology.
Cleve Moler, the chairman of the computer science department at the University of New Mexico,
started developing MATLAB in the late 1970s. He designed it to give his students access
to LINPACK and EISPACK without them having to learn Fortran. It soon spread to other
universities and found a strong audience within the applied mathematics community. Jack Little,
an engineer, was exposed to it during a visit Moler made to Stanford University in 1983.
Recognizing its commercial potential, he joined with Moler and Steve Bangert. They rewrote
MATLAB in C and founded MathWorks in 1984 to continue its development.
The MATLAB application is built around the MATLAB language, and most use of MATLAB
involves typing MATLAB code into the Command Window (as an interactive
mathematical shell), or executing text files containing MATLAB code, including scripts
and/or functions.

GUIDE
GUIs (also known as graphical user interfaces or UIs) provide point-and-click control of
software applications, eliminating the need to learn a language or type commands in order to run
the application.

34
MATLAB apps are self-contained MATLAB programs with GUI front ends that automate a task
or calculation. The GUI typically contains controls such as menus, toolbars, buttons, and sliders.
Many MATLAB products, such as Curve Fitting Toolbox, Signal Processing Toolbox, and
Control System Toolbox, include apps with custom user interfaces. You can also create your own
custom apps, including their corresponding UIs, for others to use.
MATLAB supports developing applications with graphical user interface features. MATLAB
includes GUIDE (GUI development environment) for graphically designing GUIs. It also has
tightly integrated graph-plotting features. For example the function plot can be used to produce a
graph from two vectors x and y.
To create GUI in MATLAB follow the steps listed below.
1. Click on GUIDE button on toolbar in MATLAB launch pad.
2. Make your choice of the type of GUI you need.
3. Make buttons and/or menus from the tools in GUIDE.
4. Double click on menu that is created in grey area of the GUIDE, property manager will
open.
5. Change properties according to requirement and change the code if needed.

THRESHOLD
Thresholding is the simplest method of image segmentation. From a grayscale image,
thresholding can be used to create binary images. Sezgin and Sankur (2004) categorize
thresholding methods into the following six groups based on the information the algorithm
manipulates.
1. Histogram shape-based methods, where, for example, the peaks, valleys and curvatures
of the smoothed histogram are analyzed

2. Clustering-based methods, where the gray-level samples are clustered in two parts as
background and foreground (object), or alternately are modeled as a mixture of two
Gaussians

3. Entropy-based methods result in algorithms that use the entropy of the foreground and
background regions, the cross-entropy between the original and binarized image, etc.

4. Object Attribute-based methods search a measure of similarity between the gray-level

and the binarized images, such as fuzzy shape similarity, edge coincidence, etc.

5. Spatial methods [that] use higher-order probability distribution and/or correlation

between pixels

6. Local methods adapt the threshold value on each pixel to the local image characteristics.

35
We have considered Otsu’s method of thresholding in the proposed algorithm. The algorithm
assumes that the image to be thresholded contains two classes of pixels or bi-modal histogram
(e.g. foreground and background) then calculates the optimum threshold separating those two
classes so that their combined spread (intra-class variance) is minimal.

CONTOUR
A contour line (also isoline, isopleth, or isarithm) of a function of two variables is a curve along
which the function has a constant value. In cartography, a contour line (often just called a
"contour") joins points of equal elevation (height) above a given level, such as mean sea level.
A contour map is a map illustrated with contour lines, for example a topographic map, which
thus shows valleys and hills, and the steepness of slopes. The contour interval of a contour map
is the difference in elevation between successive contour lines.
More generally, a contour line for a function of two variables is a curve connecting points where
the function has the same particular value. The gradient of the function is always perpendicular
to the contour lines. When the lines are close together the magnitude of the gradient is large: the
variation is steep. A level set is a generalization of a contour line for functions of any number of
variables.
Contour lines are curved, straight or a mixture of both lines on a map describing the intersection
of a real or hypothetical surface with one or more horizontal planes. The configuration of these
contours allows map readers to infer relative gradient of a parameter and estimate that parameter
at specific places. Contour lines may be either traced on a visible three-dimensional model of
the surface, as when a photogrammetrist viewing a stereo-model plots elevation contours, or
interpolated from estimated surface elevations, as when a computer program threads contours
through a network of observation points of area centroids. In the latter case, the method
of interpolation affects the reliability of individual isolines and their portrayal of slope, pits and
peaks.

36
CONTOUR-F
Contour-f can be explained through its name, ‘contour-filled’. A filled contour plot displays
isolines calculated from matrix Z and fills the areas between the isolines using constant colors
corresponding to the current figure's colormap. It is filled two-dimensional contour plot.
Contourf (Z) draws a filled contour plot of matrix Z, where Z is interpreted as heights with
respect to the x-y plane.Z must be at least a 2-by-2 matrix that contains at least two different
values. The number of contour lines and the values of the contour lines are chosen automatically
based on the minimum and maximum values of Z. The ranges of the x- and y-axis
are [1:n] and [1:m], where [m,n] = size(Z).

C-LABEL
C-label stands for ‘Contour plot elevation labels’. In other words, the clabel function adds height
labels to a two-dimensional contour plot.

37
CT IMAGES
X-ray computed tomography (x-ray CT) is a technology that uses computer-processed x-rays to
produce tomographic images(virtual 'slices') of specific areas of the scanned object, allowing the
user to see what is inside it without cutting it open. Digital geometry processing is used to
generate a three-dimensional image of the inside of an object from a large series of two-
dimensional radiographic images taken around a single axis of rotation. Medical imaging is the
most common application of x-ray CT. Its cross-sectional images are used for diagnostic and
therapeutic purposes in various medical disciplines. The rest of this article discusses medical-
imaging x-ray CT; industrial applications of x-ray CT are discussed at industrial computed
tomography scanning.
As x-ray CT is the most common form of CT in medicine and various other contexts, the
term computed tomography alone (or CT) is often used to refer to x-ray CT, although other types
exist (such as positron emission tomography [PET] and single-photon emission computed
tomography [SPECT]). Older and less preferred terms that also refer to x-ray CT are computed
axial tomography (CAT scan) and computer-assisted tomography. X-ray CT is a form
of radiography, although the word "radiography" used alone usually refers, by wide convention,
to non-tomographic radiography.
There are several advantages that CT has over traditional 2D medical radiography. First, CT
completely eliminates the superimposition of images of structures outside the area of interest.
Second, because of the inherent high-contrast resolution of CT, differences between tissues that
differ in physical density by less than 1% can be distinguished. Finally, data from a single CT
imaging procedure consisting of multi-planar reformatted imaging.

38
 APPENDIX-II
PSEUDO CODE
function varargout = simple_gui(varargin)
% SIMPLE_GUI M-file for simple_gui.fig
% SIMPLE_GUI, by itself, creates a new SIMPLE_GUI or raises the existing
% singleton*.
% H = SIMPLE_GUI returns the handle to a new SIMPLE_GUI or the handle to
% the existing singleton*.
% SIMPLE_GUI('CALLBACK',hObject,eventData,handles,...) calls the local
% function named CALLBACK in SIMPLE_GUI.M with the given input arguments.
% SIMPLE_GUI('Property','Value',...) creates a new SIMPLE_GUI or raises the
% existing singleton*. Starting from the left, property value pairs are
% applied to the GUI before simple_gui_OpeningFcn gets called. An
% unrecognized property name or invalid value makes property application
% stop. All inputs are passed to simple_gui_OpeningFcn via varargin.
% *See GUI Options on GUIDE's Tools menu. Choose "GUI allows only one
% instance to run (singleton)".
% See also: GUIDE, GUIDATA, GUIHANDLES

% Begin initialization code - NOT TO BE EDITED

gui_State =
create struct {'gui_Name', mfilename, ...
'gui_Singleton', gui_Singleton, ...
'gui_OpeningFcn', @simple_gui_OpeningFcn, ...
'gui_OutputFcn', @simple_gui_OutputFcn, ...
'gui_LayoutFcn', [] , ...
'gui_Callback', []};

39
% End initialization code - NOT TO BE EDITED

% --- Executes just before simple_gui is made visible.

function simple_gui_OpeningFcn(hObject, eventdata, handles, varargin)
% This function has no output args, see OutputFcn.
% hObject handle to figure
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
% varargin command line arguments to simple_gui (see VARARGIN)

%initial plotting_New Algorithm

Start
Open dialog box to read image
Read image
Change to grayscale
Original image = grayscale image
Sharpen the image
Blur the image to get noiseless image
Erode (blurred image); //structural element radius higher than dilation
Dilate (eroded image); //structural element radius lower than erosion
Estimate background
Negate background
Sub (Negative of background from Eroded image)
Sub (Background from Eroded image)
Contrast (Sub (Negative of background from Eroded image))
Contrast (Sub (Background from Eroded image))
Dilate (Contrast (Sub (Background from Eroded image)))

40
Sub ((Dilate (Contrast (Sub (Background from Eroded image)))) from (Contrast (Sub (Negative
of background from Eroded image))))
Tumor = Resulting image
Threshold (Tumor)
Tumor_Boundary = Boundary (Threshold (Tumor))
Current Data = Original Data
Show(Original Image);

% Choose default command line output for simple_gui

% Update handles structure
% UIWAIT makes simple_gui wait for user response (see UIRESUME)
% uiwait(handles.figure1);

% --- Outputs from this function are returned to the command line.
function varargout = simple_gui_OutputFcn(hObject, eventdata, handles)
% varargout cell array for returning output args (see VARARGOUT);
% hObject handle to figure
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)

% Get default command line output from handles structure

% --- Executes on selection change in disp_type.
function disp_type_Callback(hObject, eventdata, handles)
% hObject handle to disp_type (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)

41
% Hints: contents = cellstr(get(hObject,'String')) returns disp_type contents as cell array
% contents{get(hObject,'Value')} returns selected item from disp_type

val=get(value from drop down list)

Switch (val)
Case 1
Current Data = Original Image
Case 2
Current Data = Tumor
Case 3
Current Data=Tumor_Boundary;
end
% Update handles structure

% --- Executes during object creation, after setting all properties.

function disp_type_CreateFcn(hObject, eventdata, handles)
% hObject handle to disp_type (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles empty - handles not created until after all CreateFcns called

% Hint: popupmenu controls usually have a white background on Windows.

% See ISPC and COMPUTER.
if ispc && isequal(get(hObject,'BackgroundColor'), get(0,'defaultUicontrolBackgroundColor'))
set(hObject,'BackgroundColor','white');
end

42
% --- Executes on button press in clabel.
function clabel_Callback(hObject, eventdata, handles)
% hObject handle to clabel (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
clabel(contour(Current Data));

% --- Executes on button press in contour.

function contour_Callback(hObject, eventdata, handles)
% hObject handle to contour (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
Contour (Current Data);

% --- Executes on button press in contourf.

function contourf_Callback(hObject, eventdata, handles)
% hObject handle to contourf (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
Contour (Current Data);

% --- Executes on button press in new_img.

function new_img_Callback(hObject, eventdata, handles)
% hObject handle to new_img (see GCBO)

43
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
simple_gui_OpeningFcn(~,~, handles);

44