Sie sind auf Seite 1von 27

Project Report On Breast Cancer Wisconsin

BREAST CANCER WISCONSIN


Submitted in partial fulfilment of the requirements for
The award of degree of

BACHELOR OF ENGINEERING
IN
COMPUTER SCIENCE & ENGINEERING

Submitted By: Submitted To:

Abhishek Shukla (17BCS2137) Ms. Jagmeet kaur


Ankush Rai (17BCS2142) Assistant Professor
Department Of Computer Science and
Engineering.

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING


Chandigarh University, Gharuan

1
Project Report On Breast Cancer Wisconsin

DECLARATION

We hear by declare that the project entitled “BREAST CANCER WISCONSIN”


submitted by Abhishek Shukla and Ankush Rai to the Department of computer
science and engineering, Chandigarh university, Mohali in partial fulfilment of the
requirement for the award of degree of Bachelor of Engineering in Computer
science engineering is a record of bonfide project work carried out by us under
guidance of Ms. Jagmeet Kaur.

We further declare that this project is an original piece of work and it is not
submitted for any other evaluation in any other university.

Submitted By:

Abhishek Shukla (17BCS2137)


Ankush Rai (17BCS2142)

Date: April 04, 2019

2
Project Report On Breast Cancer Wisconsin

ACKNOWLEDGEMENT

We have taken efforts in this project. However, it would not have been possible
without the kind support and help of many individuals and teachers. We would like
to extend our sincere thanks to all of them.

We are highly indebted to CHANDIGARH UNIVERSITY for their guidance and


constant supervision as well as for providing necessary information regarding the
project & also for their support in completing the project.

We would like to express our gratitude towards our parents & member of
Chandigarh University for their kind co-operation and encouragement which help
me in completion of this project.

We would like to express our special gratitude and thanks to industry persons for
giving me such attention and time.

Our thanks and appreciations also go to our colleague in developing the project and
people who have willingly helped me out with their abilities.

Abhishek Shukla
Ankush Rai

3
Project Report On Breast Cancer Wisconsin

ABSTRACT
The Wisconsin Breast Cancer Epidemiology Simulation Model is a discrete-event,
stochastic simulation model using a systems-science modelling approach to replicate
breast cancer incidence and mortality in the U.S. population from 1975 to 2000. Four
interacting processes are modelled over time: natural history of breast cancer, breast
cancer detection, breast cancer treatment, and competing cause mortality. These
components form a complex interacting system simulating the lives of 2.95 million
women (approximately 1/50 the U.S. population) from 1950 to 2000 in 6-month cycles.
After a “burn in” of 25 years to stabilize prevalent occult cancers, the model outputs age-
specific incidence rates by stage and age-specific mortality rates from 1975 to 2000. The
model simulates occult as well as detected disease at the individual level and can be used
to address “What if?” questions about effectiveness of screening and treatment protocols,
as well as to estimate benefits to women of specific ages and screening histories. Breast
cancer is the leading malignancy affecting women in the United States today, with over
180,000 women estimated to be diagnosed in 2008. It is the second leading cause of
breast cancer mortality with over 40,000 women who will succumb to this disease. When
we think about breast cancer in terms of its incidence, the incidence has been steadily
increasing over the last quarter century. There has, however, been a slight decline in the
incidence rates over the last 5 years. Why is this? Is it due to a reduction in breast cancer
pick-up rates with screening mammography declining over the last 5 years, or is it
modified risk factors? For example, hormone therapy use has declined by 50%. We are
going to be discussing the risk factors today that contribute to breast cancer incidence and
talking about how we can modify these in order to prevent breast cancer in the future.

The Gompertzian growth rate for an individual tumour is fixed at its onset by a random
draw from a gamma distribution of growth rates common to all tumours in the model and
women of all ages. The mean and variance of this gamma distribution (Mean gamma and
Var gamma in Table 1) were fitted in the model calibration process described below. In
each 6-month cycle possible metastatic spread of the tumour is simulated stochastically by
a random draw from a Poisson distribution determining number of new positive lymph
nodes in that period; the Poisson distribution mean is a function of current tumour size
and instantaneous growth rate developed by Shwartz.

4
Project Report On Breast Cancer Wisconsin

List of Figures
Figure No. Title Page No.
1. Data Flow Diagram 17
2. UML Diagram 18
3. Analysis the data and find the accuracy 20
4. Using GUI tkinter 22

5
Project Report On Breast Cancer Wisconsin

Table of Contents

Sr. No. Topic Page No.


1. Declaration 2
2. Acknowledgement 3
3. Abstract 4
4. List of Figures 5
5. Chapter 1. Introduction 7
6. Chapter 2. SRS (Software requirement specification) 10
7. Chapter 3. Architecture Diagram 17
8. Chapter 4. Project methodology 19
9. Chapter 5. Screen Short 20
10. Chapter 6. Conclusion and Future Scope 25
11. References 27

6
Project Report On Breast Cancer Wisconsin

Chapter 1 Introduction

Breast cancer is the leading malignancy affecting women in the United States today, with over
180,000 women estimated to be diagnosed in 2008. It is the second leading cause of breast cancer
mortality with over 40,000 women who will succumb to this disease. When we think about breast
cancer in terms of its incidence, the incidence has been steadily increasing over the last quarter
century. There has, however, been a slight decline in the incidence rates over the last 5 years.
Why is this? Is it due to a reduction in breast cancer pick-up rates with screening mammography
declining over the last 5 years, or is it modified risk factors? For example, hormone therapy use
has declined by 50%. We are going to be discussing the risk factors today that contribute to breast
cancer incidence and talking about how we can modify these in order to prevent breast cancer in
the future.

When you think about breast cancer risk, there are a number of factors that we look at; some are
modifiable, others are not. One of the most common questions we get asked as breast cancer
clinicians is why did I get breast cancer? I do not have a family history, I have never taken
hormones, I eat right, I exercise, I go to church on Sundays, why did I get breast cancer?

Well, the easy answer is "I don't know," but truthfully, being a woman puts you at increased risk
of developing breast cancer. This is one of the most common no modifiable risk factors.
Remember, too, that men can get breast cancer and 1% of all breast cancers do occur in men.
However, women account for the vast majority of breast cancer patients.

Also, as women get older, breast cancer rates increase. The average age for detecting breast
cancer is 61 and this peaks at the 70-to-74 age group. However, it is the least in the 20-year-old
age group. Genetic mutations also increase the risk of developing breast cancer. Generally, we
talk about BRCA1 and BRCA2 gene mutations. These can increase your lifetime risk of
developing breast cancer, making this about 85%. This also increases your risk of ovarian and
breast cancer. It is important, too, to realize that it is not just the BRCA1/2 gene mutations that
increase your risk of developing breast cancer, other genetic mutations also increase breast cancer
risk. These include mutations in other genes, such as P-10 or P-53, and there are other genetic
mutations that are still yet to be discovered.

Having a personal history of breast cancer certainly increases your risk of contra lateral breast
cancer, so any patient who has a breast cancer in one breast is at 0.5% to 1% per year increased
risk of developing cancer in the contra lateral breast. Family history also increases your risk so
anyone who has an Ashkenazi Jewish heritage, patients who have a first-degree family relative
who has multiple breast cancers, or a breast or ovarian cancer, having multiple family relatives
who have breast cancer, or a family history of male breast cancer, all put you at increased risk of
developing breast cancer.

7
Project Report On Breast Cancer Wisconsin

Even without a family history or a personal history of developing breast cancer, there are other
risk factors.

For example, patients who have very dense breasts mammographic ally have been found to be at
increased risk of developing breast cancer. Their increased risk is anywhere from 1.8- to 6.0-fold
over the general population. Other benign conditions also increase your risk of developing breast
cancer.

This ranges from proliferative disorders without atypiato atypical ductal and lobular hyperplasia
all the way up to lobular carcinoma in situ. As we move across this spectrum, the risk of
developing breast cancer increases so patients with proliferative changes have about a 1.5- to 2-
fold increased risk. Patients with atypical hyperplasia are at a 4- to 5-fold increased risk and
patients with lobular carcinoma in situ have an up to 12-fold increased risk over those who do not
have lobular carcinoma in situ. It has long been known that reproductive factors increase your
risk of developing breast cancer and this is thought to be due to the number of ovulatory cycles
that a woman has. So the estrogens that you produce yourself increase your risk of developing
breast cancer. This is why patients who have very early menarche or late menopause, who are
nulliparous, or who have a late age at first full-term pregnancy are all at increased risk for
developing breast cancer.

Similarly, exogenous hormones have also been found to increase your risk of developing breast
cancer. Whether this is with oral contraceptive pills, which can minimally increase your risk of
developing breast cancer, or hormone therapy, particularly with estrogens and progestogen,
which have a 1.2- to 4-fold increased risk of developing breast cancer, any exogenous hormones
have been found to increase your risk of developing breast cancer.

Overweight, obesity, and a number of dietary factors have been looked at as potential risk factors
for developing breast cancer. People have looked at whether dietary fat impacts the risk of
developing breast cancer -- fruits and vegetable intake, calcium, vitamin D. There have been no
consistent results. More recent studies that have looked at calcium and vitamin D
supplementation, however, may yield a potential risk factor for developing breast cancer, so there
have been some studies that have found that increased calcium and increased vitamin D
supplementation may reduce one's risk of developing breast cancer. Certainly, further studies to
evaluate this in greater detail are warranted. In addition, lack of physical activity has been
consistently found to be a risk factor for developing breast cancer. Patients who engage in
consistent physical activity have been found to have a reduced risk of developing breast cancer.
The more physical activity, the lower the risk. Another consistent factor that has been found to be
associated with breast cancer is alcohol consumption. When we look at people who consume high
amounts of alcohol versus those who do not consume alcohol at all, there is a correlation between
alcohol consumption and breast cancer risk.

8
Project Report On Breast Cancer Wisconsin

Another area that has been widely studied has been high-dose radiation. People have investigated
people who have been survivors of Nagasaki and Hiroshima, and those who have had mantle
radiation for Hodgkin's disease; these patients are at extremely high risk of developing breast
cancer. There are, potentially, other risk factors that we still do not know about, some that are
potentially modifiable and others that are not.

Knowledge of risk factors and their potential implication in terms of breast cancer genesis is
important. Not only can these risk factors help us to quantify a patient's risk, but they can also,
potentially, be modified so that we can modulate risk downwards, potentially, affecting the
incidence of breast cancer in the future. Thank you for your attention.

9
Project Report On Breast Cancer Wisconsin

Chapter 2 SRS

This breast cancer databases was obtained from the University of Wisconsin Hospitals, Madison
from Dr. William H. Walberg. If you publish result when using this database, then please include
this information in your acknowledgements. Also, please cite one or more of:

1. O. L. Mangasarian and W. H. Walberg: "Cancer diagnosis via linear programming", SIAM


News, Volume 23, Number 5, September 1990, pp 1 & 18.

2. William H. Walberg and O.L. Mangasarian: "Multisurface method of pattern separation for
medical diagnosis applied to breast cytology", Proceedings of the National Academy of Sciences,
U.S.A., Volume 87, December 1990, pp 9193-9196.

3. O. L. Mangasarian, R. Setiono, and W.H. Walberg: "Pattern recognition via linear


programming: Theory and application to medical diagnosis", in: "Large-scale numerical
optimization", Thomas F. Coleman and Yuyin Li, editors, SIAM Publications, Philadelphia 1990,
pp 22-30.

4. K. P. Bennett & O. L. Mangasarian: "Robust linear programming discrimination of two


linearly inseparable sets", Optimization Methods and Software 1, 1992, 23-34 (Gordon & Breach
Science Publishers).

2.1 Sources:

-- Dr. William H. Walberg (physician)

University of Wisconsin Hospitals

Madison, Wisconsin

USA

-- Donor: Olvi Mangasarian (mangasarian@cs.wisc.edu)

Received by David W. Aha (aha@cs.jhu.edu)

10
Project Report On Breast Cancer Wisconsin

-- Date: 15 July 1992

2.2 Past Usage:

Attributes 2 through 10 have been used to represent instances.

Each instance has one of 2 possible classes: benign or malignant.

1. Walberg, ~W. ~H., \& Mangasarian, ~O.~L. (1990). Multi surface method of pattern
separation for medical diagnosis applied to breast cytology. In

-- Size of data set: only 369 instances (at that point in time)

-- Collected classification results: 1 trial only

-- Two pairs of parallel hyper planes were found to be consistent with 50% of the data

-- Accuracy on remaining 50% of dataset: 93.5%

-- Three pairs of parallel hyper planes were found to be consistent with 67% of data

-- Accuracy on remaining 33% of dataset: 95.9%

2. Zhang, ~J. (1992). Selecting typical instances in instance-based

Learning. In {\it Proceedings of the Ninth International Machine

Learning Conference} (pp. 470--479). Aberdeen, Scotland: Morgan Kaufmann.

-- Size of data set: only 369 instances (at that point in time)

-- Applied 4 instance-based learning algorithms

-- Collected classification results averaged over 10 trials

-- Best accuracy result:

-- 1-nearest neighbour: 93.7%

-- trained on 200 instances, tested on the other 169

-- Also of interest:

-- Using only typical instances: 92.2% (storing only 23.1 instances)

11
Project Report On Breast Cancer Wisconsin

-- trained on 200 instances, tested on the other 169

2.3. Relevant Information:

Samples arrive periodically as Dr. Walberg reports his clinical cases.

The database therefore reflects this chronological grouping of the data.

Group 1: 367 instances (January 1989)

Group 2: 70 instances (October 1989)

Group 3: 31 instances (February 1990)

Group 4: 17 instances (April 1990)

Group 5: 48 instances (August 1990)

Group 6: 49 instances (Updated January 1991)

Group 7: 31 instances (June 1991)

Group 8: 86 instances (November 1991)

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

Total: 699 points (as of the donated database on 15 July 1992)

Note that the results summarized above in Past Usage refer to a dataset of size 369,
while Group 1 has only 367 instances. This is because it originally contained 369 instances; 2
were removed. The following Statements summarize changes to the original Group 1's set of
data:

#. Number of Instances: 699 (as of 15 July 1992)

# Number of Attributes: 10 plus the class attribute

12
Project Report On Breast Cancer Wisconsin

2.4. Attribute Information: (class attribute has been moved to last column)

# Attribute Domain

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

1. Sample code number id number

2. Clump Thickness 1 - 10

3. Uniformity of Cell Size 1 - 10

4. Uniformity of Cell Shape 1 - 10

5. Marginal Adhesion 1 - 10

6. Single Epithelial Cell Size 1 - 10

7. Bare Nuclei 1 - 10

8. Bland Chromatin 1 - 10

9. Normal Nucleoli 1 - 10

10. Mitoses 1 - 10

11. Class: (2 for benign, 4 for malignant)

8. Missing attribute values: 16

There are 16 instances in Groups 1 to 6 that contain a single missing

(i.e., unavailable) attribute value, now denoted by "?".

2.5. Class distribution:

Benign: 458 (65.5%)

Malignant: 241 (34.5%)

13
Project Report On Breast Cancer Wisconsin

3. External Interface Requirements


3.1 User Interfaces

Operating
Windows 95 or NT or superior
system

Pentium processor at 90 MHz or


CPU
higher

Memory 16 MB RAM

Hard drive 80 MB available in the hard disk

Media CD-ROM, 2x or higher

Graphics
DirectX 3.0 or higher
hardware

3.2 Software Interfaces

A software interface for breast cancer screening and detection, comprising: a visualization screen
where a thermal image of at least one breast of a subject is displayed, pixels in said displayed
thermal image having a highest temperature value being displayed in a first colour and pixels
having a lowest temperature value being displayed in a second colour, pixels with temperature
values between said lowest and highest temperature values being displayed in gradations of
colour between said first and second colours; and a plurality of selectable software objects at least
comprising

o Python: -Python is a popular and powerful interpreted language. Unlike R, Python


is a complete language and platform that you can use for both research and
development and developing production systems .There are also a lot of modules
and libraries to choose from, providing multiple ways to do each task. It can feel
over whelming .The best way to get started using Python for machine learning is
to complete a project.

14
Project Report On Breast Cancer Wisconsin

o Tkinter: - Python offers multiple options for developing GUI (Graphical User
Interface). Out of all the GUI methods, tkinter is most commonly used method. It
is a standard Python interface to the Tk GUI toolkit shipped with Python. Python
with tkinter outputs the fastest and easiest way to create the GUI applications.
Creating a GUI using tkinter is an easy task.

o Anaconda spyder: - Spyder is a powerful scientific environment written in


Python, for Python, and designed by and for scientists, engineers and data
analysts. It features a unique combination of the advanced editing, analysis,
debugging and profiling functionality of a comprehensive development tool with
the data exploration, interactive execution, deep inspection and beautiful
visualization capabilities of a scientific package. Furthermore, Spyder offers built-
in integration with many popular scientific packages, including NumPy, SciPy,
Pandas, IPython, QtConsole, Matplotlib, SymPy, and more. Beyond its many
built-in features, Spyder's abilities can be extended even further via first- and
third-party plugins

4. System Features
It is a new ensemble of features for breast cancer diagnosis. Abstract: In this paper,
an automatic Computer Aided Diagnosis (CAD) system is completely designed for breast
cancer diagnosis and it is verified on a publicly available mammogram dataset
constructed during Image Retrieval in Medical Applications (IRMA) project.

o Python
o tkinter
o Numpy
o Pandas
o Sklearn

15
Project Report On Breast Cancer Wisconsin

5. Non-functional Requirements
5.1 Performance Requirements
The Breast Centre must have a nominated Clinical lead, a medically qualified doctor from
any specialty within the core team. This person is responsible for ensuring the
multidisciplinary approach, the full involvement of the breast experts from the core
disciplines and their regular participation in the MDMs, ensuring appropriate levels of
training and continuing medical education by the team members, breast related research
activity, performance based on breast cancer quality indicators, data collection, etc.

5.2 Communication of diagnosis

It is recommended that the diagnosis is given to the patient as soon as possible. A


preliminary communication on the diagnosis can be given to the patient by each specialist
according to their competence. Following the appropriate MDM discussion to confirm the
diagnosis and plan the treatment the results should be given to the patient by the clinician
who will take primary responsibility for providing this treatment to this patient. A breast
care nurse must be available to discuss fully with the patient the options for treatment and
to give emotional support. A suitable room with sufficient privacy should be available.
Each patient has to be fully informed about each step in the diagnostic and therapeutic
pathway and must be given adequate time to consider the options and make an informed
decision

16
Project Report On Breast Cancer Wisconsin

Chapter 3 Architecture Diagram

a) Data flow Diagram

Fig-1

17
Project Report On Breast Cancer Wisconsin

b) UML Diagram

Fig-2

18
Project Report On Breast Cancer Wisconsin

Chapter 4 Project methodology

To ensure consistency with evidence collected and analyzed for the Second Expert Report much
of the methodology following for the Continuous Update Project remains unchanged from that
used previously. Based upon the experience of conducting the systematic literature reviews for
the Second Expert Report some modifications to the methodology were made. The literature
search was restricted to Medline and included only randomized controlled trials, cohort and case-
control studies. The 2008 Continuous Update Project Breast Cancer SLR included studies
published up to December 2007. Publications in foreign languages were not included. Due to the
large number of cohort studies, analysis and interpretation of case-control studies was not
included in the Continuous Update Project SLR. Meta-analyses and forest plots of highest versus
lowest categories were prepared for breast cancer incidence. Studies with mortality endpoints
previously included in analyses were removed. Studies reporting mean difference as a measure of
association are not included in the Continuous Update Project SLR as relative risks estimated
from the mean differences are not adjusted for possible confounders, and thus not comparable to
adjusted relative risks from other studies. (For more information on methodology see the full
2008 Continuous Update Project Breast Cancer SLR (Second Expert Report).

Breast cancer contributes a significant burden to the Australian population. To support the needs
of people affected by breast cancer, a series of 6 best practice resources were developed. The
learning modules within the Breast Cancer package highlight some of these resources and
encourage health professionals working with people affected by breast cancer to implement
evidence based practices. Treatments for breast cancer are complex, given over extended periods
of time, and often result in short and longer term effects. People affected by breast cancer may
need:

1. Information and support to reduce their risk of developing breast cancer due to modifiable
behaviours.
2. Information and effective strategies to find breast cancer early
3. Information about new and emerging approaches to treat and manage breast cancer
4. A coordinated, multidisciplinary approach providing the latest evidence-based care
5. Supportive care approaches to prevent and manage the range of symptoms and effects
associated with breast cancer and its treatment.

19
Project Report On Breast Cancer Wisconsin

Chapter 5 Screen shots

5.1 Analysis the data and find the accuracy

Fig-3

Fig-4

20
Project Report On Breast Cancer Wisconsin

Fig-5

Fig-6

21
Project Report On Breast Cancer Wisconsin

Fig-7

5.2 Using GUI tkinter

Fig-8

22
Project Report On Breast Cancer Wisconsin

Fig-9

Fig-10
23
Project Report On Breast Cancer Wisconsin

Fig-11

Fig=12

24
Project Report On Breast Cancer Wisconsin

Chapter 6 Conclusion and Future Scope

Conclusion
The most important causes of cancer death among middle aged women are due to breast cancer.
Mammography is technique used by radiologists for early detection and diagnosis of cancer in
breast images. Digital mammogram has turned out to be the most effective technique for
premature breast cancer detection. Digital mammogram captures an electronic image of the breast
and accumulates it in a computer. Mammogram images are very noisy, blur, low-contrast and
fuzzy and hence the mammogram images are enhanced for accurate identification of breast
cancer. Processing these images require high computational abilities.

This research work focuses on mammogram images pre-processing and image segmentation
phases. Mammogram images are pre-processed using Dual Tree Discrete Wavelet Transform.
Pre-processed mammogram images are enhanced using curve let transform, contour let transform,
Non- sub sampled contour let transform, fuzzy Enhancement in the second phase of this research
work-means algorithm and EM algorithms are used for efficient image enhancement process for
the enhancement mammogram images.

The mammogram image enhancement technique is evaluated using two datasets which are taken
from the UCI Machine Learning Repository.

The Performance of the proposed mammogram image enhancement is evaluated based on the
following factors:

Mean Squared Error (MSE) and


Peak Signal-to-Noise Ratio (PSNR)

Execution Time
Experimental results showed that all the transform in which the non-subsample contour let
transform is the best and fuzzy enhancement is better than non-subsample contour let transform.
Thus fuzzy enhancement is used for more efficient enhancement images. It suppresses noises
while enhancing weak edges in the textures and boosting the contrast between the lesion area and
the background. It is found from the experiments that Fuzzy image enhancement method using
EM algorithm is efficient and useful in capturing relevant clinical information since its PSNR
value is high with very low MSE value.

The existing methods used in mammogram image enhancement with various image transforms
are: Wavelet Transform. Curve let Transform. Contour let Transform. According to the existing
transforms, it is observed that wavelet analysis to a signal/image, which allows not only to
identify its frequency components, but also the spatial location. The Wavelet Transform
processes the digital enhancement of mammogram imagine the wavelet domain. The Wavelet
Transform consists of steps such as data presentation, searching of the best block to fill, edge
strength, edge orientation and the confidence term. The drawback of Wavelet Transform is with
the problem of filling the missing data will occur and the PSNR value is very low. So, Curve let

25
Project Report On Breast Cancer Wisconsin

transform is used for further enhancement study.

Maximization algorithm shows next ranking but Expectation Maximization algorithm with Fuzzy
enhancement is ranked first since its PSNR value is high with very low MSE values.

Scope for Future Work


This research has focused on providing better and effective noise image Enhancement
Techniques for Mammographic images. The problems like quality of the Enhancement image
with low PSNR value still occur in these methods. In order to solve this issue, further
enhancement and segmentation methods are necessary.
The further enhancement of the proposed methods can be focused on the following ideas for
better performance and for efficient image restoration: Removal of noise from images relies on
differences in the statistical properties of noise and signal. In future care must be taken to deal
with the statistical properties of noise and signal.

Better learning techniques can be used to increase the performance and quality of the method.

It conserved the brightness of the mass core and improved the graininess and small
inhomogeneous regions in the background in an appropriate manner. The enhanced images
retained the inherent nature of mammograms.

A potential direction for future work is applied to improve segmentation method on the enhanced
mammography images, in anticipation of higher segmentation accuracy due to the advantage of
preserving the intensity variations of mammogram.

26
Project Report On Breast Cancer Wisconsin

References
 https://archive.ics.cedu/ml/datasets/Breast+Cancer+Wisconsin+(Diagnostic)

 https://breast-cancer-research.biomedcentral.com/submission-
guidelines/preparing- your-manuscript/short-report

 http://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+%28Diagnos
tic%29

 https://www.python-course.eu/python_tkinter.php

27