Scribd
Upload
99 views5 pages

"Breast Cancer Detection and Segmentation in A Mammogram": Abstract

This document proposes a method for detecting and segmenting breast cancer in mammogram images using simple image processing techniques. The method first applies an averaging filter and thresholding to detect malignant tumor regions. It then uses a Max-Mean and Least-Variance technique within a window around detected regions to identify tumors. For segmentation, wavelet transforms and k-means clustering are used to locate and extract the tumor region from the image. The proposed method aims to provide real-time detection and segmentation of breast cancer in mammograms.

Uploaded by

prakash
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
99 views5 pages

"Breast Cancer Detection and Segmentation in A Mammogram": Abstract

This document proposes a method for detecting and segmenting breast cancer in mammogram images using simple image processing techniques. The method first applies an averaging filter and thresholding to detect malignant tumor regions. It then uses a Max-Mean and Least-Variance technique within a window around detected regions to identify tumors. For segmentation, wavelet transforms and k-means clustering are used to locate and extract the tumor region from the image. The proposed method aims to provide real-time detection and segmentation of breast cancer in mammograms.

Uploaded by

prakash
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

Breast Cancer Detection and Segmentation

in a Mammogram
ABSTRACT:
Breast cancer is one of the major causes of death among women. An improvement of early
diagnostic techniques is critical for womens quality of life. Mammography is the main test used
for screening and early diagnosis. Mammography is a well-known method used for the detection
of breast cancer. Many researchers worked in the area of breast cancer detection and proposed
segmentation methods. However, no solution given by researchers is best promising and has
limitations and it is still a challenging problem to solve. We introduce a simple and easy
approach for detection of cancerous tissues in mammogram. Detection phase is followed by
segmentation of the tumor region in a mammogram image. Our approach uses simple image
processing techniques such as averaging and thresholding. We introduce a Max-Mean and Least-
Variance technique for tumor detection.

INTRODUCTION:
Every two minutes a woman is diagnosed with breast cancer. Breast cancer has been one of the
major causes of death among women since the last decades. Breast cancer is the commonest
cancer among women in Singapore. Each year, about 700 women are diagnosed with this cancer.
American statistics classify breast cancer as the second leading cause of death among women
and the most common cause of death among women with an age between 40 and 55 years.
Breast cancer takes years to develop. It is commonly classified into four stages according to size
of tumors and degree of cancer spread from the breast to other parts of the body.
For the detection of breast cancer, various techniques are used in which mammography is
the most promising technique and used by radiologist frequently. Mammogram images are
usually of low contrast and noisy. In breast mammography, bright regions represent cancer. In
some mammogram images, malignant tissues and normal dense tissues both may be present. To
contrast between malignant and normal dense tissues is not possible only through applying
thresholding. Understanding the information of mass regions of cancerous lesions in a
mammogram is necessary and helps to identify the tumor and its segmentation. Therefore,
detection of cancerous lesions in mammogram images becomes an active research area. Many
techniques including computer-aided detection systems and intensity-based methods were
introduced for breast cancer segmentation in mammogram images. However, no solution is best
promising or able to satisfy detection criteria of only including cancerous regions successfully.

EXISTING SYSTEM:
The last decade has seen a significant increase in research concerning microwave-based systems
for detection of breast cancer. Some of the modalities even have gained sufficient maturity to be
tested in clinical environments. Since screening mammography is currently the main test for
early detection of breast cancer, a huge number of mammograms need to be examined by a
limited number of radiologists, resulting misdiagnoses due to human errors by visual fatigue. In
order to improve the diagnostic accuracy and efficiency, computer-aided diagnosis has been
introduced into the screening process.

DISADVANTAGES OF EXISTING SYSTEM:

The breast tissue is heterogeneous, resulting in a complex field distribution in the body.
Efforts should be made towards suppression of clutter due to interferences from the breast
skin, nipple, chest wall, and so on.
Normal breast tissue is lossy at microwave frequencies, and tumors are very small in
cases of early detection.
The higher resolution enlarges the size of the corresponding electromagnetic problem,
which leads to an increase in the computational time required to reconstruct the image.

PROPOSED SYSTEM:
We propose a method including detection followed by segmentation of mammogram images
based on simple image processing techniques which provide good results in real time.
Our method consists of two main steps

1. Detection:In the detection phase, an averaging filter and thresholding operation is


applied on original input image which outputs malignant region area. To find the
malignant tissues, we create a rectangular window around the outputted region area and
apply Max-Mean and Least-Variance technique.
2. Segmentation: In the detection phase, an averaging filter and thresholding operation is
applied on original input image which outputs malignant region area. To find the
malignant tissues, we create a rectangular window around the outputted region area and
apply Max-Mean and Least-Variance technique.

A detection and identification method of mass structure in digital mammogram


images which detect malignant tissues in following steps:
1. Thresholding to remove the background information
2. Apply median filter for random noise removal
3. Extract the binary image contours. Thereafter, morphological open and close
operations to fill the gaps in holes inside the image region.

A segmentation method for mammograms using wavelet and k-means clustering


method in following steps:

1. Discrete wavelet transform is used to extract high level details from MRI images
2. The outputted image is then added to original input image to get sharpened image
3. K-means clustering is performed on sharpened image to locate the tumor region.
4. Final tumor region is extracted by performing thresholding on clustered image.

ADVANTAGES:
A simple and efficient approach to detect the cancer region in mammogram
images.
Robustness of the algorithm it has been tested on mammograms with differing
breast tissue densities.

APPLICATIONS:
Medical imaging applications
Pattern matching
Feature extraction

SYSTEM REQUIREMENTS
HARDWARE REQUIREMENTS:

System: Pentium IV 2.4 GHz.


Hard Disk: 40 GB.
Floppy Drive: 1.44 Mb.
Monitor: 15 VGA Colour.
Ram: 512 Mb.

SOFTWARE REQUIREMENTS:

Operating system : Windows XP/7.


Coding Language : MATLAB

CONCLUSION:
Mammography is widely used in diagnosis and screening.These enhancement tools such as
filters, fractal analysis, and segmentation algorithms like region growing and morphological
operations could be applied to other image processing fields.Edge detection and regions
segmentation algorithms work more efficient when images are preprocessed. In future work,
currently popular Artificial Intelligent techniques could be used into the segmentation and
classification process to increase the efficiency and accuracy of computer-aided diagnosed tools.
These techniques such as neural network could also be applied to segmentation and
classifications of breast tumor in MRI images.

You might also like