IJSRSET184881 | Received : 15May 2018 | Accepted :30May2018 |May-June-2018 [(4)8: 312-321]
© 2018 IJSRSET | Volume 4 | Issue 8 | Print ISSN: 2395-1990 | Online ISSN : 2394-4099
Themed Section: Engineering and Technology
312
Breast Cancer Detection in Mammogram Using FuzzyC-Means And
Random Forest Classifier
Aleena Johny
1
, Jincy J Fernandez
2
1
M.Tech Scholar, Department of Computer Science and Engineering, Rajagiri School of Engineering and
Technology Kakkanad, Kochi, India
2
Assistant Professor, Department of Computer Science and Engineering, Rajagiri School of Engineering and
Technology Kakkanad, Kochi, India
ABSTRACT
Breast Cancer is one of the important reasons for death among ladies. Many research has been done on the
diagnosis and detection of breast cancer using various image processing techniques. The proposed work deals
with a technique for extracting the malignant masses in the mammography image for the earlier detection of
breast cancer. The mammography images are complex, and also because of the noisy, inconsistent and
incomplete data, several pre-processing techniques are used to enhance and make clear the targeted areas in the
mammogram images. After segmenting the images into specific regions, based on its homogeneous
characteristics, features are extracted which helps the classification more accurate. In this work, Fuzzy C-Means
method is combined with Random Forest classifier to improve the accuracy.
Keywords: Pre-Processing, Segmentation, Post-Processing, Random Forest Classifier, Fuzzy C-Means.
I. INTRODUCTION
Nowadays, the usage of image processing techniques
in medical science are increasing day by day for the
better diagnosis and treatment of a patient. Medical
imaging helps in revealing the internal organs, which
is useful for the medical practitioners to do
laparoscopic surgeries for viewing body parts without
opening the body. The development of various
medical imaging methods such as CT, MRI, PET, [1]
helps the physicians to find the disease affected area.
Due to the inaccuracy of some image acquisition
systems, noisy images are captured which affects the
overall diagnosis of the patient. So pre-processing [2,3]
plays a key role in image processing which improves
the image quality by suppressing unwanted
distortions in the captured image. Instead of
processing the entire image which increases the
complexity in terms of time and space, the image is
divided into segments/parts based on few important
characteristics [4]. The processing such as feature
extraction are done after the extraction of region of
interest (ROI). Breast cancer is a major cause of death
among all cancers for women aged between 35 to 55
years and continues to be the leading cause of non-
preventable cancer deaths. The proposed work deals
with an approach for extracting the malignant masses
in the mammography image for the detection of
earlier breast cancer. The problem with
mammography images are they are complex. Thus,
image processing and feature extraction methods are
used to assist radiologist for detecting tumour.
Features extracted from suspicious regions in