International Research Journal of Engineering and Technology (IRJET) Volume: 04 Issue: 03 | Mar -2017
e-ISSN: 2395 -0056
www.irjet.net
p-ISSN: 2395-0072
DETECTION OF BREAST CANCER USING BPN CLASSIFIER IN MAMMOGRAMS Brundha.k[1],Gali Snehapriya[2],Swathi.U[3],Venkata Lakshmi.S[4] ----------------------------------------------------------------------------------------------------------------------------------Abstract: This paper describes a computer-aided detection
of new cancer cases and the 5-year survival is 61%
and diagnosis system for breast cancer, the most common
globally.
form of cancer among women, using mammography. The
Organization) breast cancer causes 450,000 deaths
system relies on the Multiple-Instance Learning (MIL)
worldwide each year [1].
paradigm, which has proven useful for medical decision
to
the
WHO
(World
Health
Mammography remains the most effective and
support in previous works from our team. In the proposed
valuable tool of detection of breast abnormalities and
framework, breasts are first partitioned adaptively into
many applications in the literature proved its effective use
regions. The GLCM Features are extracted from wavelet
in
sub bands. Then, features derived from the detection of
breast cancer diagnosis. X-ray mammography is
currently known as the most cost-effective imaging
lesions (masses and micro calcifications) as well as
modality for the early detection of breast cancer, and thus,
textural features, are extracted from each region and
mammograms are obtained regularly in the breast
combined in order to classify mammography examinations
screening program.
as “normal” or “abnormal”. Whenever an abnormal
A huge number of mammograms are taken by the
examination record is detected, the regions that induced
breast screening program and these mammograms are
that automated diagnosis can be highlighted. Two
visually examined by experts to detect the signs of
strategies are evaluated to define this anomaly detector. In
abnormalities. The sensitivity of mammograms varies
a first scenario, manual segmentations of lesions are used
between approximately 70% and 90%, depending on the
to train an NN that assigns an anomaly index to each
following factors: size and location of the lesion, density of
region; local anomaly indices are then combined into a
the breast tissue, patient age, exam quality and the
global anomaly index. keywords:
According
radiologists interpretation ability [1][2][3].
Computer-aided diagnosis, Grey level co-
Breast calcifications are deposits of calcium within
occurrence Matrix (GLCM), Back Propagation Network
the soft tissue [2][7]. There are two types: macro
(BPN), Wavelet Decomposition.
calcifications and micro calcifications. Micro calcifications
1. INTRODUCTION
(MCs) are tiny deposits of calcium salts which can be
Breast cancer is the second most common cancer in the
located
anywhere
in
breast
tissue.
Although
world and more prevalent in the female population. This is
mammography is considered the most effective screening
the second leading cause of death for women all over the
tool for the examination of breast MCs [2], specific
world. At the international level, it represents nearly 22%
© 2017, IRJET
|
Impact Factor value: 5.181
|
ISO 9001:2008 Certified Journal
|
Page 1649