Abstract:
Abstract
Breast cancer in women is a main public health problem in the world.This
project proposes a method for the early detection of breast cancer in
mammographic images in order to solve technic problems involves machine
quality and visual interpretation of a mammogram is requires a magnifying
glass. The abnormality may be overlooked in a way that for each thousand
cases. So, the probability of false negatives is high. Here the radiologists fail
to detect 10% to 30% of cancers .The data are collected from
Mammography Image Analysis Society database(MIAS) that employs ROI
function which applied to the images to cut off the unwanted portions of
the images and remaining of Region Of Interest(ROI) . The features was
extracted from ROI using Statistical , Wavelet Transform and Gabour Filter.
Those features are classified in two classes normal and abnormal using feed
forward neural network classifier. The proposed method achieved 79.7% of
relative accuracy for classification of breast tissues based on digital
mammogram features analysis.
