A hybrid artificial neural network classifier based on feature selection using binary dragonfly optimization for breast cancer detection

Abstract

Medical image analysis has become a challenging task as it contributes to disease diagnosis. Breast cancer has been the prominent reason for death among women. While analysing mammogram images, there is a need for clear differentiation of between benign and malignant tissues. Also, early detection of breast masses lead to prediction of breast cancer at the initial stage and minimizes risk of death. In this work, the image is preprocessed using Median filter and is segmented using Fuzzy C Means clustering. Fuzzy C-Means clustering algorithm helps in extracting the region of interest by allocating pixels with similar characteristics into a single group. A pixel may be present in various clusters with different membership values. The belongingness of a pixel to a cluster is decided by the highest membership value. Then the statistical, texture and shape features are extracted from the image. Since there may be many features that are less relevant for classification process, prominent features are selected with the help of Binary Dragonfly Optimization Algorithm and the selected features are fed into a Feed Forward Neural Network trained with Back Propagation Learning to classify the mass as benign or malignant. Experiments are conducted over 320 images from mini-MIAS database out of which 200 ROIs are used in training and 120 ROIs are used in testing phase. The region of interest from given mammogram images are extracted successfully and classified with an accuracy of 98.75%.