Optimized Artificial Neural Network based Digital Mammogram Analysis for Breast Cancer Diagnosis
Satish Saini, Ritu Vijay · International Journal of Multimedia and Ubiquitous Engineering · 2017
This paper works on the detection of the breast cancer at early stage, by utilizing the mammogram images.This work pre-processes the given image by using histogram equalization to enhance the contrast of the image.Then the grey level co-occurrence matrix is used to extract the features from the image.The extracted features are reduced to the significant subset of features by using the sequential backward selection.Then, the image is classified as malignant or benign on the basis of significant subset of features by using the ANN classifier.Moreover, ANN classifier is optimized by selecting the optimized error value as stopping criteria.The result comparison and analysis on DDSM and MIAS datasets using parameters sensitivity, specificity, accuracy signifies effectiveness of the work.