Micro Calcification Detection in Mammogram Images Using Contiguous Convolutional Neural Network Algorithm

The mortality rate decreases as the early detection of Breast Cancer (BC) methods are emerging very fast, and when starting stage BC is detected, it curable. disease depends on image processing techniques, used to identify easily accurately, especially micro calcifications visible mammography they 0.1 mm or bigger, cancer cells about 0.03 mm, which crucial for identifying in area. To achieve this calcification images, necessary focus four main steps presented work. There three significant stages process assigned find using a thermal image; procedures described below. In first process, Gaussian filter technique implemented magnify screening image. During second stage, separated from pre-processed Proposed Versatile K-means clustering (VKC) algorithm with segmentation form centroids then recalculated proposed VKC, takes mean all data points allocated that centroid’s cluster, lowering overall intra-cluster variance comparison prior phase. “means” refers averaging determining new centroid. This eliminates unnecessary areas interest. First, mammogram information taken patient begins Contiguous Convolutional Neural Network (CCNN) method. CCNN classify Micro spot feature values fourth process. assess presence high-definition digital infrared thermography technology knowledge base suggests future diagnostic treatment services breast imaging will be developed. use sophisticated techniques being developed attain greater level consistency. technique’s performance examined different classification parameters like Recall, Precision, F-measure accuracy. Finally, classified based true positive negative values.