Published Paper Details:

Cancer is one among the most frightful diseases known to man. Most people feel that getting cancer means that their life span has shorten whatever they do to treat themselves. Advancements in the recent treatment have drastically improved the survival rate of patients compared to last 2 � 3 decades. For the early detection of breast cancer mammography is the effective method that is used. Breast cancer is more effectively detected using the digital mammograms. This paper proposes a method for the detection and classification of mass abnormalities in digital mammogram images using multi SVM classifier, Radial Basis Function Neural Network (RBFNN), and Long Short-Term Memory (LSTM) . The objective of this project is to escalate the diagnostic accuracy of image processing and for a more precise classification between malignant and benign abnormalities in mass region which reduces the misclassification of breast images. Normal and abnormal abnormalities are detected from the segmented images using K-means, which correspond to the Regions of Interest (ROIs) or abnormal regions. Gray Level Co-Occurrence Matrices (GLCMs) method is used to extract texture based features from the ROI samples. Using these feature extractions as base, the image will be classified using classification techniques like Support Vector Machine (SVM) and Radial Bases Function Neural Network (RBFNN), and Long Short-Term Memory (LSTM. These classification techniques will be evaluated based on their resulting accuracy.