Detection of masses in digital mammograms using K-means and neural network

Breast cancer is a serious public health problem in several countries. It presents an efficient computer aided mass classification method in digitized mammograms using Neural Network and K Means, which performs benignmalignant classification on region of interest (ROI) that contains mass. This paper presents a research on mammography images using K-means for detecting cancer tumor mass and micro calcification to help of initiated centroid values which have separated for different area of values. One of the major mammographic characteristics for mass classification is texture. Neural Network exploits this important factor to classify the mass into benign or malignant. The statistical textural features used in characterizing the masses are entropy, standard deviation, mean, variance and co-variance. It has used different data groups with more number of samples. In order to estimate the future method. The main aim of the method is to increase the effectiveness and efficiency of the classification process in an objective manner to reduce the numbers of false-positive of malignancies. The proposed technique shows better results in less time complexity (in Seconds).