An integrated approach for detection of masses and macro calcification in mammogram images using dexterous variant median fuzzy c-means algorithm

The proposed contribution uses median fuzzy c-means approach for detection of masses and macrocalcificaiton in mammogram images. Median clustering is a powerful methodology for prototype based clustering of similarity/dissimilarity data. In the MFCM instead of calculating the mean for each cluster to determine its centroid, it calculates the median. This has the consequence of reducing error on the whole clusters with respect to the 1-norm distance metric, as divergent to the square of the 2-norm distance metric. The dataset was collected from Mammographic Image Analysis Society. The result shows the efficient detection of masses and macro calcification better than k-means and Fuzzy C-means.