Microcalcification detection in mammograms using interval type-2 fuzzy logic system with automatic membership function generation

Breast cancer is an important deleterious disease. Mortality rate from this cancer is effectively high and rapidly increasing. The detection at the earlier state can help to reduce the mortality rate. In this paper, we apply the interval type-2 fuzzy system with automatic membership function generation using the Possibilistic C-Means (PCM) clustering algorithm. We utilize four features, i.e., B-descriptor, D-descriptor, average intensity of the inside boundary, and intensity difference between the inside and the outside boundaries. We also compare the result with the result from the interval type-2 fuzzy logic system with automatic membership function generation using the Fuzzy C-Means (FCM) clustering algorithm. The interval type-2 fuzzy system with PCM membership functions generation yields the best result, i.e., 89.47% correct classification with only 6 false positives per image.