Hybrid Fuzzy and Swarm Intelligence based on Experimental Learning for Detection of Breast Tumors Through Mammography Image Analysis

In this study a hybrid fuzzy intelligent method for management of uncertainty sources in characterization of breast tumors in mammography images has been proposed . Moreover, A hybrid fuzzy evolutionary model has been applied for optimizing and boosting efficiency of the system. Applying soft computing models attempt at analysis of the mammography images based on their features . For this Fuzzy-TBO,, Fuzzy-PSO-TLBO models have been proposed and investigated. The performance evaluation was conducted using the Receiver Operator Characterization (ROC) analysis in terms of accuracy and area under the ROC curve. In order to evaluate the results, a 10-fold cross validation technique was conducted. The obtained results reveal an accuracy of 96.27% for the determining different types of masses based on the tumors’ features according to the images. The presented model competes and outperforms other proposed models in previous studies. The outcome of this study may be hopeful for the means of apropos diagnosis and representing effective treatments.