An enhanced decision support system for breast tumor identification in screening mammograms using combined classifier
M. Suganthi, M. Madheswaran · 2010
An enhanced Computer Aided Clinical Decision Making System using Multiple classifier systems (MCSs) based on the combination of a set of different classifiers for classifying the breast tumor as malignant and benign has been developed and presented in this paper. The Multilayer Back Propagation Neural Network (MBPN), Radial-Basis-Function Neural Network (RBFNN), Asymmetrical Support Vector Machine (ASVM) and combined classifier with major voting method, behaviour-knowledge space method have been used to classify the tumor. The multiple features with optimal feature selection and combined classifier with behaviour-knowledge space method is found to have the accuracy 99.97%. The performance of the proposed clinical decision support system has been estimated and found that this hybrid system will provide valuable information to the physicians in clinical pathology.