AWERProcedia Information Technology & Computer Science 1 (2012) 744-750 2 nd World Conference on Information Technology (WCIT-2011) Breast cancer detection with New CMAC neural network model Somaiyeh Dehghan a* a Computer Engineering Department, Ilkhchi Branch, Islamic Azad university, Ilkhchi, Iran. Abstract Breast cancer is the most common and the second most fatal cancer for women. The most effective way to reduce breast cancer deaths is detect it earlier. Nowadays, Fine Needle Aspiration (FNA) is regarded as a practical procedure to diagnose breast cancer. The characteristics of cell nuclei and contextual features serve as the major indicators. The researchers have designed different kinds of classifiers in order to diagnosis breast cancer. Based on the analysis done, CMAC neural network showed faster learning in high dimensional problems, but the main challenge in classification is how to deal with high dimensional attribute space which increase the memory required by CMAC neural network. In the present paper a New- CMAC neural network model is proposed for classification of breast Cancer into benign and malignant category which requires less memory. The results reveal that the proposed model is more useful than any other algorithms and has least training time with respect to other ANNs algorithms. Keywords: Breast cancer; Classification; CMAC neural network model; Datamining Selection and peer review under responsibility of Prof. Dr. Hafize Keser. ©2012 Academic World Education & Research Center. All rights reserved. 1. Introduction Breast cancer is a malignant tumor that has developed from cells of the breast. Breast cancer is the most common cancer in women in many countries. Breast cancer has become a major cause of death among women in developed countries. However earlier treatment requires the ability to detect breast cancer in early stages. Early diagnosis requires an accurate and reliable diagnosis procedure that allows physicians to distinguish benign breast tumors from malignant ones. The automatic diagnosis of breast cancer is an important, real-world medical problem. Thus, finding an accurate and effective diagnosis method is very important [1].The researchers *ADDRESS FOR CORRESPONDENCE: Somaiyeh, Dehghan, Computer Engineering Department, Ilkhchi Branch, Islamic Azad university, Ilkhchi, Iran. E-mail address : so.dehghan@iauil.ac.ir./ Tel.: +98-936-947-9350; fax: +98-412-332-6063.