Performance Analysis of Artificial Neural Networks and Statistical Methods in Classification of Oral and Breast Cancer Stages
R.HariKumar1, N.S.Vasanthi2, M.Balasubramani3

1Dr.R.Harikumar,Professor, ECE Department,.Bannari amman Institute of Technology, Sathyamangalam,India
2Dr.N.S.Vasanthi Professor and Head, Bio tech Department,.Bannari amman Institute of Technology, Sathyamangalam,India
3M.Balasubramani Assistant Professor, ECE Department, .Info Institute of Engineering, Coimbatore, India

Manuscript received on July 01, 2012. | Revised Manuscript received on July 04, 2012. | Manuscript published on July 05, 2012. | PP: 263-269 | Volume-2, Issue-3, July 2012. | Retrieval Number: C0784062312 /2012©BEIESP
Open Access | Ethics and Policies | Cite 
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Cancer staging can be divided into clinical and pathologic stage. In TNM (Tumor, Node, Metasis), prognostic tool have been identified and new methods for prognostic factors have been developed. This paper compares the classification accuracy of the TNM staging system along with that of Chi-Square Test, and Neural Networks. In this investigation, one hundred patients with breast cancer and One hundred twenty five oral cancer patients were studied. The data set using TNM variables (tumor size, number of positive regional nodes, distance metastasis, history of breast feeding, menstrual cycle, hereditary etc) of patients were used as input variables for both the classifications. When TNM classification and Chi-Square methods were compared, it was observed that Chi-Square classification closely followed that of clinical investigation. Artificial neural networks (MLP and RBF) are significantly more accurate than the TNM staging system when both use the TNM prognostic factors alone. New prognostic factors can be added to ANN to increase prognostic accuracy further

Keywords: Oral Cancer stages, Breast Cancer, TNM stages, Chi-square test, neural networks.