期刊名称：International Journal of Soft Computing & Engineering
电子版ISSN：2231-2307
出版年度：2012
卷号：2
期号：3
页码：263-269
出版社：International Journal of Soft Computing & Engineering
摘要：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
关键词：Oral Cancer stages; Breast Cancer; TNM;stages; Chi-square test; neural networks.
