Background: Up to date different methods have been used in order to dimensions reduction, classification, clustering and prediction of cancers based on gene expression profiling. The aim of this study is extracting most significant genes and classifying of Diffuse Large B-cell Lymphoma (DLBCL) patients on the basis of their gene expression profiles. Materials and Methods: We studied 40 DLBCL patients and 4026 genes. We utilized Artificial Neural Network (ANN) for classification of patients in two groups: Germinal center and Activated like. As we were faced with low number of patients (40) and numerous genes (4026), we tried to deploy one optimum network and achieve to minimum error. Moreover we used signal to noise (S/N) ratio as a main tool for dimension reduction. We tried to select suitable training data and so to train just one network instead of 26 networks. Finally, we extracted two most significant genes. Result: In this study two most significant genes based on their S/N ratios were selected. After selection of suitable training samples, the training and testing error were 0 and 7% respectively. Conclusion: We have shown that the use of two most significant genes based on their S/N ratios and selection of suitable training samples can lead to classify DLBCL patients with a rather good result. Actually with the aid of mentioned methods we could compensate lack of enough number of patients, improve accuracy of classifying and reduce complication of computations and so running time.