Tc‑Phytate Lymphoscintigraphy for Detection of Sentinel Node: Preliminary Results of the First Year’s Clinical Experience in Isfahan, Iran 99m

The improvement of high through put gene profiling based microarrays technology has provided monitoring the expression valueof thousands of genes simultaneously. detailed examination of changes in expression levels of genes can help physicians to haveefficient diagnosing, classification of tumors and cancer’s types as well as effective treatments. finding genes that can classify thegroup of cancers correctly based on hybrid optimization algorithms is the main purpose of this paper. in this paper, a hybrid particleswarm optimization and genetic algorithm method are used for gene selection and also artificial neural network (ann) is adoptedas the classifier. in this work, we have improved the ability of the algorithm for the classification problem by finding small group ofbiomarkers and also best parameters of the classifier. the proposed approach is tested on three benchmark gene expression datasets: blood (acute myeloid leukemia, acute lymphoblastic leukemia), colon and breast datasets. we used 10 fold cross validation toachieve accuracy and also decision tree algorithm to find the relation between the biomarkers for biological point of view. to test theability of the trained ann models to categorize the cancers, we analyzed additional blinded samples that were not previously used forthe training procedure. experimental results show that the proposed method can reduce the dimension of the data set and confirm themost informative gene subset and improve classification accuracy with best parameters based on datasets.