A Novel Framework to Classify Cancer through a Consecutive Utilization of Hybrid Feature Selection and Deep Learning

Abstract

Abstract Cancer prediction in the early stage is a topic of major interest in medicine since it allows accurate and efficient actions for successful medical treatments of cancer. Mostly cancer datasets contain various gene expression levels as features with less samples, so firstly there is a need to eliminate similar features to permit faster convergence rate of prediction algorithms. These features (genes) enable us to identify cancer disease, choose the best prescription to prevent cancer and discover deviations amid different techniques. To resolve this problem, we proposed a hybrid novel technique CSSMO-based gene selection for cancer prediction. First, we made alteration of the fitness of Spider Monkey Optimization (SMO) with Cuckoo search (CS) algorithm viz., CSSMO for feature selection, which helps to combine the benefit of both metaheuristic algorithms to discover a subset of genes which helps to predict a cancer disease in early stage. Further, to enhance the accuracy of the CSSMO algorithm, we choose a cleaning process, minimum redundancy maximum relevance (mRMR) to lessen the gene expression of cancer datasets. Next, these subsets of genes are classified using Deep Learning (DL) to identify different groups or classes related to a particular cancer disease. Six different datasets have been utilized to analyze the performance of the proposed approach in terms of cancer sample classification and prediction with Recall, Precision, F1-Score, and confusion matrix. The proposed gene selection method with DL achieves much better prediction accuracy than other existing Deep Learning (DL) and Machine learning models with large gene expression dataset.