Lung Cancer Prediction Using Neural Network Ensemble with Histogram of Oriented Gradient Genomic Features

摘要: This paper reports an experimental comparison of artificial neural network (ANN) and support vector machine (SVM) ensembles their “nonensemble” variants for lung cancer prediction. These learning classifiers were trained to predict using samples patient nucleotides with mutations in the epidermal growth factor receptor, Kirsten rat sarcoma viral oncogene, tumor suppressor p53 genomes collected as biomarkers from IGDB.NSCLC corpus. The Voss DNA encoding was used map nucleotide sequences mutated normal obtain equivalent numerical genomic training selected classifiers. histogram oriented gradient (HOG) local binary pattern (LBP) state-of-the-art feature extraction schemes applied extract representative features encoded nucleotides. ANN ensemble HOG best fit dataset this study accuracy 95.90% mean square error 0.0159. result is promising automated screening early detection cancer. will hopefully assist pathologists administering targeted molecular therapy offering counsel stage patients persons at risk populations.