Deep-ShrimpNet fostered Lung Cancer Classification from CT Images

Abstract

: Lung cancer affects the majority of people, due to genetic changes in lung tissues. Several existing methods on lung cancer detection are utilized with machine learning, but it does not accurately classify the lung cancer and also it takes high computation time. To overwhelm these issues, Deep-ShrimpNet fostered Lung cancer classification from CT images (LCC-Deep-ShrimpNet) is proposed. Initially, the input lung CT images are taken from IQ-OTH/NCCD Lung Cancer Dataset. Then the input lung CT images are pre-processed using Kernel co-relation method. Then these pre-processed lung CT images are given to Bayesian fuzzy clustering for extracting lung nodule region. Then the extracted lung nodule region is given into Deep-ShrimpNet classifier for representing features and classifying the lung CT images as normal (Healthy), Benign, and Malignant. The proposed LCC-Deep-ShrimpNet method is activated in python. The performance of the proposed LCC-Deep-ShrimpNet method attains 26.26%, 16.9%, 12.67%, 21.52% and 24.05% high accuracy, 68.86%, 59.57%, 57%, 62.72% and 65.69% low error rate and 60.76%, 53.67%, 68.58%, 59% and 56.61% low computation time compared with the existing methods.