Performance analysis of lung cancer detection and its classification using deep convolutional neural network with low dose Ct scan lung images over convolutional neural network with increase in classifier accuracy.

Aim: Deep learning plays a vital role in image classification due to its effective and accurate results in classification, prediction, and recognition. The main objective of the study is to detect lung cancer using a low dose computed tomography lung image dataset with deep neural network techniques(Deep CNN and CNN). Materials and Methods: Two groups used in this study are Deep Convolutional Neural Network and Convolutional Neural Network with 5l5 lung images for each sample. Binary Classification is performed for Benign and Malignant lung cancer images using a Deep Convolutional neural network algorithm(N=l0) and Convolutional neural network algorithm(N=l0). Results and Discussion: The accuracy of lung cancer detection using a Deep convolutional neural network is 95% and the Convolutional neural network is 84% with a significance of p=0.03l. Attained significant accuracy ratio (p<0.05 independent sample T-test) in SPSS statistical analysis as well. Conclusion: The proposed Deep Convolutional neural network algorithm seems to be significantly better in predicting lung cancer with more accuracy than a convolutional neural network. [ABSTRACT FROM AUTHOR]