Lungs Cancer Classification using Convolution Neural Network and CT Imaging Modality

Abstract

This is a focus on the strength of in-depth research to control the cancer as a result of medical problems. Revolutionary neural models (CNNs) have become models where he sought a comprehensive and practical understanding of his promise resulting in the production of high quality displays. We care about the new in-depth training for high-quality image recognition training can be achieved at the highest level with the lowest level of flexibility binary image processing. Our goal is to learn the basics features at the beginning of our deep convolutional neural network. This work is a concrete effort to meet an output model with medical level accuracy to classify CT images for Lungs Cancer detection. For experimental setup we are running with Python 3.6.5 for deep learning model development and image processing on 6th generation i7 processor with 32 GB RAM and 2TB SSD hardware. In this endeavor we are working with 8770 images with split and validation in 7016 by 1754 ratio from LUNA16(LUng Nodule Analysis 2016) dataset.