Lung Cancer Detection using Machine Learning

Lung cancer is a dangerous disease that taking human life rapidly worldwide. The death of the people is increasing exponentially because of lung cancer. In order to reduce the disease and save a human's life, the automated system is needed. The purpose of the lung cancer detection system is able to detect and provide reliable information to doctors and clinicians from the medical image. To minimize this problem, many systems have been proposed by using different image processing techniques, machine learning, and deep learning techniques. A computed tomography (CT) imaging modality is an efficient technique for medical screening used for lung cancer detection and diagnosis. Physician and radiologist use the CT scan images to analyze, interpret and diagnose the lung cancer from lung tissues. However, in most cases, obtaining an accurate diagnosis result without using the extra medical tool known as a computer- Aid detection and Diagnosis (CAD) system is tedious work for many physicians. To obtain an accurate result from computer-aided diagnosis system lung segmentation methods are basic once. So in this project, we have used different lung segmentation and nodules segmentation methods. Our work has consisted of preprocessing, and lung segmentation by using thresholding, and also used the U-net model for detection of the candidate nodules of the patient’s lung CT scan and classification methodology. We have used a convolutional neural network and designed a 3D CNN model that has a 0.77% accuracy performance.