Lung Nodules Detection and Classification Using Convolution Neural Network

Abstract

- Lung cancer is one of the most dangerous types among the other type of cancer because is leading to death. The doctors face many difficulties to interpret and identify the cancer from CT-scan images. Therefore, computer aided using image processing and machine learning can be useful for early detection lung nodules and classify to benign or malignant with highly accuracy, less effort and reasonable time. In this proposal convolution neural network suggested to detect and identify the nodules and classify to benign or malignant. Network trained on more than 5000 images and tested with 606 images. The results were highly promised and the network classified all the tested images.