A Review on Lung Cancer Detection and Prediction

Abstract

A cancer that begins in the lungs and most often occurs in people who smoke is specified as lung cancer. Lung cancer is the main cause of cancer death worldwide. Detection of lung cancer in the earliest stage can be very useful to improve the survival rate of patients. But diagnosis of cancer is one of the major challenging tasks for radiologists due to structure of cancer cell, where most of the cells are overlapped each other. For detecting and predicting lung cancer, an intelligent computer aided diagnosis system can be very much useful for radiologists. This paper proposed an efficient lung cancer detection and prediction by using CNN classifiers. The proposed methodology consists of three stages, i.e. pre-processing, segmentation and classification. Pre-processing stage involves converting the CT image into a gray scale image. Next segmentation is applied to clearly view the cancer affected region. Finally classification is done using CNN classifiers. A convolution neural network applied to analyzing visual imagery. Here MATLAB is used for the development of the project. The objective of this paper is to produce a review on an image processing based system that can detect and predict lung cancer from a CT image.

Keywords: CNN classifier, early detection, image processing, segmentation, prediction, lung cancer