Performance Analysis For Detection And Classification Of Lung Cancer Using Machine Learning Approaches

Abstract

Chest X-ray is often the initial imaging test used to detect abnormalities in the lungs, it's not usually sufficient for confirming a diagnosis of lung cancer. Instead, additional imaging tests like CT scans, MRI scans, or PET scans may be needed for a more detailed evaluation. These tests can provide more information about the size, location, and spread of any suspicious areas in the lungs, helping doctors to make a more accurate diagnosis.  Automated lung cancer classification is one of the important tasks due to the different mechanisms used for imaging the lungs of patients. Using training and testing methodology, machine learning approaches to identify lung cancer have shown excellent detection and classification potential. In this paper, we have demonstrated an effective approach for detecting and classifying lung cancer-related CT scan images using image processing techniques, and then further supervised machine learning algorithms are used for their classification of lung cancer. We have extracted texture features along with statistical features and supplied various extracted features to classifiers using three different classifiers known as the k-nearest neighbors’ classifier, support vector machine classifier, and random forest classifier. Based on the numerical illustrations, the best results are mentioned with high accuracy.