No abstract

<span lang="EN-US">Lung cancer, which causes the majority of fatalities worldwide each year, is one of the deadliest diseases. The survival rate of cancer patients could be improved with better cancer detection methods. Image processing and machine learning have both been used to aid in lung cancer detection, but a method that both increase accuracy and increases a patient’s survival rate has yet to be identified. In an effort to find the most effective method for the accurate lung cancer recognition, this paper analyses and compares several classification algorithms. Lung computed tomography (CT) images are enhanced by removing noise using a median filter. For filtered image, threshold segmentation is used to segment it into distinct parts. From the segmented image different features are extracted using the grey level co-occurrence matrix (GLCM). several classification strategies, including support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), and decision tree (DT) methods, are used to classify lung images as malignant or normal based on the extracted features. Methods are evaluated based on a number of various performance measures, like accuracy, a precision, the recall, and the F1-Score. Based on the experimental outcomes, SVM outperforms other classification methods in accurately detecting lung cancer with an accuracy of 99.32%.</span>