Performance Analysis and Classification of Lung Cancer types Using Machine learning

Lung cancer is a serious health risk, yet doctors are still having difficulty diagnosing it. The precise etiology of cancer and a thorough treatment plan are still unclear despite continued research. The likelihood of successful treatment is increased with early identification. To identify malignant regions within the lung, a variety of image processing techniques are used, such as feature extraction, noise reduction, identification of afflicted areas, and maybe comparison with medical history data related to lung cancer. This study demonstrates how machine learning and image processing technology can be used to accurately classify and forecast lung cancer. The first step is to gather the images. The suggested approach combines the Support Vector Machine (SVM) classifier with two different feature extraction techniques: Local Binary Patterns (LBP) and Gray-Level Co-occurrence Matrix (GLCM). The assessment procedure comprises using the dataset to apply these classifiers and evaluating how well they categorize different forms of lung cancer. Performance indicators like recall, accuracy, precision, and F1-score are used to gauge how well the classifiers work at differentiating between classes. The results of the experiments show that the combination of LBP and SVM achieves the best accuracy rate, at $95.925 \%$, closely followed by GLCM-SVM at $\mathbf{9 3 . 6 7 5 \%}$.