Published Paper Details:

Lung cancer continues to pose a significant global health threat, with over 1.15 million new cases diagnosed worldwide, making it the leading cause of cancer-related deaths. While smoking remains the most prominent risk factor for lung cancer, it is crucial to recognize that this disease can also affect individuals who have never smoked. This project introduces a comprehensive framework designed to predict lung cancer at an early stage, offering a ray of hope for individuals facing this life-threatening condition. The framework primarily focuses on the realm of computer science, with machine learning as its cornerstone. Leveraging extensive datasets, we meticulously preprocess the data and employ advanced techniques for feature extraction, including Multi-level Discrete Wavelet Transform, Principal Component Analysis (PCA), and Gray-level Co-occurrence Matrix (GLCM). These texture features serve as critical input for our machine learning classification algorithms. Our system utilizes a range of machine learning classifiers, including Support Vector Machines (SVM), Random Forest, and Artificial Neural Networks (ANN). These classifiers are trained on the extracted features, enabling the system to distinguish between different types of lung cancer. Specifically, we address the classification of non-small-cell lung cancer (NSCLC), with further subcategorization into lung squamous cell carcinoma (LUSC) and lung adenocarcinoma (LUAD), which together constitute approximately 85% of lung cancer cases. Through rigorous evaluation, encompassing essential parameters such as accuracy, recall, and precision, we assess the performance of each classification algorithm. The results obtained empower us to predict whether a given tumor is benign or malignant, facilitating early intervention and treatment. This innovative framework offers a promising avenue for the early detection of lung cancer, potentially saving countless lives. By harnessing the power of machine learning and data analysis, we aim to enhance the prognosis and management of lung cancer, ultimately contributing to a brighter future for those affected by this devastating disease.