Lung cancer remains a significant global health burden, highlighting the critical need for improved early detection strategies. Early diagnosis offers a window for timely intervention and personalized treatment plans, significantly increasing patient survival rates. However, conventional diagnostic methods often exhibit limitations in sensitivity, specificity, and scalability.

This thesis explores the potential of machine learning (ML) as a tool for lung cancer detection in computed tomography (CT) scans. ML algorithms possess a remarkable ability to analyze vast datasets and identify intricate patterns within them. This aptitude translates well to medical image analysis, enabling the analysis of CT scans for the detection of cancerous images with superior accuracy and efficiency.

By implementing and examining various ML techniques, including Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), and Random Forests, the thesis investigates their effectiveness in lung cancer detection. Additionally, it explores robust evaluation metrics like accuracy, robustness, interpretability, and scalability to assess the performance of these models