Efficacy of Deep Learning Algorithms in Detecting Lung Cancer

Abstract

Lung cancer remains a major public health concern, demanding accurate and timely detection for improved patient outcomes. Deep learning algorithms have demonstrated remarkable potential in various medical applications in the past few years, including lung cancer detection. This study evaluates the effectiveness of deep learning algorithms for detecting lung cancer using diverse datasets of lung cancer images, including X- rays and CT scans. The results, characterized by high sensitivity and accuracy, were achieved using Convolutional Neural Networks (CNNs) that were employed. Overall, deep learning algorithms show great potential in revolutionizing lung cancer detection, leading to improved patient outcomes and early intervention. However, interpretability and trust in AI models remain concerns that medical settings need to address. Keras was chosen as the development tool due to its efficiency in quickly executing tasks. After conducting a comprehensive literature review, the study culminated in suggestions for advancing research and integrating findings into clinical applications.