International Research Journal of Education and Technology

The primary aim of this project is to develop a robust lung cancer detection system utilizing a hybrid approach that combines Convolutional Neural Networks (CNN) and Transformer models. The problem statement centers on the challenges associated with accurately identifying lung cancer in CT images, which can lead to delayed diagnosis and treatment. The methodology involves the collection of a diverse dataset of annotated CT images from various sources, followed by comprehensive image preprocessing techniques to enhance image quality and remove noise. The CNN is employed for initial feature extraction, capturing intricate patterns indicative of lung cancer, while the Transformer model is integrated to improve contextual understanding and classification accuracy by leveraging attention mechanisms. Lung cancer is one of the most prevalent and lethal forms of cancer globally, accounting for a significant number of cancer- related deaths each year. Early detection is critical for improving treatment outcomes and survival rates. Traditional diagnostic methods, such as radiological imaging and manual interpretation, often suffer from limitations including variability in accuracy, reliance on the expertise of radiologists, and time-consuming processes. This highlights the urgent need for innovative solutions that leverage advanced technologies to enhance the reliability and speed of lung cancer detection.

Key Words: Lung cancer detection, Convolutional Neural Networks, Transformer model, CT images, deep learning, diagnostic tools.