HOVG-Net: A Hybrid Model for the Early Detection of Lung Cancer in Computed Tomography

This chapter explores the development and application of HOVG-Net, a hybrid model designed for the early detection of lung cancer in computed tomography (CT) scans. The model integrates traditional image processing techniques with advanced deep learning architectures, specifically the Circular Hough Transform and VGG-19. The methodology involves several stages, including image acquisition, noise removal, binary conversion, morphological opening, and segmentation using active contours. The HOVG-Net model is then applied to detect and quantify pathological features, such as tumors or cysts, with high accuracy. The chapter also includes experimental investigations, showcasing the model's effectiveness through visual aids and quantitative analysis. The results demonstrate the model's potential to improve diagnostic accuracy and facilitate early intervention. Additionally, the chapter discusses the future scope of the research, aiming to expand the framework to include the classification of different types of lung cancer, thereby enhancing personalized medicine and targeted therapies in oncology.