Pulmonary Prognosis: Predictive Analytics for Lung Cancer Detection

Globally, lung cancer is the primary cause of cancer-related deaths, highlighting the critical need for effective early detection and prognosis techniques. This study investigates the utilization of Deep Learning (DL) and Machine Learning (ML) models for Computed Tomography (CT) scan-based lung cancer screening. An extensive examination of the literature was done to examine current methods, revealing a gap in leveraging advanced models like InceptionV3 and Visual Geometry Group (VGG)-16 on the dataset for lung cancer from the Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases (IQ-OTH/NCCD). The VGG16 model, with a modified architecture, achieved an impressive accuracy of 98.18%, on the data corpus with augmented images, showcasing its potential for precise identification of lung cancer. The findings of this study could result in improved therapeutic outcomes by enhancing early diagnosis and prognosis in patients with lung cancer.