Early Detection of Lung Cancer from CT Scan Images using Deep Neural Networks

Lung cancer remains one of the leading causes of cancer-related deaths worldwide, accounting for approximately 25% of all cancer fatalities. Early and accurate detection is critical to reducing the associated mortality rate. However, manual diagnosis from chest X-rays and CT scans is challenging, particularly in the early stages, due to the potential for human error and subtle disease presentation. This study proposes a robust automated system for lung cancer detection using deep learning techniques, specifically a Convolutional Neural Network (CNN), to classify CT scan images as cancerous or non-cancerous. The system was developed and evaluated using the publicly available LUNA16 dataset. Preprocessing steps were applied to enhance the CT scan images, including segmentation techniques to isolate lung regions and generate binary masks as input for the model. Advanced methodologies such as data augmentation, batch normalization, and transfer learning were employed to optimize the model’s performance. The proposed approach achieved a remarkable accuracy of 98.6%, outperforming previously developed models. This deep learning-based system demonstrates significant potential for early-stage lung cancer detection, offering radiologists a reliable tool to manage the growing volume of diagnostic images. By providing accurate and efficient results, this technology has the potential to improve patient outcomes significantly. Impact Statement —Lung cancer is one of the deadliest diseases globally, and early detection is crucial to reducing its high mortality rate. The increasing burden on radiologists to analyze large volumes of radiographs often compromises diagnostic accuracy. Automated systems for early lung cancer detection can alleviate this burden, providing precise and efficient diagnoses that improve treatment outcomes. These systems can seamlessly integrate into clinical workflows, enabling medical professionals to focus on patient care while leveraging accurate insights from advanced image analysis. Additionally, these technologies facilitate the development of innovative treatment strategies by accurately delineating cancer dimensions and locations. Such advancements pave the way for a new era in cancer diagnosis and management.