Lung cancer remains a significant global health challenge, demanding early detection for improved patient outcomes. In recent years, deep learning, notably Convolutional Neural Networks (CNNs), has emerged as a potent tool for lung cancer detection and diagnosis from medical imaging data. This research offers an extensive review of CNN-based approaches for lung cancer detection, highlighting their strengths, limitations, and potential clinical impact. The study discusses the methodology, covering data collection, preprocessing, model architecture selection, training, evaluation, and validation, alongside future directions and clinical implications. CNNs offer researchers and healthcare professionals avenues to augment early detection, personalized treatment planning, and ultimately, enhance patient care in lung cancer management. Through rigorous development and evaluation, CNN models trained on diverse datasets of chest X-rays or CT scans have demonstrated remarkable accuracy in identifying suspicious lung lesions indicative of cancer, often outperforming conventional methods. The proposed study utilizes the GoogleNet (Inception v1) CNN model to detect lung cancer. The performance of GoogleNet improved the accuracy of detection by approximately 4.29% compared to existing methods.

Lung cancer Convolutional Neural Networks (CNNs) Medical imaging GoogleNet (Inception v1)