Transformative Impact of AI on Early Diagnosis and Treatment of Lung Cancer with a Decade of Advances in Medical Imaging and Prognosis

Cancer is the second leading cause of mortality worldwide, largely due to low survival rates resulting from diagnosis at advanced stages. This paper focuses on how machine learning (ML) and deep learning (DL) algorithms have evolved over the past decade to improve cancer detection and classification, emphasizing the importance of early diagnosis. Convolutional Neural Networks (CNNs) have demonstrated an accuracy of 89.5% in medical image recognition, highlighting their effectiveness in imaging-based diagnosis. Recent advancements such as YOLOv7 further outperform traditional diagnostic methods by providing more accurate tumor detection. Prognostic analysis using Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks has achieved accuracies of 82.3% and 84.7%, respectively. Ensemble methods exhibit superior performance with an impressive accuracy of 91.2%, outperforming individual models. Additionally, data augmentation using Generative Adversarial Networks (GANs) improves precision to 76.8%, underscoring the importance of synthetic data generation in addressing data scarcity. These findings collectively demonstrate the transformative impact of artificial intelligence in oncology and emphasize the significance of integrated, collaborative approaches for achieving improved cancer diagnosis and treatment outcomes.