Advancements in Optimization Algorithms for Lung Nodule Detection and Classification: A Review

Lung cancer remains a leading cause of cancer-related deaths globally. Timely identification and categorization of lung nodules are crucial for improving prognoses and survival rates. This review explores various optimization algorithms applied to the detection and classification of lung nodules, analyzing their effectiveness in computed tomography (CT) scans. The study delves into evolutionary, swarm-based, and gradient-based algorithms, evaluating their impact on sensitivity, specificity, accuracy, and computational efficiency. It also compares traditional machine learning, deep learning, and hybrid models while addressing associated challenges and proposing potential solutions.