<![CDATA[Lung cancer remains the leading cause of cancer-related mortality worldwide, with particularly high incidence in Asia, including Indonesia. The stage at diagnosis is a key determinant of prognosis. Therefore, early and accurate detection is essential to improve survival and quality of life. However, in regions with a high prevalence of infectious diseases such as tuberculosis (TB), diagnostic challenges persist due to overlapping radiographic features that may delay definitive diagnosis and treatment. Recent advancements in artificial intelligence (AI) have introduced promising tools to enhance diagnostic accuracy. Artificial intelligence models, especially those based on deep learning (DL) and convolutional neural networks (CNNs), can automatically detect and classify pulmonary nodules on chest X-rays and computed tomography (CT) scans with remarkable precision. By identifying subtle morphological changes that may be missed by human observers, AI significantly increases sensitivity and reduces interobserver variability. Beyond imaging, computational pathology enables AI to analyze histological slides and molecular profiles, providing faster and more consistent results while alleviating the workload of radiologists and pathologists. Despite these breakthroughs, however, clinical implementation of AI remains limited by data privacy concerns, cybersecurity issues, and the need for large, standardized datasets. Moreover, variations in algorithmic performance across imaging modalities highlight the need for external validation and reproducibility before integration into clinical workflows. This literature review explores the evolving role of AI in lung cancer diagnostics across imaging, pathology, and predictive analytics. Understanding these distinctions is crucial to realizing the full potential of AI in transforming diagnostic precision and improving clinical outcomes.]]>
