Artificial intelligence (AI) is transforming diagnostic radiology by augmenting image interpretation, enhancing diagnostic accuracy, and improving clinical decision-making. Through techniques such as machine learning (ML) and deep learning (DL), AI systems are capable of detecting patterns in imaging data that may be imperceptible to the human eye. These technologies are being applied in various modalities including CT, MRI, X-ray, and ultrasound to aid in lesion detection, disease classification, and prognosis prediction. This paper reviews the role of AI in radiology, focusing on its integration into clinical workflows, the methodologies involved in developing AI algorithms, and its application across major imaging domains. We also explore the limitations, such as data bias, interpretability, and regulatory challenges, while highlighting future opportunities in radiogenomics, explainable AI, and personalized medicine. AI, when responsibly implemented, holds the potential to enhance radiologist productivity, reduce diagnostic errors, and support value-based healthcare.