<![CDATA[General Background: Radiology has evolved from analog image interpretation to data-intensive digital analysis, creating opportunities for artificial intelligence (AI) to support diagnostic and operational processes. Specific Background: AI, particularly deep learning and convolutional neural networks, is increasingly applied in lesion detection, image segmentation, image reconstruction, workflow triage, and radiomics. Knowledge Gap: Despite rapid adoption, a comprehensive synthesis of AI applications in radiology and the associated technical, ethical, and legal barriers remains necessary. Aims: This review examines current AI applications in medical imaging, their role in precision medicine, and the major challenges affecting clinical implementation. Results: AI demonstrated expert-level performance in detecting pulmonary nodules, breast cancer, and pancreatic lesions; automated segmentation improved quantitative assessment of tumors and neurodegenerative changes; deep learning reconstruction reduced radiation dose and shortened MRI acquisition time; triage systems prioritized urgent findings and reduced turnaround time; and radiomics and radiogenomics enabled non-invasive “virtual biopsy” and prognostic modeling. Novelty: This review integrates diagnostic, operational, and predictive roles of AI across the entire radiology workflow within the concept of augmented intelligence. Implications: AI is positioned as a collaborative tool that supports radiologists and advances precision medicine, while successful adoption depends on explainability, data generalizability, privacy protection, and clear regulatory frameworks. Highlights: • AI supports lesion detection, segmentation, and image reconstruction in medical imaging.• Intelligent triage and scheduling reduce turnaround time and improve radiology workflow.• Radiomics and radiogenomics enable non-invasive tumor characterization and prognosis prediction. Keywords: Artificial Intelligence, Radiology, Deep Learning, Radiomics, Precision Medicine ]]>
