Artificial intelligence-driven change redefining radiology through interdisciplinary innovation

Abstract

Artificial intelligence (AI) is rapidly advancing, yet its applications in radiology remain relatively nascent. From a spatiotemporal perspective, this review examines the forces driving AI development and its integration with medicine and radiology, with a particular focus on advancements addressing major diseases that significantly threaten human health. Temporally, the advent of foundational model architectures, combined with the underlying drivers of AI development, is accelerating the progress of AI interventions and their practical applications. Spatially, the discussion explores the potential of evolving AI methodologies to strengthen interdisciplinary applications within medicine, emphasizing the integration of AI with the four critical points of the imaging process, as well as its application in disease management, including the emergence of commercial AI products. Additionally, the current utilization of deep learning is reviewed, and future advancements through multimodal foundation models and Generative Pre-trained Transformer are anticipated.