Abstract Integration of Artificial Intelligence (AI), particularly deep learning, into medical imaging represents a profound shift in diagnostic medicine, moving from purely descriptive analysis to advanced predictive and prescriptive analytics. This Collection explores the rapid advancement of AI-driven tools in their specific fields such as oncology, cardiology, ophthalmology and so on, highlighting their potential to improve diagnostic accuracy, workflow efficiency, and personalized treatment planning. However, significant challenges remain, including the heterogeneity of medical image data, the “black box” nature of some intelligent models, and the critical hurdles of clinical integration and validation. The research presented here addresses these frontiers, showcasing innovations in algorithm development, explainable AI, and translational application. This Editorial synthesizes the contributions and outlines the essential collaborative pathway—uniting computer scientists, clinicians, and regulatory bodies—required to translate algorithmic promise into robust, trustworthy, and equitable clinical tools that genuinely improve patient care. Introduction The advent of Artificial Intelligence (AI) in medical imaging is not just an incremental improvement but a foundational transformation. Using deep learning, these systems promise to move beyond traditional manual interpretation of images—a task subject to human variability and fatigue—towards a future of automated, quantitative, and predictive analytics. The impetus for this shift is clear: an ever-growing volume of imaging data, increasing computational power, and the urgent need for tools that can support clinical decision-making in the face of complex disease patterns. This Collection, "Artificial intelligence and medical imaging” (https://www.nature.com/collections/bjeiihhgfa), captures a snapshot of this dynamic field at a pivotal moment, presenting research that both demonstrates the remarkable potential of these technologies and thoughtfully engages with the substantial obstacles that lie between a well-trained intelligent algorithm and its effective use at the patient’s bedside. The promise: enhancing the diagnostic pipeline The core promise of AI in medical imaging lies in its ability to enhance human expertise. The