Hybrid Systems, Personalized Protocols, and Expansion to Fluoroscopy and PET Imaging

Abstract

Artificial intelligence (AI) has emerged as a transformative force in medical imaging, particularly in enabling low-dose acquisition without compromising diagnostic accuracy. This paper advances the current state of the art by proposing an integrated framework that unifies three frontier directions: (1) hybrid AI systems that seamlessly combine real-time data acquisition optimization with post-processing enhancement, (2) patient-specific personalized imaging protocols driven by clinical metadata and body metrics, and (3) the systematic expansion of AI-driven dose reduction to fluoroscopy and positron emission tomography (PET). We review the theoretical underpinnings of each component, present a unified architecture, discuss anticipated performance gains, and identify the key challenges including model generalizability, regulatory compliance, and computational feasibility that must be resolved for broad clinical adoption. Our analysis suggests that this convergent approach has the potential to reduce cumulative patient radiation exposure by up to 85% while maintaining or exceeding the diagnostic accuracy of standard-dose protocols.