Artificial Intelligence in CT Imaging: A Systematic Review of Diagnostic Accuracy, Clinical Decision–Support Impact, and Integration Pathways

ABSTRACT Artificial intelligence (AI) is rapidly transforming radiology and computed tomography (CT) imaging by enabling automated image analysis, improved diagnostic accuracy, and clinical decision–support. We performed a systematic review of peer‐reviewed studies published between January 1, 2010 and March 31, 2025 to quantify reported gains in diagnostic performance and workflow efficiency, to evaluate clinical decision–support benefits and risks, and to identify integration priorities. We searched PubMed, IEEE Xplore, Scopus, ScienceDirect, and Google Scholar and screened 128 records; 26 studies met the inclusion criteria. Extracted data included study design, AI architecture, sample size, and quantitative performance metrics; study quality was assessed using Newcastle–Ottawa Scales (NOS), Cochrane RoB 2, or AMSTAR 2 as appropriate. Across included studies, AI applications in CT showed consistent improvements in sensitivity, specificity, and time‐to‐diagnosis in specific tasks (notably lung‐nodule detection and intracranial hemorrhage triage), with reported detection‐rate increases up to ∼20% and reduced turnaround times in several real‐world implementations. Barriers include dataset bias, limited external validation, interpretability (“black‐box”) concerns, workflow integration challenges, and evolving regulatory issues. Economic analyses suggest potentially favorable return on investment (ROI) in high‐volume settings but are sensitive to licensing and infrastructure costs. To realize AI's benefits in CT imaging, rigorous multi‐center validation, transparent reporting, human‐centered workflow design, and post‐deployment surveillance are essential.