Exposure index (EI) is a critical parameter in digital radiography, providing a quantitative measure of the radiation dose received by the detector. This review examines the significance of EI, methods for its determination, influencing factors, and clinical implications. Additionally, it explores challenges in standardization efforts and the role of emerging technologies, particularly artificial intelligence (AI), in optimizing exposure management. A comprehensive review of literature published over the last two decades was conducted using databases such as PubMed, ScienceDirect, and Google Scholar. Studies addressing EI measurement, clinical applications, and advancements in exposure monitoring technology were analyzed. Guidelines from the International Electrotechnical Commission (IEC), the American Association of Physicists in Medicine (AAPM), and the European Federation of Organizations for Medical Physics (EFOMP) were also reviewed to assess standardization efforts and best practices. Findings highlight the importance of EI in radiation dose optimization and quality control. Despite standardization initiatives, variations persist across manufacturers and imaging systems due to factors such as patient characteristics, beam energy, detector sensitivity, and post-processing algorithms. Artificial intelligence-driven exposure monitoring systems have shown promise in enhancing EI accuracy and enabling real-time dose adjustments. Artificial intelligence technologies have the potential to revolutionize EI utilization by enabling automated exposure optimization, real-time monitoring, and predictive analytics. Future efforts should focus on refining AI algorithms, ensuring cross-platform standardization, and enhancing radiographer training to fully integrate AI into EI-based radiation safety protocols.
Keywords: artificial intelligence; digital radiography; exposure index; quality control; radiation dose optimization; standardization.
Copyright © 2025, Soulis et al.