Description
Artificial intelligence (AI) is increasingly used in radiology to improve diagnostic accuracy and workflow efficiency; however, there is limited standardized research comparing its performance across imaging modalities. This study aimed to evaluate the accuracy and efficiency of AI in X-ray, computed tomography (CT), and nuclear medicine. A systematic review was conducted following PRISMA guidelines, analyzing peer-reviewed studies published between 2015 and 2025. Data were extracted on key performance metrics, including sensitivity, specificity, interpretation time, and error rates, to enable cross-modality comparison. Results demonstrated that AI achieved high diagnostic accuracy in X-ray imaging, with average sensitivity and specificity near 91% and 90%, respectively, though it still had limitations in detecting subtle findings. In CT imaging, AI showed comparable specificity and slightly lower sensitivity while improving the detection of volumetric data and lesions. Nuclear medicine applications primarily demonstrated qualitative benefits, including improved image reconstruction and noise reduction, but lacked standardized quantitative metrics for direct comparison. Across modalities, AI consistently reduced interpretation time and improved workflow efficiency, although variability in study design limited full comparability. Overall, AI serves as an effective clinical decision-support tool that enhances radiologist performance rather than replacing it, highlighting the need for standardized evaluation frameworks and expanded research in nuclear medicine.
Publication Date
Spring 2026
Publisher
The University of Texas MD Anderson Cancer Center
City
Houston, TX
Keywords
artificial intelligence, radiology, X-ray, CT, nuclear medicine, diagnostic accuracy, efficiency
Disciplines
Analytical, Diagnostic and Therapeutic Techniques and Equipment | Diagnosis | Medical Specialties | Medicine and Health Sciences | Radiology
Recommended Citation
Mello, Courtney J.; Galvan, Sophia D.; Williams, Britney R.; Thai, Tuyen T.; Mor, Phuong P.; and Zafar, Saleha, "Artificial Intelligence in Radiology: A Comparative Study of Accuracy and Efficiency Across X-ray, CT, and Nuclear Medicine" (2026). Research Methods Poster Session 2026. 4.
https://openworks.mdanderson.org/rmps26/4
