Current State of Artificial Intelligence Adoption and Implementation in Neuroradiology Departments: Insights from a U.S. National Survey.
Authors
Affiliations (2)
Affiliations (2)
- From the Department of Neuroradiology (M.W.), The University of MD Anderson Center, Houston, TX; Department of Radiology and Imaging Sciences (J.W.A.), Indiana University School of Medicine, Indianapolis, IN; American Society of Neuroradiology (R.B.), Oak Brook, IL; Department of Radiology (C.D.), University of Virginia, Charlottesville, VA; Department of Radiology (A.G.), Columbia University Vagelos College of Physicians & Surgeons, New York, NY; Professor and Chair, Department of Radiology (C.P.H.), University of California San Francisco, San Francisco, CA; Professor of Radiology, Mayo Clinic College of Medicine & Science; Chair, Department of Radiology (J.M.H.), Mayo Clinic, Phoenix, AZ; Edward B. Singleton endowed Chair of Radiology (T.H.), Texas' Children's, Houston, TX; Professor and Chair of Radiology (M.V.J.), Warren Alpert School of Medicine at Brown University, Providence, RI; Department of Radiology and Biomedical Imaging (A.M., C.W.), Yale School of Medicine, New Haven CT; Shapiro Chair and Professor of Radiology (A.M.M.), University of Miami, Miller School of Medicine, Miami, FL; Department of Radiology (M.M.-B.), University of Alabama at Birmingham, Birmingham, AL; Kenneth L. and Gloria D. Krabbenhoft Chair and Professor of Radiology (B.P.), University of Iowa - Carver College of Medicine, Iowa City, IA; Radiologist-in-Chief and Lionel W. Young Chair in Radiology (T.Y.P.), Boston Children's Hospital; Professor of Radiology, Harvard Medical School; William P. Timmie Professor of Radiology (A.S.), Department of Radiology & Imaging Sciences, Emory University School of Medicine, Atlanta, GA; University of Cincinnati, Cincinnati (A.V.), OH and Professor and Chair of Radiology (C.W.), Radiologist-in-Chief of the Yale New Have Health System, Dorys McConnell Duberg Professor of Neuroscience, Assistant Dean for Translational Research. [email protected].
- From the Department of Neuroradiology (M.W.), The University of MD Anderson Center, Houston, TX; Department of Radiology and Imaging Sciences (J.W.A.), Indiana University School of Medicine, Indianapolis, IN; American Society of Neuroradiology (R.B.), Oak Brook, IL; Department of Radiology (C.D.), University of Virginia, Charlottesville, VA; Department of Radiology (A.G.), Columbia University Vagelos College of Physicians & Surgeons, New York, NY; Professor and Chair, Department of Radiology (C.P.H.), University of California San Francisco, San Francisco, CA; Professor of Radiology, Mayo Clinic College of Medicine & Science; Chair, Department of Radiology (J.M.H.), Mayo Clinic, Phoenix, AZ; Edward B. Singleton endowed Chair of Radiology (T.H.), Texas' Children's, Houston, TX; Professor and Chair of Radiology (M.V.J.), Warren Alpert School of Medicine at Brown University, Providence, RI; Department of Radiology and Biomedical Imaging (A.M., C.W.), Yale School of Medicine, New Haven CT; Shapiro Chair and Professor of Radiology (A.M.M.), University of Miami, Miller School of Medicine, Miami, FL; Department of Radiology (M.M.-B.), University of Alabama at Birmingham, Birmingham, AL; Kenneth L. and Gloria D. Krabbenhoft Chair and Professor of Radiology (B.P.), University of Iowa - Carver College of Medicine, Iowa City, IA; Radiologist-in-Chief and Lionel W. Young Chair in Radiology (T.Y.P.), Boston Children's Hospital; Professor of Radiology, Harvard Medical School; William P. Timmie Professor of Radiology (A.S.), Department of Radiology & Imaging Sciences, Emory University School of Medicine, Atlanta, GA; University of Cincinnati, Cincinnati (A.V.), OH and Professor and Chair of Radiology (C.W.), Radiologist-in-Chief of the Yale New Have Health System, Dorys McConnell Duberg Professor of Neuroscience, Assistant Dean for Translational Research.
Abstract
Artificial intelligence (AI) is rapidly transforming medical imaging, yet its integration into neuroradiology remains uneven. This survey-based study assesses AI usage, tools, applications, barriers, and future expectations among U.S. neuroradiology departments. This cross-sectional survey questionnaire comprised 19 items, blending multiple-choice, multi-select, and open-ended formats. Descriptive statistics were used to identify patterns in data. Most departments (81%) reported AI use, primarily for stroke-related applications, with smaller numbers using tools for report generation, segmentation, and image quality enhancement. Most clinical tools were FDA-approved. AI had minimal perceived impact on workload, and performance was viewed as variable, with concerns about accuracy and false positives. Cost, integration challenges, and limited efficacy evidence were the main barriers to adoption. Despite these limitations, most respondents anticipated increased AI use over the next five years. Findings underscore the need for clinician-vendor collaboration to realize AI's potential in reducing workload and improving outcomes.