Related Experiment Video
Updated: Aug 11, 2025
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
Multicenter Evaluation of AI-generated DIR and PSIR for Cortical and Juxtacortical Multiple Sclerosis Lesion
Piet M Bouman1, Samantha Noteboom1, Fernando A Nobrega Santos1
1From the MS Center Amsterdam, Anatomy & Neurosciences, Amsterdam Neuroscience, Amsterdam UMC, Vrije Universiteit Amsterdam, De Boelelaan 1117, Amsterdam, the Netherlands (P.M.B., S.N., F.A.N.S., M.M.S., J.J.G.G., M.D.S.); Translational Neuroradiology Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, Md (E.S.B., D.S.R.); Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY (E.S.B.); Bio-imaging Institute, University of Bordeaux, Bordeaux, France (G.B.); Neurology Section, Department of Neuroscience, Biomedicine and Movement Sciences, University of Verona, Verona, Italy (M. Castellaro, M. Calabrese); Department of Information Engineering, University of Padova, Padova, Italy (M. Castellaro); NMR Research Unit, Queen Square MS Centre, Department of Neuroinflammation, UCL Queen Square Institute of Neurology, Faculty of Brain Sciences, University College London, London, UK (D.T.C.); National Institute for Health Research University College London Hospitals Biomedical Research Centre, London, UK (D.T.C.); Departments of Neuroradiology (P.E., B.W.) and Neurology (M.M.), School of Medicine, Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany; Neuroimaging Research Unit, Division of Neuroscience Neurology Unit, IRCCS San Raffaele Scientific Institute Vita-Salute San Raffaele University, Milan, Italy (M.F., P.P., M.A.R.); Department of Neuroscience, Rehabilitation, Ophthalmology, Genetics, Maternal and Child Health, University of Genova, Genoa, Italy (M.I., C.L.); IRCCS Ospedale Policlinico San Martino, Largo Rosanna Benzi, Genoa, Italy (M.I., C.L.); Center for Neurologic Imaging, Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Mass (A.M., A.M.P., C.R.G.G.); Department of Radiology and Nuclear Medicine, MS Center Amsterdam, Amsterdam Neurosciences, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands (B.M.); Department of Epidemiology and Data Science, Amsterdam University Medical Center, Amsterdam, the Netherlands (J.W.R.T.); Anatomy & Neurosciences, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands (L.E.J.); and Amsterdam Neuroscience, Brain Imaging and Neurodegeneration, Amsterdam, the Netherlands (L.E.J.).
Abstract:
Background Cortical multiple sclerosis lesions are clinically relevant but inconspicuous at conventional clinical MRI. Double inversion recovery (DIR) and phase-sensitive inversion recovery (PSIR) are more sensitive but often unavailable. In the past 2 years, artificial intelligence (AI) was used to generate DIR and PSIR from standard clinical sequences (eg, T1-weighted, T2-weighted, and fluid-attenuated inversion-recovery sequences), but multicenter validation is crucial for further implementation. Purpose To evaluate cortical and juxtacortical multiple sclerosis lesion detection for diagnostic and disease monitoring purposes on AI-generated DIR and PSIR images compared with MRI-acquired DIR and PSIR images in a multicenter setting. Materials and Methods Generative adversarial networks were used to generate AI-based DIR (n = 50) and PSIR (n = 43) images. The number of detected lesions between AI-generated images and MRI-acquired (reference) images was compared by randomized blinded scoring by seven readers (all with >10 years of experience in lesion assessment). Reliability was expressed as the intraclass correlation coefficient (ICC). Differences in lesion subtype were determined using Wilcoxon signed-rank tests. Results MRI scans of 202 patients with multiple sclerosis (mean age, 46 years ± 11 [SD]; 127 women) were retrospectively collected from seven centers (February 2020 to January 2021). In total, 1154 lesions were detected on AI-generated DIR images versus 855 on MRI-acquired DIR images (mean difference per reader, 35.0% ± 22.8; P < .001). On AI-generated PSIR images, 803 lesions were detected versus 814 on MRI-acquired PSIR images (98.9% ± 19.4; P = .87). Reliability was good for both DIR (ICC, 0.81) and PSIR (ICC, 0.75) across centers. Regionally, more juxtacortical lesions were detected on AI-generated DIR images than on MRI-acquired DIR images (495 [42.9%] vs 338 [39.5%]; P < .001). On AI-generated PSIR images, fewer juxtacortical lesions were detected than on MRI-acquired PSIR images (232 [28.9%] vs 282 [34.6%]; P = .02). Conclusion Artificial intelligence-generated double inversion-recovery and phase-sensitive inversion-recovery images performed well compared with their MRI-acquired counterparts and can be considered reliable in a multicenter setting, with good between-reader and between-center interpretative agreement. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Zivadinov and Dwyer in this issue.
