M.B.J. Dijsselhof1, M. Barboure1, M. Stritt2, W. Nordhøy3, A.M. Wink1, L.T. Westlye4,5,6, J.H. Cole7, F. Barkhof1,8, J. Petr9, and H.J.M.M. Mutsaerts1
1Department of Radiology and Nuclear Medicine, Amsterdam Neuroscience, Amsterdam University Medical Center, Amsterdam, Netherlands, 2Mediri GmbH, Heidelberg, Germany, 3Department of Diagnostic Physics, Division of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway, 4Norwegian Centre for Mental Disorders Research (NORMENT), Institute of Clinical Medicine, University of Oslo & Division of Mental Health and Addiction, Oslo University Hospital, Oslo, Norway, 5Department of Psychology, University of Oslo, Oslo, Norway, 6KG Jebsen Centre for Neurodevelopmental Disorders, University of Oslo, Oslo, Norway, 7Dementia Research Centre, Queen Square Institute of Neurology; Centre for Medical Image Computing, University College London, London, United Kingdom, 8Queen Square Institute of Neurology and Centre for Medical Image Computing, University College London, London, United Kingdom, 9Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany
The structural brain-age makes predictions based on changes in tissue integrity. Adding cerebrovascular MRI biomarkers may add sensitivity to physiological and metabolic changes, hence complementing structural brain-age, and possibly improving its early pathology sensitivity. Baseline and follow-up T1w, FLAIR, and ASL data of 233 healthy participants and combinations of features and algorithms were used to predict ‘Cerebrovascular brain-age’.
The ExtraTrees algorithm utilising T1w, ASL, and FLAIR features performed best and showed good longitudinal reproducibility.
This abstract and the presentation materials are available to members only;
a login is required.