Abstract #1553
Adapting and applying the brain age paradigm for clinical imaging in multiple sclerosis (MS)
Jordan Colman1, Olivia Goodkin1,2, Michael Foster2, Nima Mahmoudi3, Mike Wattjes3, Gabriel Gonzalez-Escamilla4, Sergiu Groppa4, Giuseppe Pontillo2,5, Einar August Høgestøl6,7, Lars T Westlye7, Silvia Messina8, Jacqueline Palace8, Rosa Cortese9, Nicola De Stefano9, Alex Rovira10, Jaume Sastre-Garriga10, Stefan Ropele11, Mara Rocca12, Massimo Filippi13, Ahmed Toosy2, Olga Ciccarelli2, Tarek Yousry14,15, Ferran Prados1,2,16, Frederik Barkhof1,2,17,18, and James H Cole1,18
1Centre for Medical Image Computing, University College London, London, United Kingdom, 2Queen Square Multiple Sclerosis Centre, Department of Neuroinflammation, UCL Queen Square Institute of Neurology, London, United Kingdom, 3Medizinische Hochschule Hannover, Hannover, Germany, 4Movement Disorders, Neurostimulation and Neuroimaging, University Medicine Mainz, Mainz, Germany, 5Departments of Advanced Biomedical Sciences and Electrical Engineering and Information Technology, University of Naples "Federico II", Naples, Italy, 6Department of Neurology, Oslo University Hospital, Oslo, Norway, 7Department of Psychology, University of Oslo, Oslo, Norway, 8Nuffield Department of Clinical Neurosciences, Medical Sciences Division, University of Oxford, Oxford, United Kingdom, 9Department of Medicine, Surgery and Neuroscience, University of Siena, Siena, Italy, 10Hospital Universitari Vall d’Hebron, Barcelona, Spain, 11Neuroimaging Research Unit, Department of Neurology, Medical University of Graz, Graz, Austria, 12Neuroimaging Research Unit, Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy, 13Neurology Unit, Neurorehabilitation Unit, Neurophysiology Service, and Neuroimaging Research Unit, Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy, 14Lysholm Department of Neuroradiology, UCLH National Hospital for Neurology and Neurosurgery, London, United Kingdom, 15Neuroradiological Academic Unit, 15. Neuroradiological Academic Unit, London, United Kingdom, 16E-Health Center, Universitat Oberta de Catalunya, Barcelona, Spain, 17Department of Radiology and Nuclear Medicine, VU Medical Centre, Amsterdam, Netherlands, 18Dementia Research Centre, UCL Queen Square Institute of Neurology, London, United Kingdom
Synopsis
Brain-predicted age difference (brain-PAD; brain-predicted age – chronological age) is a potential biomarker for neurodegenerative diseases, including multiple sclerosis (MS). Previous models generally rely on T1-weighted (T1w) MRI brain scans. Here, we developed a deep-learning brain-age prediction model on FLAIR MRI. Our Inception-ResNet-V2 model was more accurate than a current state-of-the-art architecture and the FLAIR based model is comparable to a T1w MRI model. We used saliency maps, showing that areas such as the thalamus and ventricles are salient for brain-age prediction. We applied the FLAIR model to patients with MS, finding significantly higher brain-PAD compared to healthy controls.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here
