Meeting Banner
Abstract #3376

Multiparametric MRI neuroimaging signatures predict cognitive decline in Multiple Sclerosis: a 5-year longitudinal study

Oun Al-iedani1,2, Stasson Lea2, Abdulaziz Alshehri2,3,4, Vicki E. Maltby2,5,6, Rodney Lea2,7, Saadallah Ramadan2,3, and Jeannette Lechner-Scott2,5,6
1School of Biomedical Sciences and Pharmacy, College of Health, Medicine and Wellbeing, University of Newcastle, Callaghan, Australia, 2Hunter Medical Research Institute, New Lambton Heights, Australia, 3School of Health Sciences, College of Health, Medicine and Wellbeing, University of Newcastle, Callaghan, Australia, 4Department of Radiology, King Fahad University Hospital, Dammam, Saudi Arabia, 5Department of Neurology, John Hunter Hospital, New Lambton Heights, Australia, 6School of Medicine and Public Health, College of Health, Medicine and Wellbeing, University of Newcastle, Callaghan, Australia, 7School of Biomedical Sciences, Queensland University of Technology, Brisbane, Australia

Synopsis

Keywords: Multiple Sclerosis, RadiomicsThis novel longitudinal study evaluates multiparametric MRI signature for predicting cognitive decline in multiple sclerosis (MS) cohort followed for 5-years using a penalised regression machine learning approach (GLMnet). 43 MS participants were assessed at baseline and 5-years follow-up. Baseline (input) data consisted of 76 multiparametric MRI measures for different brain regions and tissues. The best performing model was for a change in tARCS (15 features; r=0.7±0.07), which was substantially higher than that for SDMT (r=0.496±0.08). These findings highlight the importance of using measures from multiple MR modalities analysed in combination with machine learning techniques when assessing cognitive decline.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords