Abstract #4122

Machine learning on resting state fMRI classifies the prevalent underlying disease in subjects with mixed dementia

Gloria Castellazzi^1,2, Letizia Casiraghi^2,3, Giovanni Savini^2,4, Fulvia Palesi^2,5, Paolo Vitali⁶, Nicoletta Anzalone⁷, Elena Sinforiani⁸, Giovanni Magenes¹, Cristina Cereda⁹, Claudia AM Gandini Wheeler-Kingshott^3,6,10, Giuseppe Micieli¹¹, and Egidio D'Angelo^2,3

¹Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy, ²Brain Connectivity Center, C. Mondino National Neurological Institute, Pavia, Italy, ³Department of Brain and Behavioral Sciences, University of Pavia, Pavia, Italy, ⁴Department of Physics, University of Milan, Mialn, Italy, ⁵Department of Physics, University of Pavia, Pavia, Italy, ⁶Brain MRI 3T research center, C. Mondino National Neurological Institute, Pavia, Italy, ⁷Scientific Institute H.S. Raffaele, Milan, Italy, ⁸Neurology Unit, C. Mondino National Neurological Institute, Pavia, Italy, ⁹Genomic and Post-Genomic Center, C. Mondino National Neurological Institute, Pavia, Italy, ¹⁰Queen Square MS Centre Department of Neuroinflammation, UCL Institute of Neurology, London, United Kingdom, ¹¹Department of Emergency Neurology, C. Mondino National Neurological Institute, Pavia, Italy

Evidence from recent studies suggests that machine learning applied on MRI can be used to reliably differentiate Alzheimer disease from other major dementia diseases, e.g. Vascular Dementia (VD). In this work we used a machine learning approach applied on features derived from resting state fMRI (rs-fMRI) to build a model that is able not only to differentiate AD from VD, but also to classify the prevalent underlying disease (AD or VD) in a group of early dementia patients for whom clinical profile presented major overlap between symptoms of AD and symptoms of VD (i.e. mixed dementia subjects, MXD).

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.