Abstract #5029

Cross-modal deep learning to predict multiple sclerosis cervical spinal cord damage with digital monitoring of motor function

Po-Jui Lu^1,2,3, Tim Woelfle^1,2,3, Alessandro Cagol^1,2,3,4, Mario Ocampo-Pineda^1,2,3, Federico Spagnolo^1,2,3,5, Óscar Reyes⁶, Lester Melie-Garcia^1,2,3, Matthias Weigel^1,2,3,7, Jens Kuhle^1,2,8, Ludwig Kappos¹, Johannes Lorscheider^1,2, and Cristina Granziera^1,2,3

¹Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital and University of Basel, Basel, Switzerland, ²Department of Neurology, University Hospital Basel, Basel, Switzerland, ³Translational Imaging in Neurology (ThINk), Department of Biomedical Engineering, University of Basel, Basel, Switzerland, ⁴Department of Health Sciences, University of Genova, Genoa, Italy, ⁵MedGIFT, Institute of Informatics, School of Management, HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland, Sierre, Switzerland, ⁶Indivi (a DBA of Healios AG), Basel, Switzerland, ⁷Division of Radiological Physics, Department of Radiology, University Hospital Basel, Basel, Switzerland, ⁸Multiple Sclerosis Centre, Departments of Biomedicine and Clinical Research, University Hospital and University of Basel, Basel, Switzerland

Synopsis

Keywords: Multiple Sclerosis, Machine Learning/Artificial Intelligence

Motivation: People with multiple sclerosis (PwMS) might suffer from cervical spinal cord atrophy, which can only be assessed through regular MRI follow-up.

Goal(s): Our goal was to explore using deep learning if the smartphone sensor signal can capture structural changes on MRI in PwMS’ cervical spinal cord.

Approach: MPRAGE-based atrophy measures and ten-second signal segments of 166 PwMS were derived. PwMS were split for five-fold cross-validation. A neural network was adapted from a ResNet pretrained on the UK-Biobank sensor dataset. Segment predictions were grouped for the prediction on PwMS.

Results: For the PwMS prediction, the NN achieved sensitivity=0.74, specificity=0.81, and F1=0.80.

Impact: The performance of the proposed cross-modal neural network indicates that smartphone walking tests correlate with structural changes in cervical spinal cord and might assist clinical assessments in multiple sclerosis.

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.