Meeting Banner
Abstract #4354

Fully Automated Segmentation of the Cervical Cord Using PropSeg: Application to Multiple Sclerosis

Marios C. Yiannakas 1 , Ahmed Mustafa 1 , Benjamin De Leener 2 , Hugh Kearney 1 , David H. Miller 1 , Julien Cohen-Adad 2 , and Claudia A. M. Wheeler-Kingshott 1

1 NMR Research Unit, Department of Neuroinflammation, Queen Square MS Centre, UCL Institute of Neurology, London, WC1N3BG, United Kingdom, 2 Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada

In this work a fully automated spinal cord segmentation method (PropSeg) is evaluated in a large cohort of people with multiple sclerosis (MS). Measurements of cervical cord cross-sectional area (CSA) were obtained and compared with those obtained through an established semi-automated method which is based on an active surface model. The results from this study suggest that PropSeg is a user-friendly, reliable and time-efficient way of obtaining CSA measurements and if validated in future studies it may prove a promising approach for analysis of large datasets in therapeutic trials in MS.

This abstract and the presentation materials are available to members only; a login is required.

Join Here