Abstract #4353
Using Diffusion and Structural MRI for the Automated Segmentation of Multiple Sclerosis Lesions
Pedro A. Gmez 1,2 , Tim Sprenger 1,2 , Ana A. Lpez 1 , Jonathan I. Sperl 2 , Brice Fernandez 3 , Miguel Molina-Romero 1,2 , Xin Liu 1,2 , Vladimir Golkov 1,2 , Michael Czisch 4 , Philipp Saemann 4 , Marion I. Menzel 2 , and Bjoern H. Menze 1
1
Technical University Munich, Munich,
Germany,
2
GE
Global Research, Munich, Germany,
3
GE
Healthcare, Munich, Germany,
4
Max
Plank Institute of Psychiatry, Munich, Germany
This work proposes to use scalar features calculated
from diffusion MR data alongside structural MR
intensities in the automated segmentation of Multiple
Sclerosis (MS) lesions. We acquired and processed
multi-contrast MR data from 7 MS patients, used random
forests to segment lesions, and evaluated our method via
DICE scores, achieving scores over 0.65. Finally, we
made use of the random forest framework to assess the
discriminative power of the estimated features. We show
that diffusion features estimated from the diffusion
tensor are as discriminative as T1 and T2 intensities
for the classification task.
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.
