Abstract #1597

Improving the T1w/FLAIR ratio as a proxy for the myelin content using machine learning

Gerhard S. Drenthen^1,2, Walter H. Backes^1,2, Jongho Lee³, and Jacobus F.A. Jansen^1,2,4

¹Department of Radiology and Nuclear Medicine, Maastricht University Medical Center, Maastricht, Netherlands, ²Mental Health and Neuroscience (MHeNs) Research Institute, Maastricht University, Maastricht, Netherlands, ³Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea, Republic of, ⁴Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands

Synopsis

Keywords: White Matter, White Matter, Myelin

Motivation: Myelin can be a useful predictor of disease progression and cognitive decline, however it requires dedicated MRI sequences. The T1w/FLAIR-ratio, which is more readily available, has previously been introduced as a proxy for the myelin content.

Goal(s): To assess whether the T1w/FLAIR-ratio can be improved upon using machine learning.

Approach: The T1w/FLAIR-ratio and myelin-water fraction (MWF) are calculated in a prospective (n=13) sample, and a new combination of the T1w and FLAIR ratio is calculated using a multi-layer perceptron (MLP).

Results: The T1w-FLAIR combination from the MLP has a stronger correlation with MWF values in the white matter.

Impact: The T1w/FLAIR-ratio can be used as a proxy for the myelin content. Here, we showed that a more optimal combination of T1w and FLAIR contrasts exist, which relates to the myelin content better.

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.