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

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.