Synthesis of CSF fraction map using deep neural networks and exploration of its potential application in assessing glymphatic dysfunction

Motivation: Methods to assess the activity of the glymphatic system are required to illustrate an association between glymphatic dysfunction and neurodegenerative diseases. Goal(s): Our aim is to develop a deep neural network-based method to assess glymphatic activity in the human brain. Approach: We trained a deep neural network to generate T2map and CSF fraction map, which is a quantitative CSF measurement. We then compared the predicted CSFF across 60 OASIS-3 subjects, which include both healthy controls and patients with Alzheimer's disease (AD). Results: Significant differences in CSFF were observed in the frontal, temporal, and posterior cingulate cortex and precuneus. Impact: Our method reduces the requirements to acquire additional multi-echo spin-echo T2w images for CSFF analysis. This may enhance the utility of CSFF analysis for assessing the dysfunction in the glymphatic system.