Deep Learning Guided Diffusion MRI Tractography in the Mouse Brain

Diffusion MRI (dMRI) tractography is the only tool for non-invasive mapping of macroscopic structural connectivity of the entire brain. Although it has been successfully used to reconstruct large white matter tracts in the human and animal brains, the sensitivity and specificity of dMRI tractography, remained limited. Especially, the fiber orientation distributions (FODs) estimated from dMRI signals, which is key to tractography, may deviate from histologically measured fiber orientation in crossing fibers and gray matter regions. In this study, we demonstrated that a deep learning network, trained using mesoscopic tract tracing data from the Allen Mouse Brain Connectivity Atlas, were able to improve the estimation of fiber orientations from mouse brain dMRI data. Tractography results based on the network generated fiber orientations showed improved specificity while maintaining sensitivity comparable to conventional dMRI tractography. Our result is a proof-of-concept of how mesoscale tract tracing data can guide dMRI tractography and enhance our ability to characterize brain connectivity. ### Competing Interest Statement The authors have declared no competing interest.