Although dMRI tractograophy has been successfully used to examine brain connectivity, its limitation, mainly in specificity, has also been reported. In this study, we generated a comprehensive mouse brain streamline database based on 2700+ viral tracer data from Allen Institute. The database was used as a ground truth to train a deep learning network to estimate fiber orientations from diffusion MRI data of the mouse brain. Compared to conventional methods, the deep learning network provided more accurate estimation of fiber orientation leading to improved tractography.
This abstract and the presentation materials are available to members only; a login is required.