Abstract
Diffusion MRI fiber tracking provides a non-invasive method for mapping the trajectories of human brain connections, but its false connection problem has been a major challenge. This study introduces topology-informed pruning (TIP), a method that improves the tractography of a target fiber bundle using its own topology information. TIP identifies singular tracts and eliminates them to improve the tracking accuracy. This method was applied to a tractography study with diffusion MRI data collected using two different diffusion sampling schemes (single-shell and grid). The accuracy of the tractography was evaluated by a team of 6 neuroanatomists in a blinded setting to examine whether TIP could improve the accuracy of tractography. The results showed that TIP achieved an average accuracy improvement of 11.93% in the single-shell scheme and 3.47% in the grid scheme. The improvement is significantly different from a random pruning (p-value < 0.001). The diagnostic agreement between TIP and neuroanatomists was comparable to the agreement between neuroanatomists. The proposed TIP algorithm can be used to automatically clean up noisy fibers in deterministic tractography, with a potential to confirm the existence of a fiber connection in basic neuroanatomical studies or clinical neurosurgical planning.