A machine learning based approach to fiber tractography

Current tractography pipelines incorporate several modelling assumptions about the nature of the diffusion-weighted signal. We present a purely data-driven and thus fundamentally new approach that tracks fiber pathways by directly processing raw signal intensities. The presented method is based on a random forest classification and voting process that guides each step of the streamline progression. We evaluated our approach quantitatively and qualitatively using phantom and in vivo data. The presented machine learning based approach to fiber tractography is the first of its kind and our experiments showed promising performance compared to 12 established state of the art tractography pipelines.

This abstract and the presentation materials are available to members only; a login is required.

Join Here