Vector Field Streamline Clustering Framework for Brain Fiber Tract Segmentation

Brain fiber tracts are widely used in studying brain diseases, which may lead to a better understanding of how disease affects the brain. The segmentation assumed enormous importance analysis. In this article, we propose novel vector field streamline clustering framework for tract segmentations. first expressed and compressed using simplification algorithm. After normalization regular-polyhedron projection, high-dimensional features each computed fed improved deep embedded (IDEC) We also provide qualitative quantitative evaluations IDEC method QB method. Our results help researchers gain perception structure. This work has potential automatically create robust bundle template that can effectively segment while enabling consistent anatomical identification.