Anatomically-Informed Multiple Linear Assignment Problems for White Matter Bundle Segmentation
This work addresses the segmentation of white matter bundles for applications in neuroscience, representing an incremental improvement over existing methods.
The paper tackled the problem of segmenting white matter bundles from human tractograms by proposing a method that integrates both anatomical and geometric information, showing significant improvement over the original method, especially for small bundles.
Segmenting white matter bundles from human tractograms is a task of interest for several applications. Current methods for bundle segmentation consider either only prior knowledge about the relative anatomical position of a bundle, or only its geometrical properties. Our aim is to improve the results of segmentation by proposing a method that takes into account information about both the underlying anatomy and the geometry of bundles at the same time. To achieve this goal, we extend a state-of-the-art example-based method based on the Linear Assignment Problem (LAP) by including prior anatomical information within the optimization process. The proposed method shows a significant improvement with respect to the original method, in particular on small bundles.