CoBundleMAP: Consistent 2D Parameterization Of Fiber Bundles Across Subjects and Hemispheres

Mohammad Khatami, Regina Wehler, and Thomas Schultz
In proceedings of IEEE Int'l Symposium on Biomedical Imaging, pages 1475-1478, 2019
 

Abstract

We present CoBundleMAP, a manifold learning based method for jointly parameterizing streamlines from diffusion MRI tractography. CoBundleMAP significantly improves the previously proposed BundleMAP approach by establishing anatomical correspondences not only between different subjects, but also between the left and right hemispheres, by introducing a two-dimensional parameterization, by focusing analysis on a reliable core part of the bundle, and via a novel mechanism for feature extraction. We use CoBundleMAP to analyze hemispheric asymmetries, and demonstrate that it improves accuracy in a gender classification task.

Images

Download Paper

Download Paper

Bibtex

@INPROCEEDINGS{Khatami:ISBI2019,
     author = {Khatami, Mohammad and Wehler, Regina and Schultz, Thomas},
      pages = {1475--1478},
      title = {CoBundleMAP: Consistent 2D Parameterization Of Fiber Bundles Across Subjects and Hemispheres},
  booktitle = {IEEE Int'l Symposium on Biomedical Imaging},
       year = {2019},
   abstract = {We present CoBundleMAP, a manifold learning based method for jointly parameterizing streamlines from
               diffusion MRI tractography. CoBundleMAP significantly improves the previously proposed BundleMAP
               approach by establishing anatomical correspondences not only between different subjects, but also
               between the left and right hemispheres, by introducing a two-dimensional parameterization, by
               focusing analysis on a reliable core part of the bundle, and via a novel mechanism for feature
               extraction. We use CoBundleMAP to analyze hemispheric asymmetries, and demonstrate that it improves
               accuracy in a gender classification task.}
}