Parcellating the intra-splenium based on the traced fiber from tractography

  • Authors:

  • Gaolang Gong;Tianzi Jiang;Sheng Xie;Fuchun Lin

  • Affiliations:

  • National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China;National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China;Department of Radiology, Peking University First Hospital, Beijing, P. R. China;National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, P. R. China

  • Venue:
  • CVBIA'05 Proceedings of the First international conference on Computer Vision for Biomedical Image Applications
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we presented an indirect approach which automatically separates the splenium of corpus callosum on mid-sagittal slice of diffusion tensor image (DTI). The callosal fibers were first extracted to decide the corresponding location in the 2D splenium. Using some specific features determined from their geometric properties, the fibers crossing the splenium were clustered into three bundles, which interconnect bilateral temporal, parietal and occipital lobes, respectively. The sub-regions of the splenium were then demarcated by mapping the clusters to the splenium. Similar distribution pattern of these three sub-regions were obtained by applying our method to two real data sets, which indicated the potential applicability of this approach for the further studies of the splenium.