“School of Cognitive”

Back to Papers Home
Back to Papers of School of Cognitive

Paper   IPM / Cognitive / 11387
School of Cognitive Sciences
  Title:   Atlas-Based Segmentation of Brain Structures in Temporal Lobe Epilepsy Using Optimized Voxel-Based Morphometry
  Author(s): 
1.  M. Shaker
2.  Hamid Soltanianzadeh
  Status:   In Proceedings
  Proceeding: Presented at and Published in the 22nd International Congress and Exhibition of Computer Assisted Radiology and Surgery (CARS?2008), Barcelona, Spain, June 25-28, 2008
  Year:  2008
  Supported by:  IPM
  Abstract:
The purpose of this study was to segment the brain structures in temporal lobe epilepsy (TLE) using 3D T1- weighed magnetic resonance images (MRI). Twelve patients with average age of 43 and standard deviation of 12 years were studied. We used specific preprocessing stages through optimized voxel-based morphometry (VBM) with additional spatial normalization steps to obtain more accurate results. Specific template creation, excluding nonbrain voxels by morphological operations, image registration, gray matter (GM) segmentation, and correction for volume changes are different stages of spatial normalization in optimized VBM. All of the gray matter voxels were labeled using an anatomical atlas to create individual regions for each of the brain structures. In our study, we examined hippocampus, amygdala, and entorhinal cortex which are most affected by TLE. The proposed approaches are evaluated by comparing automatic and expert?s segmentation results and confirming their similarity.

Download TeX format
back to top
scroll left or right