Leonid Zhukov Леонид Жуков

Level Set Segmentation

Level Set Modeling of DT-MRI Brain Data

Leonid Zhukov, David Breen, Al Barr

Segmentation of anatomical regions of the brain is one of the fundamental problems in medical image analysis. It is traditionally solved by iso-surfacing or through the use of active contours/deformable models on a gray-scale MRI data. Recently, we proposed a technique that uses diffusion properties of tissue available from DT-MRI to segment out brain structures. We develop a computational pipeline starting from raw diffusion tensor data, through computation of invariant anisotropy measures to construction of geometric models of the brain structures. This provides an environment for user-controlled 3D segmentation of DT-MRI datasets. We use a level set approach to remove noise from the data and to produce smooth, geometric models. We apply our technique to DT-MRI data of a human subject and build models of the isotropic and strongly anisotropic regions of the brain. Once geometric models have been constructed they may be combined to study spatial relationships and quantitatively analyzed to produce the volume and surface area of the segmented regions.

L. Zhukov, K. Museth, D. Breen, A.H. Barr and R. Whitaker,
Level Set Segmentation and Modeling of DT-MRI Human Brain Data.
Journal of Electronic Imaging, vol 12, pp 125-133, 2003.

i1_i3_dt_mri_model i1_i3_new_bot-small
i1_i3_dt_mri_side-small

blah

i1_MC-crop i3-scan2_1.25-crop
i1_init-crop i3-scan2-init-crop
i1_LS-crop i3-scan2-dt_mri_segment-crop

blah

i1_MC-dt_mri_segment i3_MC-before-small
i1_LS-dt_mri_segment i3_LS-after-small