Journal: Journal of Medical Imaging

Article Title: GIFTed Demons: deformable image registration with local structure-preserving regularization using supervoxels for liver applications

doi: 10.1117/1.JMI.5.2.024001

Figure Lengend Snippet: Example of sparse image representation using SLIC: (a) coronal view of 3-D CT lung and liver volume, (b) projection through 3-D supervoxel representation with supervoxel boundaries and (c) with assignment of mean intensity. The SLIC algorithm with different values of the parameter K = 11,000 (top) and K = 5500 (bottom) shows that clustering is consistent in image regions with sufficient structural information (close to edges, e.g., the sliding surfaces of lungs), while different clusters are generated in homogeneous image regions.

Article Snippet: The computation time per registration using the presented framework is ≈ 3 min per 3-D pair (on a standard CPU, running nonoptimized C++ code, MATLAB™ mex compiler) and is several times faster than our previous bilateral filtering procedure ( ≈ 60 min ) or the locally adaptive anisotropic regularization (several hours).

Techniques: Generated

Journal: Journal of Medical Imaging

Article Title: GIFTed Demons: deformable image registration with local structure-preserving regularization using supervoxels for liver applications

doi: 10.1117/1.JMI.5.2.024001

Figure Lengend Snippet: Main anatomical views of 3-D CT registration results for case #P0 of the liver dataset: (a) coronal, (b) axial, and (c) sagittal views for the color-coded (red-cyan) intensity differences between volume pair before registration (left), after registration using Demons with isotropic Gaussian kernel, iso-dem, (middle), and guided image filtering with random SLIC clustering, rdn-gif, (right). Registration using our method (right) improves registration accuracy especially close to the lung and liver surfaces (depicted by corresponding red dotted and green solid arrows, respectively).

Article Snippet: The computation time per registration using the presented framework is ≈ 3 min per 3-D pair (on a standard CPU, running nonoptimized C++ code, MATLAB™ mex compiler) and is several times faster than our previous bilateral filtering procedure ( ≈ 60 min ) or the locally adaptive anisotropic regularization (several hours).

Techniques:

Journal: Journal of Medical Imaging

Article Title: GIFTed Demons: deformable image registration with local structure-preserving regularization using supervoxels for liver applications

doi: 10.1117/1.JMI.5.2.024001

Figure Lengend Snippet: Main anatomical views of resulting 3-D displacement fields for case #P0 of the liver CT dataset: (a) coronal, (b) axial, and (c) sagittal views for the color-coded magnitude of the displacement field estimated using Demons with isotropic Gaussian kernel, iso-dem, (middle) and guided image filtering with random SLIC clustering, rdn-gif, (right). (left) The reference image with the corresponding blue contour is shown for a guidance to the displacement field. Registration using our method (right) produces a visually smooth displacement field inside the lungs and liver, and at the same, estimates sliding motion at the lung and liver interface [depicted by corresponding red dotted (for lungs) and green solid (for liver) arrows].

Article Snippet: The computation time per registration using the presented framework is ≈ 3 min per 3-D pair (on a standard CPU, running nonoptimized C++ code, MATLAB™ mex compiler) and is several times faster than our previous bilateral filtering procedure ( ≈ 60 min ) or the locally adaptive anisotropic regularization (several hours).

Techniques:

Journal: NeuroImage

Article Title: MNE software for processing MEG and EEG data

doi: 10.1016/j.neuroimage.2013.10.027

Figure Lengend Snippet: Overview of the features provided by the command-line tools and the compiled GUI applications (MNE-C) and the MNE-Matlab and MNE-Python toolboxes (✓: supported). All parts of MNE read and write data in the same file format, enabling users to use the tool that is best suited for each processing step. ECD = Equivalent Current Dipole; LCMV = Linearly Constrained Minimum-Variance

Article Snippet: MNE software consists of three core subpackages which are fully integrated: the original MNE-C (distributed as compiled C code), MNE-Matlab, and MNE-Python.

Techniques: