Abstract: A computer-implemented method for reconstructing magnetic resonance images using a parallel computing platform comprising a host unit and a graphical processing device includes receiving a plurality of coil data sets from a magnetic resonance imaging system, each respective coil data set comprising scanner data and a coil sensitivity map associated with a distinct coil included in the magnetic resonance imaging system. An iterative compressed-sensing reconstruction process is applied to reconstruct an image based on the plurality of coil data sets.

Abstract: A computer-implemented method for reconstructing magnetic resonance images using a parallel computing platform comprising a host unit and a graphical processing device includes receiving a plurality of coil data sets from a magnetic resonance imaging system, each respective coil data set comprising scanner data and a coil sensitivity map associated with a distinct coil included in the magnetic resonance imaging system. An iterative compressed-sensing reconstruction process is applied to reconstruct an image based on the plurality of coil data sets.

Abstract: The present invention discloses methods for automatically generating regions of seeding points for fiber tracking in diffusion tensor images. These methods are based on connected region grow. Seeding point selection criteria involving Fractional Anisotropy thresholding and Dominant Eigen Vector similarity are also disclosed.

Abstract: A method of volume rendering two digital images includes providing a volume-rendering computing sub-system, loading a first image volume into a memory of the volume-rendering sub-system, rendering the first image volume, wherein a 2-dimensional image is output into an image buffer and a set of depth values are output into a depth buffer, loading a second image volume into a memory of the volume-rendering sub-system, rendering the second image volume up to the depth values output from the first image volume, wherein values from the rendering of the second image volume are merged with non-zero values of the image buffer, and rendering the remainder of the second image volume to include second image volume points beyond the depth values output from the rendering of the first image volume, wherein values from the rendering of the remainder of the second image volume are merged with non-zero values of the image buffer.