Abstract: A computer-implemented method uses a plurality of input examination data sets, created by performing a plurality of imaging examinations of at least one patient on at least one scanner, to learn a model of imaging protocols. The model may learn imaging protocols by capturing common features across the plurality of input examination data sets. The method may regroup examination data sets, within the plurality of input examination data sets, with common features under a common protocol tag, and learning the model may include generating a plurality of protocol tags. The model may be updated over time based on new input examination data sets.

Abstract: A computer-implemented method and system train a model of imaging examinations based on data representing a plurality of historical imaging examinations, and generate, using the model of imaging examinations and a current schedule of imaging appointments, a schedule recommendation. The schedule recommendation recommends an imaging appointment within the current schedule of imaging appointments. The current schedule of imaging appointments may be updated based on the schedule recommendation, such as by adding the recommended imaging appointment to the current schedule or by modifying an existing imaging appointment in the current schedule. The schedule recommendation may be generated in response to a request or dynamically.

Abstract: A computer-implemented method and system train a model of imaging examinations based on data representing a plurality of historical imaging examinations, and generate, using the model of imaging examinations and a current schedule of imaging appointments, a schedule recommendation. The schedule recommendation recommends an imaging appointment within the current schedule of imaging appointments. The current schedule of imaging appointments may be updated based on the schedule recommendation, such as by adding the recommended imaging appointment to the current schedule or by modifying an existing imaging appointment in the current schedule. The schedule recommendation may be generated in response to a request or dynamically.

Abstract: A computer-implemented method uses a plurality of input examination data sets, created by performing a plurality of imaging examinations of at least one patient on at least one scanner, to learn a model of imaging protocols. The model may learn imaging protocols by capturing common features across the plurality of input examination data sets . The method may regroup examination data sets, within the plurality of input examination data sets, with common features under a common protocol tag, and learning the model may include generating a plurality of protocol tags. The model may be updated over time based on new input examination data sets.

Abstract: Methods and apparatus for acquiring diffusion-weighted images. The method comprises selecting a plurality of diffusion gradient vectors, wherein at least two of the plurality of diffusion gradient vectors correspond to different non-zero b-values. The method further comprises determining a gradient strength for each of the plurality of diffusion gradient vectors such that an echo image time (TE) remains constant when gradients corresponding to each of the plurality of diffusion gradient vectors are applied. The method further comprises acquiring the diffusion-weighted images using a gradient encoding scheme including the gradients corresponding to each of the plurality of gradient vectors.

Abstract: System and method for processing magnetic resonance imaging (MRI) data of an object to perform motion correction. The method comprises estimating, for each slice of the MRI data, parameters for a state space model using a filter that predicts the location of the object for temporally adjacent slices, wherein the state space model represents motion dynamics of the object throughout acquisition of a three-dimensional volume, registering the slices to a reference image based, at least in part, on the estimated parameters, reconstructing an image based, at least in part, on the registered two-dimensional slices, and outputting the reconstructed image.

Abstract: Methods and apparatus for characterizing biological micro structure in a voxel based, at least in part, on a set of diffusion-weighted magnetic resonance (MR) data. A multi-compartment parametric model is used to predict a diffusion signal for the voxel using information from the set of diffusion-weighted MR data. Predicting the diffusion signal comprises determining, based on the set of diffusion-weighted MR data, a first set of parameters describing isotropic diffusion in a first compartment of the multi-compartment model and a second set of parameters describing anisotropic diffusion due to the presence of at least one white matter fascicle in a second compartment of the multi-compartment model. At least one first dataset of the set of diffusion-weighted MR data is associated with a first non-zero b-value and at least one second dataset of the set of diffusion-weighted MR data is associated with a second non-zero b-value different than the first non-zero b-value.

Abstract: System and method for processing magnetic resonance imaging (MRI) data of an object to perform motion correction. The method comprises estimating, for each slice of the MRI data, parameters for a state space model using a filter that predicts the location of the object for temporally adjacent slices, wherein the state space model represents motion dynamics of the object throughout acquisition of a three-dimensional volume, registering the slices to a reference image based, at least in part, on the estimated parameters, reconstructing an image based, at least in part, on the registered two-dimensional slices, and outputting the reconstructed image.

Abstract: Methods and apparatus for characterizing biological micro structure in a voxel based, at least in part, on a set of diffusion-weighted magnetic resonance (MR) data. A multi-compartment parametric model is used to predict a diffusion signal for the voxel using information from the set of diffusion-weighted MR data. Predicting the diffusion signal comprises determining, based on the set of diffusion-weighted MR data, a first set of parameters describing isotropic diffusion in a first compartment of the multi-compartment model and a second set of parameters describing anisotropic diffusion due to the presence of at least one white matter fascicle in a second compartment of the multi-compartment model. At least one first dataset of the set of diffusion-weighted MR data is associated with a first non-zero b-value and at least one second dataset of the set of diffusion-weighted MR data is associated with a second non-zero b-value different than the first non-zero b-value.

Abstract: Methods and apparatus for acquiring diffusion-weighted images. The method comprises selecting a plurality of diffusion gradient vectors, wherein at least two of the plurality of diffusion gradient vectors correspond to different non-zero b-values. The method further comprises determining a gradient strength for each of the plurality of diffusion gradient vectors such that an echo image time (TE) remains constant when gradients corresponding to each of the plurality of diffusion gradient vectors are applied. The method further comprises acquiring the diffusion-weighted images using a gradient encoding scheme including the gradients corresponding to each of the plurality of gradient vectors.