Abstract: A computing system for self-training of a magnetic resonance imaging (MRI) tissue property artificial neural network (ANN) includes a processor and an ANN training application including instructions that, when executed by the one or more processors, are configured to cause the processor to generate tissue property maps; generate MRI fingerprint images; generate reconstructed MRI k-space data; and compare the reconstructed MRI k-space data to acquired MRI k-space data. A computer-implemented method includes generating tissue property maps; generating MRI fingerprint images; generating reconstructed MRI k-space data; and comparing the reconstructed MRI k-space data to acquired MRI k-space data. A non-transitory computer-readable storage medium storing executable instructions that, when executed by a processor, cause a computer to generate tissue property maps; generate MRI fingerprint images; generate reconstructed MRI k-space data; and compare the reconstructed MRI k-space data to acquired MRI k-space data.

Abstract: Methods and systems are provided for cine magnetic resonance fingerprinting (MRF). In one example, a method includes obtaining k-space data of an MRF scan of a subject, the k-space data acquired over a plurality of phases of at least one cardiac cycle of the subject, training an image reconstruction network (IRN) to output, for each phase, one or more subspace images of the subject using the k-space data, and training a parameter estimation network (PEN) to output, for each phase, a set of tissue parameter maps of the subject using the one or more subspace images output by the IRN for the corresponding phase. Upon training the IRN and the PEN, the method further includes obtaining (and displaying and/or saving in memory) a final set of tissue parameter maps of the subject for one or more or each of the plurality of phases.

Abstract: Methods and systems perform magnetic resonance fingerprinting (MRF) that provides tissue characterization through simultaneous quantification of water tissue properties and proton density fat fraction (PDFF), by using water-only and fat-only images from MRF. MRF is performed using rosette trajectories scanning k-space to effectively isolate water tissue and fat tissue, by separating these rosette trajectories into individual segments that are then analyzed to enable signals from fat tissue to be distinguished from water.

Abstract: Methods and systems perform magnetic resonance fingerprinting (MRF) that provides tissue characterization through simultaneous quantification of water tissue properties and proton density fat fraction (PDFF), by using water-only and fat-only images from MRF. MRF is performed using rosette trajectories scanning k-space to effectively isolate water tissue and fat tissue, by separating these rosette trajectories into individual segments that are then analyzed to enable signals from fat tissue to be distinguished from water.

Abstract: Methods and systems perform magnetic resonance fingerprinting (MRF) by obtaining scan data of a sample at a low-resolution over a k-space and obtaining other scan data at a high-resolution over the k-space. This scan data may be captured over the same regions, different regions, or where one scan data is captured over a sub-region of the other. The low-resolution and high-resolution scanning is repeated according to a scanning ratio between the first scan data and the second scan data to generate interleaved low-resolution and high-resolution scan data. From that interleaved low-resolution and high-resolution scan data, high-resolution tissue property maps of the sample are generated.

Abstract: Methods and systems perform magnetic resonance fingerprinting (MRF) by obtaining scan data of a sample at a low-resolution over a k-space and obtaining other scan data at a high-resolution over the k-space. This scan data may be captured over the same regions, different regions, or where one scan data is captured over a sub-region of the other. The low-resolution and high-resolution scanning is repeated according to a scanning ratio between the first scan data and the second scan data to generate interleaved low-resolution and high-resolution scan data. From that interleaved low-resolution and high-resolution scan data, high-resolution tissue property maps of the sample are generated.

Abstract: Methods and systems generate synthetic late gadolinium enhancement (LGE) magnetic resonance images using a magnetic resonance fingerprinting (MRF) acquisition. From a single acquisition, MRF image data is obtained, including co-registered T1 and T2 tissue property maps. Different tissue regions of interest are identified, such as viable myocardium, scar, and blood and T1 and T2 values for each are determined. Based on these, different sets of pulse sequence parameters are determined, e.g., using different synthetic image contrast models receiving the MRF image data. Synthetic LGE images at different contrasts are generated as a result, including a synthetic bright-blood LGE image, a synthetic dark-blood/gray-blood LGE image, and a synthetic optimized imaged.

Abstract: Methods and systems generate synthetic late gadolinium enhancement (LGE) magnetic resonance images using a magnetic resonance fingerprinting (MRF) acquisition. From a single acquisition, MRF image data is obtained, including co-registered T1 and T2 tissue property maps. Different tissue regions of interest are identified, such as viable myocardium, scar, and blood and T1 and T2 values for each are determined. Based on these, different sets of pulse sequence parameters are determined, e.g., using different synthetic image contrast models receiving the MRF image data. Synthetic LGE images at different contrasts are generated as a result, including a synthetic bright-blood LGE image, a synthetic dark-blood/gray-blood LGE image, and a synthetic optimized imaged.

Abstract: A computing system for self-training of a magnetic resonance imaging (MRI) tissue property artificial neural network (ANN) includes a processor and an ANN training application including instructions that, when executed by the one or more processors, are configured to cause the processor to generate tissue property maps; generate MRI fingerprint images; generate reconstructed MRI k-space data; and compare the reconstructed MRI k-space data to acquired MRI k-space data. A computer-implemented method includes generating tissue property maps; generating MRI fingerprint images; generating reconstructed MRI k-space data; and comparing the reconstructed MRI k-space data to acquired MRI k-space data. A non-transitory computer-readable storage medium storing executable instructions that, when executed by a processor, cause a computer to generate tissue property maps; generate MRI fingerprint images; generate reconstructed MRI k-space data; and compare the reconstructed MRI k-space data to acquired MRI k-space data.

Abstract: A method for quantifying T1, T2 and resonance frequency simultaneously using magnetic resonance fingerprinting (MRF) includes accessing an MRF dictionary using a magnetic resonance imaging (MRI) system. The MRF dictionary is generated by simulating signal evolutions that include associated off-resonance effects for each signal evolution. The method further includes acquiring MRF data from a region of interest in a subject using the MRI system and a MRF pulse sequence having a plurality of radio frequency (RF) excitations and a readout associated with each RF excitation. Each readout includes a plurality of segments and each segment is used to generate a time frame. The method also include comparing the MRF data to the MRF dictionary to identify a plurality of parameters including T1, T2 and resonance frequency for the MRF data and generating a report indicating the at least one of the plurality of parameters of the MRF data.

Abstract: A method for magnetic resonance fingerprinting with out-of-view artifact suppression includes acquiring MRF data from a region of interest in a subject. The MRF data is acquired using a non-Cartesian, variable density sampling trajectory. The MRF data includes data from within a desired field-of-view and data from outside the desired field-of-view. The method also includes generating a set of coil images based on the MRF data with a field-of-view larger than the desired field-of-view, determining a noise covariance based on the MRF data from outside the desired field-of-view, generating a coil combined image using an adaptive coil combination determined based on the noise covariance, applying the adaptive coil combination to the MRF data to grid each frame of the MRF data and generate MRF data with out-of-view artifact suppression. The method also includes identifying at least one property of the MRF data and generating a report.

Abstract: A method for magnetic resonance fingerprinting with out-of-view artifact suppression includes acquiring MRF data from a region of interest in a subject. The MRF data is acquired using a non-Cartesian, variable density sampling trajectory. The MRF data includes data from within a desired field-of-view and data from outside the desired field-of-view. The method also includes generating a set of coil images based on the MRF data with a field-of-view larger than the desired field-of-view, determining a noise covariance based on the MRF data from outside the desired field-of-view, generating a coil combined image using an adaptive coil combination determined based on the noise covariance, applying the adaptive coil combination to the MRF data to grid each frame of the MRF data and generate MRF data with out-of-view artifact suppression. The method also includes identifying at least one property of the MRF data and generating a report.

Abstract: A method for quantifying T1, T2 and resonance frequency simultaneously using magnetic resonance fingerprinting (MRF) includes accessing an MRF dictionary using a magnetic resonance imaging (MRI) system. The MRF dictionary is generated by simulating signal evolutions that include associated off-resonance effects for each signal evolution. The method further includes acquiring MRF data from a region of interest in a subject using the MRI system and a MRF pulse sequence having a plurality of radio frequency (RF) excitations and a readout associated with each RF excitation. Each readout includes a plurality of segments and each segment is used to generate a time frame. The method also include comparing the MRF data to the MRF dictionary to identify a plurality of parameters including T1, T2 and resonance frequency for the MRF data and generating a report indicating the at least one of the plurality of parameters of the MRF data.

Abstract: Example embodiments associated with characterizing a sample using NMR fingerprinting are described. One example NMR apparatus includes an NMR logic that repetitively and variably samples a (k, t, E) space associated with an object to acquire a set of NMR signals that are associated with different points in the (k, t, E) space. Sampling is performed with t and/or E varying in a non-constant way. The NMR apparatus may also include a signal logic that produces an NMR signal evolution from the NMR signals and a characterization logic that characterizes a tissue in the object as a result of comparing acquired signals to reference signals. Example embodiments facilitate analyzing voxels having multiple compartments that may experience magnetic exchange. The compartments may be, for example, an intracellular volume and an extracellular volume in a tissue that experiences magnetic exchange due to the movement of water between the volumes.

Abstract: Example embodiments associated with characterizing a sample using NMR fingerprinting are described. One example NMR apparatus includes an NMR logic that repetitively and variably samples a (k, t, E) space associated with an object to acquire a set of NMR signals that are associated with different points in the (k, t, E) space. Sampling is performed with t and/or E varying in a non-constant way. The NMR apparatus may also include a signal logic that produces an NMR signal evolution from the NMR signals and a characterization logic that characterizes a tissue in the object as a result of comparing acquired signals to reference signals. Example embodiments facilitate analyzing voxels having multiple compartments that may experience magnetic exchange. The compartments may be, for example, an intracellular volume and an extracellular volume in a tissue that experiences magnetic exchange due to the movement of water between the volumes.