A computing device for diffusion dictionary imaging (DDI) of microstructure and inflammation of a patient is provided. The DDI computing device is connected to other computing devices, such as a magnetic resonance imaging (MRI) scanner. The DDI computing device receives magnetic resonance (MR) signals from the MRI scanner. Once received, the DDI computing device records the one or more MR signals to a memory device. The DDI computing device computationally processes the one or more MR signals to reconstruct a diffusion MRI image using diffusion dictionary data. The MR signals include values that are used as input to algorithms of the DDI data to reconstruct the diffusion MRI image. A database is used to store DDI data, artificial intelligence (AI) data, diffusion dictionary data, and MR data.

A magnetic resonance imaging apparatus according to an embodiment executes a first imaging prior to a second imaging and includes processing circuitry. The processing circuitry receives, on a first image obtained from the first imaging, a setting of a region in which an RF (Radio Frequency) pulse is to be applied to a subject, generates a three-dimensional image based on the first image, determines, based on an imaging purpose of the second imaging, a translucent region to which translucent processing is to be performed in the three-dimensional image, and displays the translucent region, making the translucent region translucent in the three-dimensional image.

A system comprises determination of an inversion-recovery or saturation-recovery imaging pulse sequence associated with first values of echo spacing, flip angle, effective TR, trigger pulses, artifact post-suppression, and number of image data lines per acquisition, execution of a scout pulse sequence comprising a plurality of single-shot image data acquisitions to acquire respective sets of image data lines, where each of the plurality of single-shot image data acquisitions is executed using a different respective inversion time and where each of the plurality of single-shot image data acquisitions is associated with second values of echo spacing, flip angle, and number of image data lines per acquisition which are substantially similar to corresponding ones of the first values, generation of a plurality of images based on the respective sets of image data lines, determination of one of the plurality of images, the determined one of the plurality of images generated based on a set of image data lines acquired using a first inversion time, and execution of the inversion-recovery or saturation-recovery imaging pulse sequence using the first inversion time.

A system comprises determination of an inversion-recovery or saturation-recovery imaging pulse sequence associated with first values of echo spacing, flip angle, effective TR, trigger pulses, artifact post-suppression, and number of image data lines per acquisition, execution of a scout pulse sequence comprising a plurality of single-shot image data acquisitions to acquire respective sets of image data lines, where each of the plurality of single-shot image data acquisitions is executed using a different respective inversion time and where each of the plurality of single-shot image data acquisitions is associated with second values of echo spacing, flip angle, and number of image data lines per acquisition which are substantially similar to corresponding ones of the first values, generation of a plurality of images based on the respective sets of image data lines, determination of one of the plurality of images, the determined one of the plurality of images generated based on a set of image data lines acquired using a first inversion time, and execution of the inversion-recovery or saturation-recovery imaging pulse sequence using the first inversion time.

A method and a system for generating a dynamic addictive neural circuit based on weakly supervised contrastive learning are disclosed. The method includes: based on a convolutional neural network, reducing a dimensionality of voxels of multiple groups of fMRI to attributes of brain region nodes, and generating multiple groups of dynamic brain connection maps containing time series based on the attributes of the brain region nodes; extracting spatio-temporal features of brain connections in the dynamic brain connection maps; inputting the spatio-temporal features into an abnormal connection detection network, calculating an abnormal probability of brain connections based on contrastive learning, and obtaining the brain connection with a highest abnormal probability at each time point; and generating the dynamic addictive neural circuit based on neuroscientific prior knowledge and the brain connection with the greatest probability of abnormality.

Methods for reconstructing images from undersampled k-space data using a machine learning approach to learn non-linear mapping functions from acquired k-space lines to generate unacquired target points across multiple coils are described.

Systems and methods for mapping neuronal circuitry in accordance with embodiments of the invention are illustrated. One embodiment includes a method for generating a neuronal shape graph, including obtaining functional brain imaging data from an imaging device, where the functional brain imaging data includes a time-series of voxels describing neuronal activation over time in a patient's brain, lowering the dimensionality of the functional brain imaging data to a set of points, where each point represents the brain state at a particular time in the timeseries, binning the points into a plurality of bins, clustering the binned points, and generating a shape graph from the clustered points, where nodes in the shape graph represent a brain state and edges between the nodes represent transitions between brain states.

A gated truncated readout system for position sensitive or imaging detectors that improves resolution over traditional readout systems. The readout system includes two or more amplifiers that receive a multichannel output analog data from the detector. Analog gates control circuitry, included in the readout circuit, receives the signals from the amplifiers, determines a fractional value of the sum-integral of the signals, and enables analog gates operation around an area of interest, disabling all other channels where noise dominates the signal value and thereby improving interpolation accuracy of the signals centroid position and the detector resolution. Filtered signals are transmitted to a centroid interpolation signal processing device for computation of the centroid position. As a result disabling all channels where noise dominates the signal value, the gated truncated readout system provides better accuracy improved detector resolution.

In a MR water-fat image separation method and device, within one echo period, a first echo set under a first readout gradient polarity and a second echo set under a second readout gradient polarity are acquired. The first and second readout gradient polarities may be opposite, and echoes in the first echo set may be positionally one-to-one symmetric to echoes in the second echo set with respect to the echo center of the echo period. A first echo image set is obtained based on first echo set data acquired in each echo period, and a second echo image set is obtained based on second echo set data acquired in each echo period. Using the first and second echo image sets, a Dixon water-fat separation calculation is performed to obtain a water image and a fat image. The method and device can advantageously increase acquisition efficiency and the signal-to-noise ratio.

In a MR water-fat image separation method and device, within one echo period, a first echo set under a first readout gradient polarity and a second echo set under a second readout gradient polarity are acquired. The first and second readout gradient polarities may be opposite, and echoes in the first echo set may be positionally one-to-one symmetric to echoes in the second echo set with respect to the echo center of the echo period. A first echo image set is obtained based on first echo set data acquired in each echo period, and a second echo image set is obtained based on second echo set data acquired in each echo period. Using the first and second echo image sets, a Dixon water-fat separation calculation is performed to obtain a water image and a fat image. The method and device can advantageously increase acquisition efficiency and the signal-to-noise ratio.