Abstract: Systems and methods are provided for susceptibility contrast imaging of nanoparticles at low magnetic fields. A susceptibility-based MRI technique, such as imaging with a balanced steady-state free precession (bSSFP) pulse sequence, may be used for imaging a contrast agent such as biocompatible superparamagnetic nanoparticles at ultra-low fields. The contrast agent and imaging technique may be used to improving the visibility of anatomical structures and detecting diseases, such as cancer, with low-field MRI.

Abstract: Systems, methods, and media for patch-based medical image generation for complex input datasets. Patch-based medical image generation can include creating a training dataset with an image patch and corresponding sensor data patch and training a neural network using the training dataset. Then, sensor data acquired from a patient using a medical imaging system can be applied as input to the neural network, and a medical image of the patient can be generated based on an output of the neural network.

Abstract: Systems, methods, and media for complex input data configurations for imaging applications. Complex data optimization can be provided to improve accuracy of models (e.g., neural networks) used to reconstruct medical images from raw sensor data, for example. Complex data optimization can include applying raw sensor data to an input layer of a neural network to generate an input vector ordered such that real components and imaginary components of samples in the raw sensor data are adjacent. The input vector can then be applied to convolutional layer of the neural network.

Abstract: A system may transform sensor data from a sensor domain to an image domain using data-driven manifold learning techniques which may, for example, be implemented using neural networks. The sensor data may be generated by an image sensor, which may be part of an imaging system. Fully connected layers of a neural network in the system may be applied to the sensor data to apply an activation function to the sensor data. The activation function may be a hyperbolic tangent activation function. Convolutional layers may then be applied that convolve the output of the fully connected layers for high level feature extraction. An output layer may be applied to the output of the convolutional layers to deconvolve the output and produce image data in the image domain.

Abstract: A system may transform sensor data from a sensor domain to an image domain using data-driven manifold learning techniques which may, for example, be implemented using neural networks. The sensor data may be generated by an image sensor, which may be part of an imaging system. Fully connected layers of a neural network in the system may be applied to the sensor data to apply an activation function to the sensor data. The activation function may be a hyperbolic tangent activation function. Convolutional layers may then be applied that convolve the output of the fully connected layers for high level feature extraction. An output layer may be applied to the output of the convolutional layers to deconvolve the output and produce image data in the image domain.

Abstract: Systems and methods of quantum sensing include depositing a sample volume onto an ensemble of quantum defects, hyperpolarizing spins in the sample volume, performing a sensing sequence, and reading out information regarding electronic spin states of the quantum defects in the ensemble of quantum defects, which sense the hyperpolarized spins in the sample volume.

Abstract: Systems and methods are provided for susceptibility contrast imaging of nanoparticles at low magnetic fields. A susceptibility-based MRI technique, such as imaging with a balanced steady-state free precession (bSSFP) pulse sequence, may be used for imaging a contrast agent such as biocompatible superparamagnetic nanoparticles at ultra-low fields. The contrast agent and imaging technique may be used to improving the visibility of anatomical structures and detecting diseases, such as cancer, with low-field MRI.

Abstract: Disclosed is a system and method for estimating quantitative parameters of a subject using a magnetic resonance (“MR”) system using a dictionary. The dictionary may include a plurality of signal templates that sparsely sample acquisition parameters used when acquiring data. The acquired data is compared with the dictionary using a neural network. Thus, systems and methods are provided that are more computationally efficient, and have reduced data storage requirements than traditional MRF reconstruction systems and methods.

Abstract: A system and method for performing parallel magnetic resonance imaging (pMRI) process using a low-field magnetic resonance imaging (IfMRI) system includes a substrate configured to follow a contour of a portion of a subject to be imaged by the IfMRI system using a pMRI process. A plurality of coils are coupled to the substrate. Each coil in the plurality of coils has a number of turns and an associated decoupling mechanism selected to operate the plurality of coils to effectuate the pMRI process using the IfMRI system.

Abstract: Provided is a system and method for performing a magnetic resonance fingerprinting imaging process. The process includes determining acquisition parameters including at least one of repetition time (TR) or flip angle (FA), selected to control one of a duration and a number of repetitions of for a pulse sequence that samples k-space in a Cartesian acquisition pattern by acquiring an echo train. The process also includes controlling a magnetic resonance imaging (MRI) system to perform the pulse sequence a plurality of times to acquire magnetic resonance fingerprinting (MRF) data corresponding to signals from the subject excited by the pulse sequence. The process also includes estimating quantitative tissue properties of the subject by comparing the MRF data to a database and reconstructing, from the MRF data, at least one image of the subject indicating the estimated quantitative tissue properties.

Abstract: A system and method for system for performing a magnetic resonance imaging (MRI) process using an MRI system is provided. A coil system includes a substrate configured to follow a contour of a portion of a subject to be imaged by the MRI system and at least one coil coupled to the substrate and forming a spiral pattern.

Abstract: A system may transform sensor data from a sensor domain to an image domain using data-driven manifold learning techniques which may, for example, be implemented using neural networks. The sensor data may be generated by an image sensor, which may be part of an imaging system. Fully connected layers of a neural network in the system may be applied to the sensor data to apply an activation function to the sensor data. The activation function may be a hyperbolic tangent activation function. Convolutional layers may then be applied that convolve the output of the fully connected layers for high level feature extraction. An output layer may be applied to the output of the convolutional layers to deconvolve the output and produce image data in the image domain.

Abstract: Methods and systems for Nuclear Magnetic Resonance (NMR) spectra of samples having unresolved peaks are described. The methods and systems allow for the creation nuclear spin singlet states in nearly-equivalent spin pairs, for example, using continuous spin-locking with a nutation frequency matched to the coupling strength between spins.

Abstract: Methods and systems for Nuclear Magnetic Resonance (NMR) spectra of samples having unresolved peaks are described. The methods and systems allow for the creation nuclear spin singlet states in nearly-equivalent spin pairs, for example, using continuous spin-locking with a nutation frequency matched to the coupling strength between spins. The invention relates generally to the field Nuclear Magnetic Resonance (NMR). Nuclear magnetic resonance (NMR) spectroscopy can be used as a tool for determining the chemical structure and/or geometry of a molecule in a sample. In many samples, however, resonance frequencies of different nuclei fully or partially overlap, which makes chemical identification of molecule(s) in a sample difficult or impossible.

Abstract: Disclosed is a system and method for estimating quantitative parameters of a subject using a magnetic resonance (“MR”) system using a dictionary. The dictionary may include a plurality of signal templates that sparsely sample acquisition parameters used when acquiring data. The acquired data is compared with the dictionary using a neural network. Thus, systems and methods are provided that are more computationally efficient, and have reduced data storage requirements than traditional MRF reconstruction systems and methods.

Abstract: A system and method performing a medical imaging process includes arranging a subject to receive solution comprising nanodiamonds, performing an MRI imaging process to acquire data from the subject, and reconstructing the data to generate a report indicating a spatial distribution of nanodiamonds in the subject.

Abstract: Systems and methods are provided for performing a medical imaging. The system includes a main magnet system configured to generate a main static magnetic field about at least a region of interest (ROD of a subject arranged in the main magnet system. The system also includes at least one gradient coil configured to establish at least one magnetic gradient field with respect to the main static magnetic field, The system also includes a radio frequency (RF) system configured to deliver excitation pulses to the subject. The system also includes a polarization magnet system configured to generate a polarization static magnetic field in an at least partially shielded region away from the main magnet system, the polarization magnet system configured to at least partially pre-polarize a blood substitute to be injected to the subject.

Abstract: Methods and systems for Nuclear Magnetic Resonance (NMR) spectra of complex chemical mixtures are described. The methods and systems allow undesired NMR spectral background to be removed or suppressed and target spectral peaks to be uncovered, for example, when strong background signals overlap weaker peaks. In some embodiments, the methods and systems employ a quantum filter utilizing nuclear spin singlet states.

Abstract: A system and method for performing parallel magnetic resonance imaging (pMRI) process using a low-field magnetic resonance imaging (IfMRI) system includes a substrate configured to follow a contour of a portion of a subject to be imaged by the IfMRI system using a pMRI process. A plurality of coils are coupled to the substrate. Each coil in the plurality of coils has a number of turns and an associated decoupling mechanism selected to operate the plurality of coils to effectuate the pMRI process using the IfMRI system.

Abstract: A system and method for system for performing a magnetic resonance imaging (MRI) process using an MRI system is provided. A coil system includes a substrate configured to follow a contour of a portion of a subject to be imaged by the MRI system and at least one coil coupled to the substrate and forming a spiral pattern.