Anatomical, physiological, instrumental, and other related biases are removed from functional magnetic resonance imaging (“fMRI”) signal data using deep learning algorithms and/or models, such as a neural network. Bias characterization data are used as an auxiliary input to the neural network. The bias characterization data can be subject-specific bias characterization data (e.g., cortical thickness maps, cortical orientation angle maps, vasculature maps), hardware-specific bias characterization data (e.g., coil sensitivity maps, coil transmission profiles), or both. The subject-specific bias characterization data can be extracted from the fMRI signal data using a second neural network. The bias-reduced fMRI signal data can include time-series signals, functional activation maps, functional connectivity maps, or combinations thereof.

Disclosed herein are methods for imaging a tissue in a subject that involves administering to the subject a composition comprising deuterium-labeled glycolytic or fatty acid substrate and imaging the subject with deuterium magnetic resonance imaging (DMI) to detect hydrogen-deuterium oxide (HDO) in tissues of the subject. The disclosed methods can be used to detect changes in metabolic activity in a tissue. The disclosed methods can also be used to detect cancers.

The multi-modal imaging system, in particular for brain imaging, comprising a pump signal generator which emits at least one pump signal in the radio frequency (RF)-range with a first power P1 and a second power P2, a wireless detection unit, which comprises at least one parametric resonator circuit with multiple resonance modes, wherein the at least one parametric resonator circuit comprises at least two varactors, at least one capacitor and at least one inductance, wherein, in a first detection mode, the pump signal, having a first power P1, induces a first pump current in the at least one parametric resonator circuit, wherein the at least one parametric resonator circuit is operated below its oscillation threshold and generates a first output signal by amplifying a first input signal, which is provided due to a magnetic-resonance (MR) measurement, wherein an external receiving device receives the first output signal, wherein, in a second detection mode, the pump signal, having a second power P2, induces a second pump current in the at least one parametric resonator circuit, wherein the at least one parametric resonator circuit is operated above its oscillation threshold and generates a second output signal, wherein the second output signal is modulated with a second input signal, wherein the second input signal is provided by at least one neuronal probe device, connected to the at least one parametric resonator circuit, wherein the external receiving device receives the second output signal.

A neurofeedback method, including: recording electrical signals from at least one brain region of a subject, wherein changes in the recorded electrical signals over time indicate changes in an activity level of the at least one brain region; providing an audio signal having a perceived quality based on the recorded electrical signals and according to an activity level of the at least one brain region; delivering the audio signal to the subject during said recording.

A system and method is provided for controlling physiological-noise in functional magnetic resonance imaging using raw k-space data to extract physiological noise effects. The method can identify these effects when they are separable and directly reflects the artefactual effects on fMRI data, without the need for external monitoring or recording devices and to be compensated for via rigorous statistical analysis modeling of such noise sources. The physiological fluctuations may be treated as global perturbations presented around the origin point in a k-space 2D slice. Each k-space 2D slice may be acquired at a very short repetition time with an effective sampling rate to sample cardiac and respiratory rhythms through proper reordering and phase-unwarping techniques applied to the raw k-space data.

Functional magnetic resonance imaging (“fMRI”) processing that makes use of both the magnitude and phase information contained in magnetic resonance signals is implemented to enhance the visualization of blood-oxygenation-level-dependent (“BOLD”) fMRI activation. As a result, the functional activation maps generated with these techniques are more sensitive to subtle neuronal activity than maps generated with conventional fMRI techniques, which utilize only magnitude information.

The present invention relates to a system (10) for functional magnetic resonance image data acquisition. The system comprises an input unit (20), a magnetic resonance imaging “MRI” device (30), an electroencephalography “EEG” data acquisition device (40), and a processing unit (50). The input unit is configured to provide task based information to a patient, wherein the task based information extends over a period of time. The MRI device is configured to acquire functional magnetic resonance imaging “fMRI” data relating to brain activity of the patient, wherein the fMRI data extends over the period of time. The EEG device is configured to acquire EEG data relating to electrical activity of the brain of the patient, wherein the EEG data extends over the period of time. The processing unit is configured to utilize the task based information that extends over the period of time and the EEG data that extends over the period of time to determine at least one first sub-set period of time over the period of time. The processing unit is configured to determine an action associated with acquisition of the fMRI data over the at least one first sub-set period of time.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing EEG source localization. One of the methods includes obtaining brain data comprising: EEG data comprising respective channel data corresponding to each of a plurality of electrodes of an EEG sensor, and fMRI data comprising respective voxel data corresponding to each of a plurality of voxels; identifying, in a three-dimensional coordinate system, a respective location for each electrode; generating, using the respective identified locations of each electrode, data representing a location in the three-dimensional coordinate system of each voxel; determining, for each electrode, a region of interest in the three-dimensional coordinate system; and identifying, for each electrode, one or more corresponding parcellations in the brain of the subject, wherein each parcellation that corresponds to an electrode at least partially overlaps with the region of interest of the electrode.

A method for determining a brain age, the method comprising the following: providing a brain age determining convolutional neural network (CNN) (200); training the CNN (200) to determine the brain age based on a plurality of sets of input data comprising magnetic resonance imaging (MRI) scans of a brain, the set comprising at least two types of MRI volumes, wherein the at least one type of brain tissue on the first type of the MRI volume is represented by a different contrast with respect to other tissues than on a second type of the MRI volume; and performing an inference process using the trained CNN (200) to determine the brain age based on the set of input data comprising magnetic resonance imaging (MRI) scans of a brain, the set comprising at least the two types of the MRI volumes as used for the training.

In a method and an image capturing system (5) for capturing signals and image data of a volume segment of an examination object, raw data of the volume segment are captured, and image time stamps are captured at which certain of the raw data are captured. Physiological signals of the examination object are captured at the same time as capturing the raw data. Signal time stamps are captured at which certain of the physiological signals are captured. The capture of the raw data and the capture of the physiological signals is controlled by the same processor of the image capturing system, so that both the image time stamps and the signal time stamps are predetermined by the same processor.