For reconstruction of an image in MRI, unsupervised training (i.e., data-driven) based on a scan of a given patient is used to reconstruct model parameters, such as estimating values of a contrast model and a motion model based on fit of images generated by the models for different readouts and times. The models and the estimated values from the scan-specific unsupervised training are then used to generate the patient image for that scan. This may avoid artifacts from binning different readouts together while allowing for scan sequences using multiple readouts.

An MR image especially useful for computer-guided diagnostics uses at least one programmed computer to acquire an MR-image of T1 values for a patient volume containing at least one predetermined tissue type having a respectively corresponding predetermined range of expected T1 values. A color-coded T1-image is generated from the MR-image by (a) assigning a first color or spectrum of colors to those pixels having a T1 value falling within a predetermined range of expected T1 values and (b) assigning a second color or spectrum of colors to those pixels having a T1 value falling outside a predetermined range of expected T1 values. The color-coded T1-image is then displayed for use in computer-aided diagnosis of patient tissue.

An MRI scanner and a method for operation of the MRI scanner are provided. The MRI scanner has a first receiving antenna for receiving a magnetic resonance signal from a patient in a patient tunnel, a second receiving antenna for receiving a signal having the Larmor frequency of the magnetic resonance signal, and a receiver. The second receiving antenna is located outside of the patient tunnel or near an opening thereof. The receiver has a signal connection to the first receiving antenna and the second receiving antenna and is configured to suppress an interference signal by the second receiving antenna in the magnetic resonance signal received by the first receiving antenna.

There is provided a computer implemented method of automatic segmentation of three dimensional (3D) anatomical region of interest(s) (ROI) that includes predefined anatomical structure(s) of a target individual, comprising: receiving 3D images of a target individual, each including the predefined anatomical structure(s), each 3D image is based on a different respective imaging modality. In one implementation, each respective 3D image is inputted into a respective processing component of a multi-modal neural network, wherein each processing component independently computes a respective intermediate, and the intermediate outputs are inputted into a common last convolutional layer(s) for computing the indication of segmented 3D ROI(s). In another implementation, each respective 3D image is inputted into a respective encoding-contracting component a multi-modal neural network, wherein each encoding-contracting component independently computes a respective intermediate output. The intermediate outputs are inputted into a single common decoding-expanding component for computing the indication of segmented 3D ROI(s).

The present disclosure provides a system and method for image data acquisition. The method may include acquiring physiological data of a subject. The physiological data may correspond to a motion of the subject over time. The method may include obtaining a trained machine learning model configured to detect feature data represented in the physiological data. The method may include determining, based on the physiological data, an output result of the trained machine learning model that is generated based on the feature data. The method may include acquiring, based on the output result, image data of the subject using an imaging device.

K-space data obtained from a magnetic resonance imaging scan where motion was detected is split into two parts in accordance with the timing of the motion to produce first and second sets of k-space data corresponding to different poses. Sub-images are reconstructed from the k first and second sets of k-space data, which are used as inputs to a deep neural network which transforms them into a motion-corrected image.

Methods and systems are provided for reconstructing images from measurement data using one or more deep neural networks according to a decimation strategy. In one embodiment, a method for reconstructing an image using measurement data comprises, receiving measurement data acquired by an imaging device, selecting a decimation strategy, producing a reconstructed image from the measurement data using the decimation strategy and one or more deep neural networks, and displaying the reconstructed image via a display device. By decimating measurement data to form one or more decimated measurement data arrays, a computational complexity of mapping the measurement data to image data may be reduced from O(N.sup.4), where N is the size of the measurement data, to O(M.sup.4), where M is the size of an individual decimated measurement data array, wherein M<N.

An information processing apparatus according to an embodiment includes a processing circuit. The processing circuit acquires a measurement field corresponding to a spatial distribution of a predetermined physical quantity in a subject of measurement. The processing circuit calculates an unknown quantity in the subject of measurement based on a first equation between the measurement field and the unknown quantity having spatial dependence, and on the acquired measurement field. The first equation is one that is acquired based on a second equation expressing a dual field divergence of which can be expressed using the measurement field, by using the measurement field and the unknown quantity, and on the Helmholtz decomposition of the dual field.

A main magnetic field correction method for a magnetic resonance imaging system includes: obtaining an estimated image of a phantom based on a first imaging sequence, the first imaging sequence having a variable resonant frequency; pre-correcting a main magnetic field based on the estimated image; obtaining a scanned image of the phantom based on the pre-corrected main magnetic field; and determining whether the quality of the scanned image is within an acceptable range, and if not, returning to the step of obtaining the estimated image.

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.