A method for generating an MRI sequence (1) which is characterized in that a first time segment type and a second time segment type differing therefrom are predefined and the MRI sequence (1) is constructed by time segments (5, 6) of the first time segment type and time segments (5, 6) of the second time segment type being strung together alternately.

Disclosed herein is a medical system (100, 300) comprising a memory (110) storing machine executable instructions (120) and an image segmentation algorithm (122). The image segmentation algorithm is configured for outputting one or more prede-termined anatomical regions within initial magnetic resonance imaging data (124) descriptive of a predetermined field of view (109) of a subject (318). The medical system further comprises a computational system (104), wherein execution of the machine executable in-structions causes the computational system to: receive (200) the initial magnetic resonance imaging data (124); receive (202) the image segmentation comprising the one or more anatomical regions within the magnetic resonance imaging data in response to inputting the initial magnetic resonance imaging data into the image segmentation algorithm; select (204) at least one of the one or more anatomical regions as a selected image portion (128) using a predetermined criterion; and reduce (206) image intensity within the selected image.

An MRI apparatus according to an embodiment includes sequence controlling circuitry, in a first transition period, repeating application of a first MT pulse and acquisition of a first MR signal to a first frequency region being a part of a k-space; in the first steady state, repeating application of the first MT pulse and acquisition of a second MR signal to a second frequency region of the k-space, frequency in second frequency region being lower than frequency in the first frequency region; and in a second transition period, repeating application of a second MT pulse and acquisition of a third MR signal to a third frequency region being another part of the k-space, frequency in the third frequency region being higher than the frequency in the second frequency region, and processing circuitry generating one MR image on basis of the first, second, and third MR signal.

Neural network based systems, methods, and instrumentalities may be used to remove motion artifacts from magnetic resonance (MR) images. Such a neural network based system may be trained to perform the motion artifact removal tasks without reference (e.g., without using paired motion-contaminated and motion-free MR images). Various training techniques are described herein including one that feeds the neural network with pairs of MR images with different levels of motion contamination and forces the neural network learn to correct the motion contamination by transforming a first image of a contaminated pair into a second image of the contaminated pair. Other neural network training techniques are also described with an aim to reduce the reliance on training data that is difficult to obtain.

A magnetic resonance imaging apparatus according to an embodiment includes sequence controlling circuitry and processing circuitry. The sequence controlling circuitry is configured to execute (i) a first pulse sequence in which a spatially selective Inversion recovery (IR) pulse and a spatially non-selective IR pulse are applied, and subsequently an acquisition is performed and (ii) a second pulse sequence in which the spatially non-selective IR pulse is applied without applying the spatially selective IR pulse, and subsequently an acquisition is performed, while varying the first TI period, with respect to a plurality of first TI periods. The processing circuitry is configured to calculate a second TI period to be used in a third pulse sequence and a fourth pulse sequence, based on data obtained from the first pulse sequence and the second pulse sequence. The sequence controlling circuitry executes (iii) the third pulse sequence in which the spatially selective IR pulse and the spatially non-selective IR pulse are applied, and subsequently an acquisition is performed and (iv) the fourth pulse sequence in which the spatially non-selective IR pulse is applied without applying the spatially selective IR pulse, and subsequently an acquisition is performed. The processing circuitry generates a magnetic resonance image of an imaged region based on data obtained from the third pulse sequence and the fourth pulse sequence.

Provided is a method for generating Mill data including applying, by an Mill computing device, an RF excitation pulse, and completing, by the MM computing device, a K-space by acquiring a plurality of phase encoding line groups, in a state in which any other RF excitation pulse is not applied after applying the RF excitation pulse, in which each of the plurality of phase encoding line groups includes a plurality of phase encoding lines, and an absolute value of an average phase encoding size of a phase encoding line group acquired earlier is not greater than an absolute value of an average phase encoding size of a phase encoding line group acquired later, among the plurality of phase encoding line groups.

A method for performing real-time magnetic resonance (MR) imaging on a subject is disclosed. A prep pulse sequence is applied to the subject to obtain a high-quality special subspace, and a direct linear mapping from k-space training data to subspace coordinates. A live pulse sequence is then applied to the subject. During the live pulse sequence, real-time images are constructed using a fast matrix multiplication procedure on a single instance of the k-space training readout (e.g., a single k-space line or trajectory), which can be acquired at a high temporal rate.

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.

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.

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.