Abstract: For reconstruction in medical imaging, user control of a characteristic (e.g., noise level) of the reconstructed image is provided. A machine-learned model alters the reconstructed image to enhance or reduce the characteristic. The user selected level of characteristic is then provided by combining the reconstructed image with the altered image based on the input level of the characteristic. Personalized or more controllable impression for medical imaging reconstruction is provided without requiring different reconstructions.

Abstract: For reconstruction in medical imaging, user control of a characteristic (e.g., noise level) of the reconstructed image is provided. A machine-learned model alters the reconstructed image to enhance or reduce the characteristic. The user selected level of characteristic is then provided by combining the reconstructed image with the altered image based on the input level of the characteristic. Personalized or more controllable impression for medical imaging reconstruction is provided without requiring different reconstructions.

Abstract: For reconstruction in medical imaging, such as reconstruction in MR imaging, scanning is accelerated by under-sampling. In iterative reconstruction, the input to the regularizer is altered provide for correlation of non-local aliasing artifacts. Duplicates of the input image are shifted by different amounts based on the level of acceleration. The resulting shifted images are used to form the input to the regularizer. Providing an input based on shifts allows the regularization to suppress non-local as well as local aliasing artifacts.

Abstract: Determining parameter values in image points of an examination object in an MR system by an MRF technique. Comparison signal waveforms, established using predetermined recording parameters, and each assigned to predetermined values of the parameters to be determined, are loaded. An image point time series of the examination object is acquired with an MRF recording method such that the acquired image point time series are comparable with the loaded comparison signal waveforms. A signal comparison of a section of the respective signal waveform of the acquired one image point time series is carried out with a corresponding section of loaded comparison signal waveforms to establish similarity values. The values of the parameters to be determined on the basis of the most similar comparison signal waveforms determined are determined, and then stored or output.

Abstract: Various techniques of reconstructing multiple Magnetic Resonance Imaging, MRI, images for multiple slices based on an MRI measurement dataset that is acquired using a simultaneous multi-slice protocol and undersampling and K-space are disclosed. A convolutional neural network can be used to implement a regularization operation of an iterative optimization for the reconstruction, i.e., an unrolled neural network or variational neural network. A combination with Dixon imaging, i.e., separation of multiple chemical species, is disclosed.

Abstract: In a method for generating an image data set and a reference image data set: a first raw data set is provided that is acquired with a MR system and that includes measurement signals at read-out points in k-space that lie on a first k-space trajectory; a second raw data set is provided that is acquired with the same MR system and at the same examination object at read-out points that lie on a second, different k-space trajectory that is different from the first k-space trajectory; image data sets are reconstructed from the first raw data set; a reference image data set is reconstructed from the second raw data set; the reference image data set is compared with each image dataset to generate respective similarity values; and an image data set is selected having a greatest similarity value.

Abstract: In a method for generating an image dataset and one reference image dataset: a first raw dataset is provided that is recorded using a MR system, the first raw dataset including measurement signals at readout points in k-space that lie on a first k-space trajectory; a second raw dataset is provided that is recorded using the same MR system and on the same examination object, the second raw dataset including measurement signals at readout points in k-space that lie on a second, different k-space trajectory; image datasets are reconstructed from the first raw dataset, where a separate equalization coefficient set is used before the reconstruction of each image dataset; a reference image dataset is reconstructed from the second raw dataset; the reference image data set is compared with each image dataset to generate respective similarity values; and the image dataset is selected with a greatest similarity value.

Abstract: MR fingerprinting method in which an MR pulse sequence succession is output multiple times. The MR pulse sequence succession has MR pulse sequences of a same type output successively in time and differing in terms of a pulse sequence parameter that is varied according to a predefined scheme. During the first output, raw data from a region of interest (ROI) of an object is acquired in a short time interval by the raw data being acquired at a low information density. The total information density of the acquisition is increased with each repetition of the output. After the acquisition, image data from the ROI is reconstructed based on the acquired raw data. MR-parameter value datasets associated with reference image data and having MR parameter values, are determined by comparing the reconstructed image data with the reference image data. MR parameter maps are determined based on the determined MR parameter values.

Abstract: In a method and apparatus for determining parameter values in voxels of an examination object using magnetic resonance fingerprinting (MRF), a first signal comparison is made of signal characteristics of established voxel time series with first comparison signal characteristics. Further synthetic comparison signal characteristics are generated from the first comparison signal characteristics and values determined in the first signal comparison. The generated further comparison signal characteristics are used to perform a further signal comparison, with which values of at least a first and a second further parameter are determined. From the further comparison signal characteristics, a value of at least one further parameter is determined that could not necessarily already be determined in the first signal comparison.

Abstract: In a Method and a device for magnetic resonance imaging of a subject using a spoiled gradient echo sequence, a B0 magnetic field strength of at most 1.5 T is used during the sequence. As part of the sequence a slice select gradient acting as a spoil gradient is played out. Substantially simultaneously with the slice select gradient a predetermined RF pulse is played out in the sequence, wherein a time-bandwidth product of the RF pulse is set so that a majority of the energy of the RF pulse is transmitted in its central main lobe.

Abstract: For reconstruction in medical imaging, user control of a characteristic (e.g., noise level) of the reconstructed image is provided. A machine-learned model alters the reconstructed image to enhance or reduce the characteristic. The user selected level of characteristic is then provided by combining the reconstructed image with the altered image based on the input level of the characteristic. Personalized or more controllable impression for medical imaging reconstruction is provided without requiring different reconstructions.

Abstract: The disclosure facilitates determining patient motion during a magnetic resonance protocol. According to some examples, the patient motion may be corrected or compensated.

Abstract: Determining parameter values in image points of an examination object in an MR system by an MRF technique. Comparison signal waveforms, established using predetermined recording parameters, and each assigned to predetermined values of the parameters to be determined, are loaded. An image point time series of the examination object is acquired with an MRF recording method such that the acquired image point time series are comparable with the loaded comparison signal waveforms. A signal comparison of a section of the respective signal waveform of the acquired one image point time series is carried out with a corresponding section of loaded comparison signal waveforms to establish similarity values. The values of the parameters to be determined on the basis of the most similar comparison signal waveforms determined are determined, and then stored or output.

Abstract: MR fingerprinting method in which an MR pulse sequence succession is output multiple times. The MR pulse sequence succession has MR pulse sequences of a same type output successively in time and differing in terms of a pulse sequence parameter that is varied according to a predefined scheme. During the first output, raw data from a region of interest (ROI) of an object is acquired in a short time interval by the raw data being acquired at a low information density. The total information density of the acquisition is increased with each repetition of the output. After the acquisition, image data from the ROI is reconstructed based on the acquired raw data. MR-parameter value datasets associated with reference image data and having MR parameter values, are determined by comparing the reconstructed image data with the reference image data. MR parameter maps are determined based on the determined MR parameter values.

Abstract: Techniques are disclosed for providing a first magnetic resonance fingerprinting dictionary using fingerprints having a first length. A transformation matrix is also utilized that is configured to shorten the fingerprints to a second length that is shorter than the first length. A second magnetic resonance fingerprinting dictionary may then be obtained by multiplying the first magnetic resonance fingerprinting dictionary with the transformation matrix, with the fingerprints of the magnetic resonance fingerprinting dictionary having the second length. This facilitates the storage of a MRF dictionary that takes up less storage space and decreases the time taken to perform scanning operations.

Abstract: A magnetic resonance fingerprinting (MRF) method for determining parameter values in pixels of an examination object can use a magnetic resonance system with, for example, a constant magnetic field strength (e.g. of less than 1.5 tesla or a constant magnetic field strength of less than 0.5 tesla). The MRF method can be adapted for conditions that prevail with such low-field magnetic resonance systems, thus enabling the parameter values to be advantageously determined efficiently while simultaneously maintaining a high degree of quality.

Abstract: In a method and device for fingerprinting magnetic resonance imaging, a first sequence of MR data is acquired within a region of interest using a fingerprinting magnetic resonance pulse sequence; the first sequence of MR data is input to a neural network; a second sequence of MR data from the neural network is output from the neural network, the second sequence of MR data having reduced undersampling/aliasing artifacts and/or noise compared to the first sequence of MR data; values of at least one quantitative parameter are determined for the region of interest based on the second sequence of MR data; and a quantitative parameter map of the at least one quantitative parameter for the region of interest is constructed based on the determined values.

Abstract: In a Method and a device for magnetic resonance imaging of a subject using a spoiled gradient echo sequence, a B0 magnetic field strength of at most 1.5 T is used during the sequence. As part of the sequence a slice select gradient acting as a spoil gradient is played out. Substantially simultaneously with the slice select gradient a predetermined RF pulse is played out in the sequence, wherein a time-bandwidth product of the RF pulse is set so that a majority of the energy of the RF pulse is transmitted in its central main lobe.

Abstract: In a method for generating an image dataset and one reference image dataset: a first raw dataset is provided that is recorded using a MR system, the first raw dataset including measurement signals at readout points in k-space that lie on a first k-space trajectory; a second raw dataset is provided that is recorded using the same MR system and on the same examination object, the second raw dataset including measurement signals at readout points in k-space that lie on a second, different k-space trajectory; image datasets are reconstructed from the first raw dataset, where a separate equalization coefficient set is used before the reconstruction of each image dataset; a reference image dataset is reconstructed from the second raw dataset; the reference image data set is compared with each image dataset to generate respective similarity values; and the image dataset is selected with a greatest similarity value.

Abstract: In a method for generating an image data set and a reference image data set: a first raw data set is provided that is acquired with a MR system and that includes measurement signals at read-out points in k-space that lie on a first k-space trajectory; a second raw data set is provided that is acquired with the same MR system and at the same examination object at read-out points that lie on a second, different k-space trajectory that is different from the first k-space trajectory; image data sets are reconstructed from the first raw data set; a reference image data set is reconstructed from the second raw data set; the reference image data set is compared with each image dataset to generate respective similarity values; and an image data set is selected having a greatest similarity value.