Abstract: A method for determining a quantitative result CT parameter map in a region of interest of an object under examination is described. The method includes acquiring a sequence of quantitative input CT parameter maps for at least two predetermined times, the sequence being generated by a contrast-enhanced spectral multiphase CT of the region of interest; receiving a sequence of contrast-enhanced MRI image datasets, the MRI datasets having a higher temporal resolution than the sequence of input CT parameter maps; determining a relation between the MRI image datasets and the input CT parameter maps; and determining the result CT parameter map based on the determined relation and the MRI image datasets for at least one additional time, the at least one additional time being different from the predetermined time.

Abstract: A computer-implemented method of reconstructing a motion-compensated magnetic resonance image uses raw k-space data acquired at a first resolution over successive respiratory and/or cardiac cycles of a patient. After binning data based on corresponding motion states derived from these cycles, the resolution of the binned K-space data in each bin is reduced. This is done by selecting a sub-group of binned k-space data. Bin images are reconstructed from the reduced-resolution data, and histogram-equalised versions of the reconstructed reduced-resolution bin image generated for each bin. Motion fields are estimated and interpolated to the first resolution such that motion data can be incorporated into a final reconstruction of a motion compensated image.

Abstract: For medical imaging such as MRI, machine training is used to train a network for segmentation using both the imaging data and protocol data (e.g., meta-data). The network is trained to segment based, in part, on the configuration and/or scanner, not just the imaging data, allowing the trained network to adapt to the way each image is acquired. In one embodiment, the network architecture includes one or more blocks that receive both types of data as input and output both types of data, preserving relevant features for adaptation through at least part of the trained network.

Abstract: For medical imaging such as MRI, machine training is used to train a network for segmentation using both the imaging data and protocol data (e.g., meta-data). The network is trained to segment based, in part, on the configuration and/or scanner, not just the imaging data, allowing the trained network to adapt to the way each image is acquired. In one embodiment, the network architecture includes one or more blocks that receive both types of data as input and output both types of data, preserving relevant features for adaptation through at least part of the trained network.

Abstract: A method for recording a magnetic resonance image dataset includes providing a magnetic resonance sequence with a series of sequence blocks, and providing at least one correction term to compensate for a magnetic field change. The magnetic field change is produced as a change of an actual magnetic field compared to a setpoint magnetic field by gradient pulses. The magnetic field change is established via a transfer characteristic of the gradient system of the magnetic resonance installation. The at least one correction term is used to compensate for the magnetic field change, and at least one magnetic resonance image dataset is recorded with the magnetic resonance sequence using the correction term.

Abstract: To acquire measurement data of an object, a first subsampled set of diffusion-weighted measurement data with switching of diffusion gradients for diffusion encoding of the measurement data, using a first echo spacing, and a second subsampled set of non-diffusion-weighted measurement data, using the first echo spacing, are acquired. The first and second subsampled sets of measurement data are supplemented using calibration data to produce first and second complete sets of measurement data. At least the first calibration data, acquired using the first echo spacing, may be used for supplementing the second subsampled set of measurement data to produce a second complete set of measurement data. By supplementing subsampled sets of measurement data with calibration data acquired according to the same echo spacing as the subsampled measurement data, noise signals in the supplemented measurement data are advantageously eliminated.

Abstract: A local coil may include: a wireless power receiver, for converting electrical energy to AC electricity, the electrical energy being wirelessly received from a power source; an AC-DC converter, for converting the AC electricity to first DC electricity having a first voltage; a DC-DC converter, for converting the first DC electricity to second DC electricity having a second voltage; a comparator, for comparing the first voltage and the second voltage, and generating a level signal on the basis of a comparison result; and a transmitter, for sending the level signal to the power source, such that the power source adjusts an output power of the electrical energy on the basis of the level signal. The wirelessly supplying of power to a local coil as well as power feedback control is achieved to advantageously increase energy transmission efficiency and system robustness.

Abstract: A method and a system are for providing a medical data structure for a patient. The system includes a plurality of data sources, each data source to provide medical data of the patient; a computing device to implement an artificial neural network structure a plurality of encoding modules, each being realized as an artificial neural network configured and trained to generate, from the medical data from the corresponding data source, a corresponding encoded output matrix; a weighting gate module for each of the encoding modules; a concatenation module configured to concatenate weighted output matrices of the weighting gates to a concatenated output matrix; and an aggregation module realized as an artificial neural network configured and trained to receive the concatenated output matrix and to generate therefrom the medical data structure for the patient, the artificial neural network structure being trained as a whole using a cost function.

Abstract: An interface module to connect a collimator to an X-ray generator, includes: a base plate, which forms a support area for an X-ray tube unit flange of the X-ray generator; an adjustment plate, which is rotatably connected to the base plate; and at least one swivel element movably connected to the base plate and adjustment plate such that, upon rotation of the adjustment plate, the at least one swivel element pivots between a clamping position and an open position.

Abstract: A method of and an Artificial Intelligence (AI) system for predicting hemodynamic parameters for a target vessel, in particular of an aorta, as well as to a computer-implemented method of training an AI unit of the AI system are disclosed. A vessel shape model of the target vessel and a corresponding flow profile of the target vessel are received. At least one hemodynamic parameter is predicted by the AI unit based on the received vessel shape model and the received flow profile. The AI unit is arranged and configured to predict at least one hemodynamic parameter based on a received vessel shape model and a received flow profile of the target vessel (aorta).

Abstract: Techniques are disclosed for positioning a patient couch in a patient receiving area of a magnetic resonance device for a magnetic resonance examination, which includes starting an introduction of the patient couch into the patient receiving area, acquiring monitoring data within an acquisition area of at least one sensor unit by means of the at least one sensor unit during the introduction of the patient couch into the patient receiving area, evaluating the monitoring data with respect to a selected area of an examination object and/or a selected area of the patient couch, and positioning the patient couch within the patient receiving area in dependence on an acquisition of the selected area of the examination object and/or the selected area of the patient couch in the monitoring data.

Abstract: A method for reducing artifact generation echo in stimulated-echo-based strain imaging using magnetic resonance imaging (MRI) includes determining an inhomogeneity direction, determining an encoding direction, adjusting the encoding direction to correspond with the inhomogeneity direction, and capturing, via an MRI system, a magnetic resonance image of the anatomical object at an imaging location when the encoding direction corresponds with the inhomogeneity direction. The inhomogeneity direction is the direction of a local inhomogeneity of a magnetic field at the imaging location of an anatomical object. The encoding direction is the direction of an encoding gradient of a magnetic field of the MRI system.

Abstract: A method for operating a magnetic resonance facility in which a measurement gradient pulse is used to record magnetic resonance signals for sampling k-space along a trajectory section. The recorded magnetic resonance signals are assigned to k-space points using a shape function describing the time profile of the measurement gradient pulse. To correct deviations of the real time profile of the measurement gradient pulse from an assumed target profile, a first correction measurement is performed to ascertain first magnetic resonance signals of the trajectory section. A second correction measurement is then performed using a reference sampling pattern or a reference gradient pulse with fewer deviations from an assigned reference target profile. If a deviation criterion is met, a correction function for the shape function is ascertained by aligning the first and second magnetic resonance signals to one another, providing correction information to be used in an imaging measurement.

Abstract: For a computed tomography image data set of a recording region in which an at least substantially needle-shaped metal object is located, a method for correcting artifacts comprises: ascertaining an artifact data set describing, in an image space, at least one artifact caused by the at least substantially needle-shaped metal object, wherein the ascertaining uses prior knowledge about the at least one artifact; and subtracting the artifact data set from the computed tomography image data set. The computed tomography image data set being reconstructed from projection images, which are recorded at least partially such that the at least substantially needle-shaped metal object is irradiated at least substantially in the longitudinal direction.

Abstract: One or more example embodiments of the invention relates in one aspect to a computer-implemented method for providing a stroke information. The method includes receiving examination data, the examination data comprising computed tomography imaging data of an examination area of a patient, the examination area of the patient comprising at least one brain region, the at least one brain region being affected by a stroke; adjusting a causal model based on the computed tomography imaging data to obtain an adjusted causal model, wherein the adjusted causal model models a first variable as a first cause for an appearance of the examination area of the patient; receiving a first value for the first variable; generating the stroke information based on the adjusted causal model and the first value for the first variable; and providing the stroke information.

Abstract: One or more example embodiments relates to a method for controlling a motion of a component of a medical installation, comprising capturing a first position parameter via a first position sensor, the first position sensor being on the component; capturing a second position parameter via a second position sensor, the second position sensor being on the component; determining, by a control unit, a position spacing for the position sensors based on the first position parameter and the second position parameter; and generating a control signal for a drive unit of the component based on the determined position spacing.

Abstract: A magnetic resonance tomography scanner and a method for testing the magnetic resonance tomography scanner are provided. The magnetic resonance tomography scanner has a transmitter that is configured to transmit two-tone signals at different levels and to acquire intermodulation products of the two-tone signal with the receiver. A status of a receive path is inferred via a behavior of odd-order intermodulation products.

Abstract: For machine learning for abnormality assessment in medical imaging and application of a machine-learned model, the machine learning uses regularization of the loss, such as regularization being used for training for abnormality classification in chest radiographs. The regularization may be a noise and/or correlation regularization directed to the noisy ground truth labels of the training data. The resulting machine-learned model may better classify abnormalities in medical images due to the use of the noise and/or correlation regularization in the training.

Abstract: An apparatus or an add-on module for a, in particular mobile, device, is disclosed. In an embodiment, the device to be localized or the add-on module uses a measuring unit to measure, via suitable sensors, a local electromagnetic field distribution generated by a given infrastructure. An instantaneous position of the add-on module or of the device equipped therewith is then determined by comparing the measured field distribution with a specified map. In order to facilitate tracking of the add-on module or of the device, the measured field distribution and/or the determined position can be sent via a wireless data connection to a server unit.