Abstract: A method (200), and a device (100) for determining onset of sepsis is provided. In one aspect, the method (200) includes receiving at least one medical dataset associated with the patient, wherein the medical dataset comprises a plurality of features. Further, the method (200) includes extracting one or more features from the medical dataset, wherein the one or more features comprises parameters associated with the patient which are indicators of sepsis. Additionally, the method (200) includes imputing at least one missing value in the medical dataset, wherein the missing value is associated with the features in the medical dataset. The method (200) also includes determining an output parameter indicative of the onset of sepsis in the patient by using the one or more features and the at least one missing value in the medical dataset as an input for one or more trained machine learning model (700).

Abstract: The disclosure describes techniques for invalidating a local coil for a magnetic resonance tomography (MRT) system. The techniques include carrying out a measurement with the local coil on the MRT system, changing a mechanical and/or an electrical property of the local coil and/or an item of information about the local coil in the MRT system to the extent that a number of measurements possible with this local coil is reduced and, in the case where only the measurement carried out was possible with the local coil, a further measurement is no longer possible with this local coil on the MRT system. The disclosure also relates to a local coil and to an MRT system.

Abstract: A method for producing a local coil for an MRT measurement, including shaping a coil structure from an elongate conductor; shaping an antenna for the MRT measurement from the coil structure; introducing the antenna into a cavity mold that is designed to receive a liquid plastic material, wherein the antenna is arranged in the cavity mold in such a way that it is at least partially encapsulatable by liquid plastic material; shaping a local coil by filling the cavity mold with a liquid plastic material and curing the plastic material.

Abstract: Method including: a) loading sets of multislice MR data acquired simultaneously from identical slices of a subject, the slices are encoded with different phase patterns for each set of multislice MR data; b) separating the sets of multislice MR data into first single-slice MR data of the slices; c) determining slice-specific calibration data for a parallel imaging method for separating simultaneously acquired slices based on the first single-slice MR data; d) using the determined calibration data and an associated parallel imaging method for separating simultaneously acquired slices, separating each of the sets of multislice MR data into second single-slice MR data of the slices; e) determining motion correction parameters based on the second single-slice MR data, for compensating for motion effects between the sets of multislice MR data; and f) determining one motion-corrected set of multislice MR data each per set of multislice MR data using the motion correction parameters.

Abstract: A method for driving a MRI system to generate MRI data of an examination subject may include performing an accelerated echoplanar imaging with an undersampling according to a pulse sequence diagram to acquire k-space data. The pulse sequence diagram may have a plurality of repetitions respectively including: a first sampling diagram configured for an acquisition of k-space data for Nyquist ghost correction, or to generate magnetic field maps, a subsequent second sampling diagram configured for an accelerated echoplanar acquisition, and an excitation diagram that is common to both acquisitions. The first sampling diagram of a real subset of the plurality of repetitions may be modified to: supplement the acquired k-space data using a supplementation of k-space data missing due the undersampling, and/or correct image space of artifacts occurring due to the undersampling based on the k-space data acquired with the modified first sampling diagram.

Abstract: One or more example embodiments relates to an X-ray generator comprising a high-voltage transformer, the high-voltage transformer including a core; a primary winding module including the primary windings enclosing a core in a primary section in a shape of a coil; and a secondary winding module including secondary windings and a plastic section made from a plastic, the secondary windings enclosing the core in a secondary section in the shape of the coil, the plastic section at least one of enclosing or comprising the secondary windings, the plastic forming an electrical insulator, wherein the primary section and the secondary section have a common overlap area, and the high-voltage transformer is configured to at least one of generate a voltage of at least 70 kV with respect to ground or act as a unipolar high-voltage transformer to output a voltage of at least 70 kV.

Abstract: A method for providing supply data relating to supply to a parenchyma, comprises: receiving first imaging data, wherein the first imaging data relates to the parenchyma and/or a vascular structure that serves to supply the parenchyma; receiving reference data for the supply to the parenchyma; calculating the supply data based on the first imaging data and the reference data, wherein the supply data relates to the supply to the parenchyma; and providing the supply data.

Abstract: A shim tray designed to be pushed into a shim tray receptacle of a gradient coil unit may elongated and have a length in a longitudinal direction, a height in a radial direction and a width in a circumferential direction. The shim tray may include at least two shim pockets each configured to accommodate at least two shim plates, and at least two shim plates arranged one above the other in a radial direction in one of the shim pockets. The surfaces of the at least two shim plates may have an insulating coating.

Abstract: Techniques for performing magnetic resonance imaging are provided, which include applying at least two different pulse sequences designed for simultaneous excitation of at least two slices, and measuring k-space lines of the slices with a Parallel Imaging Results in Higher Acceleration (CAIPIRINHA) sampling scheme. Each pulse sequence comprises multiple different phase patterns, each phase pattern is used for exciting one of the slices, and the phase patterns of different pulse sequences are arranged relative to each other according to a Hadamard encoding. Images are reconstructed from the measured k-space lines by forming image slices based on different linear combinations of corresponding slices acquired with different pulse sequences.

Abstract: A computer-implemented method and system for automated segmentation of anatomical structures of a biological object, include acquiring an MRI image of the object constructed from a set of slices of the object, dividing the set of slices into overlapping groups of consecutive slices, and feeding each overlapping group of consecutive slices as input into a neural network for outputting a labelled map for each inputted slice. For each slice belonging to several overlapping groups, determining for each voxel a final label from specific labels assigned to the voxel by the neural network when considering the labelled maps outputted for the considered slice and assigning to each voxel the final label previously determined for the considered voxel and outputting a final segmentation map of final labels assigned to the voxels of the considered slice. A final 3D segmented image of the object is created from previously obtained final segmentation maps.

Abstract: A computer-implemented method comprises: performing an interactive segmentation process to determine a segmentation of a target volume depicted by a volumetric imaging dataset, the interactive segmentation process including multiple iterations. Each iteration of the interactive segmentation process includes: determining, using a neural network algorithm, a respective estimate of the segmentation; and obtaining, from a user interface, one or more localized user inputs correcting or ascertaining the respective estimate of the segmentation. The neural network algorithm includes multiple inputs, wherein the multiple inputs include an estimate of the segmentation determined in a preceding iteration of the multiple iterations, an encoding of the one or more localized user inputs obtained in the preceding iteration, and the volumetric imaging dataset.

Abstract: One or more example embodiments of the present invention relates to a tactile sensor cover for detecting a collision with a multilayer, two-dimensional structure. The tactile sensor cover includes a reversibly deformable top layer forming an outer side of the sensor cover; a rigid base layer forming an inner side of the sensor cover; a sensor unit running between the top layer and the base layer, the sensor unit comprising two sensor layers; and a reversibly compressible spacer layer arranged between the two sensor layers, wherein at least two of the top layer, the base layer, and the two sensor layers are embodied as layers formed via an additive manufacturing technique.

Abstract: The disclosure relates to a hygiene cover for preventing a contamination of a target surface of a medical imaging device. The hygiene cover is configured for reversibly attaching to the target surface of the medical imaging device and/or a body region of a patient, and the reversible attachment is configured to provide for maintaining a predefined relative position of the hygiene cover to the medical imaging device.

Abstract: A magnetic resonance tomography system may include an adapted ventilator with an air exit. The adapted ventilator may include an airstream generator (e.g., with a motor), an air volume amplifier which is arranged at the air exit and/or includes the air exit, and an air line section which carries an airstream that is generated by the airstream generator to the air volume amplifier. The air volume amplifier may be configured to increase an air volume of the airstream that is carried via the air line section to the air volume amplifier, so that it outputs an airstream with increased air volume.

Abstract: Methods and systems for providing an analytical result by automated evaluation of a medical data set in a distributed runtime environment are provided. In response to a request to provide the analytical result from a client computing device, a suitable version of an ML algorithm is selected from an algorithm repository unit and applied in a back-end computing device. Selection is made on the basis of areas of application which, for each version in the algorithm repository unit, characterize the version.

Abstract: Method for positioning a couch in an MR system tunnel, including: positioning a position determination unit having a magnetic field sensor at a marker position on the couch or a patient supported on the couch; evaluating sensor data of a magnetic field sensor using a control unit operable to establish the marker position in a coordinate system of the MR system, in which a FOV position of a FOV of the MR system is known; determining a desired required position of the FOV relative to the marker position for a subsequent measurement of MR data in a direction of movement of the couch corresponding to the longitudinal direction of the couch by the control unit from the marker position; and activating the couch by the control unit using the marker position and the FOV position such that the desired position of the FOV relative to the marker position is set.

Abstract: A gradient coil unit may include a gradient coil surrounding a cylinder axis and configured to generate a magnetic field gradient in a first spatial direction. The gradient coil may include a hollow cylindrical primary layer having two primary conductor structural units and a cooling duct. One primary conductor structural unit respectively of the two primary conductor structural units is formed from one primary electrical conductor respectively, where primary electrical conductor can be divided into two sections connected to one another in series. The cooling duct may be arranged at least partially between the two sections. The two sections and the cooling duct may run at least partially parallel. The two sections may have one contact surface respectively with the cooling duct.

Abstract: A method for parameterizing an imaging sequence, including: (a) receiving and/or establishing at least one fixed parameter using a computer unit; and (b) automatically setting at least one further parameter of the imaging sequence using a neural network installed on the computer unit, based on the at least one fixed parameter.

Abstract: Techniques are provided for cooling a magnetic resonance system in a cost-effective and space-saving manner. For this purpose, a magnetic resonance system is proposed which has a superconducting magnetic coil facility, an outer vacuum chamber in which the superconducting magnetic coil facility is arranged, and a first load facility for ramping down the superconducting magnetic coil facility. An electric current is introduced from the magnetic coil facility into the load facility, and the first load facility is arranged within the outer vacuum chamber.

Abstract: An X-ray generating apparatus and an imaging device. The X-ray generating apparatus includes: a casing; a heat-conduction member, the heat-conduction member being arranged to run through the casing, and a through-channel being provided in the interior of the heat-conduction member, the through-channel being configured to circulate a cooling medium; an anode target, the anode target being configured to receive electron bombardment in order to generate X-rays, and the anode target is arranged in the casing and surrounding the heat-conduction member in a rotatable fashion. The imaging device includes a cooling system and an X-ray generating apparatus. The cooling system is in communication with two ends of the heat-conduction member, and the cooling system is configured to convey a cooling medium into the heat-conduction member.