Abstract: A framework for anatomy-aware adaptation of a graphical user interface. Landmarks are first detected by passing one or more current images through a trained machine learning model. A body section may then be inferred based on the detected landmarks. One or more user interface elements may be determined based on the inferred body section. A graphical user interface may then be adapted with the determined one or more user interface elements.

Abstract: A computer-implemented method for using machine learning to suppress fat in acquired MR images includes receiving multi-echo images from an anatomical area of interest acquired using an MRI system. A first subset of the multi-echo images is acquired prior to application of contrast to the anatomical area of interest and a second subset of the multi-echo images is acquired after application of contrast to the anatomical area of interest. Next, data is generated including water images, fat images, and effective R*2 maps from the multi-echo images. The water images, the fat images, and the effective R*2 maps are used to create synthetic fat suppressed images. A neural network is trained to use the multi-echo images as input and the synthetic fat suppressed images as ground truth. A plurality of components of the neural network are saved to allow later deployment of the neural network on a computing system.

Abstract: Techniques are disclosed for creating measurement data of an examination object by means of magnetic resonance technology in a plurality of repetitions according to a pulse sequence pattern, existing information about gradients that have already been switched is considered to determine compensation gradients that are possibly to be switched in a following repetition for compensating eddy current effects. Such dynamic determination and switching of compensation gradients make it possible to dynamically compensate eddy currents. Consequently, the image quality of image data reconstructed from measurement data acquired using inventive compensation gradients is increased.

Abstract: Systems and methods are provided for performing medical imaging analysis. Input medical imaging data is received for performing a particular one of a plurality of medical imaging analyses. An output that provides a result of the particular medical imaging analysis on the input medical imaging data is generated using a neural network trained to perform the plurality of medical imaging analyses. The neural network is trained by learning one or more weights associated with the particular medical imaging analysis using one or more weights associated with a different one of the plurality of medical imaging analyses. The generated output is outputted for performing the particular medical imaging analysis.

Abstract: A method is for the characterization of plaque in a region of interest inside an examination subject by way of a plurality of image data sets. The image data sets have been reconstructed from a plurality of projection data sets, which have been acquired via a CT device using different X-ray energy spectra. The method includes: acquiring the image data sets, which include a plurality of pixels. Spectral parameter values are acquired on a pixel by pixel basis using at least two image data sets. Character parameter values are then acquired on a pixel by pixel basis to characterize plaques on the basis of the spectral parameter values. An analysis unit and a computed tomography system are also disclosed.

Abstract: Techniques are described for controlling a fleet of MR-scanner systems by means of a user interface. Each MR scanner system in the fleet of MR scanner systems comprises a hardware layer having a plurality of electronically controllable components and mechanical components to perform an MR measurement and capture MR-scanner raw data, a Measurement And Reconstruction System (MARS) computing unit configured to implement a measurement framework using a sequence to calculate real-time instructions and transmit these instructions to the components of the hardware layer for controlling the MR-scanner system, and a communication interface for communicating with an external device. Each MR scanner system has system attributes, which are transmitted to the external device via the communication interface.

Abstract: Described herein are technologies for facilitating reconstruction of flow data. In accordance with one aspect, the framework receives a four-dimensional projection image dataset and registers one or more pairs of temporally adjacent projection images in the image dataset. Two-dimensional flow maps may be determined based on the registered pairs. The framework may then sort the two-dimensional flow maps according to heart phases, and reconstruct a three-dimensional flow map based on the sorted two-dimensional flow maps.

Abstract: A method for segmenting metal objects in projection images acquired using different projection geometries is provided. Each projection image shows a region of interest. A three-dimensional x-ray image is reconstructed from the projection images in the region of interest. A trained artificial intelligence segmentation algorithm is used to calculate first binary metal masks for each projection image. A three-dimensional intermediate data set of a reconstruction region that is larger than the region of interest is reconstructed by determining, for each voxel of the intermediate data set, as a metal value, a number of first binary metal masks showing metal in a pixel associated with a ray crossing the voxel. A three-dimensional binary metal mask is determined. Second binary metal masks are determined for each projection image by forward projecting the three-dimensional binary metal mask using the respective projection geometries.

Abstract: A method for transfer of a dataset includes provisioning or generating a user-side Diffie Hellman key pair, including a secret user key and a public user key; transferring the public user key to the server; provisioning or generating a server-side Diffie Hellman key pair, including secret server and public server keys; provisioning a dataset on the server; generating a server-side Diffie Hellman key using the secret server key and the public user key, and encrypting the dataset to generate an encrypted dataset, via a resulting server-side Diffie Hellman key generated on the server side; transferring the encrypted dataset to the cloud service; retrieving the public server key and the encrypted dataset from the cloud service; and generating a user-side Diffie Hellman key using the secret user key and the public server key retrieved, and decrypting the encrypted dataset on the user device using the user-side Diffie Hellman key.

Abstract: A brazing apparatus and method for brazing an anode target plate of an X-ray generator are disclosed. The brazing apparatus comprises: a vacuum part for providing, during brazing, a vacuum environment at least for a target plate main body formed of an alloy, a brazing material, and a substrate; an induction brazing part for applying an induction current to the target plate main body, the brazing material and the substrate in the vacuum part so as to achieve heating to a temperature higher than the melting point of the brazing material, causing the substrate to be welded to the target plate main body through melting of the brazing material and a resulting reaction; and a directional energy welding part for applying a generated directional energy beam to a position of lower temperature determined on the target plate main body to perform heating.

Abstract: A method is for acquiring a magnetic resonance (MR) image dataset of at least two slices via simultaneous multi-slice excitation. An embodiment of the method includes executing an MR imaging sequence using multi-band radio-frequency excitation pulses to excite the at least two slices simultaneously in at least two repetitions, the repetitions each being executed according to a phase modulation scheme in which each of the simultaneously excited slices is assigned a phase and the phase of at least one of the simultaneously excited slices is changed from one repetition to the next, thereby acquiring an MR dataset of a collapsed image in each repetition; performing a spatial registration between the at least two collapsed images and performing motion correction on at least one of the MR datasets of the collapsed images; and reconstructing MR images of the at least two slices from the corrected MR datasets of the collapsed images.

Abstract: A method and system are for providing dose data from a cloud-based dose management system in a local Intranet. The method includes receiving study data according to at least one selection criterion from an image archiving and communication system, within the local Intranet; uploading first dose data, including or indicating at least one respective unique study-identifying characteristic value, based upon the study data received, into a cloud-based dose management system; checking whether a trigger condition is present; downloading via the dose data provisioning module, upon the checking indicating a presence of the trigger condition, second dose data, including or indicating a respective unique study-identifying characteristic value, based upon the first dose data from the cloud-based dose management system; and providing the second dose data to a reporting system or another local apparatus within the local Intranet, either automatically or upon a provisioning condition being fulfilled.

Abstract: A method of position planning for a recording system of an imaging device with respect to a selectable field of view of a patient includes acquiring current position information of the recording system and/or the imaging device, and/or setting information of a collimator of the imaging device. A current intersection volume between an X-ray beam and the patient and/or a current field of view is determined. The current intersection volume and/or the current field of view is determined as a virtual display element. A target intersection volume and/or a target field of view is received by manipulation of the virtual display element. A target position of the recording system and/or the imaging device, and/or the setting of the collimator is determined, such that, on occupying the target position, the target intersection volume and/or the target field of view becomes the current intersection volume and/or current field of view.

Abstract: An anatomical structure is detected (110) in a volume of ultrasound data by identifying (150) the anatomical structure in another volume of ultrasound data and generating (155) an image of the anatomical structure and an anatomical landmark. A group of images are generated (130) of the original volume and compared (140) to the image of the other volume. An image of the group of images is selected (150) as including the anatomical structure based on the comparison.

Abstract: The present disclosure relates to a method and a magnetic resonance imaging device for two-dimensional (2D) magnetic resonance (MR) imaging of a subject. The disclosure further relates to a corresponding computer program and a corresponding computer-readable storage medium. In one exemplary method, a k-space dataset of the subject is acquired using a simultaneous multi-slice technique. Therein, a blipped phase-encoding gradient is applied in a pseudo-random manner to achieve an incoherent undersampling at least in a k-space direction perpendicular to a slice select direction. A compressed sensing reconstruction is then performed based on the acquired k-space dataset to generate an MR image of the subject.

Abstract: The present disclosure relates to techniques to expand the dynamic range of a detector and achieve smooth transition in images used for X-ray image processing. The image finally obtained can fully retain useful information.

Abstract: In an automatic exposure control method for X-ray imaging, a visible light image of a subject under test is acquired, an initial region of interest (ROI) is defined on the visible light image, the subject under test is pre-exposed with a set pre-exposure dose to obtain a first image, an ROI on the first image is defined based on the initial ROI, a reference pixel value is defined based on the ROI, and a main exposure dose for an actual exposure is calculated according to the reference pixel value. With the imaging quality guaranteed, a physical automatic exposure control (AEC) chamber may be omitted, and the number, positions and sizes of ROIs can be adjusted according to the actual requirements.

Abstract: A computer-implemented method and a corresponding apparatus are provided for the provision of a two-dimensional visualization image having a plurality of visualization pixels for the visualization of a three-dimensional object represented by volume data for a user. Context information for the visualization is obtained by the evaluation of natural language and is taken into account in the visualization. The natural language can be in the form of electronic documents, which are assigned or can be assigned to the visualization process. In addition, the natural language can be in the form of a speech input of a user, during or after the visualization.

Abstract: A method for use in generating a computer-based visualization of 3D medical image data is described. The method includes receiving 3D medical image data and performing a selection process to select first image data forming a first portion of the 3D medical image data, the first image data representing a first anatomical object of a given type. An analysis process is performed on the first image data, a parameter of the analysis process being based on the given type of the first anatomical object. Based at least in part on a result of the analysis process, a visual parameter mapping for the first portion is determined, for use in a rendering process for generating a visualization of the 3D medical image data. Also described is a method of generating a computer-based visualization of 3D medical image data and an apparatus for performing the methods.

Abstract: A line for an electrical connection in a magnetic resonance tomography apparatus and a magnetic resonance tomography apparatus with a corresponding line are provided. The line includes an electrical interference conductor that may pick up an electromagnetic interference signal from an environment and/or irradiate the electromagnetic interference signal into the environment. The line also includes a sensor that is electrically and/or magnetically coupled to the interference line.