Abstract: A system and method includes determination of a projection axis associated with the two-dimensional projection image, generation of a second two-dimensional image from the three-dimensional image based on the projection axis, registration of the two-dimensional projection image with the second two-dimensional image, combination of the registered two-dimensional projection image with the three-dimensional image in a plane of the three-dimensional image substantially orthogonal to the projection axis, and display of the combined image.

Abstract: A method for ascertaining a magnetic field of at least one magnetic coil unit of a magnetic resonance apparatus, a magnetic resonance apparatus, and a computer program product are provided. According to the method, the magnetic field is generated by the at least one magnetic coil unit. A plurality of magnetic field vectors are detected at different positions of the magnetic field by a magnetic field sensor unit, where each magnetic field vector of the plurality of magnetic field vectors describes a strength, such as a magnitude, and a direction of the magnetic field at the respective position. The magnetic field is ascertained. To ascertain the magnetic field based on the plurality of magnetic field vectors, a model of a vector field is ascertained.

Abstract: At least one example embodiment provides an electron emitter apparatus having a first ring of field-effect emitter needles, the field-effect emitter needles of the first ring forming a first emitter surface on an inner side of the first ring; and a second ring of field-effect emitter needles, the field-effect emitter needles of the second ring forming a second emitter surface on an inner side of the second ring, wherein the first ring and the second ring are arranged in such that the first emitter surface and the second emitter surface form a substantially contiguous three-dimensional overall emitter surface, the substantially contiguous three-dimensional overall emitter surface defining a hollow channel along a longitudinal axis of the electron emitter apparatus.

Abstract: A computer-implemented method is for providing radiomics-related information. In an embodiment, the computer-implemented method includes receiving radiomics-related data; determining, based on the radiomics-related data and an assistance algorithm, a function for processing the radiomics-related data; calculating, based on the radiomics-related data and the function for processing the radiomics-related data, the radiomics-related information; and providing the radiomics-related information.

Abstract: A computer-implemented method is for operating a medical imaging system. The imaging system includes an imaging unit and a positioning apparatus for positioning an examination object. In an embodiment, the method includes ascertainment of object information relating to the examination object; determination of a region of interest for the examination object, the region of interest being defined as a region of the examination object to be examined by the imaging unit in the context of an examination to be performed; arrival at a determination concerning a positional state of the examination object relative to the positioning apparatus and, to be precise, based on the region of interest and the object information; and provision of user output for a user of the imaging system based on the determination.

Abstract: A method for providing a secondary parameter, a decision support system, a computer-readable medium and a computer program product are disclosed. In an embodiment, the method is for providing a secondary parameter in a decision support system providing a primary parameter, in particular in a clinical decision support system. The method includes: providing an input data set; approximating a secondary parameter based on the input data set by using a sub-system being trained by a machine learning mechanism, in particular by a deep learning mechanism; and providing the approximated secondary parameter. The input data set is a shape data set.

Abstract: A method is for determining a patient-adjusted breast compression in mammography. In an embodiment of the method, input data including individual, person-related data of a female patient, is determined. Furthermore, an adjusted individual compression point is determined by applying a function, trained by an algorithm based on machine learning, to the input data. The adjusted individual compression point is generated as the output data. Other embodiments include a method for providing a trained function; a breast compression determining device; a training device; and a mammography system.

Abstract: The disclosure relates to a technique for providing an image of diagnostically relevant area of a jaw region of a patient by means of a magnetic resonance apparatus by capturing information about the jaw region of the patient, which comprises at least one reference to a position and/or an extent of the diagnostically relevant area of the jaw region. The technique also includes adjusting a parameter of a magnetic resonance measurement as a function of the captured information about the jaw region of the patient, carrying out the magnetic resonance measurement with the adjusted parameter, capturing image data of the jaw region of the patient, reconstructing an image of the diagnostically relevant area of the jaw region as a function of the captured image data, and providing the image of the diagnostically relevant area of the jaw region of the patient.

Abstract: A magnetic resonance tomography unit and a method for operating the magnetic resonance tomography unit are provided. The magnetic resonance tomography unit has a transmission interference suppression device with a transmission interference suppression control system, a sensor, and a transmission interference suppression antenna. The transmission interference suppression device is configured to acquire, with the sensor, an excitation signal of the transmitter, and determine, with the transmission interference suppression control system, a transmission interference suppression signal dependent upon the acquired excitation signal of the transmitter. The transmission interference suppression device is configured to transmit, via the transmission interference suppression antenna, the transmission interference suppression signal, so that at a predetermined location outside the magnetic resonance tomography unit, the excitation signal emitted by the transmitter via the transmitter antenna is attenuated.

Abstract: A training method for training neural networks to determine a magnetic susceptibility distribution of a sample may include: storing a simulated magnetic susceptibility map of the sample, generating a modified magnetic susceptibility map by combining an influence of one or more external magnetic susceptibility sources with the simulated magnetic susceptibility map and storing the modified magnetic susceptibility maps. The method may include generating a first training image by applying a quantitative susceptibility mapping model the modified magnetic susceptibility map and storing the first training image, applying the first neural network to the first image and a second neural network to an output of the first neural network and changing network parameters of the first and the second neural network depending on a deviation of an output of the second artificial neural network from the simulated magnetic susceptibility map.

Abstract: A system for holding and controlling medical instruments during procedures includes an end effector configured to hold a medical instrument and a rotational and translational (RT) mechanism configured to rotate and translate the medical instrument along an insertion axis. The system further includes a platform coupled to the RT mechanism and a pair of parallel five-bar planar linkages configured to translate, pitch, and yaw the platform with respect to a principal axis that is parallel to the insertion axis.

Abstract: A system and method for identifying abnormal medical images. The system can be configured to receive a medical image, segment an anatomical structure from the medical image to define a segmented dataset, register the segmented dataset to a baseline dataset defining a normal anatomical structure, classify, by an abnormality classifier, whether the anatomical structure within the medical image as either abnormal or normal, wherein the abnormality classifier comprises a machine learning algorithm trained to distinguish between normal and abnormal versions of the anatomical structure in medical images, and based on whether the anatomical structure can be segmented from the medical image, whether the segmented dataset can be registered to the baseline dataset, or a classification associated with the medical image output by the abnormality classifier, flagging the medical image as either normal or abnormal.

Abstract: A method for generating result slice images with at least partially different slice thickness based on a tomosynthesis image data set of a breast includes generating average value slices and maximum value slices (MIP) based on the tomosynthesis image data set, frequency dividing the average value slices into low-pass filtered and high-pass filtered average value slices, high-pass filtering of maximum value slices to form high-pass filtered maximum value slices, mixing high-pass filtered maximum value slices and high-pass filtered average value slices to form mixed high-pass filtered maximum value slices, combining the low-pass filtered average value slices with the mixed high-pass filtered maximum value slices to form the result slice images, and applying a moving maximum value across a selected thickness of maximum value slices or across a selected thickness of mixed high-pass filtered maximum value slices.

Abstract: For detecting motion in MR imaging, a regression model, such as a convolutional neural network, is machine trained. To generalize to MR imagers, MR contrasts, or other differences in MR image generation, the regression model is trained adversarially. The discriminator for adversarial training discriminates between classes of the variation source (e.g., type of MR imager or type of contrast) based on values of features learned in the regression model for detecting motion. By adversarial training, the regression model learns features that are less susceptible or invariant to variation in image source.

Abstract: A method is for data communication in a network including a first network area and a second network area. The method includes provisioning medical patient data; provisioning identification data for identification of a patient; provisioning a code linked to the identification data; sending medical patient data and the code from the first network area to a server in the second network area; and processing the patient data by the server. The method further includes provisioning identification data or input of identification data for identification of a patient by the user; establishing of a code linked to the identification data; automatic sending of the code to the server; establishing the status of the processing patient data linked to the code; creating a corresponding status notification by the server; and sending the status notification to the user.

Abstract: Systems and methods facilitate privacy-preserving data curation in a federated learning system by transmitting a portion of a potential data sample to a remote location. The portion is inspected for quality to rule out data samples that do not satisfy data curation criteria. The remote examination focuses on checking the region of interest but maintains privacy as the examination is unable to parse any other identifiable subject information such as face, body shape etc. because pixels or voxels outside the portion are not included. The examination results are sent back to the collaborators so that inappropriate data samples can be excluded during federated learning rounds.

Abstract: Systems and methods are provided for training an artificial intelligence model for detecting calcified portions of a vessel in an input medical image. One or more first medical images of a vessel in a first modality and one or more second medical image of the vessel in a second modality are received. Calcified portions of the vessel are detected in the one or more first medical images, The artificial intelligence model is trained for detecting calcified portions of the vessel in the input medical image in the second modality based on the one or more second medical images and the detected calcified portions of the vessel detected in the one or more first medical images.

Abstract: In one embodiment, a method is for calculating an examination parameter for a computed tomography examination of an area of interest of a patient. The method includes receiving a topogram of the area of interest of the patient; determining fat distribution information by applying a trained machine learning algorithm onto the topogram; and calculating the examination parameter for the computed tomography examination of the area of interest of the patient based on the fat distribution information.

Abstract: A deep machine-learning approach is used for medical image fusion by a medical imaging system. This one approach may be used for different applications. For a given application, the same deep learning is used but with different application-specific training data. The resulting deep-learnt classifier provides a reduced feature vector in response to input of intensities of one image and displacement vectors for patches of the one image relative to another image. The output feature vector is used to determine the deformation for medical image fusion.