Abstract: Systems and methods are provided for optimizing a deep learning model. A multi-site dataset associated with different clinical sites and a deployment dataset associated with a deployment clinical site are received. A deep learning model is trained based on the multi-site dataset. The trained deep learning model is optimized based on the deployment dataset. The optimized trained deep learning model is output.

Abstract: Electrohydraulic actuator device for a motor vehicle brake system, comprising a cylinder housing, within which a pressure piston is displaced in a translational manner by a rotating threaded spindle, wherein the threaded spindle is driven via a transmission device by a rotor shaft of an electric motor, wherein the actuator device comprises an electronic unit, and a brake system for a motor vehicle having such an electrohydraulic actuator device and a pressure generator, a pressure modulation valve device for the wheel-individual generation of brake pressure at wheel brakes of the brake system, an electronic control device, which is designed for controlling the pressure generator and the pressure modulation valve device, and having a driver's brake actuation device.

Abstract: Systems and methods for performing an assessment of a lesion are provided. A plurality of input medical images of a lesion is received. The plurality of input medical images comprises an initial input medical image and one or more additional input medical images. The initial input medical image comprises a region of interest around the lesion. A mask of the lesion is curated for the initial input medical image based on the region of interest and a set of candidate masks. The region of interest in the initial input medical image is propagated to the one or more additional input medical images based on prior registration transformations. A mask of the lesion is curated for each of the one or more additional input medical images based on the propagated regions of interest and the set of candidate masks. One or more assessments of the lesion are performed based on the mask for the initial input medical image, the masks for the one or more additional input medical images, and prior assessments of lesions.

Abstract: A method for classifying medical image data using a classification algorithm configured to make an image-based correlation between an image data set and a phase of a plurality of defined phases relative to a time of administration of a contrast agent with additional plausibility checking. The image data may include at least three image data sets in each case imaging the examination region in each case at a time of capture within a period of less than two hours.

Abstract: A method for controlling a brake system in the case of leaks is provided. The brake system has a mechanically actuable master brake cylinder, which is connected to a first partial reservoir of a brake fluid vessel, and has an electric linear actuator, which is connected to a second partial reservoir of the brake fluid vessel. The master brake cylinder and the linear actuator are connected via an electrically closable circuit isolating valve. In order to protect the brake fluid, in the event of a leak during a transition to a standby state, the linear actuator is activated to take a brake fluid volume out of the first partial reservoir via the open circuit isolating valve and to displace it into the second partial reservoir.

Abstract: The invention relates to a method for separating waste polyurethane foams, wherein for each polyurethane sample (1) of a supply stream (2) comprising polyurethane samples (1) from waste at least one respective spectrum (3) is recorded, wherein the at least one respective spectrum (3) is recorded by near-infrared spectroscopy, wherein each polyurethane sample (1) of the supply stream (2) is classified by a classification algorithm (5), which classification algorithm (5) is based on machine learning, based on the respective at least one spectrum (3) into a respective class (8a-e) of at least two classes (8a-e), wherein the supply stream (2) comprising polyurethane samples (1) is separated into at least two streams (11a-e) according to the classification into the respective class (8a-e) and wherein each class (8a-e) corresponds to a type of polyurethane. The invention also relates to a system for separating waste polyurethane foams.

Abstract: In a method for an actuation of a magnetic resonance device for capturing image data from an examination region of an examination object, at least one first control sequence is provisioned, the magnetic resonance device is actuated according to the at least one first control sequence to capture first data from the examination object, the first data is analyzed with respect to a property to generate a result, and, based on the result, a selective performance of one of: a selection of a further control sequence, and termination of the actuation of the magnetic resonance device, is performed.

Abstract: A method for assigning a medical device may be implemented in a scheduler agent apparatus. The method may include receiving, from a patient agent apparatus, a utilization request containing patient parameters for examining a patient by a medical device from the group; determining the suitability of at least one medical device from the group for the examination based on the patient parameter or parameters and one or more device parameters; assigning a medical device determined to be suitable to the utilization request based on the patient parameter or parameters and device parameters; transmitting, to the patient agent apparatus, a notification regarding the assignment; and transmitting a notification to an device agent apparatus associated with the assigned medical device.

Abstract: In a method for generating a surrogate marker based on medical image data mapping an image region, the medical image data is detected using a first interface, a first subregion of the image region is selected by segmenting a first structure included in the image region, a first property of the first subregion is extracted, the surrogate marker is determined based on the first property, and the surrogate marker is provided using a second interface.

Abstract: The invention relates to a method for separating waste polyurethane foams, wherein for each polyurethane sample (1) of a supply stream (2) comprising polyurethane samples (1) from waste at least one respective spectrum (3) is recorded, wherein the at least one respective spectrum (3) is recorded by near-infrared spectroscopy, wherein each polyurethane sample (1) of the supply stream (2) is classified by a classification algorithm (5), which classification algorithm (5) is based on machine learning, based on the respective at least one spectrum (3) into a respective class (8a-e) of at least two classes (8a-e), wherein the supply stream (2) comprising polyurethane samples (1) is separated into at least two streams (11a-e) according to the classification into the respective class (8a-e) and wherein each class (8a-e) corresponds to a type of polyurethane. The invention also relates to a system for separating waste polyurethane foams.

Abstract: Systems and methods are provided for optimizing a deep learning model. A multi-site dataset associated with different clinical sites and a deployment dataset associated with a deployment clinical site are received. A deep learning model is trained based on the multi-site dataset. The trained deep learning model is optimized based on the deployment dataset. The optimized trained deep learning model is output.

Abstract: Systems and methods for performing an assessment of a lesion are provided. A plurality of input medical images of a lesion is received. The plurality of input medical images comprises an initial input medical image and one or more additional input medical images. The initial input medical image comprises a region of interest around the lesion. A mask of the lesion is curated for the initial input medical image based on the region of interest and a set of candidate masks. The region of interest in the initial input medical image is propagated to the one or more additional input medical images based on prior registration transformations. A mask of the lesion is curated for each of the one or more additional input medical images based on the propagated regions of interest and the set of candidate masks. One or more assessments of the lesion are performed based on the mask for the initial input medical image, the masks for the one or more additional input medical images, and prior assessments of lesions.

Abstract: In a computer-implemented method of training a machine learning based processor, the processor can be trained to derive image data from signal data sets of multiple spin echo sequences. The trained processor can be configured to perform image processing for Magnetic Resonance Imaging (MRI) to derive the image data.

Abstract: Systems and methods are provided for classifying an abnormality in a medical image. An input medical image depicting a lesion is received. The lesion is localized in the input medical image using a trained localization network to generate a localization map. The lesion is classified based on the input medical image and the localization map using a trained classification network. The classification of the lesion is output. The trained localization network and the trained classification network are jointly trained.

Abstract: Systems and methods are provided for classifying an abnormality in a medical image. An input medical image depicting a lesion is received. The lesion is localized in the input medical image using a trained localization network to generate a localization map. The lesion is classified based on the input medical image and the localization map using a trained classification network. The classification of the lesion is output. The trained localization network and the trained classification network are jointly trained.

Abstract: A brake system for a motor vehicle with at least four hydraulically activated wheel brakes, including for each of the wheel brakes an electrically activated first wheel valve which is designed to be open when de-energized and an electrically activated second wheel valve which is designed to be closed when de-energized, a first electrically activated pressure source, which is connected to the first wheel valves via a first brake supply line, a second electrically activated pressure source, and a pressure medium reservoir vessel which is, in particular, at atmospheric pressure, wherein the second electrically activated pressure source is connected to the second wheel valves via a second brake supply line, and a method for operating said brake system.

Abstract: For radial sampling in magnetic resonance imaging (MRI), a rescaling factor is determined from k-space data for each coil. The rescale factor is inversely proportional to the streak energy in the k-space data. The k-space data from the coils is rescaled for reconstruction, such as weighting the k-space data by the rescale factor in a data consistency term of iterative reconstruction. The rescale factor is additionally or alternatively used to determine a correction field for correction of intensity bias applied to intensities in the image-object space after reconstruction. These approaches may result in a diagnostically useful bias-corrected image with reduced streak artifact while benefiting from the efficient computation (i.e., computer operates to reconstruct more quickly).

Abstract: A brake system for a motor vehicle with at least four hydraulically activated wheel brakes. Each of the wheel brakes has a first electrically activated wheel valve which is open when de-energized and a second electrically activated wheel valve which is closed when de-energized, a first electrically activated pressure source, connected to the first wheel valves via a first brake supply line. Arranged in the first brake supply line is an electrically activated circuit isolating valve by which two of the first wheel valves can be hydraulically disconnected from the first pressure source, a second electrically activated pressure source, and a pressure medium reservoir vessel at atmospheric pressure. The circuit isolating valve is designed to be open when de-energized, and the second electrically activated pressure source is connected to the second wheel valves via a second brake supply line. A method for operating the brake system is also disclosed.

Abstract: Systems and methods are provided for classifying an abnormality in a medical image. An input medical image depicting a lesion is received. The lesion is localized in the input medical image using a trained localization network to generate a localization map. The lesion is classified based on the input medical image and the localization map using a trained classification network. The classification of the lesion is output. The trained localization network and the trained classification network are jointly trained.

Abstract: A brake system for a motor vehicle having hydraulically actuatable wheel brakes. Each wheel an electrically actuatable inlet valve and electrically actuatable outlet valve for setting wheel-specific brake pressures. A first electrically controllable pressure provision device is connected to a brake supply line to which the wheel brakes are connected. A second electrically controllable pressure provision device is connected to the brake supply line. A first electrical device activates the first pressure provision device. A second electrical device activates the second pressure provision device. Electrically independent first and second electrical partitions are provided. The first pressure provision device and the first electrical device are assigned to the first electrical partition and the second pressure provision device, the second electrical device and the inlet and outlet valves are assigned to the second electrical partition. The inlet and outlet valves are activated by the second electrical device.