Abstract: There is provided a method and corresponding system for image reconstruction based on energy-resolved x-ray data. The method comprises collecting (S1) at least one representation of energy-resolved x-ray data, and performing (S2) at least two basis material decompositions based on said at least one representation of energy-resolved x-ray data to generate at least two original basis image representation sets. The method further comprises obtaining or selecting (S3) at least two basis image representations from at least two of said original basis image representation sets, and processing (S4) said obtained or selected basis image representations by data processing based on machine learning to generate at least one representation of output image data.

Abstract: A system and method for projection based spectral X-ray imaging, such as computed tomography (CT) imaging, the system and method comprising performing projection based material decomposition based on spectral X-ray data to generate a set of material basis sinograms, and performing a weighted combination of at least part of at least two material basis sinograms of the set of material basis sinograms into a reconstructed image based on material weighting in the projection domain.

Abstract: A multi-row rolling bearing includes an inner ring having a first raceway on a first side of the bearing and a second raceway on a second side of the bearing, an outer ring having a raceway, and a first set of rolling elements between the first raceway and the raceway of the outer ring and a second set of rolling elements between the second raceway and raceway of the outer ring. The first set of rolling elements comprises a first number of rolling elements, the second set of rolling elements comprises a second number of rolling elements, and the first number of rolling elements is different from the second number of rolling elements.

Abstract: Various systems and methods are provided for denoising spectral CT image data, the system and method comprising determining a denoised linear estimation of spectral CT image data by maximizing or minimizing a first objective function, wherein at least one parameter of the denoised linear estimation is determined by at least one machine learning system. The denoiser is based on a Linear Minimum Mean Square Error (LMMSE) estimator. The LMMSE is very fast to compute, but not commonly used for CT image denoising, due to its inability to adapt the amount of denoising to different parts of the image and the difficulty to derive accurate statistical properties from the CT image data. To overcome these problems, a model-based deep learning model, such as a deep neural network that preserves a model based LMMSE structure.

Abstract: A method for estimating an accuracy of a simulation model of a machine having a rolling-element bearing includes determining sets of machine operating measurements and sets of bearing operating measurements at certain reference moments, determining values of a bearing indicator from the sets of bearing operating measurements and determining values of the bearing indicator from the simulation model of the machine, comparing the values of the measured bearing indicator and the simulated bearing indicator for identical values of the operating parameter of the machine, and estimating an accuracy of the simulation model of the machine from the comparison. Also a device for performing the method.

Abstract: A system and method for projection based spectral X-ray imaging, such as computed tomography (CT) imaging, the system and method comprising performing projection based material decomposition based on spectral X-ray data to generate a set of material basis sinograms, and performing a weighted combination of at least part of at least two material basis sinograms of the set of material basis sinograms into a reconstructed image based on material weighting in the projection domain.

Abstract: There is provided a method and system for determining one or more confidence indications for machine learning image reconstruction in Computed Tomography, CT. The method comprises acquiring (S1) energy-resolved x-ray data, and processing (S2) the energy-resolved x-ray data based on at least one machine learning system to generate a representation of a posterior probability distribution of at least one reconstructed basis image or image feature thereof. The method further comprises generating (S3) one or more confidence indications for: the at least one reconstructed basis image, or at least one derivative image originating from the at least one reconstructed basis image, or image feature of the at least one reconstructed basis image or the at least one derivative image, based on the representation of a posterior probability distribution.

Abstract: Systems and methods are provided for processing images. The system comprises at least one image recorder (20) adapted to: record a series of images, generate a set of image data for each image in the series of the recorded images; a first control unit configured to: modify each set of image data and generate a first type of image frame (25) by providing each set of image data with an identity of said image recorder (20) and a timestamp, and transmit each first type of image frame (25); at least one second control unit (10; 40) configured to: receive said first type of image frame (25), process each first type of image frame (25) and generate a second type of image frame (25?) by modifying each type of image frame (25), and transmit to a user and/or store each second type of image frames (25?).

Abstract: There is provided a method and corresponding system for image reconstruction based on energy-resolved x-ray data. The method comprises collecting (S1) at least one representation of energy-resolved x-ray data, and performing (S2) at least two basis material decompositions based on said at least one representation of energy-resolved x-ray data to generate at least two original basis image representation sets. The method further comprises obtaining or selecting (S3) at least two basis image representations from at least two of said original basis image representation sets, and processing (S4) said obtained or selected basis image representations by data processing based on machine learning to generate at least one representation of output image data.

Abstract: Systems and methods are provided for processing images. The system comprises at least one image recorder (20) adapted to: record a series of images, generate a set of image data for each image in the series of the recorded images; a first control unit configured to: modify each set of image data and generate a first type of image frame (25) by providing each set of image data with an identity of said image recorder (20) and a timestamp, and transmit each first type of image frame (25); at least one second control unit (10; 40) configured to: receive said first type of image frame (25), process each first type of image frame (25) and generate a second type of image frame (25?) by modifying each type of image frame (25), and transmit to a user and/or store each second type of image frames (25).

Abstract: There is provided an x-ray detector system including a photon-counting x-ray detector for detecting x-ray radiation from an x-ray source, and a coincidence detection system configured to determine and/or obtain information about the radiation incident on the x-ray detector based on information about the time of photon interactions in the x-ray detector and information about the location of the x-ray source in relation to the x-ray detector. There is also provide an x-ray imaging system including such an x-ray detector system, as well as a corresponding coincidence detection system and a corresponding method.

Abstract: A check valve (10) for controlling a flow of fluid by fluid pressure, comprising a housing (11) and a resilient flexible valve element (12) inside the housing (11), wherein the valve element (12) is formed as a hollow and longitudinally tapered body (16) with an open wide end (18) and a closed narrow end (19), and wherein the wide end (18) of the valve element (12), in a default configuration, engages an inner surface of the housing (11) to close the check valve (10) and is deformable by a predetermined fluid pressure from the inlet (13) to open the check valve (10). The tapered body (16) comprises a radially outwardly projecting flange (17) at the wide end (18), which flange comprises a curved outer surface portion (20) having a degree of curvature of 85 to 95 degrees, wherein the housing (11) is formed with a protrusion (29) having a curved surface (30) for engaging the curved outer surface portion (20) of the flange (17).

Abstract: There is provided an x-ray detector system including a photon-counting x-ray detector for detecting x-ray radiation from an x-ray source, and a coincidence detection system configured to determine and/or obtain information about the radiation incident on the x-ray detector based on information about the time of photon interactions in the x-ray detector and information about the location of the x-ray source in relation to the x-ray detector. There is also provide an x-ray imaging system including such an x-ray detector system, as well as a corresponding coincidence detection system and a corresponding method.

Abstract: There is provided a photon-counting x-ray detector system (200) comprising a plurality of photon-counting channels (220), and at least one anti-coincidence circuit (230), each of which is connected to least two of the channels and configured to detect coincident events in the connected channels. The x-ray detector system (200) further comprises an anti-coincidence controller (240) configured to control the operation of said at least one anti-coincidence circuit based on photon count information by gradually adapting the operation of said at least one anti-coincidence circuit with increasing count rates, starting from a threshold count rate.

Abstract: A check valve (10) for controlling a flow of fluid by fluid pressure, comprising a housing (11) and a resilient flexible valve element (12) inside the housing (11), wherein the valve element (12) is formed as a hollow and longitudinally tapered body (16) with an open wide end (18) and a closed narrow end (19), and wherein the wide end (18) of the valve element (12), in a default configuration, engages an inner surface of the housing (11) to close the check valve (10) and is deformable by a predetermined fluid pressure from the inlet (13) to open the check valve (10). The tapered body (16) comprises a radially outwardly projecting flange (17) at the wide end (18), which flange comprises a curved outer surface portion (20) having a degree of curvature of 85 to 95 degrees, wherein the housing (11) is formed with a protrusion (29) having a curved surface (30) for engaging the curved outer surface portion (20) of the flange (17).

Abstract: A method is implemented by a transparent proxy to support graceful switchover in a network, where the transparent proxy proxies one or more Transmission Control Protocol (TCP) connections involving a destination Internet Protocol (IP) address. The method includes starting a switchover timer for the destination IP address in response to receiving an instruction from an Application Flow Controller (AFC) to start the switchover timer for the destination IP address and transmitting an indication to the AFC that all of the one or more TCP connections involving the destination IP address that are proxied by the transparent proxy have ended or the switchover timer for the destination IP address has expired in response to a determination that all of the one or more TCP connections involving the destination IP address that are proxied by the transparent proxy have ended or the switchover timer for the destination IP address has expired.

Abstract: A method for reconstructing image data from x-ray data measured with an imaging system having at least one photon-counting detector includes obtaining a representation of data measured by the photon-counting detector. The method also includes generating first image data based on a projection based first functional using a first algorithm, the projection based first functional being dependent on the representation of data. The method also includes updating, based on a second functional that includes a model of at least one physical effect not included in the projection based first functional, the first image data to obtain second image data. The invention also provides an image processing device configured to reconstruct image data from x-ray data measured with an imaging system including at least one photon-counting detector as well as a corresponding computer program product.

Abstract: A method is implemented by a transparent proxy to support graceful switchover in a network, where the transparent proxy proxies one or more Transmission Control Protocol (TCP) connections involving a destination Internet Protocol (IP) address. The method includes starting a switchover timer for the destination IP address in response to receiving an instruction from an Application Flow Controller (AFC) to start the switchover timer for the destination IP address and transmitting an indication to the AFC that all of the one or more TCP connections involving the destination IP address that are proxied by the transparent proxy have ended or the switchover timer for the destination IP address has expired in response to a determination that all of the one or more TCP connections involving the destination IP address that are proxied by the transparent proxy have ended or the switchover timer for the destination IP address has expired.

Abstract: Disclosed is a photon-counting x-ray detector system having a plurality of photon-counting channels, and at least one anti-coincidence circuit, each of which is connected to least two of the channels and configured to detect coincident events in the connected channels. The x-ray detector system further includes an anti-coincidence controller configured to control the operation of the at least one anti-coincidence circuit based on photon count information by gradually adapting the operation of the at least one anti-coincidence circuit with increasing count rates, starting from a threshold count rate.

Abstract: There is provided a photon-counting x-ray detector system (200) comprising a plurality of photon-counting channels (220), and at least one anti-coincidence circuit (230), each of which is connected to least two of the channels and configured to detect coincident events in the connected channels. The x-ray detector system (200) further comprises an anti-coincidence controller (240) configured to control the operation of said at least one anti-coincidence circuit based on photon count information by gradually adapting the operation of said at least one anti-coincidence circuit with increasing count rates, starting from a threshold count rate.