Abstract: A method is for classifying an examination object by way of recordings. In an embodiment, the method includes capturing at least one optical recording of the examination object; determining and quantifying a number of defined characteristics of the examination object based upon an analysis of the optical recordings with the aid of a machine learning method; and affecting the classification of the examination object in respect of a classification criterion, based upon the quantified characteristics with the aid of a machine learning method. Also described are a classification entity and a medical imaging modality.

Abstract: To generate images, in which a first row area of a multiple-row detector is illuminated with a first X-ray spectrum and a second row area of the multiple-row detector, trailing in the direction of travel, is illuminated with a second X-ray spectrum, image data is recorded at a pitch chosen such that one slice image can be reconstructed in each case for a sectional position for the first and the second row area. Correspondingly, for the sectional position, the respective slice image for the first and the second row area is reconstructed. For a third row area, illuminated with the first and the second X-ray spectrum, a reference sectional image is reconstructed as a slice image. To generate motion-reduced first and second spectral images assigned to the first and second row area respectively, the slice images of the first and second row areas are registered to the reference sectional image.

Abstract: A method is for metal artifact reduction in CT image data, the CT image data including multiple 2D projection images acquired using different projection geometries and suitable to reconstruct a 3D image data set of a volume of an imaged object. In an embodiment, the method includes a metal artifact reduction process including at least, acquiring, using a multi-energy CT technique, energy-resolved CT image data associated with multiple energy ranges. At least one result of the multi-energy technique is used in at least one aspect of the metal artifact reduction process.

Abstract: A medical scanner generates a medical image that may have an artifact. A machine-learnt detector, trained from a library of many different types of artifacts in images, detects any artifact in the medical image for a patient. The location of the artifact is highlighted, providing an indication of possible artifact where the image may otherwise appear to represent anatomy or pathology. A machine-learnt network may be applied to the medical image to determine a correction, such as different scan or reconstruction, to remove or reduce the artifact.

Abstract: A system includes acquisition of a spectral topogram of a target, determination, based on the spectral topogram, of an attenuation associated with each of a plurality of regions of the target and a composition of each of the plurality of regions, determination of imaging parameters associated with the plurality of regions based on the determined attenuation and composition, and acquisition of an image of the target based on the imaging parameters.

Abstract: Provided are embodiments including methods, systems, and computer-program products for mitigating power supply noise using one or more current supplies. In some embodiments, power is provided to an integrated circuit, wherein a first circuit is coupled to the integrated circuit over a first path. A variation of the current level of the integrated circuit may be determined. Additional power from a second circuit is provided to the integrated circuit may be provided based at least in part on the determined variation, wherein the second circuit is coupled to the integrated circuit over a second path.

Abstract: A method is for determining at least one first characteristic value of blood in a patient. In an embodiment, the method includes acquiring, via a computed tomography device, computed tomography data of the patient for at least two energy levels of radiation using multi-energy computed tomography; defining a region of interest including blood, in at least one image data set reconstructed from the computed tomography data acquired; determining, at least in the region of interest defined, attenuation coefficients for each energy level of the at least two energy levels; performing material decomposition into at least two materials, one material of the two materials being iron, using the attenuation coefficients determined, yielding at least a fraction of iron in the region of interest defined; and determining the at least one first characteristic value, at least one of as and from the fraction of iron yielded.

Abstract: An analysis method is for automatically determining radiological result data from radiology data sets. In an embodiment, the method includes provisioning a first radiology data set at least based on X-ray data of a first X-ray energy spectrum; provisioning at least one second radiology data set at least based on X-ray data of a second X-ray energy spectrum; provisioning an analysis unit including a neural network, to analyze radiology data sets including an input layer with a plurality of cells, a number of intermediate layers and an output layer representing a radiological result; analyzing the first radiology data set and the at least one second radiology data set, at least subsets of the first radiology data set and the at least one second radiology data set being assigned to different cells of the input layer for joint processing in the neural network; and acquiring result data on the output layer.

Abstract: To generate images, in which a first row area of a multiple-row detector is illuminated with a first X-ray spectrum and a second row area of the multiple-row detector, trailing in the direction of travel, is illuminated with a second X-ray spectrum, image data is recorded at a pitch chosen such that one slice image can be reconstructed in each case for a sectional position for the first and the second row area. Correspondingly, for the sectional position, the respective slice image for the first and the second row area is reconstructed. For a third row area, illuminated with the first and the second X-ray spectrum, a reference sectional image is reconstructed as a slice image. To generate motion-reduced first and second spectral images assigned to the first and second row area respectively, the slice images of the first and second row areas are registered to the reference sectional image.

Abstract: An X-ray imaging method is for generating contrast-enhanced image data relating to an examination region of an object to be examined. In an embodiment of the method, first contrast-agent influenced measured X-ray projection data with a first X-ray energy spectrum and at least one set of second contrast-agent influenced measured X-ray projection data with a second X-ray energy spectrum are acquired from the examination region. Subsequently, image data assigned to a third X-ray energy spectrum with a third mean energy, based on the first and at least second measured X-ray projection data is reconstructed based on the first and at least second measured X-ray projection data that has been acquired. A mean energy of the first X-ray energy spectrum and a mean energy of the second X-ray energy spectrum are selected as a function of a dimension parameter value of the object that is to be examined.

Abstract: In a method and computer for determining an imaging parameter for an imaging procedure, a patient-specific imaging value for imaging an image data set is provided to a computer. An imaging parameter is determined in the computer by applying a trained imaging rule to the patient-specific imaging value. The trained imaging rule is based on a number of training data sets, wherein the training data sets each includes at least one patient-specific training imaging value and at least one training imaging parameter and at least one training quality evaluation. The complex influences of the patient-specific imaging values and the imaging parameters on the result of imaging can be quantified thereby. Allocation of the training quality evaluation by individual operators or specific groups of operators makes it possible to adjust the image recording parameters flexibly and individually. The imaging parameter can be determined such that the result of imaging is individually adjusted to an operator.

Abstract: A positioning unit includes a projector and a control unit and enables a particularly quick and precise positioning of a patient. In an embodiment, the control unit affects a control of the projector as a function of a protocol for a recording of an image of the patient such that the positioning unit is designed for the planar projection of a figure as a positioning aid on the patient couch. An immediately apparent area on the patient couch is then specified by the figure projected in a planar fashion, relative to which the patient can be positioned. The control unit can be used both to temporally control the projection process and also to control the figurative properties of the positioning aid. Furthermore, the control unit can include a device for calculating a control signal so that the control unit brings about control of the projector with the control signal.

Abstract: A system includes acquisition of a spectral topogram of a target, determination, based on the spectral topogram, of an attenuation associated with each of a plurality of regions of the target and a composition of each of the plurality of regions, determination of imaging parameters associated with the plurality of regions based on the determined attenuation and composition, and acquisition of an image of the target based on the imaging parameters.

Abstract: A method and system are for analyzing an anatomical structure of interest in 3D image data. In an embodiment, the method includes segmenting a first contour of the structure of interest in the 3D image data, the first contour defining a first segmented contour volume within the 3D image data; generating a first 2D pattern based on at least a portion of the surface of the first contour or based on at least a portion of the first segmented contour volume; performing a texture analysis on the first 2D pattern; and outputting a texture analysis information.

Abstract: A method is for controlling an x-ray imaging device, in particular a computed tomography device. The x-ray imaging device includes an x-ray source and a photon counting detector as an x-ray detector. The methods includes, for an image acquisition process of a patient: determining at least one input parameter relating to at least one of an attenuation property of the patient and a purpose of the image acquisition; at least one of determining or adapting at least one operation parameter of the x-ray detector, dependent upon the at least one input parameter determined; and performing the image acquisition using the at least one operation parameter determined or adapted.

Abstract: A medical scanner generates a medical image that may have an artifact. A machine-learnt detector, trained from a library of many different types of artifacts in images, detects any artifact in the medical image for a patient. The location of the artifact is highlighted, providing an indication of possible artifact where the image may otherwise appear to represent anatomy or pathology. A machine-learnt network may be applied to the medical image to determine a correction, such as different scan or reconstruction, to remove or reduce the artifact.

Abstract: A multi-spectral CT imaging method, preferably a CT imaging method, is described. Spectrally resolved projection scan data is acquired from a region to be imaged of an examination object. The data is assigned to a plurality of pre-determined different partial spectra. Spectrally resolved image data is reconstructed with a plurality of attenuation values for each image point of the region to be imaged. The attenuation values are each assigned to one of the pre-determined different partial spectra. Furthermore, an extremal attenuation value is determined for each image point on the basis of the plurality of attenuation values. A representative image data set is determined such that the determined extremal attenuation value is assigned to each image point.

Abstract: A method is for training a convolutional neural network of a compensation unit. The method includes: provisioning a machine learning device, the machine learning device being designed for training the convolutional neural network; provisioning a start compensation unit, including an untrained convolutional neural network, on or at the machine learning device; provisioning a training image dataset including a plurality of medical training input images and at least one training output image, wherein a reference object is shown essentially without motion artifacts in the at least one training output image and the reference object concerned is contained in the plurality of medical training input images with different motion artifacts; and training the convolutional neural network of the compensation unit in accordance with a principle of machine learning, using the training image dataset. A compensation unit, a machine learning device, a control device for controlling a medical imaging system are also disclosed.

Abstract: A method is for producing an identification unit for identifying image artifacts automatically. In an embodiment, the method includes providing a learning processing apparatus; providing an initial identification unit; providing a first image data library including artifact reference acquisitions containing image artifacts; and training the identification unit using the image artifacts. An identification method is for identifying image artifacts automatically in an image acquisition. In an embodiment, the identification method includes: providing a trained identification unit; providing an image acquisition produced via a medical imaging system; inspecting the image acquisition for image artifacts by the identification unit; and labeling the ascertained image artifacts.

Abstract: A method is for creating a classification unit for the automatic classification of materials. An embodiment of the method includes provision of a learning computing device; provision of a start classification unit; provision of a reference image set including spectral reference recordings with annotated materials; and training of the classification unit with the reference recording set. Furthermore, a classification method is for the automatic classification of materials in an image recording. An embodiment of the classification method includes provision of a trained classification unit; provision of a spectral image recording; examination of the image recording for materials via the classification unit; and identification of the determined materials. Furthermore, a classification unit, a learning computing device, a control device and a medical imaging system are disclosed.