Abstract: The present invention relates to multispectral imaging. In order to improve an identification of relevant multispectral material transitions (in particular caused by injected contrast agent), an apparatus is proposed to use the local maxima of the variances and/or covariances of the intensities of the multi-channel images to locate material transitions. In comparison to gradient vectors, the local variance is not directed and not prone to noise. An alternative apparatus is proposed to use the local covariance deficits of the intensities of the multi-channel images to locate material transitions. The proposed alternative approach is independent of spatial drifts across the image volume.

Abstract: The present invention relates to edge restoration. In order to improve a restoration of the artificially created cleansed edges, an apparatus is proposed to automatically restore image edges after digital subtraction of digital material substitution to optimally resemble image edges in unmodified locations. The appearance of edges is machine-learned in an unsupervised non-analytical way from unmodified locations, and then, after digital suppression or digital material substitution, applied to the artificially created cleansed edges.

Abstract: A computer system (MD) and relates method for spectral-data based material decomposition. The system comprises a statistical module (SM) configured to fit, per patch in input spectral imagery, a set of probability distributions (Pk) to a respective vector spectral diagram (5) for the respective patch (A). The patch is one of a plurality of patches in the input spectral imagery obtained by operation of a spectral imaging apparatus. The probability distributions are combinable into a probability map indicative of material type probabilities per image location in the input spectral imagery.

Abstract: A method for generating an image representation of slices through a body based on tomographic imaging data for the body. The method comprises processing reconstructed tomographic image slices to selectively embed in each slice image information from at least one 3D volume rendering of the slice plane within the 3D tomographic image dataset. This is done through a selection process wherein, based on a set of pre-defined criteria, a decision is made for each pixel in each reconstructed tomographic slice as to whether the pixel value should be replaced with a new, modified pixel value determined based on the at least one volume rendering. This may comprise simply swapping the pixel value for the value of the corresponding pixel value in the volume rendering, or it may comprise a more complex process, for instance blending the two values, or adjusting a transparency of the pixel value based on the at least one volume rendering.

Abstract: A training system (TS) for training a machine learning model for image quality enhancement in medical imagery. The system comprises an input interface (?IN) for receiving a training input image (?IN). The system (TS) comprises artificial neural network Got model framework (G,D) of the generative adversarial type including a generator network (G) and a discriminator (D) network. The generative network (G) processes the training input image to produce a training output image (?OUT). A down-scaler (DS) of the system downscales the training input image. The discriminator attempts to discriminate between the downscaled training input image (I?) and training output image to produce a discrimination result. A training controller (TC) adjusts parameters of the artificial neural network model framework based on the discrimination result.

Abstract: One embodiment of the present invention includes a computer-implemented method that includes receiving spectral computed tomography (CT) volumetric image data. The spectral CT volumetric image data include data for at least two different energies and/or energy ranges. The spectral CT volumetric image data is processed with a machine learning engine configured to map spectrally enhanced features extracted from the spectral CT volumetric image data onto fractional flow reserve (FFR) values to determine a FFR value. The FFR value is then visually presented.

Abstract: The invention refers to an apparatus for determining decomposed spectral image data with an improved accuracy. The apparatus (110) comprises a spectral image data providing unit (111) for providing spectral image data, a spectral image data decomposition unit (112) for calculating a basis decomposition for the spectral image data, a virtual non-contrast image generation unit for generating a virtual non-contrast image based on the decomposed spectral image data, and a contrast agent residual identification unit (113) for identifying a residual region comprising a contrast agent residual in the virtual non-contrast image based on an expected structural characteristic of the contrast agent residual, wherein the spectral image data decomposition unit (114) is configured to calculate a new basis decomposition in the residual region.

Abstract: A system (SYS) and related method for motion artifact reduction in X-ray imaging. The system (SYS) comprises an input interface (IN) for receiving a first input image (i1, I1) of an object (PAT) reconstructed from a first set of projection data, and a second input image (i2, I2) of the object reconstructed from a second set of projection data. The second set is smaller than the first set. A motion analyzer (MA) establishes an estimate for motion corruption based on the two input images. A selective combiner (?) computes an image value for an enhanced image (I1+I2, i1+i2), based on the motion estimate and on image information in the first input image (i1, I1) and/or the second input image (i2, I2).

Abstract: The invention refers to an apparatus (110) for generating an augmented image comprising a) a base image providing unit (111), wherein the base image is generated based on a combination of spectral image data, b) a contrast image providing unit (112), wherein the contrast image is generated based on a different combination of the spectral image data, c) a degree of saliency determination unit (113), wherein the degree of saliency is indicative of a difference between an image value of a voxel of the contrast image and an image value of a corresponding voxel of a predetermined template image, and d) an augmented image generation unit (114) for generating an augmented base image of the object by augmenting voxels of the base image based on the degree of saliency. The invention allows to provide the augmented base image with an improved image quality and information content.

Abstract: A system (100) includes a computer readable storage medium (122) with computer executable instructions (124), including: a biophysical simulator (126) configured to determine a fractional flow reserve value. The system further includes a processor (120) configured to execute the biophysical simulator (126), which employs machine learning to determine the fractional flow reserve value with spectral volumetric image data. The system further includes a display configured to display the determine fractional flow reserve value.

Abstract: A system (300) includes a memory (324) configured to store an inflammation map generator module (328). The system further includes a processor (322) configured to: receive at least one of spectral projection data or spectral volumetric image data, decompose the at least one of spectral projection data or spectral volumetric image data using a two-basis decomposition to generate a set of vectors for each basis represented in the at least one of spectral projection data or spectral volumetric image data, compute a concentration of each basis within a voxel from the set of vectors for each basis, and determine a concentration of at least one of fat or inflammation within the voxel from the concentration of each basis. The system further includes a display configured to display the determined concentration of the at least one of fat or inflammation.

Abstract: The present invention relates to an apparatus (10) for generating photon counting spectral image data, comprising: an input unit (20); a processing unit (30); and an output unit (40). The input unit is configured to receive non-photon counting X-ray spectral energy data. The processing unit is configured to implement a deep learning regression algorithm to generate photon counting X-ray spectral data, and the generation comprises utilization of the non-photon counting X-ray spectral energy data. The output unit is configured to output the photon counting X-ray spectral data.

Abstract: A system (100) includes a computer readable storage medium (122) with computer executable instructions (124), including: a biophysical simulator component (126) configured to determine a fractional flow reserve value via simulation and a traffic light engine (128) configured to track a user-interaction with the computing system at one or more points of the simulation to determine the fractional flow reserve value. A processor (120) is configured to execute the biophysical simulator component to determine the fractional flow reserve value and configured to execute the traffic light engine to track the user-interaction with respect to determining the fractional flow reserve value and provide a warning in response to determining there is a potential incorrect interaction. A display is configured to display the warning requesting verification to proceed with the simulation from the point, wherein the simulation is resumed only in response to the processor receiving the requested verification.

Abstract: An imaging system (102) includes a radiation source (112) configured to emit X-ray radiation, a detector array (114) configured to detect X-ray radiation and generate a signal indicative thereof, an a reconstructor (116) configured to reconstruct the signal and generate non-spectral image data. The imaging system further includes a processor (124) configured to process the non-spectral image data using a deep learning regression algorithm to estimate spectral data from a group consisting of spectral basis components and a spectral image.

Abstract: The present invention relates to X-ray image data analysis of a part of a cardiovascular system of a patient in order to estimate a level of inflammation in the part of the cardiovascular system. X-ray image data is received, a segmented model of the part of the cardiovascular system is generated and predetermined features related to inflammation are extracted from the segmented model. The extracted features are used as input to an inflammation function for calculating inflammation values of which each represents a level of inflammation in the part of the cardiovascular system. The image data analysis can improve the estimation of inflammation. Furthermore, the inflammation values can be presented to a user together with suggestions for performing actions. This can for example enable a prediction of plaque development as well as future acute coronary syndrome events.

Abstract: The present invention relates to image processing devices and related methods. The image processing device (10) comprises a data input (11) for receiving spectral computed tomography volumetric image data organized in voxels. The image data comprises a contrast-enhanced volumetric image of a cardiac region in a subject's body and a baseline volumetric image of that cardiac region, e.g. a virtual non-contrast image, wherein the contrast-enhanced volumetric image conveys anatomical information regarding coronary artery anatomy of the subject. The device comprises a flow simulator (12) for generating, or receiving as input, a three-dimensional coronary tree model based on the volumetric image data and for simulating a coronary flow based on the three-dimensional coronary tree model.

Abstract: The present invention relates to an image processing device (10) comprising a data input (11) for receiving volumetric image data comprising a plurality of registered volumetric images of an imaged object, a noise modeler (12) for generating a noise model indicative of a spatial distribution of noise in each of the plurality of registered volumetric images, a feature detector (13) for detecting a plurality of image features taking the volumetric image data into account, and a marker generator (14) for generating a plurality of references indicating feature positions of a subset of the plurality of detected image features, in which said subset corresponds to the detected image features that are classified as difficult to discern on a reference volumetric image in the plurality of registered volumetric images based on a classification and/or a visibility criterium, wherein the classification and/or the visibility criterium takes the or each noise model into account.

Abstract: A computer-implemented system for supporting an imaging operation and related methods. The system comprises one or more input interfaces (IN) for receiving input data including an input image procured by an imaging apparatus (IA) of a target location (ROI) in a conduit (VS) of an object (OB). The conduit includes a target substance (CA) and the target substance (CA) is propagatabale in the conduit towards the target location. A pretrained-machine learning component (MLC2) is configured to process the input data to obtain output data indicative of an arrival of the said target substance at said target location. An output interface (OUT) outputs said output data.

Abstract: A computing system (126) includes a computer readable storage medium (130) with computer executable instructions (128), including: a segmentation standardizer (120) configured to determine a standardized vascular tree from a segmented vascular tree segmented of volumetric image data and a predetermined set of pruning rules (206), and a biophysical simulator (122) configured to perform a biophysical simulation based on the standardized vascular tree. The computing system further includes a processor (124) configured to execute the segmentation standardizer to determine the standardized vascular tree from the segmented vascular tree segmented of volumetric image data and the predetermined set of pruning rules, and configured to execute the biophysical simulator to perform a biophysical simulation based on the standardized vascular tree. The computing system further includes a display configured to display at least one of the standardized vascular tree and a result of the biophysical simulation.

Abstract: The present invention relates to an apparatus (26) and a method for determining a fractional flow reserve. For this purpose, a new personalized hyperemic boundary condition model is provided. The personalized hyperemic boundary condition model is used to condition a parametric model for a simulation of a blood flow in a coronary tree (34) of a human subject. As a basis for the personalized hyperemic boundary condition model, a predefined hyperemic boundary condition model is used, which represents empirical derived hyperemic boundary condition parameters. However, these empirical hyperemic boundary condition parameters are not specific for a human subject under examination. In order to achieve a specification of the respective predefined hyperemic boundary condition model, specific human subject features are derived from a volumetric image of the coronary tree of the human subject.