Abstract: The present invention relates to an apparatus (10) for correcting computer tomography (“CT”) X-ray data acquired at high relative pitch, the apparatus comprising: an input unit (20); a processing unit (30); and an output unit (40). The input unit is configured to provide the processing unit with CT X-ray data of a body part of a person acquired at high relative pitch. The processing unit is configured to determine CT slice reconstruction data of the body part of the person with no or reduced high relative pitch operation reconstruction artefacts using a machine learning algorithm. The machine learning algorithm was trained on the basis of CT slice reconstruction data, and wherein the CT slice reconstruction data comprised first CT slice reconstruction data with high relative pitch reconstruction artefacts and comprised second CT slice reconstruction data with less, less severe, or no high relative pitch reconstruction artefacts.

Abstract: A mechanism for generating denoised basis images for a computed tomography scanner. An input dataset, comprising first and second basis image data, is processed using a machine-learning algorithm process to produce the denoised basis images. The first and second basis image data each comprise at least one basis image, wherein the type of image differs between the first and second basis image data.

Abstract: A method is provided for processing images comprising retrieving measured data for a first image. The method then generates partially filtered data by applying a first filter to the measured data. The first filter is a generic filter. The method then reconstructs the partially filtered data to generate a partially filtered image. The method then generates a partially processed image by applying a first processing routine to the partially filtered image. The method then generates a filtered image by applying a second filter to the partially processed image, where the second filter is a filter selected from a plurality of potential secondary filters. The method then outputs the filtered image. Systems are provided for implementing the claimed method and training methods for neural networks used in the method are provided as well.

Abstract: A mechanism for generating denoised basis projection data. Low-energy projection data and high-energy projection data is processed using a neural network that is trained to perform the dual task of decomposition and denoising. The neural network thereby directly outputs basis projection data, taking the place of existing decomposition and denoising techniques.

Abstract: The present invention relates to a spectral X-ray CT imaging system (10), comprising: a spectral X-ray CT imaging unit (20); a processing unit (30); and an output unit (40). The spectral X-ray CT imaging unit comprises an X-ray tube (22) and a dual layer X-ray detector (24), and wherein a body portion of a subject to be examiner can be located between the X-ray tube and the dual layer X-ray detector. The spectral X-ray CT imaging unit is configured to acquire an overall scan of the body portion comprising a plurality of acquisitions at different projections angles. The processing unit is configured to utilize information on the body portion for each projection of the different projections angles. The processing unit is configured to determine a voltage for the X-ray tube for each acquisition of the plurality of acquisitions, wherein the determination for each acquisition comprises utilization of the corresponding information on the body portion for the projection associated with that acquisition.

Abstract: A mechanism for processing projection data generated by a computed tomography scanner. The projection data is processed by a machine-learning algorithm trained to perform an up-sampling or super-resolution technique on input data in order to generate higher resolution projection data.

Abstract: All X-ray computerized tomography systems that are available or proposed base their reconstructions on measurements that integrate over energy. X-ray tubes produce a broad spectrum of photon energies and a great deal of information can be derived by measuring changes in the transmitted spectrum. We show that for any material, complete energy spectral information may be summarized by a few constants which are independent of energy. A technique is presented which uses simple, low-resolution, energy spectrum measurements and conventional computerized tomography techniques to calculate these constants at every point within a cross-section of an object. For comparable accuracy, patient dose is shown to be approximately the same as that produced by conventional systems. Possible uses of energy spectral information for diagnosis are presented.

Abstract: Technology provides baseline images for diagnostic applications, including receiving a diagnostic image relating to a condition of a patient, the diagnostic image reflecting one of a normal state or an abnormal state of the condition, and generating a baseline image via a neural network using the diagnostic image, where the neural network is trained to generate a prediction of the diagnostic image reflecting a normal state of the condition. The neural network can include a generative adversarial network (GAN) trained only on image data with a normal state of the condition, where generating the baseline image includes an optimization process to maximize a similarity between the diagnostic image and a response of the GAN. Generating the baseline image can include selecting a portion of the diagnostic image, and adjusting a relevance weighting to be applied to the selected portion of the diagnostic image in the optimization process.

Abstract: A method is provided for analyzing the vasculature of a subject. A vessel tree is identified in an image of a region of interest. The major vessels, forming part of a standardized tree of the major vessels, are identified, and in turn the remaining vessels of the identified vessel tree are identified, thus excluding the major vessels of the standardized tree. This isolates the collateral vessels in the region of interest, and an analysis of the collateral vessels can then be performed.

Abstract: A method and apparatus for analyzing diagnostic image data are provided in which a plurality of acquisition images of a vessel of interest having been acquired with a pre-defined acquisition method is received at a trained classifying device and classified, by the classifying device, to extract at least one quantitative feature of the vessel of interest from at least one acquisition image of the plurality of acquisition images. The at least one quantitative feature is then output associated with the at least one acquisition image while the acquisition of the diagnostic image data is still in progress and one or more adjustable image acquisition settings are adjusted based on the at least one quantitative feature to optimize the acquisition of the diagnostic image data.

Abstract: The present invention relates to the use of dark field X-ray images in an ablation treatment of a tumour. By acquiring dark field X-ray images displaying the region of interest targeted in the ablation treatment, information can be derived which allows taking a decision on terminating the ablation treatment. A set of dark field X-ray images is received (101), which is acquired at different time instants and comprises the region of interest. Dark field X-ray images of the set are compared (102), for example by determining difference images between the individual images. If during that comparison a change in the dark field X-ray images is detected over time in the region of interest, then a signal is generated (103) indicating a change has occurred. That signal may indicate that healthy tissue is being affected instead of the tumour and that consequently the ablation treatment should be ended.

Abstract: An apparatus for determining a functional index for stenosis assessment of a vessel is provided. The apparatus comprises an input interface (40) and a processing unit (50). The input interface is configured to obtain image data (30) representing a two-dimensional representation of a vessel (6). The processing unit (50) is configured to determine a course of the vessel (6) and a width (w1, w2) of the vessel along its course in the image data and is further configured to determine the functional index for stenosis assessment of the vessel based on the width of the vessel in the image data.

Abstract: An apparatus for assessing a vessel of interest and a corresponding method are provided in which the modeling of the hemodynamic parameters using a fluid dynamics model can be verified by deriving feature values from the segmented vessel of interest and inputting these feature values into a classifier. The classifier may then determine, based on the feature values whether the segmentation has been performed from proximal to distal, from distal to proximal or cannot be determined from the provided data. An incorrect segmentation order can thus be identified and potentially be corrected, thereby avoiding inaccurate simulation results.

Abstract: Multi-task deep learning method for a neural network for automatic pathology detection, comprising the steps: receiving first image data (I) for a first image recognition task; receiving (S2) second image data (V) for a second image recognition task; wherein the first image data (I) is of a first datatype and the second image data (V) is of a second datatype, different from the first datatype; determining (S3) first labeled image data (IL) by labeling the first image data (I) and determining second synthesized labeled image data (ISL) by synthesizing and labeling the second image data (V); training (S4) the neural network based on the received first image data (I), the received second image data (V), the determined first labeled image data (IL) and the determined second labeled synthesized image data (ISL); wherein the first image recognition task and the second image recognition task relate to a same anatomic region where the respective image data is taken from and/or relate to a same pathology to be recogni

Abstract: An approach for denoising a medical image. A noise map, which defines an estimate of one or more statistical parameters for each pixel of the medical image, is used to modify or normalize the medical image. The modified medical image is then processed, using a machine-learning method, to produce a denoised medical image.

Abstract: A method and apparatus for selecting one or more diagnostic images to generate a physiological model are provided in which a set of candidate images is determined for review by a user, in particular by a physician. The candidate images are hereby determined using one or more target measures, such as a density measure, a motion measure, a deviation measure or the like, that have been derived for each diagnostic image of an X-ray angiography series and by analyzing said target measure. Subsequently, a suitability score that is based on the requirements of the physiological model that shall be generated from the selected candidate images is assigned to each candidate image.

Abstract: An image processing system (IPS), comprising an input interface (IN) for receiving a projection image from a plurality of projection images of a movable object (PAT) acquired along different directions by an imaging apparatus (XA), the projection images defined in a projection domain spanned by a radiation sensitive surface of the detector (D). The system includes a motion checker (MC) configured to operate in the projection domain to decide whether the projection image is corrupted by motion of the object during acquisition.

Abstract: The invention discloses a method for preparation of spray dried solid dispersions (SDD) comprising an active pharmaceutical ingredient (API) and a dispersion polymer (DISPPOL), wherein the spray drying is done with a supersaturated solution of API in a solvent mixture comprising two solvents, this supersaturated solution further comprising DISPPOL.

Abstract: The invention relates to a marker device and a tracking system for tracking the marker device, wherein the marker device comprises a rotationally oscillatable magnetic object and wherein the rotational oscillation is excitable by an external magnetic field, i.e. a magnetic field which is generated by a magnetic field providing unit 20, 31 that is located outside of the marker device. The rotational oscillation of the magnetic object induces a current in coils, wherein based on these induced currents the position and optionally also the orientation of the marker device is determined. This wireless kind of tracking can be carried out with relatively small marker devices, which can be placed, for instance, in a guidewire, the marker devices can be read out over a relatively large distance and it is possible to use a single marker device for six degrees of freedom localization.

Abstract: The invention discloses a method for preparation of spray dried solid dispersions, SDD, comprising an active agent, AA, such as an active pharmaceutical ingredient, API, and a dispersion polymer, DISPPOL, wherein the spray drying is done with a solution of AA and of DISPPOL in a solvent comprising C1-3 alkanol and formic acid, and optionally water.