Abstract: A framework for medical data analysis, comprising a tool generation unit configured for automatically generating a first number of data analysis tools based on first medical image data and first analysis data related to the first medical image data.

Abstract: A framework for identifying a type of organ in a volumetric medical image. The framework may include receiving a volumetric medical image, the volumetric medical image comprising at least one organ or portion thereof, and further receiving a single point of interest within the volumetric medical image. Voxels are sampled from the volumetric medical image, wherein at least one voxel is skipped between two sampled voxels. The type of organ is identified at the single point of interest by applying a trained classifier to the sampled voxels.

Abstract: A system and a method are respectively for positioning an examination object and evaluation of an image with respect to a positioning of a breast of an examination object in relation to an x-ray device. In an embodiment, the system includes an x-ray device including at least one compression device to fix a breast of the examination object; at least one camera, arranged in relation to the x-ray device such that images are acquirable via the at least one camera, the images showing a current positioning of the breast of the examination object in relation to the x-ray device; and at least one display device, embodied to display the images.

Abstract: A framework for personalized recommendation. An image content profile for a current case is generated. One or more auxiliary information representations associated with the current case are further generated. Affinity scores for radiology service providers are then determined by applying service profiles of the radiology service providers, the image content profile and the one or more auxiliary information representations to a trained recommendation engine. The current case is then assigned to one of the radiology service providers based on the affinity scores.

Abstract: One or more example embodiments of the present invention relates to a computer-implemented method for providing an outline of a lesion in digital breast tomosynthesis includes receiving input data, wherein the input data comprises a reconstructed tomosynthesis volume dataset based on projection recordings, a virtual target marker within a lesion being in the tomosynthesis volume dataset; applying a trained function to at least a part of the tomosynthesis volume dataset to establish an outline enclosing the lesion, the part of the tomosynthesis volume dataset corresponding to a region surrounding the virtual target marker in the tomosynthesis volume dataset; and providing output data, wherein the output data is an outline of a two-dimensional area or a three-dimensional volume surrounding the target marker.

Abstract: A computer implemented method and apparatus for determining a location at which a given feature is represented in medical imaging data is disclosed. A first descriptor for a first location in first medical imaging data is obtained. The first location is the location within the first medical imaging data at which the given feature is represented. A second descriptor for each of a plurality of candidate second locations in second medical imaging data is obtained. A similarity metric indicating a degree of similarity with the first descriptor is calculated for each of the plurality of candidate second locations. A candidate second location is selected from among the plurality of candidate second locations based on the calculated similarity metrics. The location at which the given feature is represented in the second medical imaging data is determined based on the selected candidate second location.

Abstract: A computer-implemented method is for clinical decision support. In an embodiment, the method includes receiving patient data of a target patient; determining, based on the patient data, a number of potential clinical outcomes associated with the target patient; calculating, for each respective potential clinical outcome, a respective probability of being indicated by the patient data; selecting, based on the plurality of probabilities calculated, one or more anamnestic questions from a set of anamnestic questions stored; presenting the one or more anamnestic questions selected to a user via a user interface; receiving one or more answers to the one or more anamnestic questions selected, from the user; and adapting the plurality of probabilities based upon the one or more answers received.

Abstract: Method and apparatus for image retrieval. An image descriptor of a query image indicating a medical abnormality and non-image patient data may be received. For each of a plurality of candidate images stored in a database, an image descriptor of the candidate image and data about a medical abnormality known to be indicated by the candidate image may further be received. A similarity metric between the image descriptors of the query image and the candidate image may be determined for each candidate image. A first probability of the query image medical abnormality being the candidate image medical abnormality given the non-image patient data associated with the query image may be determined for each candidate image. A score may then be determined for each candidate image based on the determined similarity metric and the determined first probability. One or more of the candidate images may be retrieved from the database in accordance with the determined scores.

Abstract: A computer-implemented method is for classifying a region of interest in a medical image data set depicting a body part of a patient. The region of interest contains an object of potential pathological relevance. In an embodiment, the method includes a plurality of steps. One step is directed to generate a plurality of different representations of the region of interest. Another step is directed to determine, for each of the representations, a classification to generate a corresponding plurality of classifications. Thereby, each classification indicates a pathological relevance of the object in the respective representation. Yet, a further step is directed to calculate an ensemble classification for the region of interest based on the plurality of classifications.

Abstract: A method for visualizing a region of interest inside an examination object into which an examination instrument has been introduced, and a tomosynthesis system for executing the method. Raw datasets are acquired from a number of lateral acquisition angles. A number of synthetic projections are calculated from the raw datasets. The synthetic projections are output in the form of an image sequence which represents the examination object in a rotating visualization. An image reconstruction device and a tomosynthesis system, as well as a computer program product and a computer-readable medium are described.

Abstract: A first x-ray image is acquired at a predetermined position of a focal point and with a first orientation of an x-ray tube of an x-ray device. Subsequently, the x-ray tube is adjusted by rotating about a predetermined angle and by positioning, wherein the focal point is situated in the predetermined position prior to the adjustment and after the adjustment. After the adjustment, the x-ray tube is situated in a second orientation. Subsequently, a second x-ray image is acquired at the predetermined position and with the second orientation. A combined x-ray image from at least the first and second x-ray image is produced.

Abstract: A computer-implemented method for identifying features in 3D image volumes includes dividing a 3D volume into a plurality of 2D slices and applying a pre-trained 2D multi-channel global convolutional network (MC-GCN) to the plurality of 2D slices until convergence. Following convergence of the 2D MC-GCN, a plurality of parameters are extracted from a first feature encoder network in the 2D MC-GCN. The plurality of parameters are transferred to a second feature encoder network in a 3D Anisotropic Hybrid Network (AH-Net). The 3D AH-Net is applied to the 3D volume to yield a probability map;. Then, using the probability map, one or more of (a) coordinates of the objects with non-maximum suppression or (b) a label map of objects of interest in the 3D volume are generated.

Abstract: A method ascertains a time for a fresh calibration for ascertaining up-to-date calibration parameters of an x-ray device. The x-ray device has multiple degrees of freedom of movement for its recording arrangement. X-ray images of a calibration phantom are recorded for recording positions of the recording arrangement and are evaluated to ascertain the calibration parameters allowing ascertainment of geometry parameters. In multiple operating phases, situated between two calibrations, of a further x-ray device of identical design to the x-ray device, a piece of use information describing the accumulated use of the degrees of freedom of movement during the operating phase and a piece of difference information describing the difference in the calibration parameters between the calibrations delimiting the operating phase, is ascertained and used or determining the time for a fresh calibration.

Abstract: A method for the automatic generation of synthetic projections of an examination object from at least one three-dimensional data set acquired by way of a medical imaging system. The three-dimensional data set is used as a basis for determining position information relating to the arrangement of structures of the examination object and at least one synthetic projection based on the position information. We also describe a projection-image-ascertaining facility for the automatic generation of synthetic projections and a computer program product for executing the method.

Abstract: A method is provided for the automatic determination of at least one joint load information item concerning a joint of a patient, wherein at least one image data set of the loaded joint is recorded by an imaging apparatus. Several image data sets of the joint, of which at least one is three-dimensional, are recorded in each case for different loading states by the imaging apparatus. By combined evaluation of the image data sets, the at least one joint load information item is determined.

Abstract: A system and a method are respectively for positioning an examination object and evaluation of an image with respect to a positioning of a breast of an examination object in relation to an x-ray device. In an embodiment, the system includes an x-ray device including at least one compression device to fix a breast of the examination object; at least one camera, arranged in relation to the x-ray device such that images are acquirable via the at least one camera, the images showing a current positioning of the breast of the examination object in relation to the x-ray device; and at least one display device, embodied to display the images.

Abstract: A method automatically evaluates x-ray image data from an examination region of a patient. X-ray image data is received from the examination region. Furthermore x-ray image data is segmented and anatomical structures are detected in the individual segments. In addition reference image data that comes closest to the segmented x-ray image data is determined. This process is undertaken on the basis of a comparison of the segmented x-ray image data with reference image data from a reference database. The reference image data of the reference database has quality information relating to the image quality of the reference image data in each case. Finally a decision is made on the basis of the quality information of the established reference image data as to whether the received x-ray image data is to be retained or rejected.

Abstract: A computer-implemented method for identifying features in 3D image volumes includes dividing a 3D volume into a plurality of 2D slices and applying a pre-trained 2D multi-channel global convolutional network (MC-GCN) to the plurality of 2D slices until convergence. Following convergence of the 2D MC-GCN, a plurality of parameters are extracted from a first feature encoder network in the 2D MC-GCN. The plurality of parameters are transferred to a second feature encoder network in a 3D Anisotropic Hybrid Network (AH-Net). The 3D AH-Net is applied to the 3D volume to yield a probability map;. Then, using the probability map, one or more of (a) coordinates of the objects with non-maximum suppression or (b) a label map of objects of interest in the 3D volume are generated.

Abstract: A method of performing digital tomosynthesis includes the steps of obtaining an initial volume (I) formed with a plurality of slices (100); performing edge detection in a slice (100); processing the detected edges (11E) to obtain a weighting volume (Wxyz); and generating a composite slab (Scomp, Smeta) on the basis of the weighting volume (Wxyz).

Abstract: A method for planning an examination of an examination object by a tomosynthesis machine includes: Raw data of the examination object are acquired from defined acquisition angles. An auxiliary data set is reconstructed from the raw data. Depth data are calculated based on the auxiliary data set calculating a number of projections from the perspective of a respectively defined projection center from the auxiliary data set or from the raw data. Each of the projections has a number of image points each linked with associated depth data. The projections are displayed and at least one projection is chosen. A position of an examination region of the examination object is marked therein. A real three-dimensional position of the examination region is calculated using the marked position and its depth data, and an examination path to the examination region is calculated.