Abstract: One or more example embodiments of the present invention relates to a method for determining a Background Parenchymal Enhancement (BPE) in a contrast medium-enhanced X-ray examination of a breast comprising providing images of the X-ray examination, the images having been taken after administration of the contrast medium, the images comprising at least one low energy (LE) image taken at a predetermined low X-ray energy and a high energy (HE) image taken at a predetermined high X-ray energy, creating an iodine image from the LE image and the HE image and calculating a volumetric BPE as a sum of all pixel values in the iodine image for which the following two conditions apply i) iodine enrichment is present in the iodine image, and ii) fibroglandular tissue (FGT) is present. The method further includes obtaining BPE result data based on the iodine image and volumetric BPE and outputting the BPE result data.

Abstract: A computer-implemented method for position control of an object under investigation before acquiring a projective X-ray image of a region of interest, the computer-implemented method comprising: receiving object information of the object under investigation in an examination pose; retrieving an object model relating to the examination pose and the region of interest; adapting the object model to the object under investigation based on the object information; and evaluating the examination pose based on the adapted object model.

Abstract: A training-device comprises: a data-generator to generate synthetic training-images from a first set of parameter-values and synthetic testing-images from a second set of parameter-values, wherein the parameter-values are from a common parameter-set, and each image is linked to a ground truth; a training-unit to train a machine learning model with training-images in a supervised manner; and a testing-unit to test a trained model based on testing-images, evaluate individual test-qualities, and determine parameter value-ranges for groups of testing-images representing ranges with a relatively poor image-density, wherein at least one of (i) test-qualities are below a threshold value or (ii) the relative number of training-images compared to other parameter value-ranges is below a threshold.

Abstract: A method for automatically determining spine deformation from an image showing a number of vertebrae of the spine, comprises: detecting center points of the number of vertebrae shown in the image; constructing a center line based on the center points; computing a local tilt at points along the center line; determining positive and negative tilt-maxima of the local tilt and selecting two reference vertebrae having center points closest to the positive and negative tilt-maxima; segmenting an upper endplate of the cranial reference vertebra; segmenting a lower endplate of the caudal reference vertebra; computing an angle between the upper endplate and the lower endplate; and outputting the angle.

Abstract: A method is for determining a positioning quality of an external apparatus inserted into a patient's body. In the method, image data of the patient's body is detected; an at least one first anatomical landmark is detected in or with a first subregion, in which the external apparatus is positioned as expected; at least a first subsection of the external apparatus is sought in or with the at least one first subregion; a second anatomical landmark is detected in or with at least one second subregion; at least one second subsection is then detected based upon the already localized subsection; and a quality of the positioning of the at least one second subsection is determined by measuring a suitable dimension between the localized at least one second subsection and the at least one second landmark. A training method, a positioning quality determination facility and a training facility are also disclosed.

Abstract: A computer-implemented method, comprising: receiving input data including a medical image and an in-image annotation; applying a first function to the input data to determine a relevance value of pixels in the image and a relevance map; applying a second function to the medical image to generate a de-identified medical image; applying a trained function to the medical image and the de-identified medical image to determine a first property in the medical image and a second property in the de-identified medical image; applying a comparison function to the first property and the second property to determine a similarity value, wherein in response to the similarity value being below a similarity threshold, the relevance map is adjusted and the applying of the second function, the applying of the trained function and the applying of the comparison function are repeated; and providing the de-identified medical image and the in-image annotation.

Abstract: A device for organ positioning assessment for acquiring images in the course of a medical examination of a patient, comprises: a data-interface configured to receive and/or automatically retrieve physical patient-data; a pre-assessment-unit configured to generate a positioning-advice for the medical examination based on the type of medical examination and the patient-data; a data-interface configured to output the positioning-advice; a data-interface configured to receive and/or automatically retrieve a number of examination-images of the patient; a post-assessment-unit configured to generate patient-specific feedback-data based at least on the number of examination-images and the positioning-advice; and a data-interface configured to output the feedback-data.

Abstract: In a method, comparison features are extracted from labeled reference image data. Features are also extracted from the image data. A statistical comparison of the comparison features with the features then takes place. On the basis of the statistical comparison and a quality criterion, the quality of the AI-based result data is determined. A method for correcting result data is additionally described. Furthermore, a method for AI-based acquisition of result data on the basis of measured examination data is described. Also described is a validation entity. An entity for correcting result data is additionally described. Furthermore, an entity for acquiring result data is described. Also described is a medical imaging entity.

Abstract: One or more example embodiments relates to a computer implemented method for performing a check of a stacked system. The method comprises receiving input data. The method further comprises applying a first function to the input data to generate an intermediate output data. The method further comprises performing a check based on the intermediate output data. If the check is positive, the method comprises providing the intermediate output data to a second function at least as part of an intermediate input data, applying the second function to the intermediate input data to generate an output data and providing the output data.

Abstract: A computer-implemented method for position control of an object under investigation before acquiring a projective X-ray image of a region of interest, the computer-implemented method comprising: receiving object information of the object under investigation in an examination pose; retrieving an object model relating to the examination pose and the region of interest; adapting the object model to the object under investigation based on the object information; and evaluating the examination pose based on the adapted object model.

Abstract: A method for automatically adapting a collimation for a dynamic X-ray imaging, comprises: receiving criteria data for adapting the collimation, wherein the criteria data include first criteria and second criteria; acquiring optical image data from an examination object; generating an adapted collimation based on the acquired optical image data and the first criteria; acquiring an X-ray frame from the examination object with the adapted collimation; performing an automatic check of the adapted collimation of the acquired X-ray frame by checking whether the adapted collimation meets the second criteria based on the acquired X-ray frame; and generating a re-adapted collimation such that the second criteria are more likely fulfilled by the next acquired X-ray frame in response to the automatic check not being passed, or maintaining the adapted collimation in response to the automatic check being passed.

Abstract: A computer-implemented method, comprising: receiving input data including a medical image and an in-image annotation; applying a first function to the input data to determine a relevance value of pixels in the image and a relevance map; applying a second function to the medical image to generate a de-identified medical image; applying a trained function to the medical image and the de-identified medical image to determine a first property in the medical image and a second property in the de-identified medical image; applying a comparison function to the first property and the second property to determine a similarity value, wherein in response to the similarity value being below a similarity threshold, the relevance map is adjusted and the applying of the second function, the applying of the trained function and the applying of the comparison function are repeated; and providing the de-identified medical image and the in-image annotation.

Abstract: A computer-implemented method comprises: receiving input data, wherein the input data includes the X-ray image dataset, which includes an X-ray image and first metadata; applying a trained function to the input data to generate output data, wherein the output data includes second metadata, and wherein the first metadata and the second metadata are compared; and providing the output data, wherein the first metadata are confirmed in case the first metadata and the second metadata agree, or the first metadata are suggested to be corrected with the second metadata in case the first metadata and the second metadata do not agree.

Abstract: One or more example embodiments of the present invention relates to a method for determining a Background Parenchymal Enhancement (BPE) in a contrast medium-enhanced X-ray examination of a breast comprising providing images of the X-ray examination, the images having been taken after administration of the contrast medium, the images comprising at least one low energy (LE) image taken at a predetermined low X-ray energy and a high energy (HE) image taken at a predetermined high X-ray energy, creating an iodine image from the LE image and the HE image and calculating a volumetric BPE as a sum of all pixel values in the iodine image for which the following two conditions apply i) iodine enrichment is present in the iodine image, and ii) fibroglandular tissue (FGT) is present. The method further includes obtaining BPE result data based on the iodine image and volumetric BPE and outputting the BPE result data.

Abstract: A computer program, a system and a method for normalizing medical images from a type of image acquisition device using a machine learning unit are disclosed. An embodiment of the method includes receiving a set of image data with images; decomposing each of the images of the set of images into components by incorporating at least information from different settings of the image acquisition device-specific image processing algorithms; and normalizing each of the components via a machine learning unit by processing at least information from the different settings of the image acquisition device-specific processing algorithms to provide a set of normalized images with a relatively decreased variability score.

Abstract: According to a method for correcting a 2D measurement value is described, 2D image data of an examination object is received. Landmarks in the 2D image data are detected, and 2D positions of the landmarks are calculated. A corrected measurement value of the examination object is predicted, using a trained model, which depends on the received 2D image data, the estimated 2D positions of the landmarks and a reference parameter of a reference 3D orientation of the examination object.

Abstract: A method for automatically determining spine deformation from an image showing a number of vertebrae of the spine, comprises: detecting center points of the number of vertebrae shown in the image; constructing a center line based on the center points; computing a local tilt at points along the center line; determining positive and negative tilt-maxima of the local tilt and selecting two reference vertebrae having center points closest to the positive and negative tilt-maxima; segmenting an upper endplate of the cranial reference vertebra; segmenting a lower endplate of the caudal reference vertebra; computing an angle between the upper endplate and the lower endplate; and outputting the angle.

Abstract: In a method, comparison features are extracted from labeled reference image data. Features are also extracted from the image data. A statistical comparison of the comparison features with the features then takes place. On the basis of the statistical comparison and a quality criterion, the quality of the AI-based result data is determined. A method for correcting result data is additionally described. Furthermore, a method for AI-based acquisition of result data on the basis of measured examination data is described. Also described is a validation entity. An entity for correcting result data is additionally described. Furthermore, an entity for acquiring result data is described. Also described is a medical imaging entity.

Abstract: With a device and an associated method, an ultrasound unit is coupled with a coupling unit to an existing x-ray unit. The ultrasound unit is guided with the aid of controllable elements of a positioning unit of the x-ray unit on a patient for an ultrasound examination. In this manner X-ray recordings and ultrasound recordings of an object can be produced.

Abstract: A method is for determining a positioning quality of an external apparatus inserted into a patient's body. In the method, image data of the patient's body is detected; an at least one first anatomical landmark is detected in or with a first subregion, in which the external apparatus is positioned as expected; at least a first subsection of the external apparatus is sought in or with the at least one first subregion; a second anatomical landmark is detected in or with at least one second subregion; at least one second subsection is then detected based upon the already localized subsection; and a quality of the positioning of the at least one second subsection is determined by measuring a suitable dimension between the localized at least one second subsection and the at least one second landmark. A training method, a positioning quality determination facility and a training facility are also disclosed.