Abstract: One or more example embodiments of the present invention relates to a mammography system for recording an X-ray recording dataset of a region of interest of a breast of an examinee, comprising a compression unit for fixing the breast for the recording; and an interrupt unit triggerable by the examinee and connected to the compression unit and an X-ray source, the interrupt unit being configured to release the fixation and to stop the X-ray radiation.

Abstract: One or more example embodiments of the present invention relates to a breast fixation element for a mammography system having a flat elastic surface element including a fastening element for fixing the breast to a support surface of the mammography system, wherein a shape of the breast fixation element is adapted to a shape of the breast.

Abstract: A method is for generating a synthetic mammogram. In an embodiment, the method incudes acquisition of a plurality of projection data sets at a plurality of projection angles; and generation of at least one synthetic mammogram with an image property essentially equivalent to a conventional full-field digital mammography acquisition based on several projection data sets.

Abstract: A method is for creating a synthetic mammogram based upon a dual energy tomosynthesis recording of an examination region. In an embodiment the method includes making a low energy tomosynthesis recording with a first X-ray energy spectrum; making a high energy tomosynthesis recording with a second X-ray energy spectrum of relatively higher energy compared with the first X-ray energy spectrum, wherein the examination region includes a contrast medium distribution; determining a subtraction volume based upon the high energy tomosynthesis recording and the low energy tomosynthesis recording; generating a three-dimensional probability map with a weighting factor per voxel based upon the subtraction volume; and creating a synthetic mammogram based upon the three-dimensional probability map.

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 method is for generating a first synthetic mammogram. In an embodiment, the method includes acquiring a tomosynthesis dataset including a plurality of projection images of a tissue region from different projection directions in a projection angle range; reconstructing a slice image dataset based on the tomosynthesis dataset; localizing tissue changes in the slice image dataset; determining a first projection direction for a first synthetic mammogram based on the spatial distribution of the tissue changes in the slice image dataset and generating the first synthetic mammogram in the first projection direction based on the tomosynthesis dataset.

Abstract: A method is for creating a synthetic mammogram based upon a dual energy tomosynthesis recording of an examination region. In an embodiment the method includes making a low energy tomosynthesis recording with a first X-ray energy spectrum; making a high energy tomosynthesis recording with a second X-ray energy spectrum of relatively higher energy compared with the first X-ray energy spectrum, wherein the examination region includes a contrast medium distribution; determining a subtraction volume based upon the high energy tomosynthesis recording and the low energy tomosynthesis recording; generating a three-dimensional probability map with a weighting factor per voxel based upon the subtraction volume; and creating a synthetic mammogram based upon the three-dimensional probability map.

Abstract: A method is for generating a synthetic mammogram. In an embodiment, the method incudes acquisition of a plurality of projection data sets at a plurality of projection angles; and generation of at least one synthetic mammogram with an image property essentially equivalent to a conventional full-field digital mammography acquisition based on several projection data sets.

Abstract: A method is for operating an X-ray device. In an embodiment, the method includes acquiring a sequence of images of a patient; moving an acquisition arrangement including at least one X-ray tube assembly, during the acquiring of the sequence of images, along the patient in a scanning direction; evaluating at least two different images, showing at least one common feature of the patient, to determine depth information for the at least one common feature; and actuating a collimator aperture of a collimator of the X-ray tube assembly, as a function of position information describing a position of the acquisition arrangement in the scanning direction, to change an aperture angle of a radiation field generated by the X-ray tube assembly in the scanning direction.

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 is for operating an X-ray device. In an embodiment, the method includes acquiring a sequence of images of a patient; moving an acquisition arrangement including at least one X-ray tube assembly, during the acquiring of the sequence of images, along the patient in a scanning direction; evaluating at least two different images, showing at least one common feature of the patient, to determine depth information for the at least one common feature; and actuating a collimator aperture of a collimator of the X-ray tube assembly, as a function of position information describing a position of the acquisition arrangement in the scanning direction, to change an aperture angle of a radiation field generated by the X-ray tube assembly in the scanning direction.

Abstract: A method for determining a three-dimensional image data set from a plurality of two-dimensional projection images of an object under examination applies at least one morphological operation to each projection image in order to provide a processing image associated with the respective projection image. At least one respective imaging segment is segmented, in which a highly absorbent region is mapped, depending on the associated processing image, and a respective mask image is generated in which pixels belonging to the imaging segment are marked. An associated synthetic image for each projection image is determined, the image data of which within the imaging segment is set to predetermined values. The projection images and the synthetic images are separately filtered. The three-dimensional image data set is determined by backprojecting the mask images to determine a mask value for each voxel of the image data set.

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 for determining a three-dimensional image data set from a plurality of two-dimensional projection images of an object under examination applies at least one morphological operation to each projection image in order to provide a processing image associated with the respective projection image. At least one respective imaging segment is segmented, in which a highly absorbent region is mapped, depending on the associated processing image, and a respective mask image is generated in which pixels belonging to the imaging segment are marked. An associated synthetic image for each projection image is determined, the image data of which within the imaging segment is set to predetermined values. The projection images and the synthetic images are separately filtered. The three-dimensional image data set is determined by backprojecting the mask images to determine a mask value for each voxel of the image data set.