Abstract: A method for segmenting an image includes registering an annotated template image to an acquired reference image using only rigid transformations to define a transformation function relating the annotated template image to the acquired reference image. The defined transformation function is refined by registering the annotated template image to the acquired reference image using only affine transformations. The refined transformation function is further refined by registering the annotated template image to the acquired reference image using only multi-affine transformations. The twice refined transformation function is further refined by registering the annotated template image to the acquired reference image using deformation transformations.

Abstract: Dose values are displayed. The dose values display the take-up of radiation by an examination volume to be expected during an irradiation. An examination volume is segmented in an image, and the dose values are assigned to areas of the surface of the examination volume. The surface of the examination volume is displayed as a plane such that the areas displayed as flat will be graphically encoded by the dose values assigned to the respective areas.

Abstract: The present embodiments relate to a method for registering medical image data. The method includes providing a registration parameter set for each of a plurality of different application cases, each of the plurality of different application cases being defined by at least one feature. Each registration parameter set contains registration parameters predefined for the associated application case. The method also includes providing first image data and second image data, which are to be registered onto one another. In response to the specification of an application case for the first image data and the second image data to be registered, a registration parameter set is automatically selected from the provided registration parameter sets in accordance with the specified application case. The method includes automatically performing a registration of the first image data onto the second image data using the selected registration parameter set.

Abstract: The present embodiments relate to a method for checking a segmentation of a structure in image data, where the segmentation to be checked provides a segmentation region that approximates the structure imaged in the image data and that is delimited by a segmentation contour. The method includes spatially resolved automatic determination of characteristic values that are suitable for serving as an indicator of the accuracy of the segmentation of the structure on the basis of the image data, the segmentation contour to be checked, or a segmentation method applied during the performance of the segmentation to be checked. The method also includes spatially resolved automatic determination of confidence values for a plurality of positions on the segmentation contour using the characteristic values determined for the corresponding positions. The confidence values may indicate the reliability of the segmentation to be checked at the corresponding positions.

Abstract: A method for determining a 4D plan for carrying out intensity-modulated radiation therapy of a target volume subject to irregular periodic motion, with a radiation therapy apparatus is provided. The method includes selecting positions of a radiation source. The number of positions is selected to be identical in all 3D radiation therapy plans. The method also includes selecting a number of respective aperture settings assigned to a respective position of the radiation source to be identical in all 3D radiation therapy plans. A geometrical, temporal, and/or dynamic restriction that restricts a change of the aperture from one aperture setting to another aperture setting is predetermined, and the 3D radiation therapy plans are determined such that the 3D radiation therapy plans fulfill predetermined restrictions for aperture settings in each case.

Abstract: In order to increase efficiency, an image processing system may create a template identifying volumes of interest to be segmented based on user-specified data relating to a type of treatment and an anatomical site to be treated. The user of the image processing system may create, arrange, view, and manage a patient model including the volumes of interest, reference points, and/or distance measurements based on the arrangement of information using anatomical site rather than using type of imaging modality. The image processing system may segment the identified volumes of interest from image data received from one or more imaging modalities. The image processing system may generate a representation of the patient model including the segmented volumes of interest. The representation of the patient model may be indexed by the volumes of interest.

Abstract: The present embodiments relate to a system for automatic generation of structure datasets that are used for planning radiotherapy. The system includes a receiver unit that receives an image dataset of a person being examined. A central segmentation unit is provided. The receiver unit forwards the image dataset automatically to the central segmentation unit, the central segmentation unit having an identification unit for identifying a region of the body and a plurality of segmentation modules. Each segmentation module of the plurality of segmentation modules segments the image dataset using different segmentation methods. The identification unit, following identification of the region of the body, selects a segmentation module on the basis of the region of the body identified and automatically forwards the image dataset to the selected segmentation module. The selected segmentation module segments the image dataset, identifies predetermined structures in the image dataset, and generates a structure dataset.

Abstract: A method for separating tissue classes in MR images is presented. The method includes acquiring a plurality of magnetic resonance images of a subject with different acquisition parameters and generating a multi-dimensional intensity distribution model from the plurality of magnetic resonance images. The multi-dimensional intensity distribution model represents a distribution of intensities of voxels in each magnetic resonance image of the plurality. The method also includes identifying clusters of correlated intensities in the multi-dimensional intensity distribution model and assigning the clusters into one or more tissue classes based on the correlated intensities of each of the cluster.

Abstract: The present invention relates to a nucleic acid molecule for use in the treatment or preventive treatment of a patient after stent implantation or balloon dilatation, wherein the nucleic acid molecule is selected from (a) a single-stranded nucleic acid molecule comprising or consisting of the sequence of SEQ ID NO: 1, 2, 3 or 4 or a sequence having at least 90% sequence identity to the sequence of SEQ ID NO: 1, 2, 3 or 4; (b) a hairpin RNA, wherein one of the regions forming the double-stranded portion of said hairpin RNA comprises or consists of the sequence of SEQ ID NO: 1, 2, 3 or 4 or a sequence having at least 90% sequence identity to the sequence of SEQ ID NO: 1, 2, 3 or 4; (c) an at least partially double-stranded RNA comprising two separate single strands, wherein a region within one of the strands, said region being located within the double-stranded portion of said double-stranded RNA, comprises or consists of the sequence of SEQ ID NO: 1, 2, 3 or 4 or a sequence having at least 90% sequence identit

Abstract: The present embodiments relate to a method for checking a segmentation of a structure in image data, where the segmentation to be checked provides a segmentation region that approximates the structure imaged in the image data and that is delimited by a segmentation contour. The method includes spatially resolved automatic determination of characteristic values that are suitable for serving as an indicator of the accuracy of the segmentation of the structure on the basis of the image data, the segmentation contour to be checked, or a segmentation method applied during the performance of the segmentation to be checked. The method also includes spatially resolved automatic determination of confidence values for a plurality of positions on the segmentation contour using the characteristic values determined for the corresponding positions. The confidence values may indicate the reliability of the segmentation to be checked at the corresponding positions.

Abstract: The present embodiments relate to a method for registering medical image data. The method includes providing a registration parameter set for each of a plurality of different application cases, each of the plurality of different application cases being defined by at least one feature. Each registration parameter set contains registration parameters predefined for the associated application case. The method also includes providing first image data and second image data, which are to be registered onto one another. In response to the specification of an application case for the first image data and the second image data to be registered, a registration parameter set is automatically selected from the provided registration parameter sets in accordance with the specified application case. The method includes automatically performing a registration of the first image data onto the second image data using the selected registration parameter set.

Abstract: Methods and systems dedicated to automatic object segmentation from image data are provided. In a first step a fuzzy seed set is generated that is learned from training data. The fuzzy seed set is registered to image data containing an object that needs to be segmented from a background. In a second step a random walker segmentation is applied to the image data by using the fuzzy seed set as an automatic seeding for segmentation. Liver segmentation, lung segmentation and kidney segmentation examples are provided.

Abstract: A method for segmenting an image includes registering an annotated template image to an acquired reference image using only rigid transformations to define a transformation function relating the annotated template image to the acquired reference image. The defined transformation function is refined by registering the annotated template image to the acquired reference image using only affine transformations. The refined transformation function is further refined by registering the annotated template image to the acquired reference image using only multi-affine transformations. The twice refined transformation function is further refined by registering the annotated template image to the acquired reference image using deformation transformations.

Abstract: Methods and systems dedicated to automatic object segmentation from image data are provided. In a first step a fuzzy seed set is generated that is learned from training data. The fuzzy seed set is registered to image data containing an object that needs to be segmented from a background. In a second step a random walker segmentation is applied to the image data by using the fuzzy seed set as an automatic seeding for segmentation. Liver segmentation, lung segmentation and kidney segmentation examples are provided.