Abstract: The invention relates to a segmentation system for segmenting an object in an image. The segmentation system is configured to place a surface model comprising surface elements within the image, to determine for each surface element a respective sub volume (6) of the image and to use a neural network (51) for determining respective distances between the surface elements and the boundary of the object in the image based on the determined subvolumes. The surface model is then adapted in accordance with the determined distances, in order to segment the object. This segmentation, which is based on the subvolumes of the image and the neural network, is improved in comparison to known techniques which rely, (10) for instance, on a sampling of candidate points along lines being perpendicular to the respective surface element and on a determination of likelihoods for the candidate points that they indicate a boundary of the object.

Abstract: Slice alignment approaches are described for short axis cardiac magnetic resonance cine slice stacks, which do not require additional scans, such as long axis scans or full 3D scans, and which are able to deal with cardiac structures having complex shapes. Both approaches do not need contours to follow a quadratic curvature function, and are well suitable for the purpose of obtaining a segmentation of a cardiac structure using a deformable surface model. Namely, such a deformable surface model is unable, but also not desired, to fully adapt to the ‘zig-zag’-shaped pattern in the boundary of the cardiac structure due to the slice misalignment. Having removed or reduced the misalignment between image slices, such a deformable surface model may better adapt to the cardiac structure in the image data and 10 thereby provide a better segmentation of the cardiac structure.

Abstract: There is provided a method and apparatus for refining a model of an anatomical structure in an image. A model for the anatomical structure in the image is acquired. The model comprises a plurality of control points, each control point corresponding to a feature in the anatomical structure. The model is placed in the image with respect to the anatomical structure. Based on a user input received to adjust the model in the image, a position of at least one of the plurality of control points is adjusted to alter a shape of the model to the anatomical structure in the image, wherein adjustment of the position of one or more of the at least one control points is restricted based on information relating to the at least one control point.

Abstract: The invention provides for a method for switching between fields of view of an ultrasound probe. The method begins by obtaining an anatomical model representing a region of interest of a subject and establishing a first field of view relative to an ultrasonic probe, wherein the first field of view comprises an initial portion of the region of interest. Ultrasound data is then obtained from the first field of view by way of the ultrasonic probe and a first anatomical feature is identified within the first field of view based on the ultrasound data. A location in digital space of the first field of view relative to the anatomical model is determined based on the first anatomical feature. A second field of view is then established based on the anatomical model and the first field of view, wherein the first field of view functions as a reference field of view. The field of view is then switched from the first field of view to the second field of view.

Abstract: The invention provides for a medical imaging system (100, 300, 400) comprising a memory (110) containing machine executable instructions (120) and a processor (106). Execution of the machine executable instructions cause the processor to: receive (200) a magnetic resonance image (300), receive (202) meta data descriptive of the magnetic resonance image, wherein the metadata comprises reference gray scale value data (124) for two or more tissue types; and segment (204) the magnetic resonance image using an image segmentation algorithm (126) that uses the reference gray scale value data.

Abstract: The invention relates to a method for weighing pharmaceutical containers (10) nested in a carrier (11), in which at least one of the nested containers (10) is weighed by means of a weighing device (1), wherein a relative movement between the at least one pharmaceutical container (10) and the carrier (11) is brought about in order to release the pharmaceutical containers (10) from the carrier (11) in order to increase the weighing accuracy.

Abstract: There is provided a method and apparatus for refining a model of an anatomical structure in an image. A model for the anatomical structure in the image is acquired. The model comprises a plurality of control points, each control point corresponding to a feature in the anatomical structure. The model is placed in the image with respect to the anatomical structure. Based on a user input received to adjust the model in the image, a position of at least one of the plurality of control points is adjusted to alter a shape of the model to the anatomical structure in the image, wherein adjustment of the position of one or more of the at least one control points is restricted based on information relating to the at least one control point.

Abstract: There is provided a method and apparatus for segmenting two-dimensional images of an anatomical structure. A time sequence of two-dimensional images of the anatomical structure is acquired (202) and a segmentation model for the anatomical structure is acquired (204). The segmentation model comprises a plurality of segments. The acquired segmentation model is applied to the entire time sequence of two-dimensional images of the anatomical structure simultaneously in time and space to segment the time sequence of two-dimensional images by way of the plurality of segments (206).

Abstract: A system and computer-implemented method are provided for preprocessing medical image data for machine learning. Image data is accessed which comprises an anatomical structure. The anatomical structure in the image data is segmented to obtain a segmentation of the anatomical structure as a delineated part of the image data. A grid is assigned to the delineated part of the image data, the grid representing a partitioning of an exterior and interior of the type of anatomical structure using grid lines, wherein said assigning comprises adapting the grid to fit the segmentation of the anatomical structure in the image data. A machine learning algorithm is then provided with an addressing to the image data in the delineated part on the basis of coordinates in the assigned grid. In some embodiments, the image data of the anatomical structure may be resampled using the assigned grid.

Abstract: An ultrasound imaging system for acquiring ultrasound images of an anatomical feature of interest in a subject, comprising a controller operable by a user and configured to: process input ultrasound images to extract anatomical data; determine a set of constraints to be applied to the ultrasound images, the constraints being spatial, temporal and/or of image quality, derived from the extracted anatomical data and/or on user input; monitor the ultrasound images, as they are received, for determining their compliance with the determined constraints; and output an indication based on the determined compliance. The user can adapt the imaging process using the feedback of these indications, and can decide to stop the process based on satisfactory indications.

Abstract: A method and apparatus for segmenting a two-dimensional image of an anatomical structure includes acquiring (202) a three-dimensional model of the anatomical structure. The three-dimensional model includes a plurality of segments. The acquired three-dimensional model is adapted to align the acquired three-dimensional model with the two-dimensional image (204). The two-dimensional image is segmented by the plurality of segments of the adapted three-dimensional model.

Abstract: The invention relates to a segmentation system for segmenting an object in an image. The segmentation system is configured to place a surface model comprising surface elements within the image, to determine for each surface element a respective sub volume (6) of the image and to use a neural network (51) for determining respective distances between the surface elements and the boundary of the object in the image based on the determined subvolumes. The surface model is then adapted in accordance with the determined distances, in order to segment the object. This segmentation, which is based on the subvolumes of the image and the neural network, is improved in comparison to known techniques which rely, (10) for instance, on a sampling of candidate points along lines being perpendicular to the respective surface element and on a determination of likelihoods for the candidate points that they indicate a boundary of the object.

Abstract: An ultrasound imaging system comprises a display for displaying a received ultrasound image. A user interface is provided for receiving user commands for controlling the ultrasound imaging process, and it receives a user input which identifies a point or region of the displayed ultrasound image. An image depth is determined which is associated with the identified point or region and the imaging process is controlled to tailor the imaging to the identified point or region.

Abstract: It is an object of the invention to provide for an improved radiation treatment. According to a first aspect of the invention, this object is achieved by a method for determining a patient specific locally varying margin on a treatment target and/or an organ at risk in order to compensate for local intrafraction motion expected during a radiotherapy fraction to be delivered over a radiotherapy fraction time interval. The patient specific locally varying margin is determined based on a displacement and/or an estimate of the displacement of at least a first location and a second location on the treatment target and/or organ at risk.

Abstract: A system (100) and computer-implemented method are provided for data collection for distributed machine learning of a machine learnable model. A privacy policy data (050) is provided defining computer-readable criteria for limiting a selection of medical image data (030) to a subset of the medical image data to obfuscate an identity of the at least one patient. The medical image data is selected based on the computer-readable criteria to obtain privacy policy-compliant training data (060) for transmission to another entity. The system and method enable medical data collection at clinical sites without requiring manual oversight, and enables such selections to be made automatically, e.g., based on a request for medical image data which may be received from outside of the clinical site.

Abstract: A system and method are provided for volume rendering of image data of an image volume. A segmentation model is applied to the image data of the image volume, thereby delineating a sub-volume of the image volume. The image data inside the sub-volume is volume rendered. A user interface is provided which enables a user to interactively adjust the sub-volume by applying at least one of: a push action and a pull action to the sub-volume. The push action may cause part of the sub-volume to be pulled inwards, whereas the pull action may cause part of the sub-volume to be pulled outwards. The volume rendering of the sub-volume may be updated in response to a user's adjustment of the sub-volume.

Abstract: The present invention relates to a medical imaging system (10) for planning an implantation of a cardiac implant (42), comprising: a receiving unit (12) for receiving a plurality of three-dimensional (3D) cardiac images (14, 14?) showing different conditions of a heart (32) during a cardiac cycle; a segmentation unit (22) for segmenting within the plurality of 3D cardiac images (14, 14?) a target implant region (38) and a locally adjacent region (40) that could interfere with the cardiac implant (42); a simulation unit (24) for simulating the implantation of the cardiac implant (42) within the target implant region (40) in at least two of the plurality of 3D cardiac images (14, 14?); a collision evaluation unit (26) for evaluating an overlap (46) of the simulated cardiac implant (42) with the segmented locally adjacent region (40) in at least two of the plurality of 3D cardiac images (14, 14?); and a feedback unit (28) for providing feedback information to a user concerning the evaluated overlap (46).

Abstract: There is provided a method and apparatus for adjusting a model of an anatomical structure in a sequence of images of the anatomical structure. The model is placed with respect to the anatomical structure in the sequence of images. A user input is received to adjust the model in a selected image of the sequence, and based on the user input, a part of the model that lies in the selected image and a previously unadjusted part of the model that lies in one or more other images of the sequence is adjusted, whilst fixing in place a previously adjusted part of the model that lies in other images of the sequence.

Abstract: An ultrasound imaging apparatus (10) for segmenting an anatomical object in a field of view (29) of an ultrasound acquisition unit (14) is disclosed. The ultrasound imaging apparatus comprises a data interface (32) configured to receive a two-dimensional ultrasound data (30) of the object in the field of view in an image plane from the ultrasound acquisition unit and to receive a three-dimensional segmentation model (46) as a three-dimensional representation of the object from a segmentation unit (36). An image processor (34) is configured to determine a two-dimensional segmentation model (50) on the basis of the three-dimensional segmentation model and a segmentation plane (48), wherein the segmentation plane and an image plane of the two-dimensional ultrasound data correspond to each other.

Abstract: Disclosed is a device for filling a receptacle, comprising at least one filling station (48) for filling at least one receptacle (36), and at least one receptacle holder (38) for conveying the receptacle (36) relative to the filling station (48), characterized in that at least one driving surface (13) and at least one mover (20) which can be coupled to the driving surface (13) especially in a magnetic manner are provided, the mover (20) being arranged so as to be movable and/or rotatable on the driving surface (13) in at least two degrees of freedom, and in that the receptacle holder (38) is disposed on the mover (20).