Abstract: The invention relates a system for assisting in planning a radiation therapy treatment provided using a treatment plan comprising irradiation parameters for controlling a delivery of radiation. The system is configured to (i) receive a first dose distribution, (ii) obtain a first objective function, which depends upon at least one parameter and a dose distribution, (iii) determine a first value of the parameter such that the first objective function fulfills a predefined criterion when being evaluated for the first value of the parameter and for a second dose distribution derived from the first dose distribution, (iii) provide the first objective function in connection with the first value of the at least one parameter to a user for modifying the first objective function to generate a second objective function, and (v) determine the treatment plan using the second objective function. Further, the invention relates to a corresponding method and computer program.

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: A device for optimizing a radiation therapy plan (30) for delivering therapeutic radiation to a patient using a therapeutic radiation source (16) while modulated by a multi-leaf collimator (MLC) (14) includes at least one electronic processor (25) connected to a radiation therapy device (12). A non-transitory computer readable medium (26) stores instructions readable and executable by the at least one electronic processor to perform a radiation therapy plan optimization method (102) including: optimizing MLC settings of the MLC respective to an objective function wherein the MLC settings define MLC leaf tip positions for a plurality of rows of MLC leaf pairs at a plurality of control points (CPs). The optimizing is performed in two or more iterations with a resolution of the MLC settings increasing in successive iterations.

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 relates to a dynamic sliding-window-like initialization for, for example, iterative VMAT algorithms. Specifically, a dynamic sliding window conversion method is contemplated where typical dynamic VMAT constraints are taken into account to find an optimal set of suitable openings (i.e. binary masks) that can be used as quasi-feasible start initialization for any VMAT algorithm that can refine until a deliverable plan is reached. Here, a multileaf leaf tip trajectory least square constrained optimization is performed to find a set of optimal unidirectional trajectories for all MLC leaf pairs of all arc points. To ensure that a quasi-feasible (or better quasi-deliverable) solution is returned, for example, a maximum dose rate, a maximum gantry speed, a maximum leafs speed, and a maximum treatment time may be enforced.

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: The present invention relates to a device and method for sketch template generation or adaption. To provide an efficient link between the image data and the template sketch, the device comprises a model input (40) configured to obtain a patient-adapted anatomical model, a parameter extraction unit (41) configured to extract a set of model parameters from the patient-adapted model, and a sketch unit (42) configured to generate or adapt a sketch template based on the extracted set of model parameters.

Abstract: The invention relates to a system for assisting in evaluating a contour of an anatomic structure (22) with respect to a dose distribution corresponding to a treatment plan for a radiation therapy treatment of a patient. The system comprises an evaluation unit particularly configured to evaluate the dose distribution in varying distances from the contour of the anatomic structure (22) to determine at least one point where the evaluated dose distribution fulfills a predetermined condition, and to determine the distance between the at least one point and the contour and/or to visualize the at least one point to a user of the system.

Abstract: The invention relates to the planning of a radiation therapy treatment of at least one structure in a region of a patient body. A planning unit obtains a first treatment plan generated on the basis of a planning image of the body region and on the basis of dose objectives. Moreover, the planning unit receives a further image of the body region of the patient body, determines a transformation for generating an adapted treatment plan from the first treatment plan and/or for generating an adapted dose distribution from the dose distribution corresponding to the first treatment plan on the basis of the further image and determines an adapted treatment plan on the basis of the transformation and/or the adapted dose distribution. In accordance with the invention, the transformation on the basis of the dose objectives.

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 planning system (7) for planning a volumetric modulated arc radiation therapy procedure, wherein the volumetric modulated arc radiation therapy procedure includes rotating a radiation source (2), which is configured to emit a radiation beam (3) for treating a subject (4), along an arc around the subject, in order to apply the radiation beam to the subject in different treatment directions. A sequence of sub-arcs groups is provided, wherein a respective sub-arcs group comprises several sub-arcs of the arc, which are evenly distributed along the arc, wherein a treatment plan is generated by sequentially determining for each sub-arcs group treatment parameters, which define a property of the radiation beam, in the provided sequence. Determining the treatment parameters by using this sequence leads to an increased likelihood that really an optimal treatment plan is generated.

Abstract: A system and method are provided for display of medical image data, with the display of the medical image data being determined on the basis of schematic image data of a schematic representation of an anatomical structure. The schematic representation may provide a particular view of the anatomical structure. The type of anatomical structure and the view of the anatomical structure provided by the schematic representation may be determined based on one or more image features in the schematic image data. The view may be characterized as a geometrically-defined perspective at which the anatomical structure is shown in the schematic representation. An output image may be generated showing the anatomical structure in the medical image data in accordance with said determined geometrically-defined perspective. A user may thus be provided with a display of medical image data which is easier to interpret having considered said schematic representation.

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: In planning of radiation therapy treatment of at least one structure in a region of a patient body, a first treatment plan is generated on the basis of a planning image of the body region and on the basis of dose objectives. A further image of the body region of the patient body is received, and a transformation is determined for generating an adapted treatment plan from the first treatment plan and/or for generating an adapted dose distribution from the dose distribution corresponding to the first treatment plan on the basis of the further image and determines an adapted treatment plan on the basis of the transformation and/or the adapted dose distribution. The transformation on the basis of the dose objectives. In adapting the dose distribution, an efficient iterative dosimetric patient setup optimization may be employed to reduce the dose computations.

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: The invention relates to a system and a method for evaluating a treatment plan for an external radiation therapy treatment, the treatment plan comprising parameters for controlling an external radiation therapy apparatus during the treatment. The system comprises a database storing historic treatment plans and storing for each historic treatment plan a quality parameter indicative of whether a deviation between a planned dose distribution and a measured dose distribution resulting from an execution of the treatment plan is within an acceptable limit. An evaluation unit determines a threshold value for each of a plurality of treatment plan metrics based on the historic treatment plans and the associated quality parameters. Further, the evaluation unit calculates a value of each of the metrics for the treatment plan and compares the value of each of the metrics with the threshold value determined for the respective metric.

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: A system (10) includes a computing system (124) with a processor (130) and computer readable storage medium (126) with computer readable and executable instructions (128), including a radiation plan module (136), a radiation plan optimization module (138) and a radiation plan visualization module (140). The processor is configured to execute the instructions, which causes the processor to construct and visually present, via a display monitor (132), a two-dimensional plot with three-dimensions of data from a radiation plan, and two dimensions along two axes of the plot and a third dimension represented through intensity.