Abstract: Techniques for generating a radiotherapy treatment plan are provided. The techniques include receiving an input parameter related to a patient, the input parameter being of a given type; processing the input parameter with a machine learning technique to estimate a realizable plan parameter of a radiotherapy treatment plan, wherein the machine learning technique is trained to establish a relationship between the given type of input parameter and a set of realizable radiotherapy treatment plan parameters to achieve a target radiotherapy dose distribution; and generating the radiotherapy treatment plan based on the estimated realizable plan parameter.

Abstract: The present disclosure relates to systems, methods, and computer-readable storage media for radiotherapy. Embodiments of the present disclosure may receive a plurality of training data and determine one or more predictive models based on the training data. The one or more predictive models may be determined based on at least one of a conditional probability density associated with a selected output characteristic given one or more selected input variables or a joint probability density. Embodiments of the present disclosure may also receive patient specific testing data. In addition, embodiments of the present disclosure may predict a probability density associated with a characteristic output based on the one or more predictive models and the patient specific testing data. Moreover, embodiments of the present disclosure may generate a new treatment plan based on the prediction and may use the new treatment plan to validate a previous treatment plan.

Abstract: Techniques for the operation and use of a model that learns the general representation of multimodal images is disclosed. In various examples, methods from representation learning are used to find a common basis for representation of medical images. These include aspects of encoding, fusion, and downstream tasks, with use of the general representation and model. In an example, a method for generating a modality-agnostic model includes receiving imaging data, encoding the imaging data by mapping data to a latent representation, fusing the encoded data to conserve latent variables corresponding to the latent representation, and training a model using the latent representation. In an example, a method for processing imaging data using a trained modality-agnostic model includes receiving imaging data, encoding the data to the defined encoding, processing the encoded data with a trained model, and performing imaging processing operations based on output of the trained model.

Abstract: Techniques for the operation and use of a model that learns the general representation of multimodal images is disclosed. In various examples, methods from representation learning are used to find a common basis for representation of medical images. These include aspects of encoding, fusion, and downstream tasks, with use of the general representation and model. In an example, a method for generating a modality-agnostic model includes receiving imaging data, encoding the imaging data by mapping data to a latent representation, fusing the encoded data to conserve latent variables corresponding to the latent representation, and training a model using the latent representation. In an example, a method for processing imaging data using a trained modality-agnostic model includes receiving imaging data, encoding the data to the defined encoding, processing the encoded data with a trained model, and performing imaging processing operations based on output of the trained model.

Abstract: The present invention introduces a method, device and a computer program for removing artifacts present in individual channels of a multichannel measurement device. At first, a basis is generated defining an n-dimensional subspace of the N-dimensional signal space, where n is smaller than N, where using in the definition of the n-dimensional basis a physical model of a Signal Space Separation method, or a statistical model based on the statistics of recorded N-dimensional signals. Thereafter, a combined (n+m)-dimensional basis is formed by adding m signal vectors to the n-dimensional basis, each of these m signal vectors representing a signal present only in a single channel of the N-channel device. After this the recorded N-dimensional signal vector is decomposed into n+m components in the combined basis, and finally, components corresponding to the m added vectors in the combined basis are subtracted from the recorded N-dimensional signal vector.

Abstract: The present disclosure relates to systems, methods, and computer-readable storage media for radiotherapy. Embodiments of the present disclosure may receive a plurality of training data and determine one or more predictive models based on the training data. The one or more predictive models may be determined based on at least one of a conditional probability density associated with a selected output characteristic given one or more selected input variables or a joint probability density. Embodiments of the present disclosure may also receive patient specific testing data. In addition, embodiments of the present disclosure may predict a probability density associated with a characteristic output based on the one or more predictive models and the patient specific testing data. Moreover, embodiments of the present disclosure may generate a new treatment plan based on the prediction and may use the new treatment plan to validate a previous treatment plan.

Abstract: The leaves of a multi-leaf collimator can be driven more easily and hence more quickly if they are supported on a ball-race instead of in a sliding groove. A recirculating path is preferred, in which the rolling elements of the ball-race support the leaf over part of their path and then return to a start of the path. In addition, the rolling elements could be driven by a drive screw in order to drive the leaf.

Abstract: A patient support includes a bed, one or more mechanisms configured for manipulating at least one of position and orientation of the bed, and a display configured for displaying a user interface and receiving inputs to control at least the one or more mechanisms.

Abstract: A patient support system includes a floor cavity in the floor of a treatment room; a patient support device comprising a treatment table; a base; a first movement mechanism on which the treatment table is mounted; a second movement mechanism mounted on the base and attached to the first movement mechanism, wherein the first and second movement mechanisms are moveable independently of each other; the first movement mechanism is configured to raise and lower the treatment table and the second movement mechanism is configured to raise and lower the first movement mechanism such that in a lowered position the second movement mechanism is contained within the floor cavity.

Abstract: A radiotherapy apparatus comprises a rotatable gantry, supporting a source of therapeutic radiation and a source of diagnostic radiation, the two sources being rotationally (or angularly) spaced apart around a rotation axis of the gantry, with at least one collimator associated with the source of therapeutic radiation and arranged to limit the cross-sectional area of a beam produced by that source, a control means arranged to conduct a treatment fraction using the apparatus by causing the apparatus to i. acquire images of a patient using the source of diagnostic radiation, ii. retain those images at least temporarily, iii. subsequently, after further rotation of the gantry, select a retained image acquired when the source of diagnostic radiation was at a rotational position corresponding to the instantaneous rotational position of the source of therapeutic radiation, and iv. control the beam relative to the patient using information derived from the selected image.

Abstract: An apparatus for placement of an optical marker for radiotherapy onto a surface, wherein the optical marker has a reflective element positioned on a body having an outline and shaped and configured such that the reflective element is in a predetermined position relative to the outline of the body, the apparatus comprising a sheet of material having a hole therethrough which is shaped and configured to conform to the outline of the body and which has an upper surface with markings thereon configured for aligning with an image projected onto the surface on which the optical marker is to be placed.

Abstract: An apparatus and method of segmenting an image using scribble segmentation is provided. An image is segmented by constraining the membership value of a subset of image elements, solving a weighted biharmonic equation subject to the constrained membership values wherein the weights are determined from similarities between image elements, and determining the final segmentation based on the membership value of each image element. An image may also be segmented by constraining a membership value of a subset of image elements, determining the unknown membership values given the constraints by solving a linear equation system using a multigrid technique, and updating a coarser level of the multigrid hierarchy to account for additional constraints using patch matrices.

Abstract: A workflow management system for radiotherapy treatment of a patient using radiotherapy equipment comprising: a patient radiofrequency identification (RFID) tag and a radiofrequency (RF) detection device, which provides a patient unique identifier matchable to a patient's treatment plan; a plurality of optical markers, wherein in at least one patient optical marker is positioned on the patient and at least one reference optical marker is positioned at a reference point on the radiotherapy equipment; an optical reader to detect each of the plurality of optical markers; wherein the system matches the patient's unique identifier to the patient treatment plan.

Abstract: A patient support system includes a floor cavity in the floor of a treatment room; a patient support device comprising a treatment table; a base; a first movement mechanism on which the treatment table is mounted; a second movement mechanism mounted on the base and attached to the first movement mechanism, wherein the first and second movement mechanisms are moveable independently of each other; the first movement mechanism is configured to raise and lower the treatment table and the second movement mechanism is configured to raise and lower the first movement mechanism such that in a lowered position the second movement mechanism is contained within the floor cavity.

Abstract: A workflow management system for radiotherapy treatment of a patient using radiotherapy equipment comprising: a patient radiofrequency identification (RFID) tag and a radiofrequency (RF) detection device, which provides a patient unique identifier matchable to a patient's treatment plan; a plurality of optical markers, wherein in at least one patient optical marker is positioned on the patient and at least one reference optical marker is positioned at a reference point on the radiotherapy equipment; an optical reader to detect each of the plurality of optical markers; wherein the system matches the patient's unique identifier to the patient treatment plan.

Abstract: The present invention introduces a method, apparatus and computer program for magnetic resonance imaging or magnetoencephalography applications in order to control currents of a coil assembly (20), and thus achieving desired magnetic fields precisely in the measuring volume (21). The approach is an algebraic method where a field vector is generated for the test currents of each coil (20). Vector and matrix algebra is applied and a linear set of equations is formed. Field components and their derivatives up to the desired order can be taken into account. Principal component analysis or independent component analysis can be applied for determination of the dominant external interference components. By checking the condition value for the matrix (33, 45), it is possible to investigate whether a reasonable solution of currents for desired magnetic fields is possible to achieve. Finally, solved currents can be installed into a current supply unit (29) feeding the coils of the assembly (20).

Abstract: Methods and systems are provided for protecting a critical structure during the administration of radiation treatment to a patient. A register receives proposed positions for one or more radiation beams with respect to a critical structure. A processor predicts a cumulative dose volume for the critical structure based on the dose distribution, and determines if the cumulative dose volume exceeds a tolerance value. If the cumulative dose volume exceeds the tolerance value, the dose distribution may be translated at least in part based on a relationship between the cumulative dose volume and the dose distribution position.

Abstract: The present invention relates to a novel manner of measuring DC fields using a multi-channel MEG or MKG measuring instrument; and on the other hand, to a manner of eliminating from the measurement result the interference signals caused by the DC currents. The invention combines the monitoring system of a testee's movement and the method for motion correction of the measured signals so that the signals produced by the DC currents of a moving testee's are visible in the final measurement result as a static signal component in a conventional MEG or MKG measurement. In that case, in the measurement, it is not necessary to beforehand prepare oneself for measuring the DC fields.

Abstract: The present invention relates to a frame for attaching to a patient. The present invention also relates to a stereoguide and a member for attaching to a patient. The present invention also relates to a method for manufacturing the frame, member and stereoguide of the present invention. The frame, member and stereoguide are constructed from a composite material comprising a matrix material and electromagnetically inert fibers.

Abstract: An in-line 4D cone beam CT reconstruction algorithm, i.e.