A system and a method for monitoring anatomical changes in a subject in radiation therapy are provided, as well as an arrangement for medical imaging and analysis and a computer program product for carrying out the method. For monitoring anatomical changes in a subject in radiation therapy, the following steps are performed. First anatomical image data and subsequent anatomical image data of the subject are received. The first anatomical image data and the subsequent anatomical image data are analyzed. This analysis comprises registering the subsequent anatomical data to the first anatomical data. Changes between the first anatomical image data and the subsequent anatomical image data are identified as change states, and the identified change states are matched to corresponding qualitative descriptions. A monitoring report is provided, which comprises the qualitative descriptions of the identified changes.
A computing system (SYS) and relates method for supporting radiation therapy planning. An input interface (IF1; UI-I) is provided for receiving input radiation treatment plan templates, or types of such plan templates, for plural radiation treatment plans. A trained machine learning model (M) of the system (SYS) is configured to compute plural dose maps associated with the received radiation treatment plan templates or with the types of such plan templates.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
3.
STRUCTURE CONTOURING, SUCH AS FOR SEGMENTATION OR RADIATION TREATMENT PLANNING, USING A 3D PAINT BRUSH COMBINED WITH AN EDGE-DETECTION ALGORITHM
Techniques are described for contouring of a region of interest based on imaging parameters of spatial imaging data and guided by user input of locations in the spatial imaging data, which may be used for segmentation or radiation treatment planning. An approach is described of combining a new paint brush tool with an edge-detection algorithm to correct for both the jagged contours and the painting routine not being executed often enough. By using an edge-detection algorithm, the user does not need to focus as much attention on moving the mouse accurately because the system will find the true organ boundary (e.g., using the image gradient) automatically, which may also lead to more time savings.
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.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 30/20 - ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
5.
A SYSTEM FOR GENERATING OBJECTIVE FUNCTIONS FOR TREATMENT PLANNING
System (OGS) and related method for generating an objective function for use in radiation treatment, RT, planning. The system may include a machine learning model (M) and a training system (TS) for training the model (M) based on training data. The training data may include previous (at least partial) RT plans, and a user awarded ranking thereof. The model, once trained, may be used as the objective function. The system allows a user to turn, in a defined manner, clinical objectives or goals into a computable objective function which can be used for RT planning.
G06N 3/10 - Interfaces, programming languages or software development kits, e.g. for simulating neural networks
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
6.
PARTICLE THERAPY USING TEMPORO-SPATIAL DOSE HETEROGENEITIES
Systems and methods may be used for protecting healthy tissue in particle therapy. For example, a method may include defining a particle arc range for a radiotherapy treatment of a patient. The method may include generating a spot selection for an arc sequence, including a trajectory for delivering the radiotherapy treatment, for example, based on a temporal dose heterogeneity parameter or a spatial dose heterogeneity parameter. The method may include optimizing fluence of the arc sequence for the radiotherapy treatment, for example, based on an applied temporal dose heterogeneity specific cost function or an applied spatial dose heterogeneity specific cost function.
A method of radiation treatment planning for a radiotherapy system, the method comprising: receiving a first reference objective and a second reference objective, each reference objective representing a goal to be achieved by the radiotherapy system, and the first reference objective comprising a reference dose to be delivered to a reference volume of an anatomical structure, optimising a set of parameters, according to the received first reference objective and the received second reference objective, the set of parameters relating to characteristics of radiation to be delivered by the radiotherapy system, wherein optimising the set of parameters comprises: optimising the set of parameters based on the first reference objective to obtain a dose-volume metric for the anatomical structure, and further optimising the set of parameters based on the second reference objective using the dose-volume metric as constraint, and generating a radiation treatment plan using the further optimised set of parameters.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
8.
SYSTEM AND METHOD FOR RADIATION TREATMENT PLANNING
A computer-implemented method for radiation treatment planning, the method comprising: receiving a reference dose value, wherein the reference dose value is a defined maximum radiation dose within a first region for radiation treatment in a patient; applying an optimization procedure to a treatment plan for radiation treatment of the patient, wherein the optimization procedure seeks to minimize a cost function which is representative of a dose excess value above the reference dose value; and responsive to determining that the dose excess value is below a threshold value: decreasing the reference dose value; and reapplying the optimization procedure to the treatment plan, wherein the optimization procedure seeks to minimize the cost function based on the decreased reference dose value.
A computer-implemented method may be provided to aid in radiation treatment planning, the method comprising: receiving a reference objective, the reference objective representing a goal to be achieved by a radiotherapy system; selecting a cost function associated with the reference objective from a plurality of cost functions, the selected cost function being associated with an assigned initial weight value, the assigned initial weight value corresponding to sensitivity of an example dose distribution relative to changes in the selected cost function; applying an optimization procedure to a radiation treatment plan for radiation treatment in a patient according to the received reference objective, wherein the optimization procedure uses the assigned initial weight value of the selected cost function and seeks to minimize the selected cost function.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
10.
SYSTEM AND METHOD FOR RADIATION TREATMENT PLANNING
A method for radiation treatment planning for delivering radiation therapy by a radiotherapy system, the method comprising: receiving a reference objective, the reference objective representing a goal to be achieved by the radiotherapy system; performing an optimisation procedure, according to the received reference objective, to determine a set of parameters, the set of parameters relating to characteristics of radiation to be delivered by the radiotherapy system, wherein the optimisation procedure comprises: optimising the set of parameters to obtain an achieved value, and responsive to the achieved value not meeting the reference objective, obtaining a relaxed objective using the achieved value and a relaxation value, and determining a configuration of the radiotherapy system using the optimised set of parameters and the relaxed objective.
A computer-implemented method may be provided to aid in radiation treatment planning, the method comprising: receiving treatment plan parameters including a reference dose value for a target region of a patient and a defined dose value for a surrounding region; determining whether the defined dose value for the surrounding region exceeds a threshold; and responsive to determining that the defined dose value for the surrounding region does not exceed the threshold, modifying the defined dose value for the surrounding region, and applying an optimization procedure to a treatment plan for radiation treatment of the patient with the modified dose value for the surrounding region.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
Dose-sparing opportunities may be determined using what are referred to as opportunity dose-volume histogram (ODVH), where an ODVH is modelled based on an anatomy of the patient in an imaging or radiotherapy treatment session and depends to some degree on the treatment modality (e.g., energy of the x-rays or gamma-rays, degrees of freedom in the external beam arrangements, and the ideal target dose patterns).
Systems and methods are disclosed for performing operations comprising: receiving multi-parametric input data representing data associated with a patient; receiving an indication of a disease associated with the patient; processing the multi-parametric input data to generate one or more metrics corresponding to a plurality of different modalities for treating the disease associated with the patient; selecting, based on the one or more metrics, a given modality from the plurality of different modalities to treat the disease associated with the patient; and configuring parameters of the given modality based on a portion of the multi-parametric input data.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
Systems and techniques may be used for determining a line segment to be delivered from a particle beam towards a target. An example technique may include continuously scanning the particle beam at a constant rate from a starting point to an ending point, and determining a plurality of spots located between the starting point and the ending point. The technique may include determining a plurality of beamlets based on the plurality of spots, and determining, using an amount of dose to be delivered via each beamlet, a total amount of dose to be delivered. The technique may include generating a line segment having the starting point and the ending point, the line segment having the total amount of dose to be delivered based on the plurality of beamlets.
Systems and techniques may be used to generate a radiotherapy treatment plan to execute using a particle beam from a continuously rotating gantry towards a target. A technique may include identifying a target location within a tumor of a patient, providing a particle beam configured to deliver radiotherapy treatment to the tumor along a trajectory using at least two energies including a first energy and a second energy, the first energy greater than the second energy, and determining a first location along the trajectory past the target location and a second location before the target location along the trajectory. The technique may include determining a configuration for the particle beam to deliver the first energy to the first location and the second energy to the second location. In some examples, a radiotherapy treatment plan according to the configuration may be output.
Systems and techniques may be used for generating an image using one or more protons. For example, a technique may include detecting, over a time period using two orthogonal two-dimensional detector arrays, a magnetic field corresponding to a proton in motion. The technique may include determining a trajectory of the proton based on the magnetic field over the period of time, and generating a two-dimensional proton image using the trajectory. The two-dimensional proton image may be output for display.
Systems and methods are disclosed for generating radiotherapy machine parameters used in a radiotherapy treatment plan, based on machine learning prediction. The systems and methods include: obtaining three-dimensional image data which indicates target dose areas and organs-at-risk areas of a subject; generating anatomy projection images from the image data, each anatomy projection image providing a view from a respective beam angle of the radiotherapy treatment; using a trained neural network model (trained with corresponding pairs of anatomy projection images and control point images) to generate control point images, each control point image indicating an intensity and aperture(s) of a control point of the radiotherapy treatment to apply at a respective beam angle; and generating a set of final control points for use in the radiotherapy treatment to control a radiotherapy treatment machine, based on optimization of the control points indicated by the generated control point images.
G05B 13/02 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
18.
NEURAL NETWORK FOR GENERATING SYNTHETIC MEDICAL IMAGES
Systems, computer-implemented methods, and computer readable media for generating a synthetic image of an anatomical portion based on an origin image of the anatomical portion acquired by an imaging device using a first imaging modality are disclosed. These systems may be configured to receive the origin image of the anatomical portion acquired by the imaging device using the first imaging modality, receive a convolutional neural network model trained for predicting the synthetic image based on the origin image, and convert the origin image to the synthetic image through the convolutional neural network model. The synthetic image may resemble an imaging of the anatomical portion using a second imaging modality differing from the first imaging modality.
A61B 5/00 - Measuring for diagnostic purposes Identification of persons
A61B 5/055 - Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fieldsMeasuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
System and techniques may be adapted for use in radiotherapy treatment planning. A technique may include determining a set of optimization functions with initial optimization goals, including at least one optimization function depending on LET and at least one optimization function for selecting a dose. The technique may include generating, for example using processing circuitry, a treatment plan via automated multicriteria optimization of the set of optimization functions while preserving the initial optimization goals using the patient information. In some examples, the treatment plan may be output (e.g., stored or displayed).
Systems and techniques may be used for radiotherapy. An example system may include a fixation device arranged to receive and immobilize a patient. The example system may include a first filter arranged to extend along a first portion (e.g., a spine or cranium) of the patient, the first filter attached to the fixation device at a first location, the first filter including a plurality of beam attenuating elements. The example system may include a fixed beam proton delivery system arranged to deliver a therapeutic proton radiation dose attenuated via the first filter to the first portion of the patient.
Systems (500) and methods (700) for verifying a primary dose profile generated by a radiation machine using cloud-based services are disclosed. An exemplary system (500) can include a cloud (530,600) that provides cloud-based services, and a user interface (136) that enables multi-tenant access to the cloud-based services. A file service (610) can extract from a patient (501) DICOM file image information and information about a radiation machine. A dose engine service (620) can determine a secondary radiation dose profile by applying a dose algorithm (624) to the image and the radiation machine information. The applied dose algorithm (624) can be different from the dose algorithm used by the radiation machine to generate the primary dose profile. A dose evaluation service (630) can use the secondary radiation dose profile to verify accuracy of the primary dose profile based on a consistency indicator between the primary and secondary dose profiles.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 30/20 - ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
A computer-implemented image evaluation method for a radiotherapy device, a radiotherapy device and a computer-readable medium are provided. The computer-implemented image-evaluation method comprises obtaining a time series of images of a subject disposed in the radiotherapy device. The computer-implemented image-evaluation method further comprises determining a quality factor for an image of the time series of images. The computer-implemented image-evaluation method further comprises, in response to determining that the quality factor does not meet a condition, generating a computer-executable instruction for adjusting operation of the radiotherapy device.
Methods, systems and computer-readable media for controlling a radiotherapy apparatus are disclosed. A method for controlling a radiotherapy apparatus comprises obtaining a first treatment plan comprising positioning information of a beam shaping apparatus of the radiotherapy apparatus; receiving, during delivery of a radiation therapeutic beam to a target on a patient, information including a positional shift of the target; and generating a revised treatment plan based on the first treatment plan, the generating of the revised treatment plan comprising determining an updated configuration of the beam shaping apparatus from the positioning information of the first treatment plan based on the positional shift of the target.
Methods, systems and computer-readable media for controlling a radiotherapy apparatus are disclosed. A method for controlling a radiotherapy apparatus comprises obtaining a first treatment plan comprising positioning information of a beam shaping apparatus of the radiotherapy apparatus; receiving, during delivery of a radiation therapeutic beam to a target on a patient, information including a positional shift of the target; and generating a revised treatment plan based on the first treatment plan, the generating of the revised treatment plan comprising determining an updated configuration of the beam shaping apparatus from the positioning information of the first treatment plan based on the positional shift of the target.
The present disclosure relates to systems and methods for developing radiotherapy treatment plans though the use of machine learning approaches and neural network components. A neural network is trained using one or more three-dimensional medical images, one or more three-dimensional anatomy maps, and one or more dose distributions to predict a fluence map or a dose map. During training the neural network receives a predicted dose distribution determined by the neural network that is compared to an expected dose distribution. Iteratively the comparison is performed until a predetermined threshold is achieved. The trained neural network is then utilized to provide a three-dimensional dose distribution.
G06N 3/084 - Backpropagation, e.g. using gradient descent
G16H 30/20 - ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
G16H 40/63 - ICT specially adapted for the management or administration of healthcare resources or facilitiesICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for local operation
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
26.
COMPOSITE FIELD SEQUENCING (CFS) FOR PROTON BEAM THERAPY
System and techniques may be adapted for use in composite field sequencing for proton therapy. A technique may include generating a proton therapy plan in a treatment planning system, the proton therapy plan including a plurality of static fields. The technique may include creating a single data file of a single dynamic field representing the plurality of static fields. The single data file may be sent to a proton therapy system for delivery of the single dynamic field. The technique may include receiving a response information related to a dose delivered to a patient by the single dynamic field.
G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
27.
AN ARTIFICIAL INTELLIGENCE SYSTEM TO SUPPORT ADAPTIVE RADIOTHERAPY
The present application describes a computing system, a computer readable medium, and/or related method for supporting decision making in adaptive therapy. An input interface of receives an input image. A machine learning module predicts, based at least in part on the input image, a dose distribution associated with a first planning technique or a first treatment modality. A comparator compares a planned dose distribution as per a current treatment plan with the predicted dose distribution, to obtain a comparison result. The comparison result enables a user to gauge whether an actual re-planning would yield a dosimetric benefit before committing time or computational resources.
Using a computer-implemented intermediary by which contouring performed by two participants, such as two physicians, can be compared. First, contouring performed by each participant can be compared to contouring performed by the intermediary. Then, by way of the common intermediary and a transitive analysis, contouring performed by each participant can be compared.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 30/20 - ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
29.
COMPARING HEALTHCARE PROVIDER CONTOURS USING AUTOMATED TOOL
Using a computer-implemented intermediary by which contouring performed by two participants, such as two physicians, can be compared. First, contouring performed by each participant can be compared to contouring performed by the intermediary. Then, by way of the common intermediary and a transitive analysis, contouring performed by each participant can be compared.
G06T 7/174 - SegmentationEdge detection involving the use of two or more images
G16H 40/20 - ICT specially adapted for the management or administration of healthcare resources or facilitiesICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
Systems and methods are disclosed for performing operations comprising: receiving dose information representing dose delivered during a first radiotherapy treatment fraction; accessing one or more previous dose information representing dose delivered during one or more previous radiotherapy treatment fractions; computing a measure of biologically effective dose (BED) based on a combination of the dose information delivered during a first radiotherapy treatment fraction and the dose delivered during the one or more previous radiotherapy treatment fractions; and performing an isotoxic planning process for delivering a second radiotherapy treatment fraction following the first radiotherapy treatment fraction based on the computed measure of BED.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
31.
DYNAMIC CONTEXTUAL INTERFACES TO ELECTRONIC MEDICAL RECORDS DATABASE
A system and method for presenting a dynamic patient whiteboard may include displaying a custom user interface including the dynamic patient whiteboard. The custom user interface may display a patient list including a plurality of patients and related disease state, cancer type, or treatment protocol, in an example, The dynamic patient whiteboard may include a plurality of oncology-related tasks, and each oncology-related task of the plurality of oncology-related tasks may include a task status. An electronic medical records (EMR) database may be accessed. A processor may be used to determine whether a task status for an oncology-related task has been updated, and in response optionally update the dynamic patient whiteboard to reflect the updated task status. Context information may be displayed for the updated task or other tasks, for example based on a particular user identity.
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Systems and methods may be used for protecting healthy tissue in particle therapy. For example, a method may include defining a particle arc range for a radiotherapy treatment of a patient. The method may include generating a spot selection for an arc sequence, including a trajectory for delivering the radiotherapy treatment, for example, based on a temporal dose heterogeneity parameter or a spatial dose heterogeneity parameter. The method may include optimizing fluence of the arc sequence for the radiotherapy treatment, for example, based on an applied temporal dose heterogeneity specific cost function or an applied spatial dose heterogeneity specific cost function.
Techniques for contouring of a region of interest based on imaging parameters of spatial imaging data and guided by user input of locations in the spatial imaging data, which may be used for segmentation or radiation treatment planning. An approach of combining a new paint brush tool with an edge-detection algorithm to correct for both the jagged contours and the painting routine not being executed often enough. By using an edge-detection algorithm, the user does not need to focus as much attention on moving the mouse accurately because the system will find the true organ boundary (e.g., using the image gradient) automatically, which may also lead to more time savings.
A non-transitory computer readable medium (26) stores instructions executable by at least one electronic processor (20) to perform a radiation therapy (RT) treatment decision method (100) that includes: calculating (102) an initial score (30) for a pre-interventional patient for each RT option of a set of RT options (32), wherein the initial score for each RT option is indicative of likelihood of discontinuation of RT in accordance with that RT option; displaying (104) the initial scores and, via a user interface (28), receiving a selection of at least one RT option from the set of RT options; for each selected RT option: optimizing (106) a RT plan (34) for the patient in accordance with the selected RT treatment option; computing (108) one or more toxicity metrics (36) for the optimized RT plan, and calculating (110) a final score (38) based on the one or more toxicity metrics for the optimized RT plan, the final score being indicative of likelihood of discontinuation of the RT treatment in accordance with the optimized RT plan; and displaying (112) the final score for the at least one selected RT option and, via the user interface, receiving a selection of a final RT option.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 50/30 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indicesICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for individual health risk assessment
35.
Planning radiation therapy using a personalized hematologic risk score
Thereto a method and a system for planning radiation therapy are provided, as well as an arrangement for radiation therapy planning and a computer program product for carrying out the method. For planning the radiation therapy, the following steps are performed. Patient data of a subject to be treated is received as well as image data of the subject to be treated. The image data comprises anatomical image data of one or more organs at risk associated with the functioning of the immune system. Next, the patient 122 data and the image data are processed to obtain a risk score for the one or more organs at risk associated with the functioning of the immune system. The risk score is indicative of the risk of hematologic toxicity in the subject to be treated in response to the radiation therapy. Then the radiation therapy treatment is planned using the obtained risk score.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
36.
System, method and computer program for determining a radiation therapy plan for a radiation therapy system
The invention relates to a system for determining a radiation therapy plan for a radiation therapy system (100), comprising a multi-leaf collimator. The radiation therapy plan determination system (110) comprises a therapy system characteristics providing unit (111), wherein the characteristics comprise possible leaf positions and possible radiation fluence values, a planning objectives providing unit (112), wherein the planning objectives are indicative of a desired therapeutic radiation dose distribution, an optimization function providing unit (113), wherein the optimization function is indicative of a deviation of a radiation dose distribution from the planning objectives and of an uncertainty of the radiation dose distribution at edges of the possible apertures, and a therapy plan optimization unit (114) adapted to determine a sequence of possible apertures and possible radiation fluence values for which the optimization function is optimized. Thus, an optimal therapy plan can be provided for each individual patient.
Systems and methods are disclosed for generating radiotherapy machine parameters used in a radiotherapy treatment plan, based on machine learning prediction. The systems and methods include: obtaining three-dimensional image data which indicates target dose areas and organs-at-risk areas of a subject; generating anatomy projection images from the image data, each anatomy projection image providing a view from a respective beam angle of the radiotherapy treatment; using a trained neural network model (trained with corresponding pairs of anatomy projection images and control point images) to generate control point images, each control point image indicating an intensity and aperture(s) of a control point of the radiotherapy treatment to apply at a respective beam angle; and generating a set of final control points for use in the radiotherapy treatment to control a radiotherapy treatment machine, based on optimization of the control points indicated by the generated control point images.
Systems and methods are disclosed for performing operations comprising: receiving a plurality of training images representing different phases of a periodic motion of a target region in a patient; applying a model to the plurality of training images to generate a lower-dimensional feature space representation of the plurality of training images; clustering the lower-dimensional feature space representation of the plurality of training images into a plurality of groups corresponding to the different phases of the periodic motion; and classifying a motion phase associated with a new image of the target region in the patient based on the plurality of groups of the clustered lower-dimensional feature space representation of the plurality of training images.
G06F 18/21 - Design or setup of recognition systems or techniquesExtraction of features in feature spaceBlind source separation
G06F 18/2135 - Feature extraction, e.g. by transforming the feature spaceSummarisationMappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
G06F 18/214 - Generating training patternsBootstrap methods, e.g. bagging or boosting
Systems and methods are disclosed for performing operations comprising: receiving multi-parametric input data representing data associated with a patient; receiving an indication of a disease associated with the patient; processing the multi-parametric input data to generate one or more metrics corresponding to a plurality of different modalities for treating the disease associated with the patient; selecting, based on the one or more metrics, a given modality from the plurality of different modalities to treat the disease associated with the patient; and configuring parameters of the given modality based on a portion of the multi-parametric input data.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
Systems and methods for generating a radiotherapy treatment plan using information about gantry angle-indexed dose (GAID) variation are discussed. An exemplary system can include an interface to receive a beam model for use in the radiation machine, and a processor that can determine, for the radiation machine, a GAID variation represented by a plurality of radiation doses at different gantry angles. The processor can determine a radiation treatment plan for the patient using the beam model and the GAID variation.
Systems and techniques may be used for generating an image using one or more protons. For example, a technique may include detecting, over a time period using two orthogonal two-dimensional detector arrays, a magnetic field corresponding to a proton in motion. The technique may include determining a trajectory of the proton based on the magnetic field over the period of time, and generating a two-dimensional proton image using the trajectory. The two-dimensional proton image may be output for display.
Systems and techniques may be used to generate a radiotherapy treatment plan to execute using a particle beam from a continuously rotating gantry towards a target. A technique may include identifying a target location within a tumor of a patient, providing a particle beam configured to deliver radiotherapy treatment to the tumor along a trajectory using at least two energies including a first energy and a second energy, the first energy greater than the second energy, and determining a first location along the trajectory past the target location and a second location before the target location along the trajectory. The technique may include determining a configuration for the particle beam to deliver the first energy to the first location and the second energy to the second location. In some examples, a radiotherapy treatment plan according to the configuration may be output.
Systems and techniques may be used for determining a line segment to be delivered from a particle beam towards a target. An example technique may include continuously scanning the particle beam at a constant rate from a starting point to an ending point, and determining a plurality of spots located between the starting point and the ending point. The technique may include determining a plurality of beamlets based on the plurality of spots, and determining, using an amount of dose to be delivered via each beamlet, a total amount of dose to be delivered. The technique may include generating a line segment having the starting point and the ending point, the line segment having the total amount of dose to be delivered based on the plurality of beamlets.
Systems and methods are disclosed for monitoring anatomic position of a human subject and modifying a radiotherapy treatment based on anatomic position changes, as determined with a regression model trained to estimate movement of a region of interest. Example operations for movement monitoring and therapy control include: obtaining 3D image data for a subject, which provides a reference volume and at least one defined region of interest; obtaining real-time 2D image data corresponding to the subject, captured during the radiotherapy treatment session; extracting features from the 2D image data; producing a relative motion estimation of a region of interest with a machine learning regression model, the model trained to estimate a spatial transformation from the 2D image data based on training from the reference volume; and controlling a radiotherapy beam of a radiotherapy machine used in the radiotherapy session, based on the relative motion estimation.
Systems and methods are disclosed for monitoring anatomic position of a human subject for a radiotherapy treatment session, based on use of a regression model trained to estimate movement of a region of interest based on 2D image data input. Example operations for movement estimation include: obtaining 3D image data for a subject, which provides a reference volume and at least one defined region of interest; obtaining 2D image data corresponding to the subject, captured in real time (during the radiotherapy treatment session); extracting features from the 2D image data; analyzing the extracted features with a machine learning regression model, trained to estimate a spatial transformation in the three dimensions of the reference volume; and outputting and using a relative motion estimation of the at least one region of interest, produced from the machine learning regression model, the relative motion estimation being estimated from the extracted features.
Systems and methods are disclosed for monitoring anatomic position of a human subject for a radiotherapy treatment session, and optionally modifying a radiotherapy treatment based on anatomic position changes. Example operations for movement monitoring and therapy control include: obtaining 3D image data for a subject, which provides a reference volume and at least one defined region of interest; obtaining real-time 2D image data corresponding to the subject, captured during the radiotherapy treatment session; extracting features from the 2D image data; producing a relative motion estimation of a region of interest with a machine learning regression model, the model trained to estimate a spatial transformation from the 2D image data based on training from the reference volume; and controlling a radiotherapy beam of a. radiotherapy machine used in the radiotherapy session, based on the relative motion estimation.
Techniques for generating a synthetic computed tomography (sCT) image from a cone-beam computed tomography (CBCT) image are provided. The techniques include receiving a CBCT image of a subject; generating, using a generative model, a sCT image corresponding to the CBCT image, the generative model trained based on one or more deformable offset layers in a generative adversarial network (GAN) to process the CBCT image as an input and provide the sCT image as an output; and generating a display of the sCT image for medical analysis of the subject.
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
Systems and methods arc disclosed for generating radio-therapy treatment machine parameters based on projection images of a target anatomy. The systems and methods include receiving an image depicting an anatomy of a subject: generating a first projection image based on the received image that represents a view of the anatomy from a first gantry angle of tire radiotherapy treatment machine; applying a machine learning model to the first projection image to estimate a first graphical aperture image representation of multi-leaf collimator (MLC) leaf positions at the first gantry angle and the radiation intensity at that angle, the machine learning model being trained to establish a relationship between projection images representing different views of a patient anatomy and respective graphical aperture image representations of the MLC leaf positions at different gantry angles corresponding to the different views: and generating radiotherapy treatment machine parameters based on the first graphical aperture image representation.
Systems and methods are disclosed for performing operations comprising: receiving first and second images depicting an anatomy of a subject; applying a trained machine learning model to a first data set associated with the first image and a second data set associated with the second image to estimate a biomechanically accurate DVF representing a mapping of pixels or voxels from the first image to the second image, the machine learning model trained to establish a relationship between a plurality of pairs of data sets associated with images of a patient anatomy and respective biomechanically accurate DVF representations of pixel or voxel mapping between the plurality of pairs of data sets; applying the estimated biomechanically accurate DVF to deform a dose from a previous treatment session.
Systems and methods are disclosed for performing operations comprising: receiving first and second images depicting an anatomy of a subject; applying a trained machine learning model to a first data set associated with the first image and a second data set associated with the second image to estimate a biomechanically accurate DVF representing a mapping of pixels or voxels from the first image to the second image, the machine learning model trained to establish a relationship between a plurality of pairs of data sets associated with images of a patient anatomy and respective biomechanically accurate DVF representations of pixel or voxel mapping between the plurality of pairs of data sets; applying the estimated biomechanically accurate DVF to deform a dose from a previous treatment session.
In providing radiation therapy (RT) support, a patient specific toxicity risk is estimated for a RT side effect using a Bayesian network that receives as inputs values of biomarkers of the patient. A patient-specific RT plan is optimized with respect to parameters including the patient-specific toxicity risk. During delivery of RT according to the plan, at least one updated value is received for the biomarkers of the patient, and an updated patient-specific toxicity risk is estimated using the Bayesian network with the updated value(s). The Bayesian network biomarker nodes and a toxicity risk node representing the patient specific toxicity risk, and directed arcs with arc weights representing strengths of interdependencies between the nodes connected by the directed arcs. A graphical user interface (GUI) is provided via which a clinician may interact with the Bayesian network. A test recommendation may be initiated or updated for scheduling of a patient test based on the updated patient-specific toxicity risk.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 50/30 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indicesICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for individual health risk assessment
52.
Planning apparatus for planning a radiation therapy
The invention relates to a planning apparatus for planning a radiation therapy. A medical image, in which a target to be irradiated is indicated, is reformatted based on ray geometries to be used during the radiation therapy to be planned, resulting in several reformatted medical images. Radiation therapy parameters being indicative of intensities of rays 5 to be used for irradiating a target 4 are determined based on the reformatted medical images by using a neural network unit. This allows to determine high quality radiation therapy parameters and hence allows for an improved planning of a radiation therapy. In particular, radiation and absorptions physics can be captured better, which can lead to the improved quality.
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.
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.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 30/20 - ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
55.
DETERMINING HEMATOLOGIC TOXICITY RISK FOLLOWING RADIOTHERAPY
Described is a computer-implemented method for determining a risk of hematologic toxicity in a subject to be treated with radiotherapy. The method involves processing treatment data including a prescribed dose of radiation for the subject and imaging data displaying radiation- sensitive tissues such as bone marrow and/or lymphoid organs in the subject to determine a received dose of radiation to be delivered to the radiation-sensitive tissues. The method further comprises processing patient data such as blood cell counts and the received dose of radiation to obtain a risk of hematologic toxicity in the subject in response to the radiotherapy. Also provided is a system and computer program product for performing the method.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
System and methods may be used for arc fluence optimization without iteration to arc sequence generation. A method may include defining a particle arc range for a radiotherapy treatment of a patient, and generating an arc sequence, including a set of parameters for delivering the radiotherapy treatment, without requiring a dose calculation. The method may include optimizing fluence of the arc sequence for the radiotherapy treatment without iterating back to arc sequence generation, and outputting the fluence optimized arc sequence for use in the radiotherapy treatment.
Systems and methods may be used for fluence optimization without iteration to sequence generation. For example, arc sequence generation may occur before arc fluence optimization. A method may include generating an arc sequence, including a set of parameters for delivering a radiotherapy treatment, without requiring a dose calculation, wherein the set of parameters includes an organ at risk sparing level. The method may include optimizing fluence of the arc sequence for a radiotherapy treatment without iterating back to arc sequence generation. The fluence optimized arc sequence may be output for use in the radiotherapy treatment.
System and methods may be used for arc fluence optimization without iteration to arc sequence generation. A method may include defining a particle arc range for a radiotherapy treatment of a patient, and generating an arc sequence, including a set of parameters for delivering the radiotherapy treatment, without requiring a dose calculation. The method may include optimizing fluence of the arc sequence for the radiotherapy treatment without iterating back to arc sequence generation, and outputting the fluence optimized arc sequence for use in the radiotherapy treatment.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
59.
METHOD TO OPTIMALLY SPLITTING ARCS IN MODULATED ARC THERAPY (MAT) PLANS
A non-transitory computer readable medium (26) stores instructions executable by at least one electronic processor (20) to perform a method (100, 200) of identifying possible arc segments for removal in a modulated arc therapy plan. The method includes: iteratively optimizing a modulated arc therapy plan for an initial arc segment; and computing a geometric freedom (GF) metric for each control point (CP) of the initial arc segment.
Described is a computer-implemented method for identifying responsiveness to therapy for a subject suffering from cancer. The method involves determining values of biomarkers such as the levels of TREX1, PD-L1 and/or immune cell infiltration in a cancerous lesion. The biomarker values are processed to obtain a score indicative of responsiveness of the cancerous lesion to combined radio- and immunotherapy treatment. The method may obtain scores for multiple treatment modalities (such as different doses and/or fractionations of radiotherapy) and/or different cancer lesions in the subject. Also provided is a system and computer program product for performing the method.
C12Q 1/6886 - Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material for cancer
G16H 20/10 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 50/30 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indicesICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for individual health risk assessment
61.
Machine learning optimization of fluence maps for radiotherapy treatment
Systems and methods are disclosed for generating fluence maps for a radiotherapy treatment plan that uses machine learning prediction. The systems and methods include identifying image data that indicates treatment constraints for target dose areas and organs at risk areas in an anatomy of the subject, generating anatomy projection images that represent a view of the subject from respective beam angles, using a trained neural network model to generate the computer-simulated fluence map representations based on the anatomy projection images, where the fluence maps indicate a fluence distribution of the radiotherapy treatment at each of the beam angles.
Systems and methods are disclosed for generating fluence maps for a radiotherapy treatment plan that uses machine learning prediction. The systems and methods include identifying image data that indicates treatment constraints for target dose areas and organs at risk areas in an anatomy of the subject, generating anatomy projection images that represent a view of the subject from respective beam angles, using a trained neural network model to generate the computer-simulated fluence map representations based on the anatomy projection images, where the fluence maps indicate a fluence distribution of the radiotherapy treatment at each of the beam angles.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
Systems and methods are provided for generating a pseudo-CT prediction model that can be used to generate pseudo-CT images. An exemplary system may include a processor configured to retrieve training data including at least one MR image and at least one CT image for each of a plurality of training subjects. For each training subject, the processor may extract a plurality of features from each image point of the at least one MR image, create a feature vector for each image point based on the extracted features, and extract a CT value from each image point of the at least one CT image. The processor may also generate the pseudo-CT prediction model based on the feature vectors and the CT values of the plurality of training subjects.
A61B 5/00 - Measuring for diagnostic purposes Identification of persons
A61B 5/055 - Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fieldsMeasuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
A61B 90/00 - Instruments, implements or accessories specially adapted for surgery or diagnosis and not covered by any of the groups , e.g. for luxation treatment or for protecting wound edges
G16H 30/20 - ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
G16H 50/50 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
64.
AUTOMATED DETECTION OF LUNG CONDITIONS FOR MONITORING THORACIC PATIENTS UNDERTGOING EXTERNAL BEAM RADIATION THERAPY
A computerized system (SRS) for radiation therapy support. The system comprises an input interface (IN) for receiving an input image acquired by an imaging apparatus (IA1). The input image represents a region of interest (ROI) internal of a patient (PAT) and acquired before delivery of a dose fraction by a radiation therapy delivery apparatus (RTD). A pre-trained machine learning unit (MLU) of the system is configured to process the input image to detect a medical condition. A communication component (RC) of the system is configured to provide, based on the detected medical condition, an indication for one or more clinical actions to be performed in relation to the patient.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 40/67 - ICT specially adapted for the management or administration of healthcare resources or facilitiesICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
A system and a method for monitoring anatomical changes in a subject in radiation therapy are provided, as well as an arrangement for medical imaging and analysis and a computer program product for carrying out the method. For monitoring anatomical changes in a subject in radiation therapy, the following steps are performed. First anatomical image data and subsequent anatomical image data of the subject are received. The first anatomical image data and the subsequent anatomical image data are analyzed. This analysis comprises registering the subsequent anatomical data to the first anatomical data. Changes between the first anatomical image data and the subsequent anatomical image data are identified as change states, and the identified change states are matched to corresponding qualitative descriptions. A monitoring report is provided, which comprises the qualitative descriptions of the identified changes.
A statistical learning technique that does not rely upon paired imaging information is described herein. The technique may be computer-implemented and may be used in order to train a statistical learning model to perform image synthesis, such as in support of radiation therapy treatment planning. In an example, a trained statistical learning model may include a convolutional neural network established as a generator convolutional network, and the generator may be trained at least in part using a separate convolutional neural network established as a discriminator convolutional network. The generator convolutional network and the discriminator convolutional network may form an adversarial network architecture for use during training. After training, the generator convolutional network may be provided for use in synthesis of images, such as to receive imaging data corresponding to a first imaging modality type, and to synthesize imaging data corresponding to a different, second imaging modality type.
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
Using a computer-implemented intermediary by which contouring performed by two participants, such as two physicians, can be compared. First, contouring performed by each participant can be compared to contouring performed by the intermediary. Then, by way of the common intermediary and a transitive analysis, contouring performed by each participant can be compared.
Using a computer-implemented intermediary by which contouring performed by two participants, such as two physicians, can be compared. First, contouring performed by each participant can be compared to contouring performed by the intermediary. Then, by way of the common intermediary and a transitive analysis, contouring performed by each participant can be compared.
Using a computer-implemented intermediary by which contouring performed by two participants, such as two physicians, can be compared. First, contouring performed by each participant can be compared to contouring performed by the intermediary. Then, by way of the common intermediary and a transitive analysis, contouring performed by each participant can be compared.
Systems and techniques may be used to estimate a patient state during a radiotherapy treatment. For example, a method may include generating a dictionary of expanded potential patient measurements and corresponding potential patient states using a preliminary motion model. The method may include training, using a machine learning technique, a correspondence motion model relating an input patient measurement to an output patient state using the dictionary. The method may include estimating, using a processor, the patient state corresponding to an input image using the correspondence motion model.
G16H 50/50 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 30/20 - ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
Systems and methods are disclosed for generating radiotherapy treatment machine parameters based on projection images of a target anatomy. The systems and methods include operations including receiving a set of pairs of image data for each gantry angle of a radiotherapy treatment machine, wherein each pair of the set of pairs comprises a given projection image that represents a view of an anatomy of a subject from a given gantry angle and a given graphical aperture image of multi-leaf collimator (MLC) leaf positions at the given gantry angle based on the given projection image; training a generative adversarial network (GAN) model based on the set of pairs of image data for each gantry angle; and using the trained GAN model to predict an aperture image of MLC leaf positions for a desired gantry angle based on a projection image that represents a view of an anatomical region of interest.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
Systems and methods are disclosed for generating radiotherapy treatment machine parameters based on projection images of a target anatomy. The systems and methods include operations including receiving a set of pairs of image data for each gantry angle of a radiotherapy treatment machine, wherein each pair of the set of pairs comprises a given projection image that represents a view of an anatomy of a subject from a given gantry angle and a given graphical aperture image of multi-leaf collimator (MLC) leaf positions at the given gantry angle based on the given projection image; training a generative adversarial network (GAN) model based on the set of pairs of image data for each gantry angle; and using the trained GAN model to predict an aperture image of MLC leaf positions for a desired gantry angle based on a projection image that represents a view of an anatomical region of interest.
Systems and methods are disclosed for generating radiotherapy treatment machine parameters based on projection images of a target anatomy. The systems and methods include operations including receiving a set of pairs of image data for each gantry angle of a radiotherapy treatment machine, wherein each pair of the set of pairs comprises a given projection image that represents a view of an anatomy of a subject from a given gantry angle and a given graphical aperture image of multi-leaf collimator (MLC) leaf positions at the given gantry angle based on the given projection image; training a generative adversarial network (GAN) model based on the set of pairs of image data for each gantry angle; and using the trained GAN model to predict an aperture image of MLC leaf positions for a desired gantry angle based on a projection image that represents a view of an anatomical region of interest.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
Systems and methods for generating a radiotherapy treatment plan using information about gantry angle-indexed dose (GAID) variation are discussed. An exemplary system can include an interface to receive a beam model for use in the radiation machine, and a processor that can determine, for the radiation machine, a GAID variation represented by a plurality of radiation doses at different gantry angles. The processor can determine a radiation treatment plan for the patient using the beam model and the GAID variation.
Techniques for enhancing image segmentation with the integration of deep learning are disclosed herein. An example method for atlas-based segmentation using deep learning includes: applying a deep learning model to a subject image to identify an anatomical feature, registering an atlas image to the subject image, using the deep learning segmentation data to improve a registration result, generating a mapped atlas, and identifying the feature in the subject image using the mapped atlas. Another example method for training and use of a trained machine learning classifier, in an atlas-based segmentation process using deep learning, includes: applying a deep learning model to an atlas image, training a machine learning model classifier using data from applying the deep learning model, estimating structure labels of areas of the subject image, and defining structure labels by combining the estimated structure labels with labels produced from atlas-based segmentation on the subject image.
Systems and techniques may be used to estimate a relative motion of patient anatomy using a deep learning network during a radiotherapy treatment. For example, a method may include using a first deep neural network to relate input real-time partial patient measurements and a patient model including a reference volume to output patient states. The method may include using a second deep neural network to relate the patient states and the reference volume to relative motion information between the patient states and the reference volume. The deep neural networks may be used in real time to estimate a relative motion corresponding to an input image.
G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
G06T 7/246 - Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G06N 3/04 - Architecture, e.g. interconnection topology
Embodiments disclose a method and system for segmenting medical images. In certain embodiments, the system comprises a database configured to store a plurality of medical images acquired by an image acquisition device. The plurality of images include at least one first medical image of an object, and a second medical image of the object, each first medical image associated with a first structure label map. The system further comprises a processor that is configured to register the at least one first medical image to the second medical image, determine a classifier model using the registered first medical image and the corresponding first structure label map, and determine a second structure label map associated with the second medical image using the classifier model.
Systems, computer-implemented methods, and computer readable media for generating a synthetic image of an anatomical portion based on an origin image of the anatomical portion acquired by an imaging device using a first imaging modality are disclosed. These systems may be configured to receive the origin image of the anatomical portion acquired by the imaging device using the first imaging modality, receive a convolutional neural network model trained for predicting the synthetic image based on the origin image, and convert the origin image to the synthetic image through the convolutional neural network model. The synthetic image may resemble an imaging of the anatomical portion using a second imaging modality differing from the first imaging modality.
A61B 5/00 - Measuring for diagnostic purposes Identification of persons
A61B 5/055 - Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fieldsMeasuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
Systems and techniques may be used to estimate a real-time patient state during a radiotherapy treatment using a magnetic resonance linear accelerator (MR-Linac). For example, a method may include generating a dictionary of expanded potential patient measurements and corresponding potential patient states using a preliminary motion model. The method may include training, using a machine learning technique, a correspondence motion model relating an input patient measurement to an output patient state using the dictionary. The method may include estimating, using a processor, the patient state corresponding to a 2D MR image using the correspondence motion model. The method may include directing radiation therapy, using the MR-Linac, to a target according to the patient state.
A radiation therapy delivery device console (50) controls a radiation therapy delivery device (36) and an imaging device (40, 42), and further performs adaptive radiotherapy (ART) recommendation as follows. The imaging device is controlled to acquire a current image (44) of a patient. At least one perturbation of the current image is determined compared with a radiation therapy planning image (1) from which a radiation therapy plan (22) for the patient has been generated. An ART recommendation score is computed, indicating whether ART should be performed, based on the determined at least one perturbation. A recommendation is displayed as to whether ART should be performed based on the computed ART recommendation score, or an alarm is displayed conditional upon the computed ART recommendation score satisfying an ART recommendation criterion.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
81.
PREDICTING RADIOTHERAPY CONTROL POINTS USING PROJECTION IMAGES
Systems and methods are disclosed for generating radiotherapy treatment machine parameters based on projection images of a target anatomy. The systems and methods include receiving an image depicting an anatomy of a subject; generating a first projection image based on the received image that represents a view of the anatomy from a first gantry angle of the radiotherapy treatment machine; applying a machine learning model to the first projection image to estimate a first graphical aperture image representation of multi-leaf collimator (MLC) leaf positions at the first gantry angle and the radiation intensity at that angle, the machine learning model being trained to establish a relationship between projection images representing different views of a patient anatomy and respective graphical aperture image representations of the MLC leaf positions at different gantry angles corresponding to the different views; and generating radiotherapy treatment machine parameters based on the first graphical aperture image representation.
Techniques for generating a synthetic computed tomography (sCT) image from a cone-beam computed tomography (CBCT) image are provided. The techniques include receiving a CBCT image of a subject; generating, using a generative model, a sCT image corresponding to the CBCT image, the generative model trained based on one or more deformable offset layers in a generative adversarial network (GAN) to process the CBCT image as an input and provide the sCT image as an output; and generating a display of the sCT image for medical analysis of the subject.
Embodiments of the disclosure may be directed to an image processing system configured to receive a medical image of a region of a subject's body taken at a first time and to receive a surface image of an exterior portion of the region of the subject's body taken at the first time. The image processing may also be configured to receive a medical image of the region of the subject's body taken at a second time and to register the medical image taken at the first time, the surface image taken at the first time, and the medical image taken at the second time.
A61B 5/055 - Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fieldsMeasuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
A61B 90/00 - Instruments, implements or accessories specially adapted for surgery or diagnosis and not covered by any of the groups , e.g. for luxation treatment or for protecting wound edges
84.
A METHOD OF PROVIDING PROTON RADIATION THERAPY UTILIZING PERIODIC MOTION
Techniques are described herein for delivering a particle beam from a continuously rotating gantry towards a target according to a determined patient state. The determined patient state and an identified gantry angle of a gantry may be used to deliver a set of beamlets (e.g., a pattern of radiation dose) to the target. The particle beam may rotate through a range of gantry angles. The set of beamlets may be delivered continuously while the gantry rotates.
Techniques are described herein for delivering a particle beam from a continuously rotating gantry towards a target according to a determined patient state. The determined patient state and an identified gantry angle of a gantry may be used to deliver a set of beamlets (e.g., a pattern of radiation dose) to the target. The particle beam may rotate through a range of gantry angles. The set of beamlets may be delivered continuously while the gantry rotates.
Techniques for generating cancer registry records are provided. The techniques include obtaining a plurality of rules that define cancer registry record generation as a function of patient health records; obtaining one or more electronic health records associated with a patient that include cancer related treatment information; processing the cancer related treatment information in the one or more electronic health records to generate a cancer registry record for the patient that represents a portion of the cancer related treatment information; determining that the cancer registry record includes insufficient cancer related treatment information; and updating the cancer registry record to address the insufficient cancer related treatment information by evaluating the cancer related treatment information against the plurality of rules.
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 70/20 - ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
Techniques for generating cancer registry records are provided. The techniques include obtaining a plurality of rules that define cancer registry record generation as a function of patient health records; obtaining one or more electronic health records associated with a patient that include cancer related treatment information; processing the cancer related treatment information in the one or more electronic health records to generate a cancer registry record for the patient that represents a portion of the cancer related treatment information; determining that the cancer registry record includes insufficient cancer related treatment information; and updating the cancer registry record to address the insufficient cancer related treatment information by evaluating the cancer related treatment information against the plurality of rules.
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 50/50 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
G16H 50/30 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indicesICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for individual health risk assessment
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16B 50/30 - Data warehousingComputing architectures
Techniques are described herein for delivering a particle beam composed of a plurality of beamlets from a continuously rotating gantry towards a target, by determining a plurality of predefined spots on the target and configuring them into a set of smaller spots on the outside of the target and a set of larger spots on the inside of the target, optimizing the delivery of the rotating particle beam such that the inside edge and the outside edge of the arc of the rotating beam are delivered to the spots located at the center of the target, and the central component of the arc of the beam is delivered to the spots located at the outside of the target.
Techniques are described herein for delivering a particle beam composed of a plurality of beamlets from a continuously rotating gantry towards a target, by determining a plurality of predefined spots on the target and configuring them into a set of smaller spots on the outside of the target and a set of larger spots on the inside of the target, optimizing the delivery of the rotating particle beam such that the inside edge and the outside edge of the arc of the rotating beam are delivered to the spots located at the center of the target, and the central component of the arc of the beam is delivered to the spots located at the outside of the target.
Systems and techniques may be used to estimate a relative motion of patient anatomy using a deep learning network during a radiotherapy treatment. For example, a method may include using a first deep neural network to relate input real-time partial patient measurements and a patient model including a reference volume to output patient states. The method may include using a second deep neural network to relate the patient states and the reference volume to relative motion information between the patient states and the reference volume. The deep neural networks may be used in real time to estimate a relative motion corresponding to an input image.
Systems and techniques may be used to estimate a relative motion of patient anatomy using a deep learning network during a radiotherapy treatment. For example, a method may include using a first deep neural network to relate input real-time partial patient measurements and a patient model including a reference volume to output patient states. The method may include using a second deep neural network to relate the patient states and the reference volume to relative motion information between the patient states and the reference volume. The deep neural networks may be used in real time to estimate a relative motion corresponding to an input image.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Systems and methods include training a deep convolutional neural network (DCNN) to reduce one or more artifacts using a projection space or an image space approach. In a projection space approach, a method can include collecting at least one artifact contaminated cone beam computed tomography (CBCT) projection space image, and at least one corresponding artifact reduced, CBCT projection space image from each patient in a group of patients, and using the artifact contaminated and artifact reduced CBCT projection space images to train a DCNN to reduce artifacts in a projection space image. In an image space approach, a method can include collecting a plurality of CBCT patient anatomical images and corresponding registered computed tomography anatomical images from a group of patients, and using the plurality of CBCT anatomical images and corresponding artifact reduced computed tomography anatomical images to train a DCNN to remove artifacts from a CBCT anatomical image.
A61B 6/00 - Apparatus or devices for radiation diagnosisApparatus or devices for radiation diagnosis combined with radiation therapy equipment
G06K 9/66 - Methods or arrangements for recognition using electronic means using simultaneous comparisons or correlations of the image signals with a plurality of references, e.g. resistor matrix references adjustable by an adaptive method, e.g. learning
Systems and techniques may be used to estimate a patient state during a radiotherapy treatment. For example, a method may include generating a dictionary of expanded potential patient measurements and corresponding potential patient states using a preliminary motion model. The method may include training, using a machine learning technique, a correspondence motion model relating an input patient measurement to an output patient state using the dictionary. The method may include estimating, using a processor, the patient state corresponding to an input image using the correspondence motion model.
G16H 50/50 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
G16H 30/20 - ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
Systems and techniques may be used to estimate a real-time patient state during a radiotherapy treatment using a magnetic resonance linear accelerator (MR-Linac). For example, a method may include generating a dictionary of expanded potential patient measurements and corresponding potential patient states using a preliminary motion model. The method may include training, using a machine learning technique, a correspondence motion model relating an input patient measurement to an output patient state using the dictionary. The method may include estimating, using a processor, the patient state corresponding to a 2D MR image using the correspondence motion model. The method may include directing radiation therapy, using the MR-Linac, to a target according to the patient state.
Systems and techniques may be used to estimate a patient state during a radiotherapy treatment. For example, a method may include generating a dictionary of expanded potential patient measurements and corresponding potential patient states using a preliminary motion model. The method may include training, using a machine learning technique, a correspondence motion model relating an input patient measurement to an output patient state using the dictionary. The method may include estimating, using a processor, the patient state corresponding to an input image using the correspondence motion model.
Systems and techniques may be used to estimate a real-time patient state during a radiotherapy treatment using a magnetic resonance linear accelerator (MR-Linac). For example, a method may include generating a dictionary of expanded potential patient measurements and corresponding potential patient states using a preliminary motion model. The method may include training, using a machine learning technique, a correspondence motion model relating an input patient measurement to an output patient state using the dictionary. The method may include estimating, using a processor, the patient state corresponding to a 2D MR image using the correspondence motion model. The method may include directing radiation therapy, using the MR-Linac, to a target according to the patient state.
The present disclosure relates to a method for use in adaptive radiotherapy and a treatment planning device. The method may comprise accessing a first medical image and a second medical image that represent a region of interest of a patient at different times. Each medical image is segmented into a target region and at least one non-target region. The method may further comprise accessing a deformation vector field including a plurality of vectors, wherein each vector defines a geometric transformation to map a respective voxel in the first medical image to a corresponding voxel in the second medical image. The method may further comprise generating a modified deformation vector field by: identifying a first vector in the deformation vector field that maps a voxel in the first medical image to a voxel that is in a non-target region in the second medical image; and determining whether the first vector causes a distance between the mapped voxel and the target region to increase and, if so, reducing the magnitude of the first vector. The method may further comprise post-processing the modified deformation vector field to compensate for changes in the shape or size of the target region.
Systems, computer-implemented methods, and computer readable media for generating a synthetic image of an anatomical portion based on an origin image of the anatomical portion acquired by an imaging device using a first imaging modality are disclosed. These systems may be configured to receive the origin image of the anatomical portion acquired by the imaging device using the first imaging modality, receive a convolutional neural network model trained for predicting the synthetic image based on the origin image, and convert the origin image to the synthetic image through the convolutional neural network model. The synthetic image may resemble an imaging of the anatomical portion using a second imaging modality differing from the first imaging modality.
A61B 5/055 - Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fieldsMeasuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
A61B 5/00 - Measuring for diagnostic purposes Identification of persons
G01R 33/56 - Image enhancement or correction, e.g. subtraction or averaging techniques
An image segmentation method is disclosed. The method includes receiving a plurality of atlases and a subject image, each atlas including an atlas image showing a structure of interest and associated structure delineations, the subject image being acquired by an image acquisition device and showing the structure of interest. The method further includes calculating, by an image processor, mapped atlases by registering the respective atlases to the subject image, and determining, by the image processor, a first structure label map for the subject image based on the mapped atlases. The method also includes training, by the image processor, a structure classifier using a subset of the mapped atlases, and determining, by the image processor, a second structure label map for the subject image by applying the trained structure classifier to one or more subject image points in the subject image. The method additional includes combining, by the image processor, the first label map and the second label map to generate a third label map representative of the structure of interest.
Techniques for generating radiotherapy treatment plans and establishing machine learning models for the generation and optimization of radiotherapy dose data are disclosed. An example method for generating a radiotherapy dose distribution using a generative model, trained in a generative adversarial network, includes: receiving anatomical data of a human subject that indicates a mapping of an anatomical area for radiotherapy treatment; generating radiotherapy dose data corresponding to the mapping with use of the trained generative model, as the generative model processes the anatomical data as an input and provides the dose data as output; and identifying the radiotherapy dose distribution for the radiotherapy treatment of the human subject based on the dose data. Another example method for training of the generative model includes establishing values of the generative model and a discriminative model of the generative adversarial network using adversarial training, including in a conditional generative adversarial network arrangement.
