System and method for radiation treatment planning

Abstract

Disclosed is a computer-implemented method for providing a radiation treatment planning tool comprising providing input data comprising patient anatomy and / or geometry data and prescription data as input for an acceptability model; and providing, making use of the acceptability model, at least one of: a proposed radiation treatment plan, a predicted acceptability for a candidate radiation treatment plan and / or the proposed radiation treatment plan, a predicted probability that a radiation treatment plan meeting a predetermined acceptability threshold exists for the input data. The acceptability is yielded by the acceptability model and the output parameters of the radiation treatment plan comprise one or more dosimetric parameters and / or one or more treatment parameters.

Description

[0001] Brainlab AG

[0002] Attorney’s File: B19161WO

[0003] SYSTEM AND METHOD FOR RADIATION TREATMENT PLANNING

[0004] FIELD OF THE INVENTION

[0005] The present invention relates to a computer-implemented method for providing a radiation treatment planning tool, corresponding computer program product and computer-readable medium, and a system for radiation treatment planning.

[0006] TECHNICAL BACKGROUND

[0007] The present invention has the object of improving radiation treatment planning. A challenge in radiation treatment planning is that it can take many iterations to generate a final radiation treatment plan. A reason behind this is that even for one set of prescription data there are various possibilities for a feasible radiation treatment plan given a specific patient geometry / anatomy and prescription. The plans may, for example, be different in terms of trade-offs between competing goals resulting from the prescription. Which solution is chosen as final treatment plan has high variability, so the process of treatment planning remains inefficient.

[0008] An object underlying the subject-matter of the present application is to allow for improved radiation treatment planning, particularly arriving at a final radiation treatment plan more efficiently.

[0009] Aspects of the present invention, examples and exemplary steps and their embodiments are disclosed in the following. Different exemplary features of the invention can be combined in accordance with the invention wherever technically expedient and feasible.

[0010] EXEMPLARY SHORT DESCRIPTION OF THE INVENTION

[0011] In the following, a short description of the specific features of the present invention is given which shall not be understood to limit the invention only to the features or a combination of the features described in this section. The disclosed computer-implemented method for providing a radiation treatment planning tool comprises providing input data comprising patient anatomy and / or geometry data and prescription data as input for an acceptability model and providing, making use of the acceptability model, at least one of: a proposed radiation treatment plan, the proposed radiation treatment plan being obtained by selecting and / or modifying and / or modelling a radiation treatment plan, the selecting and / or modifying and / or modelling taking into account a predicted acceptability of output parameter values of the radiation treatment plan, a predicted acceptability for a candidate radiation treatment plan and / or the proposed radiation treatment plan based on acceptability of output parameter values of the candidate radiation treatment plan, the predicted acceptability to allow for subsequent determination of a radiation treatment plan, a predicted probability that a radiation treatment plan meeting a predetermined acceptability threshold exists for the input data based on acceptability of the output parameter values of potential radiation treatment plans, the predicted probability to allow for adjusting prescription data for radiation treatment plan generation. The acceptability is yielded by the acceptability model and the output parameters of the radiation treatment plan comprise one or more dosimetric parameters and / or one or more treatment parameters.

[0012] GENERAL DESCRIPTION OF THE INVENTION

[0013] In this section, a description of the general features of the present invention is given for example by referring to possible embodiments of the invention.

[0014] The invention provides a method, system, computer program product, and computer- readable medium according to the independent claims. Preferred embodiments are provided by the dependent claims.

[0015] The disclosed computer-implemented method for providing a radiation treatment planning tool comprises providing input data comprising patient anatomy and / or geometry data and prescription data as input for an acceptability model and providing, making use of the acceptability model, at least one of: a proposed radiation treatment plan, the proposed radiation treatment plan being obtained by selecting and / or modifying and / or modelling a radiation treatment plan, the selecting and / or modifying and / or modelling taking into account a predicted acceptability of output parameter values of the radiation treatment plan, a predicted acceptability for a candidate radiation treatment plan and / or the proposed radiation treatment plan based on acceptability of output parameter values, in particular output parameter value ranges, of the candidate radiation treatment plan, the predicted acceptability to allow for subsequent determination of a radiation treatment plan, a predicted probability that a radiation treatment plan meeting a predetermined acceptability threshold exists for the input data based on acceptability of the output parameter values of potential radiation treatment plans, the predicted probability to allow for adjusting prescription data for radiation treatment plan generation. The acceptability is yielded by the acceptability model and the output parameters of the radiation treatment plan comprise one or more dosimetric parameters and / or one or more treatment parameters.

[0016] In the present disclosure, unless otherwise specified, “treatment plan” and “radiation treatment plan” and “plan” are used interchangeably.

[0017] In other words, an acceptability prediction can be used in different ways. For example, a radiation treatment plan may be suggested, a radiation treatment plan may be evaluated in terms of acceptability and / or a feasibility of creating an acceptable plan may be evaluated.

[0018] A treatment planning tool may, for example, be a tool that supports automatic or semiautomatic generation, modification, and / or selection of a treatment plan.

[0019] A radiation treatment plan may comprise one or more radiation treatment parameters and / or one or more dosimetric parameters. These parameters may be used for configuring a radiation treatment apparatus and / or its settings, for example.

[0020] The acceptability, as will also be described below, may be taken into account, for example, as at least one of: a clinical constraint, e.g. dose and / or volume parameters, an optimization constraint, an optimization boundary condition, optimization weights, selection criteria, filter criteria, and / or sorting criteria.

[0021] The predicted acceptability may be an absolute predicted acceptability and / or a predicted acceptability relative to other candidate radiation treatment plans and / or parameter values.

[0022] The predicted acceptability may, for example, be for used in subsequent determination and / or selection of a radiation treatment plan. This will be explained in detail below.

[0023] As explained above, making use of the acceptability model, a proposed radiation treatment plan, may be provided. As an example, the proposed radiation treatment plan may be obtained by selecting a radiation treatment plan, which may be fully automatic based on selection criteria applied to the acceptability of the output parameter values. The proposed radiation treatment plan may also be obtained by modifying an initial radiation treatment plan. This can be done iteratively, for example until a selection criterion for acceptability is met. Similarly, the proposed radiation treatment plan may be obtained by modelling a radiation treatment plan. In each case, the selecting and / or modifying and / or modelling taking into account a predicted acceptability of output parameter values of the radiation treatment plan.

[0024] This allows for efficient convergence on a proposed radiation treatment plan, with a high probability of the plan being acceptable.

[0025] Alternatively or in addition to providing a proposed radiation treatment plan, the method may comprise providing, making use of the acceptability model, a predicted acceptability for a candidate radiation treatment plan and / or the above-described proposed radiation treatment plan. This may be done based on acceptability of output parameter values of the candidate or proposed radiation treatment plan. The predicted acceptability allows for subsequent determination of a (final) radiation treatment plan, for example by applying criteria concerning the predicted acceptability for selecting a (final) radiation treatment plan.

[0026] This may be a fast way of arriving at a radiation treatment plan and may even avoid detailed evaluation of the different output parameters and / or newly generating or modifying a radiation treatment plan in case an acceptable plan might already be available for selection. Moreover, where multiple, potentially similar plans, are available, objective selection may be possible, potentially even in an automated manner.

[0027] Providing a proposed radiation treatment plan may be combined with providing a predicted acceptability, particularly of the proposed radiation treatment plan. This may allow for safeguarding against using plans that were proposed erroneously and / or be a plausibility check. It may also be a way of determining, if a proposed plan is not selected, what other plans could be selected based on their acceptability.

[0028] The method may, alternatively or in addition, comprise providing, making use of the acceptability model, a predicted probability that a radiation treatment plan meeting a predetermined acceptability threshold exists for the input data based on acceptability of the output parameter values of potential radiation treatment plans. The predicted probability allows, particularly may be used, for adjusting prescription data for radiation treatment plan generation. In particular, prescription data may be automatically adjusted in response to determining that no radiation treatment plan meeting the predetermined acceptability threshold is met and / or a user output may be provided to prompt the user to modify the prescription data in response to determining that no radiation treatment plan meeting the predetermined acceptability threshold is met. In other words, need for input adjustment may be identified and optionally automatically carried out and / or prompted.

[0029] This allows for avoiding inefficiencies due to generating or modifying radiation treatment plans by identifying in advance cases where it is unlikely that an acceptable plan can be obtained. Inputs may be adjusted prior to the more resource-consuming part of treatment plan generation / modification.

[0030] Predicting the probability that a radiation treatment plan meeting a predetermined acceptability threshold exists may be combined with the other steps above, e.g. carried out before them or after them or between iterations.

[0031] Carrying it out before them may avoid generating / modifying treatment plans and / or determining acceptability of candidate treatment plans when there is no prospect of success.

[0032] Predicting the probability that a radiation treatment plan meeting a predetermined acceptability threshold exists may be combined, for example, with generating / modifying a treatment plan as described above. For example, if a first attempt or a number of iterations do not yield an acceptable plan, probability that an acceptable plan exists may be carried out. This may avoid further modification / generation iterations.

[0033] Similarly, when the above-described determining whether candidate treatment plans are acceptable does not yield any acceptable candidate treatment plan, the probability that an acceptable plan exists may be carried out. This may avoid further modification / generation iterations.

[0034] Thus, it can be understood from the above that the methods of the present disclosure allow for addressing the challenges explained in the introduction. Particularly, improved radiation treatment planning, particularly arriving at a final radiation treatment plan more efficiently, can be provided.

[0035] It is noted that “acceptability” may refer to an acceptability of individual output parameter values, such as dosimetric parameter values and or treatment parameter values, associated with a plan and / or to an acceptability of the treatment plan. In many cases, this may coincide, as a plan may only be found acceptable if all output parameter values are found acceptable. In other cases, this may not be the case. Where technically sensible and not specified otherwise, features concerning an acceptability may be applicable to the acceptability of a plan and to the acceptability of output parameter values.

[0036] The method of the present disclosure may comprise obtaining the acceptability model based on data referred to as “plan analytics data” or “PAD”, the plan analytics data comprising multiple sets of PAD input data and corresponding PAD output data. The PAD input data comprise patient anatomy and / or geometry data and prescription data. The corresponding PAD output data comprise corresponding dosimetric parameters and / or treatment parameters. The PAD may be representative of and / or comprise acceptability data, the acceptability data indicative of a recorded acceptance of PAD output parameter values / ranges. In particular, the acceptance may be a clinic-specific and / or physician-specific acceptance.

[0037] The acceptance may be based on acceptable plans and / or acceptable output parameter values, such as dosimetric parameter values and / or treatment parameter values. The acceptable output parameter values may be comprised in acceptable plans and may be obtained by extracting them from the acceptable plans. Alternatively, they may be determined as acceptable independently of the plan.

[0038] For example, the PAD output parameter values may indicate predicted acceptable values and / or ranges of output parameters.

[0039] PAD allow for a relatively low-effort modelling of acceptability of output parameter values and / or treatment plans with adequate precision. Another advantage is that clinical records will typically comprise such data, such that there is a lot of data as a basis for the modelling. Accordingly, predictions of the model can be rather precise.

[0040] According to the present disclosure, providing a proposed radiation treatment plan may comprise at least one of: modelling a new a radiation treatment plan using an optimization function with one or more acceptable output parameter values, particularly ranges, as constraints and / or weights and / or modifying an initial a radiation treatment plan to yield acceptable output parameter values and / or an acceptable final radiation treatment plan.

[0041] Automatic radiation treatment planning usually involves optimization procedures, as the underlying problem of different competing treatment goals can be suitably addressed using optimization. Optimizations can be influenced by setting, besides optimization goals, optimization weights, priorities, constraints, or the like. Providing a radiation treatment plan wherein the acceptable output parameter values / ranges are used to tweak the optimization, e.g. in the form of constraints, allows for efficient and fast convergence on a final treatment plan. This similarly applies to modifying plans based on the acceptable output parameter values / ranges, e.g. in an iterative process.

[0042] The method of the present disclosure may comprise providing one or more proposed radiation treatment plans and associated output parameter values, particularly ranges, as well as predicted acceptable parameter values, particularly ranges, yielded by the acceptability model to a user for confirmation and / or further modification of the radiation treatment plan.

[0043] This allows for a user to determine whether parameter values / ranges of a given radiation treatment plan are likely to be acceptable. In particular, where out-of-range values / ranges could generally render an overall plan unacceptable, the user may nonetheless confirm a treatment plan based on which and how much the values / ranges are out-of-range. Alternatively, modifications to the plan can be made in a more targeted manner based on which parameter values / ranges are out-of-range and by how much. This allows for efficient convergence on a final radiation treatment plan.

[0044] According to the present disclosure, the acceptability model may employ range-based heuristics for a respective (acceptable) parameter range of at least one of the one or more dosimetric parameters and / or at least one of the one or more treatment parameters, the heuristics in particular employing the respective parameter range for predicting acceptability in a binary manner, e.g. acceptable or inacceptable, or in a probabilistic manner, e.g. providing a probability of acceptability for a treatment plan and / or output parameter values.

[0045] Alternatively or in addition, the model may comprise a multivariate analysis of a parameter set, the parameter set comprising parameters comprised in the one or more of the dosimetric parameters and / or one or more treatment parameters, in particular the multivariate analysis configured to predict treatment plans with high probability of acceptance.

[0046] A multivariate analysis allows for a more precise determination in complex scenarios where a trade-off between several competing metrics or parameters is made in treatment plan generation. Here, the simpler and less computationally expensive heuristic approach may not be as efficient and / or precise as a multivariate analysis. Such cases are also particularly prone to being inefficient without the use of the present method due to their complexity. According to the present disclosure, the plan analytics data may be alphanumeric data. For example, the plan analytics data may not comprise image data. This is advantageous for computing efficiency and in the light of image data not always being made available. The latter would reduce the amount of data that can be used for creating the model and thereby its accuracy.

[0047] According to the present disclosure, the plan analytics data are stored as Digital Imaging and Communications in Medicine, DICOM, file. This is a standardized format, which is advantageous in the light allowing for wide applicability and compatibility of the method and leveraging an already large data basis available as DICOM files.

[0048] According to the present disclosure, the plan analytics data may provide a meta description of a radiation treatment plan. The meta description may allow for a more abstract and / or standardized representation of the individual cases, which makes modelling based thereon more efficient and reliable.

[0049] According to the present disclosure, patient anatomy and / or geometry data may comprise data related to a lesion comprising, for example, at least one of a descriptor of shape of a lesion, a distance of a lesion to organs at risk, location of a lesion relative to other body parts (e.g., skull), sphericity of a lesion, convexity of a lesion, distance to other lesions, distance of a lesion to skin, diameter of a lesion, volume of a lesion. These are typical inputs for radiation treatment planning, e.g. fully or semi-automatic planning.

[0050] According to the present disclosure, dosimetric parameters may comprise at least one of a dose volume, a conformity index, gradient index, mean dose. Other dose / volume parameter can be added. Alternatively or in addition, dosimetric parameters may comprise dosimetric parameters for radiation target structures and / or dosimetric parameters for anatomical risk structures, in particular organs at risk.

[0051] According to the present disclosure, the treatment parameters may comprise at least one of arc trajectory, collimator information, delivery time, or the like.

[0052] Such dosimetric parameters and / or the treatment parameters may be used for selection and / or configuration of radiation treatment equipment and its settings. The dosimetric parameters allow for configurations / settings to be adjusted specifically to the patient at hand. The treatment parameters may be useful for hardware setup and settings. Taking into account these parameters may be advantageous, for example considering that different irradiation setups may be present in given clinics. Therefore, inefficiencies due to plans that are unsuitable for the given setup are proposed can be reduced.

[0053] The method of the present disclosure may comprise providing a final radiation treatment plan based on the proposed radiation treatment plan and / or the predicted acceptability of a radiation treatment plan and / or the output parameter values.

[0054] In particular, this may be done fully automatically or based on user confirmation.

[0055] Providing the final radiation treatment plan may be based on a selection of the proposed radiation treatment plan, for example based on predicted acceptability of the plan and / or of its output parameter values, and / or by selection among a set of potential radiation treatment plans, for example based on predicted acceptability of the plan and / or of its output parameter values.

[0056] The method of the present disclosure may comprise, for input patient anatomy and / or geometry data and prescription data and by means of the acceptability model, predicting ranges of expected acceptable output parameter values corresponding to the given input patient anatomy and / or geometry data and prescription data, particularly clinic-specific and / or physician-specific expected acceptable output parameter values.

[0057] PAD are often available per clinic and / or per clinician. This allows for high granularity for modelling acceptability.

[0058] The expected acceptable output parameter values may be used for scoring and / or ranking and / or filtering and / or selecting of a potential treatment plan. Based thereon, an efficient generating and / or narrowing down or selecting of a treatment plan is possible, particularly in a highly granular way.

[0059] According to the present disclosure, the method may comprise generating and / or retrieving a candidate radiation treatment plan, and scoring, for a selected set of PAD output metrics how many output parameter values for the generated candidate radiation treatment plan are in the predicted (acceptable) ranges. The candidate radiation treatment plan may be generated and / or retrieved semi-automatically, automatically, or manually. The scoring may be automated. Scoring may, in particular, be advantageous for subsequent selection, ranking, and or filtering of candidate radiation treatment plans, particularly by automated procedures. According to the present disclosure, the method may comprise computing a / the probability of acceptability of the candidate radiation treatment plan as fraction of metric in range, particularly relative to a total number of evaluated metrics, and / or computing a / the probability of acceptability of the candidate radiation treatment plan as a weighted sum of the metrics calculated with clinic-specific and / or physician-specific weights.

[0060] A metric according to the present disclosure may, for example, be represented by one of the above-described output parameters. The metric may be in range in case the parameter value of said output parameter meets certain criteria, particularly is within a certain range. The probability of acceptability of a treatment plan may, thus, be judged by how many of the parameter values meet the criteria. Where some metrics may be considered to have higher priority than other metrics, for example by different clinics or physicians, this may be reflected more precisely by a weighted sum of the metrics, wherein the weights can be chosen according to priority.

[0061] Thus, acceptability can be objectively quantified, particularly at high granularity. Such quantification may, in particular, be used for subsequent automated steps, such as filtering and / or selection of plans, or the like.

[0062] According to the present disclosure, the method may comprise providing a user interface, wherein the user interface is configured to indicate, for a given treatment plan, lack of acceptability of the given treatment plan, wherein lack of acceptability may be automatically determined in case the probability of acceptance of a treatment plan is below a predetermined threshold. The probability may optionally be provided alongside the indication of lack of acceptability.

[0063] The user interface may, alternatively or in addition, be configured to indicate for different aspects of the treatment plan, such as parameters like dosimetric and / or treatment parameter values of the treatment plan, that the respective aspect is out-of-range, in particular out of an acceptable parameter value range, and optionally the extent to which the aspect is out-of-range.

[0064] For example, a user interface may indicate to a planner that the plan is estimated to be inacceptable or that there is a high likelihood of it being inacceptable. A table or plot or other visualization may, for example, be employed to show output parameter values, such as dosimetric values or treatment parameter values, that are out-of-range and how far they are out-of-range.

[0065] The above allows for faster and more efficient convergence on a final treatment plan.

[0066] According to the present disclosure, the method may comprise providing a / the user interface, configured to provide to a user, such as a planner or clinician, for a given treatment plan, the acceptability for other planners / clinicians and / or other clinics. For example, this may aid in providing high quality planning, particularly where a clinic may not (yet) have much experience and / or much historical data applicable for the case at hand.

[0067] As another example, a user interface may indicate past plans for previous patient geometries (could be part of the acceptability model, but not necessarily). This would allow, for example, to provide a functionality show historically accepted plans for a clinic I physician similar to the current patient. This could improve efficiency of creating a radiation treatment plan and also may improve acceptability of the acceptability model.

[0068] A user interface may also be provided allowing a user to update the acceptability model, in particular based on the outcome of the method steps described above. For example, after obtaining a final treatment plan, an additional PAD file may be created and added to the PAD. Thus PAD can be updated. Updating PAD based on a final treatment plan may also be carried out automatically.

[0069] The present disclosure also provides a system for radiation treatment planning, the system comprising one or more processing devices configured to carry out and / or control any of the steps of the method according to the present disclosure, particularly of the method claims.

[0070] The present disclosure also provides a computer program product comprising instructions which, when the program is executed by a computer, cause the computer carry out and / or control any of the steps of the method according to the present disclosure, particularly of the method claims.

[0071] The present disclosure also provides a computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out and / or control any of the steps of the method according to the present disclosure, particularly of the method claims. The features and advantages outlined above in the context of the method similarly apply to the system, computer program product, and computer-readable medium of the present disclosure.

[0072] For example, the invention does not involve or in particular comprise or encompass an invasive step which would represent a substantial physical interference with the body requiring professional medical expertise to be carried out and entailing a substantial health risk even when carried out with the required professional care and expertise. For example, the invention does not comprise a step of positioning a medical implant in order to fasten it to an anatomical structure or a step of fastening the medical implant to the anatomical structure or a step of preparing the anatomical structure for having the medical implant fastened to it. More particularly, the invention does not involve or in particular comprise or encompass any surgical or therapeutic activity. For this reason alone, no surgical or therapeutic activity and in particular no surgical or therapeutic step is necessitated or implied by carrying out the invention.

[0073] DEFINITIONS

[0074] In this section, definitions for specific terminology used in this disclosure are offered which also form part of the present disclosure.

[0075] Computer implemented method

[0076] The method in accordance with the invention is for example a computer implemented method. For example, all the steps or merely some of the steps (i.e. less than the total number of steps) of the method in accordance with the invention can be executed by a computer (for example, at least one computer). An embodiment of the computer implemented method is a use of the computer for performing a data processing method. An embodiment of the computer implemented method is a method concerning the operation of the computer such that the computer is operated to perform one, more or all steps of the method.

[0077] The computer for example comprises at least one processor and for example at least one memory in order to (technically) process the data, for example electronically and / or optically. The processor being for example made of a substance or composition which is a semiconductor, for example at least partly n- and / or p-doped semiconductor, for example at least one of II-, III-, I V-, V-, Vl-semiconductor material, for example (doped) silicon and / or gallium arsenide. The calculating or determining steps described are for example performed by a computer. Determining steps or calculating steps are for example steps of determining data within the framework of the technical method, for example within the framework of a program. A computer is for example any kind of data processing device, for example electronic data processing device. A computer can be a device which is generally thought of as such, for example desktop PCs, notebooks, netbooks, etc., but can also be any programmable apparatus, such as for example a mobile phone or an embedded processor. A computer can for example comprise a system (network) of "sub-computers", wherein each sub-computer represents a computer in its own right. The term "computer" includes a cloud computer, for example a cloud server. The term "cloud computer" includes a cloud computer system which for example comprises a system of at least one cloud computer and for example a plurality of operatively interconnected cloud computers such as a server farm. Such a cloud computer is preferably connected to a wide area network such as the world wide web (WWW) and located in a so-called cloud of computers which are all connected to the world wide web. Such an infrastructure is used for "cloud computing", which describes computation, software, data access and storage services which do not require the end user to know the physical location and / or configuration of the computer delivering a specific service. For example, the term "cloud" is used in this respect as a metaphor for the Internet (world wide web). For example, the cloud provides computing infrastructure as a service (laaS). The cloud computer can function as a virtual host for an operating system and / or data processing application which is used to execute the method of the invention. The cloud computer is for example an elastic compute cloud (EC2) as provided by Amazon Web Services™. A computer for example comprises interfaces in order to receive or output data and / or perform an analogue-to-digital conversion. The data are for example data which represent physical properties and / or which are generated from technical signals. The technical signals are for example generated by means of (technical) detection devices (such as for example devices for detecting marker devices) and / or (technical) analytical devices (such as for example devices for performing (medical) imaging methods), wherein the technical signals are for example electrical or optical signals. The technical signals for example represent the data received or outputted by the computer. The computer is preferably operatively coupled to a display device which allows information outputted by the computer to be displayed, for example to a user. One example of a display device is a virtual reality device or an augmented reality device (also referred to as virtual reality glasses or augmented reality glasses) which can be used as "goggles" for navigating. A specific example of such augmented reality glasses is Google Glass (a trademark of Google, Inc.). An augmented reality device or a virtual reality device can be used both to input information into the computer by user interaction and to display information outputted by the computer. Another example of a display device would be a standard computer monitor comprising for example a liquid crystal display operatively coupled to the computer for receiving display control data from the computer for generating signals used to display image information content on the display device. A specific embodiment of such a computer monitor is a digital lightbox. An example of such a digital lightbox is Buzz®, a product of Brainlab AG. The monitor may also be the monitor of a portable, for example handheld, device such as a smart phone or personal digital assistant or digital media player.

[0078] The invention also relates to a program which, when running on a computer, causes the computer to perform one or more or all of the method steps described herein and / or to a program storage medium on which the program is stored (in particular in a non-transitory form) and / or to a computer comprising said program storage medium and / or to a (physical, for example electrical, for example technically generated) signal wave, for example a digital signal wave, carrying information which represents the program, for example the aforementioned program, which for example comprises code means which are adapted to perform any or all of the method steps described herein.

[0079] Within the framework of the invention, computer program elements can be embodied by hardware and / or software (this includes firmware, resident software, micro-code, etc.). Within the framework of the invention, computer program elements can take the form of a computer program product which can be embodied by a computer-usable, for example computer- readable data storage medium comprising computer-usable, for example computer-readable program instructions, "code" or a "computer program" embodied in said data storage medium for use on or in connection with the instruction-executing system. Such a system can be a computer; a computer can be a data processing device comprising means for executing the computer program elements and / or the program in accordance with the invention, for example a data processing device comprising a digital processor (central processing unit or CPU) which executes the computer program elements, and optionally a volatile memory (for example a random access memory or RAM) for storing data used for and / or produced by executing the computer program elements. Within the framework of the present invention, a computer-usable, for example computer-readable data storage medium can be any data storage medium which can include, store, communicate, propagate or transport the program for use on or in connection with the instruction-executing system, apparatus or device. The computer-usable, for example computer-readable data storage medium can for example be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, apparatus or device or a medium of propagation such as for example the Internet. The computer-usable or computer-readable data storage medium could even for example be paper or another suitable medium onto which the program is printed, since the program could be electronically captured, for example by optically scanning the paper or other suitable medium, and then compiled, interpreted or otherwise processed in a suitable manner. The data storage medium is preferably a non-volatile data storage medium. The computer program product and any software and / or hardware described here form the various means for performing the functions of the invention in the example embodiments.

[0080] The computer and / or data processing device can for example include a guidance information device which includes means for outputting guidance information. The guidance information can be outputted, for example to a user, visually by a visual indicating means (for example, a monitor and / or a lamp) and / or acoustically by an acoustic indicating means (for example, a loudspeaker and / or a digital speech output device) and / or tactilely by a tactile indicating means (for example, a vibrating element or a vibration element incorporated into an instrument). For the purpose of this document, a computer is a technical computer which for example comprises technical, for example tangible components, for example mechanical and / or electronic components. Any device mentioned as such in this document is a technical and for example tangible device.

[0081] Acquiring data

[0082] The expression "acquiring data" for example encompasses (within the framework of a computer implemented method) the scenario in which the data are determined by the computer implemented method or program. Determining data for example encompasses measuring physical quantities and transforming the measured values into data, for example digital data, and / or computing (and e.g. outputting) the data by means of a computer and for example within the framework of the method in accordance with the invention. The meaning of "acquiring data" also for example encompasses the scenario in which the data are received or retrieved by (e.g. input to) the computer implemented method or program, for example from another program, a previous method step or a data storage medium, for example for further processing by the computer implemented method or program. Generation of the data to be acquired may but need not be part of the method in accordance with the invention. The expression "acquiring data" can therefore also for example mean waiting to receive data and / or receiving the data. The received data can for example be inputted via an interface. The expression "acquiring data" can also mean that the computer implemented method or program performs steps in order to (actively) receive or retrieve the data from a data source, for instance a data storage medium (such as for example a ROM, RAM, database, hard drive, etc.), or via the interface (for instance, from another computer or a network). The data acquired by the disclosed method or device, respectively, may be acquired from a database located in a data storage device which is operably to a computer for data transfer between the database and the computer, for example from the database to the computer. The computer acquires the data for use as an input for steps of determining data. The determined data can be output again to the same or another database to be stored for later use. The database or database used for implementing the disclosed method can be located on network data storage device or a network server (for example, a cloud data storage device or a cloud server) or a local data storage device (such as a mass storage device operably connected to at least one computer executing the disclosed method). The data can be made "ready for use" by performing an additional step before the acquiring step. In accordance with this additional step, the data are generated in order to be acquired. The data are for example detected or captured (for example by an analytical device). Alternatively or additionally, the data are inputted in accordance with the additional step, for instance via interfaces. The data generated can for example be inputted (for instance into the computer). In accordance with the additional step (which precedes the acquiring step), the data can also be provided by performing the additional step of storing the data in a data storage medium (such as for example a ROM, RAM, CD and / or hard drive), such that they are ready for use within the framework of the method or program in accordance with the invention. The step of "acquiring data" can therefore also involve commanding a device to obtain and / or provide the data to be acquired. In particular, the acquiring step does not involve an invasive step which would represent a substantial physical interference with the body, requiring professional medical expertise to be carried out and entailing a substantial health risk even when carried out with the required professional care and expertise. In particular, the step of acquiring data, for example determining data, does not involve a surgical step and in particular does not involve a step of treating a human or animal body using surgery or therapy. In order to distinguish the different data used by the present method, the data are denoted (i.e. referred to) as "XY data" and the like and are defined in terms of the information which they describe, which is then preferably referred to as "XY information" and the like.

[0083] Treatment beam

[0084] The present disclosure may relate to the field of providing data for controlling a treatment beam. The treatment beam treats body parts which are to be treated and which are referred to in the following as "treatment body parts". These body parts are for example parts of a patient's body, i.e. anatomical body parts. The present invention relates to the field of medicine and for example to the use of beams, such as radiation beams, to treat parts of a patient's body, which are therefore also referred to as treatment beams. A treatment beam treats body parts which are to be treated and which are referred to in the following as "treatment body parts". These body parts are for example parts of a patient's body, i.e. anatomical body parts. Ionising radiation is for example used for the purpose of treatment. For example, the treatment beam comprises or consists of ionising radiation. The ionising radiation comprises or consists of particles (for example, subatomic particles or ions) or electromagnetic waves which are energetic enough to detach electrons from atoms or molecules and so ionise them. Examples of such ionising radiation include x-rays, high-energy particles (high-energy particle beams) and / or ionising radiation emitted from a radioactive element. The treatment radiation, for example the treatment beam, is for example used in radiation therapy or radiotherapy, such as in the field of oncology. For treating cancer in particular, parts of the body comprising a pathological structure or tissue such as a tumour are treated using ionising radiation. The tumour is then an example of a treatment body part.

[0085] The treatment beam is preferably controlled such that it passes through the treatment body part. However, the treatment beam can have a negative effect on body parts outside the treatment body part. These body parts are referred to here as "outside body parts". Generally, a treatment beam has to pass through outside body parts in order to reach and so pass through the treatment body part.

[0086] Reference is also made in this respect to the following web pages: http: / / www.elekta.com / healthcare_us_elekta_vmat.php and http: / / www.varian.com / us / oncology / treatments / treatment_techniques / rapidarc.

[0087] Arrangement of treatment beams

[0088] A treatment body part can be treated by one or more treatment beams issued from one or more directions at one or more times. The treatment by means of the at least one treatment beam thus follows a particular spatial and temporal pattern. The term "beam arrangement" is then used to cover the spatial and temporal features of the treatment by means of the at least one treatment beam. The beam arrangement is an arrangement of at least one treatment beam.

[0089] The "beam positions" describe the positions of the treatment beams of the beam arrangement. The arrangement of beam positions is referred to as the positional arrangement. A beam position is preferably defined by the beam direction and additional information which allows a specific location, for example in three-dimensional space, to be assigned to the treatment beam, for example information about its co-ordinates in a defined co-ordinate system. The specific location is a point, preferably a point on a straight line. This line is then referred to as a "beam line" and extends in the beam direction, for example along the central axis of the treatment beam. The defined co-ordinate system is preferably defined relative to the treatment device or relative to at least a part of the patient's body. The positional arrangement comprises and for example consists of at least one beam position, for example a discrete set of beam positions (for example, two or more different beam positions), or a continuous multiplicity (manifold) of beam positions.

[0090] For example, one or more treatment beams adopt(s) the treatment beam position(s) defined by the positional arrangement simultaneously or sequentially during treatment (for example sequentially if there is only one beam source to emit a treatment beam). If there are several beam sources, it is also possible for at least a subset of the beam positions to be adopted simultaneously by treatment beams during the treatment. For example, one or more subsets of the treatment beams can adopt the beam positions of the positional arrangement in accordance with a predefined sequence. A subset of treatment beams comprises one or more treatment beams. The complete set of treatment beams which comprises one or more treatment beams which adopt(s) all the beam positions defined by the positional arrangement is then the beam arrangement.

[0091] BRIEF DESCRIPTION OF THE DRAWINGS

[0092] In the following, the invention is described with reference to the appended figures which give background explanations and represent specific embodiments of the invention. The scope of the invention is however not limited to the specific features disclosed in the context of the figures, wherein

[0093] Fig. 1 illustrates a method for providing a radiation planning treatment tool according to the present disclosure;

[0094] Fig. 2 schematically illustrates a system for radiation treatment planning according to the present disclosure; and

[0095] Figs. 3a and 3b schematic illustrations of different methods according to the present disclosure. DESCRIPTION OF EMBODIMENTS

[0096] Fig. 1 illustrates the basic steps of a computer-implemented method according to the present disclosure.

[0097] The method comprises, in step S11, providing input data comprising patient anatomy and / or geometry data and prescription data as input for an acceptability model. For example, the data may be data pertaining to a given patient for creating a treatment plan for said patient. Generally, these inputs can be used for generating radiation treatment plans. In the present case, these inputs or information extracted from the inputs are provided to an acceptability model (alternatively or in addition to a module that generates a radiation treatment plan) that is able to model acceptable output parameter ranges for output parameters of treatment plans that could be generated from these inputs. This can be leveraged in different ways, as shown, for example, in step S12.

[0098] The method comprises providing in step S12, making use of the acceptability model, a proposed radiation treatment plan and / or a predicted acceptability for a candidate radiation treatment plan and / or the proposed radiation treatment plan and / or a predicted probability that a radiation treatment plan meeting a predetermined acceptability threshold exists.

[0099] Specifically, the method may comprise, in step S12a, providing a proposed radiation treatment plan, the proposed radiation treatment plan being obtained by selecting and / or modifying and / or modelling a radiation treatment plan, the selecting and / or modifying and / or modelling taking into account a predicted acceptability of output parameter values of the radiation treatment plan.

[0100] The acceptability may be taken into account, for example, in optimization constraints, optimization boundary conditions, optimization weights, selection criteria, filter criteria, sorting criteria, or the like.

[0101] Step S12a of providing a proposed radiation treatment plan may comprise modelling a new a radiation treatment plan using an optimization function with (predicted acceptable) output parameter values / ranges as constraints, boundary conditions, weights, or the like. Alternatively or in addition, an initial radiation treatment plan may be modified to yield acceptable output parameter values / ranges. In an example, the method may comprise providing a proposed radiation treatment plan and associated output parameter values / ranges and predicted acceptable parameter values / ranges yielded by the acceptability model to a user for confirmation and / or further modification of the radiation treatment plan, e.g. as part of step S14 described below.

[0102] Alternatively or in addition to step S12a, the method may comprise, in step S12b, providing a predicted acceptability for a candidate radiation treatment plan and / or the proposed radiation treatment plan of step S12a based on acceptability of output parameter values of the candidate radiation treatment plan and / or the proposed radiation treatment plan, the predicted acceptability to allow for subsequent determination of a (final) radiation treatment plan. The predicted acceptability may, for example, be an absolute predicted acceptability and / or a predicted acceptability relative to other candidate radiation treatment plans.

[0103] Alternatively or in addition, the method may comprise, in step S12c, providing a predicted probability that a radiation treatment plan meeting a predetermined acceptability threshold exists for the input data based on acceptability of the output parameter values of potential radiation treatment plans, the predicted probability to allow for adjusting prescription data for radiation treatment plan generation.

[0104] The acceptability is yielded by the acceptability model. There are different acceptability model types that can be used. The acceptability model may employ range-based heuristics for a parameter, or it may comprise a multivariate analysis of a parameter set, for example. In principle Machine Learning (ML) models may also be employed.

[0105] The output parameters of the radiation treatment plan comprise one or more dosimetric parameters and / or one or more treatment parameters.

[0106] The method may comprise, in optional step S10, obtaining the acceptability model based on plan analytics data, PAD, the plan analytics data comprising multiple sets of PAD input data and corresponding PAD output data, wherein the PAD input data comprise patient anatomy and / or geometry data and prescription data and the corresponding PAD output data comprise corresponding dosimetric parameters and / or treatment parameters. The PAD are representative of and / or comprise acceptability data, the acceptability data indicative of a recorded acceptance of PAD output parameter values, in particular clinic-specific and / or physician-specific acceptance. For example, the PAD output parameter values may indicate predicted acceptable values and / or ranges of output parameters. The plan analytics data may be considered to provide a meta description of a radiation treatment plan. They need not comprise image data. In an example, the plan analytics data may be stored as Digital Imaging and Communications in Medicine, DICOM, file.

[0107] The method may comprise, in optional step S13, providing a final radiation treatment plan based on the proposed radiation treatment plan and / or the predicted acceptability.

[0108] The method may comprise, in optional step S14, providing a user interface.

[0109] In an example, the user interface is configured to indicate, for a given treatment plan, lack of acceptability of the given treatment plan, wherein lack of acceptability may be automatically determined when it is determined that the probability of acceptance is below a predetermined threshold. Alternatively or in addition, in an example, the user interface is configured to indicate for different aspects of the treatment plan, such as output parameters like dosimetric values or treatment parameters of the treatment plan, that the respective aspect is out-of- range, in particular out of an acceptable parameter value range, and optionally the extent to which the aspect is out-of-range.

[0110] In one exemplary method of the present disclosure, the method may comprise, for input patient anatomy and / or geometry data and prescription data and by means of the acceptability model, predicting ranges of expected acceptable output parameter values corresponding to the given input patient anatomy and / or geometry data and prescription data, particularly clinic-specific and / or physician-specific expected acceptable output parameter values.

[0111] In this example, the method may comprise generating and / or retrieving a candidate radiation treatment plan (semi-automatically, automatically, or manually), and scoring, for a selected set of PAD output metrics how many output parameter values for the generated candidate radiation treatment plan are in the predicted ranges. Further in this example, the method may comprise computing a / the probability of acceptability of the candidate radiation treatment plan as fraction of metric in range, particularly relative to a total number of evaluated metrics. Alternatively or in addition, in this example, the method may comprise computing a / the probability of acceptability of the candidate radiation treatment plan as a weighted sum of the metrics calculated with clinic-specific and / or physician-specific weights.

[0112] The method may be carried out using any suitable system, particularly a system according to the present disclosure, for example the system of Fig. 2. Fig. 2 schematically illustrates a system 1 for radiation treatment planning according to the present disclosure. The system comprises one or more processing devices 2 configured to carry out the method of the present disclosure, such as outlined in the context of Fig. 1 or Figs. 3a-3b, the general description, or the claims.

[0113] The system may optionally comprise a device 3 for receiving user input and a device 4 for providing output to a user, which may be provided separately or formed integrally, such as in a touch display. A user interface may, for example, be provided by device 4 or devices 3 and 4 together.

[0114] Further features and advantages of the system and method will be understood from the discussion below.

[0115] The present disclosure can leverage modelling clinical acceptability of a radiation treatment plan, for example by analyzing meta data of plans for a given clinical practice.

[0116] As an example software modules, such as “RT Elements”, may be employed in providing highly automated treatment planning solutions, for example for stereotactic radiosurgery planning. Often, the software modules are used for treatment planning for multiple brain metastases, spinal metastases, or lesions in the brain.

[0117] Although treatment plan optimization is highly automated in RT Elements, it is common that users tweak treatment plans. Some physicists would do so on a day-to-day basis, others only in outlier cases.

[0118] Although in principle these indications are fairly standardized, the inventors observed that selection of a final treatment plan, for example based on judgement on treatment plan quality, varies from clinic to clinic or even physician to physician.

[0119] This leads to limitation as to the efficiency of treatment planning tools, due to a large variability and potential trial-and-error.

[0120] The present method leverages modelling of acceptability to address these challenges.

[0121] Specifically, to reflect and tackle variability, Plan Analytics Data, PAD, are provided. They may be considered as providing a treatment plan meta description. Such data is widely available, for different planners, clinics, physicians, and the like. Accordingly, the data may, for example, be used to reflect planner differences and clinal acceptance of treatment plans.

[0122] PAD may, for example, be collected by storing PAD for treatment plans obtained using software modules like RT Elements.

[0123] PAD may comprise meta descriptors of patient anatomy / geometry (e.g. shape of the lesions, distance to organs at risks) and dosimetric parameters (e.g. Conformity Index, dose volumes) for target structures and organs at risk. In some examples, treatment parameters like arc trajectory and collimator information may be included in the PAD. Generally this information is sufficient for the purposes of the present method. Accordingly, in examples of the method, image data is not included in the PAD. This makes it easier to work with the data, particularly without dealing with protected health information, PHI. The PAD may be stored as DICOM file. DICOM is an international standard allowing to transmit, store, retrieve, print, process, and display medical imaging information.

[0124] A software module, which is referred to as PAD Extractor hereinbelow, may be used for gathering PAD files, e.g. for a clinic. These files can then be analyzed.

[0125] PAD may comprise PAD files and / or information extracted from PAD files.

[0126] PAD files may, for example, track, for a respective proposed treatment plan, whether the proposed treatment plan was approved. For example, they may track the “Clinically Approved” field of an RT Elements treatment plan. Furthermore, the geometric and dosimetric meta data may be retrieved. For example, several, in particular all available, clinically approved plans of a clinic and / or clinician can be loaded and correlated. The results may be representative of plan metrics, particularly values and / or ranges of plan metrics (e.g. output parameters such as dosimetric or treatment parameters), which were acceptable for clinical treatment for a given patient geometry. These values and / or ranges in turn can be used for modeling of clinical acceptance.

[0127] Some guidelines may allow for objective (quantitative) evaluation of clinical acceptability, e.g. reference ranges or constraints. Thresholds of various parameters can be used. However, especially in the context of multiple targets and high doses, users like clinicians may deviate from the criteria, e.g. from the parameters, for example may make judgements that stricter or less strict than the recommendations. Thus, without the benefits of the method of the present disclosure, even when using good planning techniques, treatment planning may involve ping-pong between physician and physicist to obtain a final treatment plan that is accepted for treatment.

[0128] The final treatment plans obtained, thus, often depend much on the clinician and their experience and / or common practices in their immediate work environment, such as the clinic.

[0129] This results in variability among clinicians and clinics. This makes it difficult to increase efficiency in treatment planning if trying to provide a treatment planning tool that can be widely used.

[0130] Many clinics employ digital record keeping tracking past treatments by listing and correlating various plan parameters. The present method allows for leveraging such data as PAD to increase efficiency.

[0131] For example, the present methods model clinical acceptability. Based thereon, acceptable treatment plans can be generated efficiently over a wide user base, such as different clinicians and clinics.

[0132] Below, some examples for aspects of the method of the present disclosure will be provided making reference to Figs. 3a-3b.

[0133] It is noted that below the terms “clinical planning”, “treatment planning”, and “radiation treatment planning” may be used interchangeably.

[0134] In Figs. 3a-3b, modeling of acceptability based on PAD is shown schematically, with an input part, in this example having geometric input data and prescription input data, and an output part having dosimetric output data and optionally other plan output data.

[0135] Generally, a starting point for generating a treatment plan may, for example be a given geometry of a patient, e.g. described by the patient’s images, derived structure sets, and by the clinical treatment decision, e.g. described by the prescription and constraints.

[0136] For providing an acceptability model, these starting points may be translated into meta information. The meta information may form or be part of the input part of PAD. PAD from previous treatment plans may be used as a basis. Particularly, they may build up a database.

[0137] Based thereon, a PAD-based model may be built such that, given a certain input part of PAD, a corresponding output part of the PAD can be predicted. For example, the dosimetry that is achievable for same or similar input parameters, described numerically e.g. in dose volumes and conformity indices, can be predicted. For example, for a patient with a three- lesion cluster, to predict acceptability (ranges), using (modeled) plan data which contains datapoint similar to a three-lesion cluster may be a good approximation.

[0138] These outputs may be used as a basis for predicting acceptability with high granularity, e.g. on a clinic or physician level.

[0139] To provide an example: In clinic 1 only plans with a Conformity Index (Cl) of < 1.3 are clinically accepted whereas for Gradient Index (Gl) the range of accepted plans ranges from 3-9. In contrast, in clinic 2 Cl’s may spread from 1.2-1.6 and Gl is in a range of 2.5-5. Clinic 3 might have two different ranges of acceptance, based on target volume. Clinic 4 might base their decisions on “gut feeling”: which can be considered to be a decision that is based on a (non-trivial) combination of parameters, such as geometric parameters. The method of the present disclosure allows to provide efficient treatment planning in spite of this complexity and variability.

[0140] Based on PAD, particularly the PAD output, several approaches can be applied to model acceptance according to the method of the present disclosure. Two examples:

[0141] 1. Range-based heuristics: Dosimetric plan qualifiers like Conformity Index, Gradient Index, V12 (V12 being an example for a dose volume parameter, i.e. , how large is the volume receiving at least 12 Gy, useful for example in cranial radiation treatment plans) can be chosen as heuristics to determine clinically acceptable plans. These ranges can be used either binary or probabilistic. The ranges can, for example, be learned intermittently or continuously from expanding clinical PAD, e.g. for a given clinic.

[0142] 2. Non-trivial combination of parameters: Instead of heuristics, multivariate analysis can be applied to characterize the set of plans with high probability of clinical acceptance.

[0143] Dosimetry may, in some examples, not be the only criteria for clinical acceptance. Further, the arc setup, delivery time and complexity can be modeled in a similar way. As an example, complexity may depend on field size (smaller is more complex) and on the leaves and gantry motion, e.g. large leaves motion between two gantry positions means more complexity. High variation of dose rate also means more complexity.

[0144] Any of the above modeling approaches may be used in the steps S12a, S12b, and / or S12c described above in the context of Fig. 1 or other methods of the present disclosure.

[0145] As a detailed example, a potential way of carrying out step S12a will be explained in detail below. Specifically, an example for automatic generation of a proposed (clinically acceptable) treatment plan will be described. A corresponding exemplary and non-limiting workflow is illustrated in Figs. 3a-3b, “Example usage of acceptability modeling in clinical treatment planning workflow”.

[0146] An acceptability model, such as the one described above in detail, can be used to automatically generate clinically acceptable treatment plans as follows:

[0147] Patient data may be provided, e.g. loaded, and a prescription may be provided, such as selected by a user. Based thereon, an initial (reference) plan can be provided by a user or automatically, e.g. using software modules such as RT Elements. Even a default template may be used. The initial plan may be a rough estimation and still render acceptable results, as it only serves as a starting point.

[0148] Geometric patient data and prescription data comprised in or extracted from the patient data and prescription may be used to provide / generate PAD input data.

[0149] The acceptability model may predict PAD output data comprising (acceptable) PAD output parameter values and / or ranges. Acceptability of output parameter values may be predicted by the acceptability model. This may entail predicting a probability of acceptability or a score. Alternatively, acceptability of a plan might be predicted without intermediate prediction of acceptability of output parameter values and / or ranges.

[0150] Optionally, predicted ranges and / or values of acceptable PAD output parameters can be shown in a user interface, based on the patient-specific PAD input data. Thus, information provided by the model and also be leveraged by a user, e.g. to evaluate if the initial plan or specific parameter values associated with said plan is within the range of clinical acceptability, potentially on clinic or clinician level. Alternatively or in addition, a probability of acceptability obtained by the acceptability model of the initial plan and / or parameter values may be visualized. For the example given above, a plan with Cl 1.2 and Gl 6, would give a high probability for clinical acceptance in clinic 1 but low probability in clinic 2. This information could be visualized for the planner to calculate a plan based on the models of the clinically approved plans. In addition, the user interface could show graphs representing treatment plans similar to the given plan.

[0151] In the present example, the clinical acceptable values / ranges provided by the acceptability model may be used as constraints and / or weights provided for an optimizer, specifically the optimization function, used for treatment plan generation, for example one used for obtaining the initial reference plan.

[0152] This can be done in a loop. Accordingly, the treatment plan provided using the optimizer may be iteratively improved, optionally in a fully automated manner.

[0153] The method of the present disclosure allows for the generated treatment plan to take into account the clinic or clinician practice for acceptability of plans automatically.

[0154] In an optional step, clinical acceptability of the generated treatment plan or another treatment plan may be estimated. The estimated acceptability may be used to automatically select a final treatment plan, for example by applying criteria for minimum required estimated acceptability.

[0155] Optionally, a range representation or a probability of clinical acceptability could be presented to the user alongside a generated treatment plan.

[0156] In the above examples, PAD comprise plan data. The acceptability model may take, in addition to the plan data, other input data, such as patient information like age or primary disease category. The inputs can be extended to entail a variety of parameters that are documented together with accepted treatment plans.

[0157] As can be understood from the present disclosure, the present method may acquire Plan Analytics Data (PAD) stored for a plurality of clinically accepted treatment plans, compute a patient specific reference plan, and compute a probability that a given radiotherapy treatment plan is clinically acceptable based on the acquired PAD and based on the patient specific reference plan. In an example, the acceptability model may provide a predicted acceptability of the initial plan, as well as acceptability of individual parameter ranges / values. This increases explainability of the predicted acceptability of a plan and may improve subsequent planning steps to make planning more efficient. Both may also be provided in a user interface, such that a user gains information on the parameters that influenced the prediction of the acceptability of the plan and may be causes for acceptance or non-acceptance of the plan.

[0158] For example, a user interface may indicate to a planner that the plan is estimated to be inacceptable or that there is a high likelihood of it being inacceptable. A table or plot or other visualization may, for example, be employed to show dosimetric values or the like that are out-of-range and how far they are out-of-range.

[0159] It will be understood that the method allows for increased planning efficiency leveraging, among others, learning from past treatment planning processes.

[0160] In the above detailed example as illustrated in Figs. 3a-3b, reference was made to automated generation of a radiation treatment plan.

[0161] However, it is noted that other alternatives are possible. For example, an initial or reference plan that is possible for a given input may be selected, rather than generated. The initial selection may at least in part be carried out by a user. Yet alternatively, the treatment planning process may omit automatic optimization procedure. For example, subsequent changes or selections for optimization of the treatment plan could be done via user input.

[0162] Alternatively or in addition, the output of the acceptability model may not necessarily be used for automatic generation of a treatment plan. Instead, it may be used for selection criteria for automatic or user-based selection among available potential treatment plans.

[0163] Yet alternatively, the output of the acceptability model may yield a probability of an acceptable treatment plan being achievable based on the input data. This may be used, for example, to alter the input data, particularly the prescription, automatically or based on user input. In this case, for example, no initial or reference treatment plan may be provided and no selection among potential treatment plans may be made.

[0164] All of the above contribute to improved planning efficiency. While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered exemplary and not restrictive. The invention is not limited to the disclosed embodiments. In view of the foregoing description and drawings it will be evident to a person skilled in the art that various modifications may be made within the scope of the invention, as defined by the claims.

Claims

Brainlab AGAttorney’s File: B19161WOCLAIMS1. A computer-implemented method for providing a radiation treatment planning tool, the method comprising: providing (S11) input data comprising patient anatomy and / or geometry data and prescription data as input for an acceptability model; providing (S12), making use of the acceptability model, at least one of: a proposed radiation treatment plan, the proposed radiation treatment plan being obtained by selecting and / or modifying and / or modelling a radiation treatment plan (S12a), the selecting and / or modifying and / or modelling taking into account a predicted acceptability of output parameter values of the radiation treatment plan, a predicted acceptability for a candidate radiation treatment plan and / or the proposed radiation treatment plan based on acceptability of output parameter values of the candidate radiation treatment plan and / or the proposed radiation treatment plan (S12b), the predicted acceptability to allow for subsequent determination of a radiation treatment plan, a predicted probability that a radiation treatment plan meeting a predetermined acceptability threshold exists for the input data based on acceptability of the output parameter values of potential radiation treatment plans (S12c), the predicted probability to allow for adjusting prescription data for radiation treatment plan generation, wherein the acceptability is yielded by the acceptability model, and wherein the output parameters of the radiation treatment plan comprise one or more dosimetric parameters and / or one or more treatment parameters.

2. The method of claim 1, comprising obtaining (S10) the acceptability model based on plan analytics data, PAD, the plan analytics data comprising multiple sets of PAD input data and corresponding PAD output data, wherein the PAD input data comprise patient anatomy and / or geometry data and prescription data and the corresponding PAD output data comprise corresponding dosimetric parameters and / or treatment parameters, wherein the PAD are representative of and / or comprise acceptability data, the acceptability data indicative of a recorded acceptance of PAD output parameter values, in particular clinicspecific and / or physician-specific acceptance.

3. The method of claims 1 or 2, wherein providing a proposed radiation treatment plan comprises at least one of: modelling a new a radiation treatment plan using an optimization function with one or more acceptable output parameter values, particularly ranges, as constraints and / or weights and / or modifying an initial a radiation treatment plan to yield acceptable output parameter values, particularly ranges, wherein the method comprises providing one or more proposed radiation treatment plans and associated output parameter values, particularly ranges, as well as predicted acceptable parameter values, particularly ranges, yielded by the acceptability model to a user for confirmation and / or further modification of the radiation treatment plan.

4. The method of any of the preceding claims, wherein the acceptability model employs range-based heuristics for a respective parameter range of at least one of the one or more dosimetric parameters and / or at least one of the one or more treatment parameters, the heuristics in particular employing the respective parameter range for predicting acceptability in a binary manner, e.g. acceptable or inacceptable, or in a probabilistic manner, e.g. providing a probability of acceptability, and / or wherein the model comprises a multivariate analysis of a parameter set, the parameter set comprising parameters comprised in the one or more of the dosimetric parameters and / or one or more treatment parameters, in particular the multivariate analysis configured to predict treatment plans with high probability of acceptance.

5. The method of any of claims 2 to 4, wherein the plan analytics data are alphanumeric data, and / or wherein the plan analytics data are stored as Digital Imaging and Communications in Medicine, DICOM, file, and / or wherein the plan analytics data provide a meta description of a radiation treatment plan.

6. The method of any of the preceding claims, wherein patient anatomy and / or geometry data comprise data related to a lesion, in particular may comprise at least one of a descriptor of shape of a lesion, a distance of a lesion to organs at risk, location of a lesion relative to other body parts (e.g., skull), sphericity of a lesion, convexity of a lesion, distance to other lesions, distance of a lesion to skin, diameter of a lesion, volume of a lesion.

7. The method of any of the preceding claims, wherein dosimetric parameters comprise at least one of a dose volume, a conformity index, gradient index, mean dose, and / or wherein dosimetric parameters comprise dosimetric parameters for radiation target structures and / or dosimetric parameters for anatomical risk structures, in particular organs at risk.

8. The method of any of the preceding claims, wherein the treatment parameters comprise at least one of arc trajectory, collimator information, delivery time.

9. The method of any of the preceding claims, comprising providing (S13) a final radiation treatment plan based on the proposed radiation treatment plan and / or the predicted acceptability.

10. The method of any of the preceding claims, comprising for input patient anatomy and / or geometry data and prescription data and by means of the acceptability model, predicting ranges of expected acceptable output parameter values corresponding to the given input patient anatomy and / or geometry data and prescription data, particularly clinic-specific and / or physician-specific expected acceptable output parameter values.

11. The method of claim 10, comprising generating and / or retrieving a candidate radiation treatment plan, and scoring, for a selected set of PAD output metrics how many output parameter values for the generated candidate radiation treatment plan are in the predicted ranges.

12. The method of claim 11 , comprising computing a / the probability of acceptability of the candidate radiation treatment plan as fraction of metric in range, particularly relative to a total number of evaluated metrics, and / or computing a / the probability of acceptability of the candidate radiation treatment plan as a weighted sum of the metrics calculated with clinic-specific and / or physician-specific weights.

13. The method of any of the preceding claims, comprising providing a user interface (S14), wherein the user interface is configured to indicate, for a given treatment plan, lack of acceptability of the given treatment plan, wherein lack of acceptability may be automatically determined in case the probability of acceptance is below a predetermined threshold, and / or wherein the user interface is configured to indicate for different aspects of the treatment plan, such as parameters like dosimetric values of the treatment plan, that the respective aspect is out-of-range, in particular out of an acceptable parameter value range, and optionally the extent to which the aspect is out-of-range.

14. A system for radiation treatment planning, the system comprising one or more processing devices configured to carry out the method of any of claims 1 to 13.

15. A computer program product comprising instructions which, when the program is executed by a computing system, cause the computing system to carry out the method of any of claims 1 to 13.

16. A computer readable medium having stored thereon instructions which, when the program is executed by a computing system, cause the computing system to carry out the method of any of claims 1 to 13.

Images