Treatment planning for radiotherapy
Patent Information
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- ELEKTA SHANGHAI TECH CO LTD
- Filing Date
- 2023-08-31
- Publication Date
- 2026-07-08
AI Technical Summary
Current radiotherapy treatment planning methods are inefficient and inflexible, leading to delays and reduced accuracy due to the need for frequent updates in patient anatomy and position, and limitations in imaging modalities and adaptation techniques.
A computer-implemented method for determining a radiotherapy treatment plan by obtaining a plurality of candidate plans based on different images, selecting the most suitable plan by comparing the current daily image to the candidate images, and adapting or shifting the selected plan to align with the current patient anatomy and position.
This approach enables more efficient and accurate radiotherapy treatment planning by reducing computational complexity, minimizing delays between image acquisition and treatment, and improving the alignment of treatment plans with the current patient anatomy, thereby enhancing treatment accuracy and efficiency.
Smart Images

Figure CN2023115998_06032025_PF_FP_ABST
Abstract
Description
Treatment planning for radiotherapy
[0001] This disclosure relates to radiotherapy, and in particular to methods, devices and computer-readable media for determining a radiotherapy treatment plan.Background
[0002] Radiotherapy can be described as the use of ionising radiation, such as X-rays, to treat a human or animal body. Radiotherapy is commonly used to treat cancer, for example to treat tumours within the body of a patient or subject. In such treatments, ionising radiation is used to irradiate, and thus destroy or damage, cells which form part of the tumour.
[0003] A radiotherapy device typically comprises a gantry which supports a beam generation system, or other source of radiation, which is rotatable around a patient. For example, for a linear accelerator (linac) device, the beam generation system may comprise a source of radio frequency energy, a source of electrons, an accelerating waveguide, beam shaping apparatus, etc.
[0004] Treatment may be administered to a patient according to a treatment plan. The treatment may be administered using a radiotherapy device configured to execute the treatment plan. A treatment plan for a subject may comprise information specifying the radiotherapy device parameters to be used for treating the subject. These parameters may be optimised for delivering a particular radiative dose to the anatomical position of the target (tumour) within the subject and avoiding delivering substantial dose to healthy tissue within the subject. For example, the treatment plan may specify one or more of dose rates, beam angles, time durations, beam shapes, etc.
[0005] Generating a treatment plan may comprise solving a computational problem according to mathematical objective functions. It may be desired to deliver a dose above a first threshold to a first volume of a patient and to deliver a dose below a second threshold to a second volume of the patient. These are constraints that the solution to the computational problem must meet. The solution can specify, for example, what beam shaping is to be performed, one or more time periods over which radiation is to be applied, angles around the gantry from which radiation is to be applied and / or intensity of the radiation beam. The computational problem may be solved using these degrees of freedom to meet the constraints and the treatment plan for a radiotherapy session may comprise this solution.
[0006] A treatment plan is typically generated based on a reference image of a subject, for example a CT image. This treatment plan may be referred to as a reference treatment plan. This reference image depicts the internal anatomy of the subject, including, for example, one or more tumours and organs at risk, at the time the reference image is taken. However, a course of radiotherapy treatment may take place in multiple sessions over a number of days. The internal anatomy of the subject may vary over this timespan, for example due to growth of a tumour. As such, the internal anatomy depicted in the reference image may differ relative to the internal anatomy immediately preceding a particular treatment session.
[0007] In order to account for this, adaptive treatment planning may be performed. In other words, a treatment plan may be adapted, or a new treatment plan may be generated, immediately preceding a particular treatment session, to be applied in that treatment session. For example, an image of the patient may be generated with the subject in a treatment position, i.e. on a patient positioning surface. This may be referred to as a daily image. A treatment plan may be generated based on the daily image. This may be referred to as a daily treatment plan. Basing a treatment on such a daily treatment plan according to this adaptive approach can improve treatment quality because more up-to-date anatomical information is used to generate this plan.
[0008] Since the daily treatment plan is generated based on a daily image generated with the patient in the treatment position, it is desirable that the patient does not move between generation of the daily image and application of the resulting daily treatment plan. However, since generation of a treatment plan is computationally complex, it can also be time consuming. For example, it may be 5-20 minutes after the daily image is taken that the daily treatment plan is ready for delivery. Over this timescale, the patient may experience discomfort and may, potentially inadvertently, move relative to the position they were in when the daily image was generated, and may be more likely to move during the treatment itself. This may result in the daily treatment plan being less applicable to the new position of the patient, which may reduce the accuracy of the radiotherapy treatment and / or make it more inefficient by requiring additional positional adjustments to be made.
[0009] The more the position and internal anatomy of the patient differ relative to the reference image on which the reference treatment plan is based, the more substantial and more time-consuming may be the adaptation required to generate the daily treatment plan. This can increase the delay between generation of the daily image and application of the treatment, further exacerbating the issues relating to accuracy and efficiency explained above.
[0010] Moreover, previous approaches to adaptive treatment planning may not be as flexible as would be desired. For example, previous approaches may simply adapt the most recently generated treatment plan, which may be suboptimal. In addition, previous approaches may be limited in the imaging modalities which can be used as the basis for generating treatment plans, which may not be optimal for tumours in different parts of subject anatomies. In addition, it should be appreciated that some of the delay between a daily image being taken and treatment commencing, as described above, may be due to a clinician evaluating various characteristics of a treatment plan and navigating a workflow, which may take longer than would be desirable according to previous approaches.
[0011] Accordingly, there is a need for more efficient generation of radiotherapy treatment plans. There is also a need for reducing the complexity involved in generation of radiotherapy treatment plans. There is also a need for more flexibility and / or more versatility in the generation of radiotherapy treatment plans. It would also be advantageous to increase the accuracy and / or the efficiency of radiotherapy treatments.
[0012] The present invention seeks to address these and other disadvantages encountered in the prior art.Summary
[0013] An invention is set out in the independent claims.
[0014] According to an aspect, there is provided a computer-implemented method for determining a radiotherapy treatment plan, the method comprising: obtaining a plurality of candidate treatment plans each based on a respective image of a plurality of images; obtaining a current daily image; and selecting one of the plurality of candidate treatment plans based on comparing the current daily image to the plurality of images.
[0015] According to another aspect, there is provided a computer-readable medium comprising computer-executable instructions, which, when executed by a processor, cause performance of the above-mentioned method.
[0016] According to a further aspect there is provided a control device comprising: a memory comprising computer executable instructions; and a processor configured to execute the computer executable instructions to cause performance of the above-mentioned method.
[0017] According to a further aspect there is provided a radiotherapy device comprising: a radiation source configured to generate a radiotherapy beam; an imaging device configured to generate one or more images of a subject; and the above-mentioned control device.
[0018] Figures
[0019] Specific embodiments are now described, by way of example only, with reference to the drawings, in which:
[0020] Figure 1 depicts an example radiotherapy device or apparatus according to the present disclosure;
[0021] Figure 2 depicts an example treatment planning environment according to the present disclosure;
[0022] Figure 3 depicts a further example treatment planning environment according to the present disclosure;
[0023] Figure 4 depicts example techniques for determining a current treatment plan according to the present disclosure;
[0024] Figures 5 depicts an example method for determining a treatment plan according to the present disclosure;
[0025] Figures 6a and 6b depict a further example method for determining a treatment plan according to the present disclosure;
[0026] Figure 7 depicts a block diagram of one example implementation of a radiotherapy system according to the present disclosure;
[0027] Figure 8 depicts an example computer program product according to the present disclosure.Detailed Description
[0028] The current disclosure provides techniques for determining a radiotherapy treatment plan. A plurality of candidate treatment plans are obtained. Each of the plurality of candidate treatment plans is based on a corresponding image of a plurality of images. In other words, each of the plurality of treatment plans is based on a different image of a subject, in which the anatomy and / or position of the subject may differ relative to the other images. The plurality of candidate treatment plans may include a reference treatment plan and one or more previous daily treatment plans. Accordingly, the plurality of images may include a reference image and one or more previous daily images. A current daily image is obtained. This current daily image of the subject may depict the most up to date anatomy and position of the subject. The current daily image is compared to the plurality of images, and one of the plurality of candidate treatment plans is selected based on the comparison. The selected treatment plan may be the candidate treatment plan which is based on an image of the plurality of images that is most similar to the current daily image.
[0029] The techniques of the present disclosure enable more flexible, versatile and efficient use of previously-generated images and previously-generated treatment plans. According to the techniques of the present disclosure, the most suitable plan from any of the previously-generated treatment plans may be used as the basis for determining a current treatment plan to use, either through using this previously-generated treatment plan directly, or through shifting the previously-generated treatment plan to the current position of the subject, or through generating a new treatment plan based on the previously-generated treatment plan. This enables use of a treatment plan which is closest to the current anatomy and position of the subject. This also reduces the complexity of determining the current treatment plan through reducing the changes that need to be made to previously-generated treatment plans. Accordingly, the current techniques are more computationally efficient than previous approaches. Because of this, the current techniques enable faster generation of the current treatment plan, which reduces the time period between generation of the current daily image and starting treatment. This can improve the comfort of the subject and can improve the accuracy and efficiency of radiotherapy treatment.
[0030] Figure 1 depicts an example radiotherapy device suitable for delivering, and configured to deliver, a beam of radiation to a patient during radiotherapy treatment. The device and its constituent components will be described generally for the purpose of providing useful accompanying information for the present invention. The device depicted in Figure 1 is in accordance with the present disclosure and is suitable for use with the disclosed systems and apparatuses. While the device in Figure 1 is an MR-linac, the implementations of the present disclosure may be any radiotherapy device, for example a linac device.
[0031] The device 100 depicted in Figure 1 is an MR-linac. The device 100 comprises both MR imaging apparatus 112 and radiotherapy (RT) apparatus which may comprise a linac device. The MR imaging apparatus 112 is shown in cross-section in the diagram. In operation, the MR scanner produces MR images of the patient, and the linac device produces and shapes a beam of radiation and directs it toward a target region within a patient’s body in accordance with a radiotherapy treatment plan. The depicted device does not have the usual ‘housing’ which would cover the MR imaging apparatus 112 and RT apparatus in a commercial setting such as a hospital.
[0032] The MR-linac device depicted in Figure 1 comprises a source of radiofrequency waves 102, a waveguide 104, a source of electrons 106, a source of radiation 106, a collimator 108 such as a multi-leaf collimator configured to collimate and shape the beam, MR imaging apparatus 112, and a patient support surface 114. In use, the device would also comprise a housing (not shown) which, together with the ring-shaped gantry, defines a bore (though the techniques of the present disclosure are also applicable to non-bore based radiotherapy devices) . The moveable support surface 114 can be used to move a patient, or other subject, into the bore when an MR scan and / or when radiotherapy is to commence. The terms patient and subject may be used interchangeably herein. The MR imaging apparatus 112, RT apparatus, and a subject support surface actuator are communicatively coupled to a control device, which may also be referred to as a controller or processor. The controller is also communicatively coupled to a memory device comprising computer-executable instructions which may be executed by the controller.
[0033] The RT apparatus comprises a source of radiation and a radiation detector (not shown) . Typically, the radiation detector is positioned diametrically opposed to the radiation source. The radiation detector is suitable for, and configured to, produce radiation intensity data. In particular, the radiation detector is positioned and configured to detect the intensity of radiation which has passed through the subject. The radiation detector may also be described as radiation detecting means, and may form part of a portal imaging system.
[0034] The radiation source may comprise a beam generation system. For a linac, the beam generation system may comprise a source of RF energy 102, an electron gun 106, and a waveguide 104. The radiation source is attached to the rotatable gantry 116 so as to rotate with the gantry 116. In this way, the radiation source is rotatable around the patient so that the treatment beam 110 can be applied from different angles around the gantry 116. In a preferred implementation, the gantry is continuously rotatable. In other words, the gantry can be rotated by 360 degrees around the patient, and in fact can continue to be rotated past 360 degrees. The gantry may be ring-shaped. In other words, the gantry may be a ring-gantry.
[0035] The source 102 of radiofrequency waves, such as a magnetron, is configured to produce radiofrequency waves. The source 102 of radiofrequency waves is coupled to the waveguide 104 via circulator 118, and is configured to pulse radiofrequency waves into the waveguide 104. Radiofrequency waves may pass from the source 102 of radiofrequency waves through an RF input window and into an RF input connecting pipe or tube. A source of electrons 106, such as an electron gun, is also coupled to the waveguide 104 and is configured to inject electrons into the waveguide 104. In the electron gun 106, electrons are thermionically emitted from a cathode filament as the filament is heated. The temperature of the filament controls the number of electrons injected. The injection of electrons into the waveguide 104 is synchronised with the pumping of the radiofrequency waves into the waveguide 104. The design and operation of the radiofrequency wave source 102, electron source and the waveguide 104 is such that the radiofrequency waves accelerate the electrons to very high energies as the electrons propagate through the waveguide 104.
[0036] The design of the waveguide 104 depends on whether the linac accelerates the electrons using a standing wave or travelling wave, though the waveguide typically comprises a series of cells or cavities, each cavity connected by a hole or ‘iris’ through which the electron beam may pass. The cavities are coupled in order that a suitable electric field pattern is produced which accelerates electrons propagating through the waveguide 104. As the electrons are accelerated in the waveguide 104, the electron beam path is controlled by a suitable arrangement of steering magnets, or steering coils, which surround the waveguide 104. The arrangement of steering magnets may comprise, for example, two sets of quadrupole magnets.
[0037] Once the electrons have been accelerated, they may pass into a flight tube. The flight tube may be connected to the waveguide by a connecting tube. This connecting tube or connecting structure may be called a drift tube. The electrons travel toward a heavy metal target which may comprise, for example, tungsten. Whilst the electrons travel through the flight tube, an arrangement of focusing magnets act to direct and focus the beam on the target.
[0038] To ensure that propagation of the electrons is not impeded as the electron beam travels toward the target, the waveguide 104 is evacuated using a vacuum system comprising a vacuum pump or an arrangement of vacuum pumps. The pump system is capable of producing ultra-high vacuum (UHV) conditions in the waveguide 104 and in the flight tube. The vacuum system also ensures UHV conditions in the electron gun. Electrons can be accelerated to speeds approaching the speed of light in the evacuated waveguide 104.
[0039] The source of radiation is configured to direct a beam 110 of therapeutic radiation toward a patient positioned on the patient support surface 114. The source of radiation may comprise a heavy metal target toward which the high energy electrons exiting the waveguide are directed. When the electrons strike the target, X-rays are produced in a variety of directions. A primary collimator may block X-rays travelling in certain directions and pass only forward travelling X-rays to produce a treatment beam 110. The X-rays may be filtered and may pass through one or more ion chambers for dose measuring. The beam can be shaped in various ways by beam-shaping apparatus, for example by using a multi-leaf collimator 108, before it passes into the patient as part of radiotherapy treatment.
[0040] In some implementations, the source of radiation is configured to emit either an X-ray beam or an electron particle beam. Such implementations allow the device to provide electron beam therapy, i.e. a type of external beam therapy where electrons, rather than X-rays, are directed toward the target region. It is possible to ‘swap’ between a first mode in which X-rays are emitted and a second mode in which electrons are emitted by adjusting the components of the linac. In essence, it is possible to swap between the first and second mode by moving the heavy metal target in or out of the electron beam path and replacing it with a so-called ‘electron window’ . The electron window is substantially transparent to electrons and allows electrons to exit the flight tube.
[0041] The subject or patient support surface 114 is configured to move between a first position substantially outside the bore, and a second position substantially inside the bore. In the first position, a patient or subject can mount the patient support surface. The support surface 114, and patient, can then be moved inside the bore, to the second position, in order for the patient to be imaged by the MR imaging apparatus 112 and / or imaged or treated using the RT apparatus. The movement of the patient support surface is effected and controlled by a subject support surface actuator, which may be described as an actuation mechanism. The actuation mechanism is configured to move the subject support surface in a direction parallel to, and defined by, the central axis of the bore. The terms subject and patient are used interchangeably herein such that the subject support surface can also be described as a patient support surface. The subject support surface may also be referred to as a moveable or adjustable couch or table.
[0042] The radiotherapy apparatus / device depicted in Figure 1 also comprises MR imaging apparatus 112. The MR imaging apparatus 112 is configured to obtain images of a subject positioned, i.e. located, on the subject support surface 114. The MR imaging apparatus 112 may also be referred to as the MR imager. The MR imaging apparatus 112 may be a conventional MR imaging apparatus operating in a known manner to obtain MR data, for example MR images. The skilled person will appreciate that such a MR imaging apparatus 112 may comprise a primary magnet, one or more gradient coils, one or more receive coils, and an RF pulse applicator. The operation of the MR imaging apparatus is controlled by the controller.
[0043] The control device is a computer, processor, or other processing apparatus. The control device may be formed by several discrete processors; for example, the control device may comprise an MR imaging apparatus processor, which controls the MR imaging apparatus 110; an RT apparatus processor, which controls the operation of the RT apparatus; and a subject support surface processor which controls the operation and actuation of the subject support surface. The control device is communicatively coupled to a memory, e.g. a computer readable medium.
[0044] The linac device also comprises several other components and systems as will be understood by the skilled person. For example, in order to ensure the linac does not leak radiation, appropriate shielding is also provided.
[0045] The radiotherapy device and / or the control device may be configured to perform any of the method steps presently disclosed and may comprise computer executable instructions which, when executed by a processor cause the processor to perform any of the method steps presently disclosed, or when executed by the control device cause the control device to perform any of the method steps presently disclosed, or when executed by the radiotherapy device cause the radiotherapy device to perform any of the method steps presently disclosed. Any of the steps that the radiotherapy device and / or the control device is configured to perform may be considered as method steps of the present disclosure and may be embodied in computer executable instructions for execution by a processor. A computer-readable medium may comprise the above-described computer executable instructions.
[0046] Figure 2 depicts an example treatment planning environment 200 according to the present disclosure. The treatment planning environment 200 may be computationally implemented. The treatment planning environment 200 may be implemented according to any of the features and techniques described in relation to Figures 7 and 8 below.
[0047] The treatment planning environment 200 comprises candidate treatment plans 210. The candidate treatment plans 210 may be described as existing or previously determined treatment plans.
[0048] Candidate treatment plans 210 may be described as treatment plans which are available for use in an upcoming treatment session, either directly or following some adjustment or coordinate shift.
[0049] The treatment planning environment 200 comprises a plurality of images 220, i.e. images of a subject. The plurality of images 220 may have been generated using any suitable imaging modality, including MR (magnetic resonance) imaging, CT (computed tomography) / CBCT (cone beam computed tomography) / X-ray, sCT (synthetic CT) , PET (positron emission tomography) , optical imaging, infra-red imaging, ultra-sound imaging or time-of-flight techniques, etc. One, multiple, or all of the plurality of images 220 may depict the internal anatomy of the subject. The plurality of images may be images suitable for use in treatment planning.
[0050] Each of the candidate treatment plans 210 may be based on a respective image of the plurality of images 220. Each image of the plurality of images 220 may depict different sizes and / or shapes and / or positions of tumours and / or organs at risk. A treatment plan of the candidate treatment plans 210 which corresponds to an image of the plurality of images 220 may be generated so as to optimise the dose distribution to the anatomy of the subject as depicted in that image. In other words, the calculations and determinations which are performed as part of generation of the treatment plan may seek to apply a clinically specified dose to one or more tumours depicted in that image, and to apply less than a clinically specified dose to one or more organs at risk.
[0051] The candidate treatment plans 210 may comprise a reference plan 212. The plurality of images 220 may comprise a reference image 222. The reference plan 212 may be generated based on the reference image 222. The reference image 222 may be the earliest generated image of the plurality of images 220, e.g. may have been generated before any treatment sessions have occurred. The reference image 222 may be a CT image. The reference image 222 may serve as a baseline for the spatial coordinates, anatomy and / or position of the subject.
[0052] The candidate treatment plans 210 may comprise one or more previous daily plans 214, i.e. previous daily plans 214i to 214n. The plurality of images 220 may comprise one or more previous daily images 224, i.e. previous daily images 224i to 224n. The number (n minus i) of previous daily plans 214 may equal the number (n minus i) of previous daily images 224. Each of the previous daily plans 214 may be based on a respective previous daily image 224. Each of the previous daily images 224 may have been generated on a different respective day, e.g. before a respective treatment session on that respective day. It is common for radiotherapy treatment to be administered in multiple treatment sessions each on a respective day. Before each of these treatment sessions, a respective daily image may be generated. Each of the previous daily images 224 may be a daily image generated on / for a treatment session on a previous day, i.e. on a day previous to a current time / day. Each of the previous daily images 224 may have been generated subsequent to generation of the reference image 222.
[0053] The treatment planning environment 200 comprises a current daily image 230, i.e. an image of the subject. The current daily image 230 may be a daily image generated before a treatment session which is about to occur. In other words, at a present time currently being considered, the current daily image 230 may be the most recently generated image of the plurality of images 220. The present time currently being considered may be on a day a treatment session is scheduled to occur, shortly before the treatment session is scheduled to begin, e.g. approximately 1, 2, 3, 4, 5, 10, 15 or 20 minutes before the treatment session is to begin. The current daily image 230 may have been generated subsequent to generation of the reference image 222 and subsequent to generation of the previous daily images 224.
[0054] The treatment planning environment comprises a current treatment plan 240. The current treatment plan 240 may be a treatment plan suitable to be used for administering a treatment session at the present time currently being considered. The current treatment plan 240 may be determined based on the current daily image 230. As described further herein, the current treatment plan 240 may be determined further based on one or more of the plurality of images 220 and on one or more of the candidate treatment plans 210. In particular, the current treatment plan 240 may be determined, generated, selected, shifted or adapted based on comparing the current daily image 230 to the plurality of images 220. The current treatment plan 240 may be based on a treatment plan of the candidate treatment plans 210 for which the corresponding image of the plurality of images 220 is most similar to the current daily image 230.
[0055] Figure 3 depicts a further example treatment planning environment 300 according to the present disclosure. The treatment planning environment 300 may be computationally implemented. The treatment planning environment 300 may be implemented according to any of the features and techniques described in relation to Figures 7 and 8 below. Treatment planning environment 300 may be part of the same treatment planning environment as treatment planning environment 200, or may be combined with treatment planning environment 200.
[0056] Treatment planning environment 300 comprises the reference image 222, previous daily images 224i to 224n and current daily image 230. Treatment planning environment 300 also comprises the reference plan 212, previous daily plans 214i to 214n and current plan 240.
[0057] Treatment planning environment 300 also comprises a number of coordinate shifts or SROs (spatial registration objectives) . Each of these SROs defines the coordinate shift between two images. Each of the SROs may be generated by registration of one image to the other image, image fusion, or any other suitable technique. The SROs may be computationally generated and may be confirmed or verified by a clinician, which may improve the safety of radiotherapy techniques and workflows as described herein. The SROs may be expressed as vectors in any suitable coordinate system, e.g. may indicate an X, Y, Z shift between two images.
[0058] Each of the SROs may define the coordinate shift between an image and the reference image 222. As depicted in Figure 3, SROi may define the coordinate shift between previous daily image 224i and reference image 222. SROn may define the coordinate shift between previous daily image 224n and reference image 222. SROcurrent may define the coordinate shift between current daily image 230 and reference image 222. According to the current disclosure, an SRO may be determined and stored for any / all generated images, i.e. all reference images 222, previous daily images 224i to 224n and current daily image 230. This enables each image to be related to each other image, which advantageously enables more flexible and efficient use of previously generated images and plans, as will be described below.
[0059] According to some previous approaches, only a reference plan may be used for determining a current plan. However, the anatomy on which this is based may differ significantly relative to the current subject anatomy, which may entail more significant and more time-consuming adaptation than is desirable. According to other previous approaches, only a most recently generated plan may be used for determining a current plan on the assumption that this will be most relevant to the current anatomy of the subject. However, in some cases, for example lung cancer, the most recently generated plan may be less good than older plans since it may be more important to select an image in which the state of the lung is similar (e.g. in terms of atelectasis and pulmonary dilation) than an image which is more recent.
[0060] According to the current disclosure, a current plan 240 may be based on any previously-generated treatment plan, i.e. any of candidate plans 210. For example, current plan 240 could be determined based on reference plan 212 or based on any of previous daily plans 214i to 214n. The images 222 224i to 224n and 230, and the coordinate shifts between them, may be used to relate the plans 212, 214i to 214n and 240 to each other as appropriate. In other words, one or more of the candidate plans 210 may be translated, shifted or adapted based on the images and coordinate shifts to make the one or more of the candidate plans 210 more applicable to or aligned with a current position or anatomy of the subject.
[0061] For example, previous daily plan 214n may be selected as the plan on which to base the current plan 240. In this case, the previous daily plan 214n may first be shifted according to coordinate shift SROn, and second be shifted according to coordinate shift SROcurrent. Since in general the position of the subject will have moved between the previous daily image 224n and the current daily image 230, these coordinate shifts account for that change by translating the previous daily plan 214n from being applicable to a subject located as depicted in previous daily image 224n to the subject located as depicted in current daily image 230. In particular, this may be performed by way of a first translation of the previous daily plan 214n to be applicable to a subject located as depicted in the reference image 222, and a second translation of the previous daily plan 214n, translated to be applicable to the subject located as depicted in the reference image 222, to be applicable to a subject located as depicted in the current daily image 230. In other examples, the coordinate shifts SROn and SROcurrent may be resolved, i.e. added together or otherwise combined, to define a single coordinate shift accounting for both these individual coordinate shifts.
[0062] Figure 4 depicts example techniques for determining a current treatment plan according to the present disclosure. These techniques may be computationally implemented and may be implemented according to any of the features and techniques described in relation to Figures 7 and 8 below. These techniques may be implemented as part of treatment planning environment 200 and / or treatment planning environment 300.
[0063] Figure 4 depicts the candidate treatment plans 210, including reference plan 212 and previous daily plans 214i to 214n. Figure 4 also depicts the current treatment plan 240. As depicted in Figure 4, there are various different options for determining current treatment plan 240 according to the present disclosure.
[0064] One of candidate treatment plans 210 may be selected, this one of the candidate treatment plans 210 being referred to as selected treatment plan 250. Selected treatment plan 250 may be selected based on comparing the plurality of images 220 to the current daily image 230, i.e. by determining which of the plurality of images 220 is closest to or most similar to the current daily image 230. This may be determined by registering one image to the other, subtracting one image from the other, determining a coordinate shift between the images, determining a similarity of shape / position of tumours / organs at risk in the images and / or any other suitable techniques. The one of the candidate treatment plans 210 selected as the selected treatment plan 250 may be the treatment plan corresponding to the image of the plurality of images 220 which is closest or most similar to the current daily image 230.
[0065] According to a first example, it is determined to use the selected treatment plan 250 directly as the current treatment plan 240. This may, for example, be based on a determination that the position and anatomy of the subject in the current daily image 230 are highly similar to the position and anatomy of the subject in the image corresponding to the treatment plan selected from the candidate treatment plans 210. For example, this high similarity may be determined, by determining whether the relative positional changes and relative anatomical changes are within one or more respective thresholds.
[0066] According to a second example, the selected treatment plan 250 may be used as the starting point for generating a new treatment plan 262, which may then be used as the current treatment plan 240. This may, for example, be based on a determination that the anatomy and / or the position of the subject in the current daily image 230 are dissimilar (e.g. outside one or more thresholds) to the anatomy and / or the position of the subject in the image corresponding to the treatment plan selected from the candidate treatment plans 210. This example may also be described as adapting the selected treatment plan 250. For example, when generating the new treatment plan 262, one or more of its parameters may have starting values corresponding to the values in the selected treatment plan 250, and may be adapted or optimised starting from those starting values. Because the selected treatment plan 250 is based on an image close to the current subject anatomy, as depicted in the current daily image 230, this may reduce the computation required to arrive at the current treatment plan 240, for example by reducing the number of iterations needed to generate it when compared to optimising from generic starting values.
[0067] According to a third example, the selected treatment plan 250 may be shifted 264 to determine a shifted treatment plan. This may, for example, be based on a determination that the position of the subject in the current daily image 230 is dissimilar (e.g. outside one or more thresholds) to the position of the subject in the image corresponding to the treatment plan selected from the candidate treatment plans 210. The selected treatment plan 250 may be translated, e.g. in X and / or Y and / or Z coordinates, such that it is applicable to a subject as positioned in the current daily image 230. For example, this coordinate shift may be or may be based on one or more of the coordinate shifts / SROs described in relation to Figure 3. This example may increase the efficiency of determining the current treatment plan 240 by removing the need to generate a new treatment plan, but rather translating the most appropriate of the previously-generated candidate treatment plans 210, which is less computationally complex and less time-consuming.
[0068] According to a fourth example, the selected treatment plan 250 may be shifted 264 to determine a shifted treatment plan and this shifted treatment plan may be used as the starting point for generating a new treatment plan 262, which may then be used as the current treatment plan 240. In other words, this example may be a combination of the second and third examples described above. This may, for example, be based on a determination that the anatomy and / or the position of the subject in the current daily image 230 are dissimilar (e.g. outside one or more thresholds) to the anatomy and / or the position of the subject in the image corresponding to the treatment plan selected from the candidate treatment plans 210. This example may further increase the efficiency of determining the current treatment plan 240. This is because it is computationally complex to take account of both anatomical changes and position shifts when adapting or generating a treatment plan. Performing deformable image registration on one or more anatomical features which have changed shape and moved may require additional iterations to arrive at a result, which may increase the computation and time required to arrive at an appropriate treatment plan. According to the fourth example, the position shift is first taken into account at 264, and a new treatment plan is then generated based on this at 262. Because the shift has already been accounted for at 264, the generation at 262 is faster and less computationally complex because it may only need to account for anatomical shape changes when performing deformable image registration.
[0069] Therefore, the current disclosure enables efficient re-use of previously generated images and treatment plans, and increased flexibility in the way these can be used in order to enable further efficiency gains.
[0070] Figure 5 depicts an example method 500 for determining a treatment plan according to the present disclosure. These techniques may be computationally implemented and may be implemented according to any of the features and techniques described in relation to Figures 7 and 8 below.
[0071] These techniques may be implemented as part of treatment planning environment 200 and / or treatment planning environment 300.
[0072] In a step 502, the method may comprise obtaining a plurality of candidate treatment plans 210 each based on a respective image of a plurality of images 220. The candidate treatment plans 210 may comprise a reference plan 212 and may comprise one or more previous daily plans 214. The plurality of images 220 may comprise a reference image 222 and may comprise one or more previous daily images 224. In some examples, the candidate treatment plans 210 and / or the plurality of images 220 may be obtained by retrieving them from storage. In some examples, the candidate treatment plans 210 and / or the plurality of images 220 may be obtained by generating them using a computer (e.g. comprising treatment planning software) and an imaging device respectively. The plurality of images 210 may have been generated using any suitable imaging modality, including CT, CBCT, MRI / sCT, etc.
[0073] In a step 504, the method 500 may comprise obtaining a current daily image 230. In some examples, the current daily image 230 may be retrieved from storage. In some examples, the current daily image 230 may be generated using an imaging device using any suitable imaging modality, including CT, CBCT, MRI / sCT, etc.
[0074] In a step 506, the method 500 may comprise selecting one of the plurality of candidate treatment plans 210 based on comparing the current daily image 230 to the plurality of images 220. The selected treatment plan 250 may be the treatment plan of the plurality of candidate treatment plans 210 which corresponds to / is based on the image of the plurality of images 220 which is determined, via the comparing, to be most similar to the current daily image 230. The selected treatment plan 250 may be used as the current treatment plan 240 directly, or may be used as the basis for the current treatment plan 240 via adapting the selected treatment plan 250 / generating a new treatment plan and / or shifting the selected treatment plan 250.
[0075] Figures 6a and 6b depict a further example method 600 for determining a treatment plan according to the present disclosure. These techniques may be computationally implemented and may be implemented according to any of the features and techniques described in relation to Figures 7 and 8 below. These techniques may be implemented as part of treatment planning environment 200 and / or treatment planning environment 300. Method 600 may be considered to be an example workflow for determining a treatment plan. Figures 6a and 6b depict respective parts of the same method 600.
[0076] Beginning with Figure 6a, in a step 602, the method 600 may comprise daily image acquisition 602 of sCT and CBCT images. As the skilled person would understand, acquisition of the sCT image may comprise acquisition of an MR image and generation of a pseudo-CT or synthetic CT ( ‘sCT’ ) image based on this.
[0077] In a step 604, the method 600 may comprise calculating and confirming the SRO. The SRO may describe a coordinate shift, e.g. between the daily image (s) and a reference image. Confirming the SRO may comprise a clinician checking the SRO.
[0078] In a step 606, the method 600 may comprise correcting the position by SRO. In other words, the SRO calculated in step 604 may be corrected or adjusted, for example based on the check by the clinician.
[0079] In a step 608, the method 600 may comprise registering the daily and reference images by SRO. In other words, the daily image may be mapped onto the reference image using the coordinate shift defined in the SRO. This may account for changes in position of the subject.
[0080] In a step 610, the method 600 may comprise adapting anatomy from reference to daily image, then editing and confirming. This may account for changes in shape of parts of the anatomy of the subject. The initial adaptation may be performed automatically using one or more algorithms; the editing and confirming may be performed by a clinician.
[0081] In a step 612, the method 600 may comprise checking or determining which image modality to use.
[0082] If CBCT image modality is used, in a step 614 the method may comprise calculating the reference plan on a reference CT image with the adapted anatomy of the subject.
[0083] If sCT image modality is used, in a step 616 the method may comprise calculating the reference plan on a daily CT image with the adapted anatomy of the subject.
[0084] In a step 618, the method 600 may comprise evaluating the reference plan with the adapted anatomy of the subject.
[0085] Turning to Figure 6b, which follows directly from Figure 6a (i.e. step 620 of Figure 6b follows on from step 618 of Figure 6a) , in a step 620 the method 600 may comprise checking or determining whether to accept the reference plan. For example, it may be determined whether the reference plan meets one or more dosimetric objectives of the treatment and basing the checking or determining on this.
[0086] If the reference plan is used, the method 600 may continue to a step 634 of exporting the radiotherapy plan (i.e. the reference plan) .
[0087] If the reference plan is not used, the method 600 may continue to a step 622 of checking or determining which image modality to use.
[0088] If CBCT image modality is used, in a step 624 the method 600 may comprise checking or determining whether to generate a plan based on CBCT or based on reference CT.
[0089] If CBCT is used, in a step 628 the method may comprise creating a plan based on CBCT with adapted density from reference CT.
[0090] If reference CT is used, in a step 630 the method 600 may comprise creating an adaptive plan based on the reference CT with adapted subject anatomy.
[0091] If sCT image modality is used, in a step 626 the method 600 may comprise creating an adaptive plan based on daily sCT with adapted subject anatomy.
[0092] Following on from step 628, 630 or 626, as applicable, in a step 632 the method 600 may comprise selecting the best plan based on comparison between adapted plan and reference plans (including previous adapted plan) . For example, the best plan may be considered to be the plan which meets the highest number of dosimetric objectives, e.g. based on exceeding and / or not exceeding respective thresholds.
[0093] In a step 634 following on from step 632, the method 600 may comprise exporting the radiotherapy plan, i.e. the best plan selected in step 632.
[0094] It will be appreciated that the method 600 provides significant flexibility in use / re-use of previously generated images and treatment plans in order to determine the best treatment plan to use for a given treatment session, current subject anatomy and current subject position. Determining the best treatment plan to use may take into account which treatment plan will provide the most dosimetrically desirable treatment and which treatment plan will be providable fastest and with the highest computational efficiency. It will be appreciated that one or more steps of method 600 may be omitted, for example depending on the particular treatment planning scenario being considered.
[0095] According to the techniques of the present disclosure, a translation of spatial coordinates of a treatment plan may be performed before the treatment plan is adapted. The translation may be based on comparing the current daily image to the previous image on which the treatment plan is based. The translation may be based on the spatial registration objective (SRO) for these images, which may be verified by a clinician. The translation may take into account changes in position of the subject between the images. The adaptation of the treatment plan then takes into account the changes in the shapes of parts of the anatomy of the subject, for example through deformable image registration. Isolating this from the changes in position may make the adaptation faster, more efficient and more accurate.
[0096] According to previous approaches, conventional linacs generally use CBCT as the daily image. However, sites may also be configured with some in-house or vender’s software to generate synthetic CT (sCT) images based on MR images. According to the techniques of the present disclosure, the system and workflow are able to consume either CBCT or sCT as the input daily image. The difference between use of these in the workflow is how to collect the electron density for each voxel, which is important for dose calculation accuracy. For a CBCT image, the mean average density of each organ based on the reference image may be automatically adopted. For an sCT image, the density in the sCT image could be used, or the user (e.g. a clinician) could determine to use the same strategy as used with CBCT. Incorporating the ability to use either CBCT or sCT daily images provides more flexibility to users. Moreover, users could use different daily image sources for different indications for which different imaging modalities are advantageous. For example, a clinic could use sCT for tumours in the lung of a subject, but use CBCT for other indications. The techniques of the current disclosure enable acceptance of both image modalities and provide an integrated and similar workflow, thus reducing system complexity and the learning curve for users. According to the techniques of the present disclosure, a plan evaluation strategy may be provided to a user, e.g. a clinician, to help selection of the most suitable treatment plan. A number of criteria may be defined. These may be dosimetric criteria, such as whether a tumour receives a dose equal to or exceeding a first threshold and whether an organ at risk receives a dose not exceeding a second threshold. The number of satisfied criteria for each plan may be summed to provide a respective total number of satisfied criteria for each plan. The plans may be ordered by this total number of satisfied criteria. In some examples, the plan evaluation strategy may take into account if a plan almost satisfies a criterion, e.g. whether it is within a predefined absolute value or predefined percentage of the criterion. For example, the plan evaluation strategy may assign a value of 1 to a satisfied criterion and a value of 0.5 to an almost satisfied criterion. The criteria used may be customisable or selectable by users, allowing them to assess plans according to the requirements most relevant for an upcoming treatment. This approach of the present disclosure is more efficient than previous approaches, such as a clinician needing to compare the dose distribution and dose-volume histogram (DVH) between a current adaptive plan and reference plans, which may require the clinician to look through additional data in detail. The plan evaluation strategy referred to above may be applied to candidate treatment plans or may be applied to one more determined current treatment plans.
[0097] Workflows for generating an adaptive plan may sometimes be found to be long and to not provide a user (e.g. a clinician) with as much guidance as would be desirable for leading them through different stages of the workflow. According to the techniques of the present disclosure, a streamlined interface tool, e.g. a graphical user interface, may be provided which displays the current status, historic steps and / or coming steps in a workflow. This may provide more cohesive guidance to the user in the context of the workflow as a whole. It may also display selectable or adjustable options at decision points, which enable the user to make selections to determine which of two or more options to follow in the workflow. The user selection may be input using an input device. This may enable more accurate steps to be taken in the workflow more quickly, which may improve the accuracy and efficiency of treatment and treatment planning.
[0098] Figure 7 illustrates a block diagram of one example implementation of a radiotherapy system 700. The radiotherapy system 700 comprises a computing system 710 within which a set of instructions, for causing the computing system 710 to perform any one or more of the methods discussed herein, may be executed.
[0099] The computing system 710 shall be taken to include any number or collection of machines, e.g. computing device (s) , that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methods discussed herein. That is, hardware and / or software may be provided in a single computing device, or distributed across a plurality of computing devices in the computing system. In some implementations, one or more elements of the computing system may be connected (e.g., networked) to other machines, for example in a Local Area Network (LAN) , an intranet, an extranet, or the Internet. One or more elements of the computing system may operate in the capacity of a server or a client machine in a client-server network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. One or more elements of the computing system may be a personal computer (PC) , a tablet computer, a set-top box (STB) , a Personal Digital Assistant (PDA) , a cellular telephone, a web appliance, a server, a network router, switch or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine.
[0100] The computing system 710 includes controller circuitry 711 and a memory 713 (e.g., read-only memory (ROM) , flash memory, dynamic random access memory (DRAM) such as synchronous DRAM (SDRAM) or Rambus DRAM (RDRAM) , etc. ) . The memory 713 may comprise a static memory (e.g., flash memory, static random access memory (SRAM) , etc. ) , and / or a secondary memory (e.g., a data storage device) , which communicate with each other via a bus (not shown) .
[0101] Controller circuitry 711 represents one or more general-purpose processors such as a microprocessor, central processing unit, accelerated processing units, or the like. More particularly, the controller circuitry 711 may comprise a complex instruction set computing (CISC) microprocessor, reduced instruction set computing (RISC) microprocessor, very long instruction word (VLIW) microprocessor, processor implementing other instruction sets, or processors implementing a combination of instruction sets. Controller circuitry 711 may also include one or more special-purpose processing devices such as an application specific integrated circuit (ASIC) , a field programmable gate array (FPGA) , a digital signal processor (DSP) , network processor, or the like. One or more processors of the controller circuitry may have a multicore design. Controller circuitry 711 is configured to execute the processing logic for performing the operations and steps discussed herein.
[0102] The computing system 710 may further include a network interface circuitry 715. The computing system 710 may be communicatively coupled to an input device 720 and / or an output device 730, via input / output circuitry 717. In some implementations, the input device 720 and / or the output device 730 may be elements of the computing system 710. The input device 720 may include an alphanumeric input device (e.g., a keyboard or touchscreen) , a cursor control device (e.g., a mouse or touchscreen) , an audio device such as a microphone, and / or a haptic input device. The output device 730 may include an audio device such as a speaker, a video display unit (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT) ) , and / or a haptic output device. In some implementations, the input device 720 and the output device 730 may be provided as a single device, or as separate devices.
[0103] In some implementations, computing system 710 includes training circuitry 718. The training circuitry 718 may be configured to train a method of determining a radiotherapy treatment plan. For example, training circuitry 718 may train a model for performing a method of determining a radiotherapy treatment plan. The model may comprise a deep neural network (DNN) , such as a convolutional neural network (CNN) and / or recurrent neural network (RNN) . Training circuitry 718 may be configured to execute instructions to train a model that can be used to determine a radiotherapy treatment plan, as described herein. Training circuitry 718 may be configured to access training data and / or testing data from memory 713 or from a remote data source, for example via network interface circuitry 715. In some examples, training data and / or testing data may be obtained from an external component, such as image acquisition device 740 and / or treatment device 750. In some implementations, training circuitry 718 may be used to update, verify and / or maintain the model for determining a radiotherapy treatment plan.
[0104] In some implementations, the computing system 710 may comprise image processing circuitry 719. Image processing circuitry 719 may be configured to process image data 780 (e.g. images, or imaging data) , such as medical images obtained from one or more imaging data sources, a treatment device 750 and / or an image acquisition device 740. Image processing circuitry 719 may be configured to process, or pre-process, image data. For example, image processing circuitry 719 may convert received image data into a particular format, size, resolution or the like. In some implementations, image processing circuitry 719 may be combined with controller circuitry 711.
[0105] In some implementations, the radiotherapy system 700 may further comprise an image acquisition device 740 and / or a treatment device 750, such as those disclosed herein. The image acquisition device 740 and the treatment device 750 may be provided as a single device. In some implementations, treatment device 750 is configured to perform imaging, for example in addition to providing treatment and / or during treatment. The treatment device 750 comprises the main radiation delivery components of the radiotherapy system, such as the linac.
[0106] Image acquisition device 740 may be configured to perform positron emission tomography (PET) , computed tomography (CT) , cone beam computed tomography (CBCT) , magnetic resonance imaging (MRI) , etc.
[0107] Image acquisition device 740 may be configured to output image data 780, which may be accessed by computing system 710. Treatment device 750 may be configured to output treatment data 760, which may be accessed by computing system 710.
[0108] Computing system 710 may be configured to access or obtain treatment data 760, planning data 770 and / or image data 780. Treatment data 760 may be obtained from an internal data source (e.g. from memory 713) or from an external data source, such as treatment device 750 or an external database. Planning data 770 may be obtained from memory 713 and / or from an external source, such as a planning database. Planning data 770 may comprise information obtained from one or more of the image acquisition device 740 and the treatment device 750.
[0109] The various methods described above may be implemented by a computer program. The computer program may include computer code (e.g. instructions) 810 arranged to instruct a computer to perform the functions of one or more of the various methods described above. The steps of the methods described above may be performed in any suitable order. For example, a step may be performed before, after, simultaneously or substantially simultaneously with another step. The computer program and / or the code 810 for performing such methods may be provided to an apparatus, such as a computer, on one or more computer readable media or, more generally, a computer program product 800, depicted in Figure 8. The computer readable media may be transitory or non-transitory. The one or more computer readable media 800 could be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or a propagation medium for data transmission, for example for downloading the code over the Internet. Alternatively, the one or more computer readable media could take the form of one or more physical computer readable media such as semiconductor or solid state memory, magnetic tape, a removable computer diskette, a random access memory (RAM) , a read-only memory (ROM) , a rigid magnetic disc, and an optical disk, such as a CD-ROM, CD-R / W or DVD. The instructions 810 may also reside, completely or at least partially, within the memory 713 and / or within the controller circuitry 711 during execution thereof by the computing system 710, the memory 713 and the controller circuitry 711 also constituting computer-readable storage media.
[0110] In an implementation, the modules, components and other features described herein can be implemented as discrete components or integrated in the functionality of hardware components such as ASICS, FPGAs, DSPs or similar devices.
[0111] A “hardware component” is a tangible (e.g., non-transitory) physical component (e.g., a set of one or more processors) capable of performing certain operations and may be configured or arranged in a certain physical manner. A hardware component may include dedicated circuitry or logic that is permanently configured to perform certain operations. A hardware component may comprise a special-purpose processor, such as an FPGA or an ASIC. A hardware component may also include programmable logic or circuitry that is temporarily configured by software to perform certain operations.
[0112] In addition, the modules and components can be implemented as firmware or functional circuitry within hardware devices. Further, the modules and components can be implemented in any combination of hardware devices and software components, or only in software (e.g., code stored or otherwise embodied in a machine-readable medium or in a transmission medium) .
[0113] Unless specifically stated otherwise, as apparent from the following discussion, it is appreciated that throughout the description, discussions utilizing terms such as “obtaining” , “selecting” , “generating” , “adapting” , "receiving” , “determining” , “comparing ” , “enabling” , “maintaining” , “identifying” or the like, refer to the actions and processes of a computer system, or similar electronic computing device, that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices.
[0114] The current disclosure comprises the following items, which are combinable with any of the techniques set out in the description and claims of the current disclosure:
[0115] A computer-implemented method for determining a radiotherapy treatment plan, the method comprising: obtaining a previously-generated treatment plan based on a previously-generated image; obtaining a current daily image; determining a coordinate shift between the current daily image and the previously-generated image; translating the previously-generated treatment plan by the coordinate shift to determine a shifted treatment plan; and generating an adapted treatment plan based on the shifted treatment plan and the current daily image. The coordinate shift may account for positional changes of the subject, while the generation of the adapted treatment plan may account for shape changes to the anatomy of the subject.
[0116] A computer-implemented method for determining a radiotherapy treatment plan, the method comprising: obtaining a previously-generated treatment plan based on a previously-generated image; obtaining a current daily image comprising a CBCT image or an sCT image; and determining an adapted treatment plan by adapting the previously-generated treatment plan based on a comparison between the previously-generated image and the current daily image. The method may be applicable to using one or both of CBCT images and sCT images as the daily image. Obtaining a current daily image may comprise obtaining a daily CBCT image and a daily sCT image and determining which of these to use as the current daily image. In other words, the method may comprise obtaining / providing CBCT and sCT images and receiving a selection of one of these images to be used as the current daily image.
[0117] A computer-implemented method for determining a radiotherapy treatment plan, the method comprising: obtaining a plurality of candidate treatment plans; for each of the candidate treatment plans, determining a respective number of criteria which are satisfied; and determining which of the candidate treatment plans to use as a current daily plan based on the respective numbers of criteria which are satisfied. The criteria may be dosimetric criteria, e.g. may comprise whether a tumour receives at least a threshold dose and / or whether an organ at risk receives below a threshold dose. The candidate treatment plan which has the highest number of satisfied criteria may be selected as or used to determine the current daily plan. The criteria may be customisable or selectable by a user.
[0118] A computer-implemented method for determining a radiotherapy treatment plan, the method comprising: generating a graphical user interface depicting at least one of current status, previous steps and future steps of a radiotherapy treatment planning workflow; and exporting the graphical user interface to a display device for display to a user. The graphical user interface maybe configured to accept user input via the display device or via an input device communicatively coupled thereto, the user input for selecting one or more of the future steps from a plurality of future steps at a decision point of the radiotherapy treatment planning workflow.
[0119] A computer-implemented method comprising: generating computer-executable instructions for displaying a graphical user interface to a clinician, the graphical user interface comprising fields for at least one of: current status of determining a radiotherapy treatment plan; previous steps in determining the radiotherapy treatment plan; upcoming workflow steps in determining the radiotherapy treatment plan; and a workflow decision point for determining the radiotherapy treatment plan; and transmitting the computer-executable instructions to a display device.
[0120] A computer-readable medium comprising instructions, which, when executed by a processor, cause performance of any of the above-mentioned methods.
[0121] A control device comprising: a memory comprising computer executable instructions; and a processor configured to execute the computer executable instructions to perform any of the above-mentioned methods.
[0122] A radiotherapy device comprising: a radiation source configured to generate a radiotherapy beam; an imaging device configured to generate one or more images of a subject; and the above-mentioned control device.
[0123] It is to be understood that the above description is intended to be illustrative, and not restrictive. Many other implementations will be apparent to those of skill in the art upon reading and understanding the above description. Although the present disclosure has been described with reference to specific example implementations, it will be recognized that the disclosure is not limited to the implementations described, but can be practiced with modification and alteration within the spirit and scope of the appended claims. Accordingly, the specification and drawings are to be regarded in an illustrative sense rather than a restrictive sense. The scope of the disclosure should, therefore, be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.
Claims
1.A computer-implemented method for determining a radiotherapy treatment plan, the method comprising:obtaining a plurality of candidate treatment plans each based on a respective image of a plurality of images;obtaining a current daily image; andselecting one of the plurality of candidate treatment plans based on comparing the current daily image to the plurality of images.2.A computer-implemented method according to claim 1, wherein selecting the one of the plurality of candidate treatment plans comprises selecting the candidate treatment plan which is based on an image, of the plurality of images, which is most similar to the current daily image.3.A computer-implemented method according to claim 1 or claim 2, wherein the plurality of candidate treatment plans comprise:a reference plan generated based on a reference image of the plurality of images; andat least one previous daily plan each generated based on a respective previous daily image of the plurality of images.4.A computer-implemented method according to claim 3, wherein the at least one previous daily plan comprises multiple previous daily plans, and the at least one previous daily image comprises multiple previous daily images.5.A computer-implemented method according to claim 3 or claim 4, wherein selecting the one of the plurality of treatment plans is based on comparing the current daily image to the reference image and to the at least one daily image.6.A computer-implemented method according to any preceding claim, comprising determining to use the selected one of the plurality of treatment plans as a current treatment plan.7.A computer-implemented method according to any of claims 1-5, comprising generating a new treatment plan based on the selected one of the plurality of treatment plans.8.A computer-implemented method according to any of claims 1-5, comprising shifting the spatial coordinates of the selected one of the plurality of treatment plans based on the comparing to generate a shifted treatment plan.9.A computer-implemented method according to claim 8, wherein the shifting of the spatial coordinates of the selected one of the plurality of treatment plans comprises performing a first translation to shift the spatial coordinates of the selected one of the plurality of treatment plans to the spatial coordinates of a subject as depicted in the reference image, and subsequently performing a second translation to shift the spatial coordinates of the selected one of the plurality of treatment plans to the spatial coordinates of the subject as depicted in the current daily image.10.A computer-implemented method according to claim 9, wherein the first translation and the second translation are based on respective coordinate shifts retrieved from storage.11.A computer-implemented method according to claim 10, wherein the coordinate shifts are spatial registration objectives.12.A computer-implemented method according to claim 10 or claim 11, wherein the coordinate shifts are verified by a clinician.13.A computer-implemented method according to any of claims 8-12, comprising determining to use the shifted treatment plan as a current treatment plan.14.A computer-implemented method according to any of claims 7-11, comprising generating a new treatment plan based on the shifted treatment plan.15.A computer-implemented method according to any preceding claim, wherein the selecting the one of the plurality of candidate treatment plans is further based on determining whether each of the plurality of candidate treatment plans satisfies a plurality of predefined criteria.16.A computer-implemented method according to claim 15, wherein at least one of the plurality of predefined criteria comprises a radiation dose to a tumour exceeding a first threshold.17.A computer-implemented method according to claim 15 or claim 16, wherein at least one of the plurality of predefined criteria comprises a radiation dose to an organ at risk not exceeding a second threshold.18.A computer-implemented method according to any of claims 15-17, wherein the plurality of predefined criteria are customisable or selectable by a clinician.19.A computer-implemented method according to any preceding claim, wherein obtaining the daily image comprises providing an option to a user to select whether a CBCT image or a synthetic CT image should be used as the daily image, and obtaining the CBCT image or the synthetic image respectively in response to the user selection.20.A computer-implemented method according to any preceding claim, further comprising:generating computer-executable instructions for displaying a graphical user interface to a clinician, the graphical user interface comprising fields for at least one of:current status of determining the radiotherapy treatment plan;previous workflow steps in determining the radiotherapy treatment plan;upcoming workflow steps in determining the radiotherapy treatment plan; anda workflow decision point for determining the radiotherapy treatment plan; andtransmitting the computer-executable instructions to a display device.21.A computer-readable medium comprising computer-executable instructions, which, when executed by a processor, cause performance of the method of any preceding claim.22.A control device comprising:a memory comprising computer executable instructions; anda processor configured to execute the computer executable instructions to cause performance of the method of any of claims 1-20.23.A radiotherapy device comprising:a radiation source configured to generate a radiotherapy beam;an imaging device configured to generate one or more images of a subject; andthe control device of claim 22.