System and computer software for optimized radiotherapy

Abstract

A system, method, and computer software are disclosed that enable automatically calling imaging parameters from a computer memory to control an MRI system for the purpose of performing a treatment-day scan of a patient on a treatment table within a radiation therapy system prior to treatment. The treatment-day scan can be automatically initialized and then the MRI system can be controlled to perform the treatment-day scan according to the called imaging parameters. A re-optimized radiation therapy plan can be automatically generated and the predicted dose to the patient's anatomical structure based on the plan can be displayed. Healthcare providers can be enabled to perform multiple re-optimization tasks simultaneously through a parallel workflow interface and then control a radiation therapy device to deliver radiation according to the selected radiation therapy plan.

Description

Technical Field

[0001] Related Applications This application claims priority and the benefit thereof to U.S. Provisional Patent Application No. 63 / 270,855, filed on October 22, 2021, entitled "Systems, Methods, and Computer Software for Optimized Radiation Therapy", which is incorporated herein by reference.

[0002] Description of Related Art Radiation therapy involves delivering a radiation dose to a patient at a specific location to treat tissue, most typically cancerous tissue or tumors. To primarily deliver radiation to the target tissue and avoid irradiating healthy tissue, the radiation beam is shaped and delivered from specific directions in a specific sequence according to a radiation treatment plan. Specifically, an optimization process is used to mathematically determine the optimal radiation delivery parameters for a radiation treatment plan based on, among other things, the radiation prescription determined by a healthcare provider, the imaging of the patient, and the capabilities of the radiation therapy device. In some cases, the delivery of radiation can be guided by imaging before and / or during therapy, and the treatment plan can be improved through re-optimization.

Summary of the Invention

[0003] Systems, methods, and computer software related to improved radiation therapy planning and treatment are disclosed. In one aspect, imaging parameters can be automatically retrieved from computer memory to control an MRI system for the purpose of performing a treatment-day scan of a patient prior to treatment. The treatment-day scan can then be automatically initialized and the MRI system can be controlled to perform the treatment-day scan according to the retrieved imaging parameters. Next, a re-optimized radiation therapy plan can be automatically generated and a predicted dose to the patient's anatomical structure based on the re-optimized radiation therapy plan can be displayed. In some implementations, the prescribed dose to the anatomical structure can be displayed simultaneously with the display of the predicted dose. Finally, a radiation therapy device can be controlled to deliver radiation according to the selected radiation therapy plan.

[0004] In some variations, the automatic initialization of the treatment-day scan can be based on the sensor indicating that the door to the treatment room is closed or that the patient has been detected as being positioned at the isocenter.

[0005] In some embodiments, the disclosed systems, methods, and software can provide additional treatment plan re-optimization that includes the generation of a new re-optimized radiation treatment plan or the modification of one of the automatically generated re-optimized radiation treatment plans. Further, the disclosed systems, methods, and software can enable medical personnel to perform different re-optimization tasks simultaneously, including those through a parallel workflow interface. This can include, for example, enabling multiple medical personnel to perform auto-contouring simultaneously, or enabling medical personnel to attempt different re-optimization strategies simultaneously. In yet other variations, based on user input, the imaging plane can be moved and the re-optimized radiation treatment plan can be updated based on the new location of the imaging plane. Some embodiments also enable the receipt of user input that modifies tracking parameters, dose parameters, structural shape, or boundary parameters that the system utilizes when controlling a radiation therapy device to deliver radiation.

[0006] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate some aspects of the subject matter disclosed herein and, together with the specification, help explain some of the principles associated with the disclosed implementations.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

[0008] Conventional radiation therapy planning and delivery consists of multiple steps. First, the patient is imaged (e.g., with MRI and / or CT) to create a record of the patient's biological structure and identify target locations (e.g., tumors or areas of potential microscopic disease) for radiation treatment. Next, the images are reviewed by medical personnel and a radiation treatment plan is determined. When it comes time to treat the patient (which may be days or weeks later), the patient goes to a treatment facility and receives treatment according to the radiation treatment plan.

[0009] Briefly, a radiation treatment plan is a series of operations typically performed by a radiation delivery system in conjunction with an imaging system to provide prescribed doses to various locations of the patient's biological structure. A radiation treatment plan can include steps that define, for example, the delivery angle of the radiation beam, the beam-on time, the beam collimator settings, the patient treatment couch position, the settings of the imaging devices used during treatment delivery, etc. While the above is intended to provide a simplified introduction to radiation treatment planning, an actual radiation treatment plan may have other aspects not specifically listed.

[0010] Adaptive radiation therapy provides variable or additional fine-tuning of a radiation treatment plan based on the patient's current physical condition. For example, if the patient has gained or lost weight between the initial imaging and the treatment day, the shape and location of the patient's healthy organs and targets may have changed from the original treatment plan. This can mean, for example, that it may be necessary to adjust the position of the treatment couch and re-optimize the treatment plan to deliver a clinically acceptable treatment plan.

[0011] Prior to the present disclosure, in adaptive radiation therapy, the physical presence of clinical team members such as attending clinicians, medical physicists, dosimetrists, and therapists was required at the console of the radiation therapy system in a redundant procedure to re-optimize the calculations. For example, the control device of the therapy system was manually driven by a human operator who set up and acquired the treatment-day imaging, performed the adaptive calculations manually, and evaluated alternative treatment plans. Medical practitioners with different roles in the process, such as medical physicists and attending clinicians, had to review and perform the tasks that were completely sequential in turn, which required coordination among them to perform the tasks. Under the time pressure with the patient waiting on the treatment table, many system settings and therapy decisions had to be made.

[0012] Terms such as "medical practitioner" and "attending clinician" used herein are provided for the purpose of illustrating that many embodiments of the present disclosure are intended to be used in a clinical environment to treat the medical physical conditions of various patients. However, such terms should not be considered limiting, but rather should be considered equivalent to the general term "user" since the disclosed software can be used by anyone.

[0013] As described in more detail below, the present disclosure describes many image-guided radiation therapy systems and computer-implemented processes that enable improvements in the adaptive radiation therapy process and improve dose delivery, safety, efficiency, and convenience in many processes.

[0014] Initial and pre-treatment imaging scans can use any number and combination of different imaging types for the purpose of characterizing the patient for delivery of radiation therapy. In some embodiments, the imaging types can include, for example, one or more of 2D planar, volumetric, 4D volumetric, and real-time 4D volumetric. 2D planar imaging generally refers to substantially planar slices (e.g., axial, sagittal, or coronal planes) through the patient. Volumetric imaging generally refers to constructing a 3D patient volume depicting a region of the patient. 4D volume generally refers to a volume (3D) image of the patient over time. For example, a 4D volume image can capture the volume of the patient at different points in time corresponding to the patient's respiratory cycle. In some implementations, 4D imaging can demonstrate binned respiratory cycle intervals from some measurement of the respiratory cycle, such as chest height or spirometer air volume. Thus, the "time" of 4D volumetric imaging need not be a function of actual time. In contrast, "real-time" 4D volumetric imaging generally refers to 4D volumetric imaging that is reconstructed in real-time (optionally provided to a healthcare provider or made available to a radiation therapy system). As used herein, "real-time" means that the delay between image data capture and image development is minimal. Specifically, by making the acquisition, reconstruction, and processing times shorter than the frame rate, the imaging and the procedure can be synchronized. In this way, the use of such real-time images can provide information to the healthcare provider or system about the patient's nearly current state. In practice, the implementation of real-time imaging can involve a delay of less than one second and sometimes much shorter, e.g., 0.25 seconds, to reconstruct and display the volume image. The required frame rate can depend on the speed of the motion being tracked within the patient, and 0.25 seconds is sufficient to resolve typical heart and respiratory motions.

[0015] The imaging required to characterize a patient's anatomy for use on a treatment day may be described with respect to what is herein called "imaging parameters". Examples of imaging parameters may include contrast, dimensionality, frame rate, resolution, field of view, scanning order, etc. Specific examples of the foregoing may include contrast (e.g., T1 / T2), dimensionality (e.g., 3D, 4D, real-time 4D), frame rate (e.g., 10Hz, 4Hz, 2Hz), resolution (e.g., 0.5mm, 1.0mm, 2.0mm), field of view (e.g., 30cm DSV, 50cm DSV, 75cm DSV), scanning order (e.g., any desired order of scanning the axial, sagittal and coronal planes to generate an image corresponding to any of the imaging types described above).

[0016] In connection with the determination and acquisition of the desired imaging parameters, they can be stored in a database or other computer system so that they can be called up at any time. For example, as described herein, at a particular time on the treatment day, the imaging parameters can be automatically called up and made ready to be used to perform the required imaging sequence with the patient before (or during) the patient's treatment.

[0017] FIG. 1 is a simplified block diagram of an exemplary radiation therapy planning and treatment system. As depicted, the radiation therapy planning and treatment system 100 can include an image-guided radiation therapy (IGRT) system 110 positioned within a treatment room 120. Examples of IGRT systems can include medical linear accelerators (linacs), particle (proton, neutron, etc.) therapy systems, or electron beam systems. Such systems can be guided by imaging systems such as MRI, CT. The exemplary imaging system shown depicts an open or split-type MRI where the radiation beam (e.g., delivered by a linac) is between halves of an open-type MRI. The IGRT system can similarly include or incorporate a treatment table 130 for supporting a patient within the IGRT system during treatment. The treatment table can be configured to be adjustable in up to three dimensions (e.g., X, Y, Z) to position the patient in a desired location.

[0018] The treatment room 120 can be an arched room or other enclosure that may be radiation shielded to protect other parts of the facility from radiation generated by the radiation therapy device. The treatment room can similarly include magnetic and / or RF shielding to prevent external interference with the IGRT system and to prevent leakage of magnetic fields or RF from the IGRT system. A door 140 can be used to allow access to the treatment room. Such a door can be provided with shielding similar to that of the treatment room to prevent the effects as described above. As further described herein, the door 140 can similarly include an interlock or sensor to detect whether the treatment room door is closed.

[0019] One or more computer systems, schematically simplified as server 150, can control the IGRT system and the treatment table. Server 150 can be located inside the treatment facility or at a remote location. The server can be in wired and / or wireless communication with the IGRT system 110, the treatment table 130, and / or more computers, such as control consoles 160 and one or more remote computers 170. In some embodiments, the server operates as a web server and can thus be configured to have the ability to display one or more radiation treatment plans or treatment delivery information in any combination of control consoles and remote computers. Such a display of the radiation treatment plan or other data from the server can be synchronized and real-time, thereby enabling the user to interactively and collaboratively edit and / or approve the radiation treatment plan. In some embodiments, the server and the software running thereon can request the establishment of a secure connection before transmitting and / or receiving data regarding any of the operations described herein.

[0020] The control console 160 can be a workstation or other computing terminal that a healthcare provider may use to control the operation of the IGRT system. In some embodiments, the console may be close to the treatment room to enable the healthcare provider providing the treatment to access the IGRT system and the patient. In contrast, the remote computer 170 does not necessarily have to be close to the treatment room and can be any connected computer system, such as a computer used by a healthcare provider, such as a radiation oncologist or a medical physicist. Examples of remote computers can potentially include, for example, desktop computers, laptop computers, tablet computers, smartphones, etc.

[0021] In order to enable the patient to observe the progress of treatment and to assist the patient in positioning his or her body during the therapy, a patient display 180 can be included in some embodiments. The patient display can be, for example, a visual projection onto a computer screen or a screen or video-compatible goggles. Such a screen or surface can be placed inside the MRI bore or can still be accessible to the patient while being located outside the MRI system.

[0022] FIG. 2 is a flow diagram of an exemplary process for radiation therapy implemented by software in conjunction with an image-guided radiation therapy system. Process 200 is depicted as an example showing many features of the disclosed software, but not all elements of process 200 nor the order in which they are depicted are required.

[0023] The patient's treatment can be started by transporting the patient to the treatment room and placing the patient on the treatment table. At this time, the healthcare provider may firmly fix the patient to prevent movement and ensure accurate radiation delivery. The system may then automatically position the treatment table in the appropriate location within the IGRT system. In some cases, this may include translating the treatment table into an imaging system such as an MRI. In other cases, for example, for a radiation source that utilizes a robotic arm, the treatment table may remain substantially stationary.

[0024] Embodiments of the present disclosure can shorten the overall time to safely treat a patient by utilizing disclosed software processes such as the exemplary process 200 in FIG. 2. This process can include, at 210, automatically calling imaging parameters from a computer memory (e.g., on server 150). These imaging parameters can be used to control an MRI system (e.g., at 240 below) for the purpose of performing a treatment day scan of the patient on the treatment table prior to treatment. The imaging parameters can include those determined from the process of obtaining an initial scan as described above. The imaging parameters can be loadable within software for performing treatment day scans, such as on server 150. Optionally, the imaging parameters can be displayable in other optionally connected computer systems, such as on console 160 or remote computer 170.

[0025] The treatment of the patient can be expedited by a system that automatically initializes a treatment day scan based on detection of a trigger for the treatment day scan. For example, in some embodiments, the automatic initialization may be based on the sensor indicating that the door to the treatment room is closed. For example, there may be mechanical, electrical, or optical sensors that detect the closing and / or locking of the door to the treatment room. The output of such sensors can be convertible into an electrical signal or status within a software system and utilized as a trigger for the disclosed process to perform the initialization of the treatment day scan.

[0026] In other embodiments, the automatic initialization may be based on detecting that the patient is at the isocenter. For example, various IGRT systems can include sensors such as lasers, cameras, etc. that can detect the position of the patient in relation to the isocenter. Such detection and analysis can be performed by, for example, image analysis, time-of-flight measurement, phase shift translational registration algorithms, etc. For example, the phase shift translational registration algorithm can analyze the imaging of the patient taken during patient positioning and determine the best shift within the patient's body to align each part of the patient's biological structure (e.g., the target tumor) to its state at the initial imaging scan. In some embodiments, this may include restricting the field of view of these imaging scans to a fairly small area (e.g., 2 - 3 cm) so that the shift determined as a result of changes in other patient biological structures such as nearby organs is not distorted. Once the required shift has been determined, in some cases, the patient may be requested or assisted to physically move to a location closer to the isocenter. However, in other embodiments, the patient treatment table may be computer-controlled based on the determined required shift to move the patient to the isocenter. In various embodiments, process steps 210 and 220 are reversible. This means, for example, that the automatic calling of imaging parameters may not occur until, for example, the treatment is ready as determined by closing the door to the treatment room or determining that the patient is at the isocenter.

[0027] The process may include, at 230, automatically initializing the treatment day scan, for example, after detecting the trigger for the treatment day scan as described above. The treatment day scan can be initialized for execution according to imaging parameters automatically called from the initial imaging session. The automatic calling of imaging parameters can thus avoid extensive input of imaging parameters by medical staff and at the same time reduce the possibility of operator error.

[0028] The process may include, at 240, controlling an imaging (e.g., MRI) system to perform a treatment-day scan according to the called imaging parameters. For example, sequences such as scan plane, contrast type, etc. can be automatically and sequentially executed by the imaging system to provide imaging data that captures the patient's current biological structure, which is similar to the initial imaging session.

[0029] A treatment-day scan may be performed to identify the target for radiation therapy and the location of other anatomical structures (referred to herein as "organs at risk" (OAR)) that may have prescription limits for the amount of radiation that may be received. For example, in some cases, the patient may have changed weight between the treatment day and the time they were first scanned to generate the initial radiation treatment plan. Such weight changes (or any other biological changes such as bladder or rectal distension, inflammation, surgery, etc.) can, as a result, lead to changes in the shape and / or location of the patient's relevant anatomical structures. Using the treatment-day scan, the system can then next re-optimize or generate a radiation treatment plan or prompt it based on the current physical condition of the patient.

[0030] The process may include, at 250, automatically generating at least one re-optimized radiation treatment plan. In some embodiments regarding the generation / re-optimization of treatment plans, "automatically" means that the re-optimized radiation treatment plan can occur before any assessment of the original treatment plan. For example, rather than a healthcare provider determining that it is necessary to re-optimize the radiation treatment plan based on a treatment-day scan, the system can automatically generate a radiation treatment plan re-optimized based on the treatment-day scan. In some embodiments, the automatic generation can occur immediately (or with a slight delay) when the treatment-day scan is completed. However, it is contemplated that in some systems, a delay may be provided for various reasons. Thus, while some embodiments of the present disclosure may have a delay of zero or slight (e.g., 1 second to perhaps 30 seconds), other embodiments may have a delay of up to several minutes and still occur before the assessment of the original treatment plan. Such relatively long delays may not be optimal for the rapid treatment of patients, but can be used in some embodiments of the disclosed systems.

[0031] Further explanation and details of various embodiments of a system for generating a re-optimized radiation treatment plan are provided below with reference to FIG. 3. Similarly, any number of re-optimized radiation treatment plans can be generated by the system, and different plans can have different constraints or use different methods. In this way, a number of re-optimized radiation treatment plans can be provided, and the best one (i.e., the one that most fully satisfies the radiation prescription) can be selected either automatically by the system or by the user.

[0032] A process that does not conflict with the present disclosure may include displaying a predicted dose to a patient's anatomical structure based on a re-optimized radiation treatment plan (at step 260 of FIG. 2). In some embodiments, the predicted dose may be automatically displayed without any medical staff input. The predicted dose may be provided for display on either the control console 110 and / or the remote computer 170. The predicted dose displayed can take forms such as, for example, a heat map, a dose volume histogram, a bar graph, etc. The predicted dose can include quantities calculated regarding what dose to deliver to various targets or the patient's biological structures based on the corresponding imaging and radiation delivery system. The predicted dose can be calculated using methods such as, for example, the Monte Carlo method, the pencil beam method, the convolution / superposition method, the discrete ordinates / Boltzmann transport method, or any combination thereof.

[0033] The system may similarly store a list of targets and / or other patient biological structures (e.g., OARs), and optionally also a "prescription dose" that includes the radiation dose that the attending clinician has determined should be delivered to each patient and the amount of tissue volume scheduled to receive radiation. The prescription dose can define such dose ranges, lower and / or upper limits. Such a prescription dose can thus serve as the ultimate goal for re-optimization of the radiation treatment plan. This allows for acceptable variations within the acceptable treatment plan criteria considering the variations expected in the patient's daily changes.

[0034] Furthermore, some embodiments of the present disclosure can calculate and display a prescription plan and / or dose based on the original radiation treatment plan. In this way, it is possible to facilitate the selection by a medical staff or by a system that itself compares the newly generated re-optimized radiation treatment plan and (optionally) the original treatment plan to determine which best meets the prescription.

[0035] The process may include, at 270, a step in which the system determines whether the provided treatment plan (e.g., either the initial treatment plan or the generated and re-optimized treatment plan) is acceptable. For example, this can include the system comparing the predicted dose with the prescribed dose. If all prescriptions are met with the initial treatment plan or the generated and re-optimized treatment plan, one (e.g., the best one) may be designated as acceptable within the system. If all prescriptions are not met or if it is determined that the provided radiotherapy plan is not acceptable for some reason, the process can provide additional plan re-optimization as described below.

[0036] The process may include, at 280, a step of providing additional plan re-optimization and approval. For example, in some embodiments, the system can allow a medical practitioner to modify the contours (i.e., “automatic” contouring) generated by a computer of the patient's anatomy in order to modify the predicted dose. In other embodiments, the relative electron density map can be modified, thereby changing the re-optimization. Details of these and further embodiments are described below with reference to FIG. 3.

[0037] If a satisfactory re-optimized radiotherapy plan is generated and approved by the required personnel or determined by the system to meet the prescriptions, treatment may be initiated as described in step 290, and radiotherapy may be controlled to deliver radiation according to the selected radiotherapy plan. In some embodiments, the selected radiotherapy plan can be automatically delivered by the system, for example, immediately when a sufficiently excellent radiotherapy plan becomes available. In other embodiments, the selected radiotherapy plan can be delivered by the system in conjunction with a command from a control console (e.g., pressing a button to initiate treatment).

[0038] As mentioned above, for example, based on pre-called imaging parameters, one or more of 2D imaging, multi-plane 2D imaging, 3D imaging, 4D imaging, and real-time 4D volume imaging can be performed to perform imaging during treatment, and an imaging system such as an MRI can be constructed. In some embodiments, the control of the radiation therapy device can be further based on imaging. In such dynamic control of radiation delivery, patient movement and / or changes in the patient's biological structure can be considered. In some embodiments, the collimating system, the rotating gantry supporting the radiation source, the configuration of the robotic arm supporting the radiation source, etc. can be adjusted to adapt the radiation delivery based on the analysis during the progress of imaging. In other embodiments, the radiation delivery can be interrupted for analysis, and the subsequent resumption of delivery can be adjusted based on imaging.

[0039] Furthermore, some embodiments of the present disclosure can calculate and display data and / or information for controlling a radiation therapy device based on imaging. Examples of such data and / or information may include imaging dimensionality, imaging parameters, tissue tracking boundary types and generation parameters, and tissue tracking algorithm parameters. The imaging dimensionality can indicate whether the image is 2D, 3D, real-time 4D volume, etc. The tissue tracking algorithm parameters can include, for example, noise removal. Examples of tissue tracking boundary types may include identification of whether it is a target, an OAR, a boundary (e.g., an extended region around the boundary where radiation can be delivered tolerantly), and the boundary generation parameters can define various tools for creating boundaries, such as a free-drawing line, or a movable brush region that can expand / contract an existing boundary by pushing the boundary so as not to enter the brush region.

[0040] FIG. 3 is a flow diagram of an exemplary software-implemented process for automatic radiotherapy treatment plan re-optimization (e.g., step 250 in FIG. 2). Process 300 describes an example of calculations that can be formed to generate and / or select a re-optimized radiotherapy treatment plan. The elements in process 300 need not be executed in the order shown, and not all elements are required in all embodiments.

[0041] Process 300 may include, at 310, a step of performing rigid registration of the patient's anatomical structure. Rigid registration can include determining a shift (e.g., a shift of the patient's treatment table) that improves the alignment between the current patient position and the position where the patient should be (e.g., positioning the treatment target at the isocenter). The determination of the shift can be calculated by a system using image analysis techniques such as image difference, image spectral cross-correlation, etc.

[0042] The process may include, at 320, a step of automatically contouring the patient's anatomical structure in treatment-day imaging. Automatic contouring can include the system determining the edges around various anatomical structures in the patient's image. These edges (or contours) thus define the predicted extent of the anatomical structure in 2D (or 3D). Instead of the medical staff having to examine multiple frames of the image and manually draw the contours to determine them, the system can be configured to determine (or automatically contour) the biological structure in any number of ways. One exemplary method may include gradient analysis, where it is assumed that the gradients in the image represent changes in the patient's body structure, such as the boundary between a tumor and healthy tissue.

[0043] The process may include, at 330, performing deformable image registration. Deformable image registration allows for non-rigid changes in the patient's anatomy when registering the patient. For example, the shape of a tumor in a current image may be elongated compared to its shape in a previous image. By weighting the differences between pixels or voxels, it is possible to provide an optimal shift improvement such that, despite the deformed image, the best patient positioning for treatment results from the calculated shift. In other examples, deformable image registration can be used to optimally align sequential images that may have undergone legitimate deformations. For example, to construct a 4D patient volume for display or radiotherapy treatment planning purposes, the elements of a current volume image can be deformed to determine the shift for optimal alignment with a previous image.

[0044] The process may include, at 340, calculating a relative electron density map. A relative electron density map (RED) can be used when generating a radiotherapy treatment plan re-optimized to provide a more accurate dose calculation, because the method for calculating the ionizing radiation dose for megavolt photon beams is most accurate when this information is available. RED can be generated, for example, by setting segmented anatomical structures to known RE values (known as RED structure override), applying deformable image registration to a patient-derived RED or a template of a similar patient, generating a synthetic CT from the patient's MR image, or a combination of these methods.

[0045] The process may include, at 350, calculating a 3D patient table shift and / or calculating a predicted dose to an anatomical structure. As described above, various registration techniques can result in a determination of how the system needs to adjust the patient to position the patient in the proper position for treatment. The calculated patient table shift can be any combination of X, Y, and Z shifts and rotations. In other embodiments, the calculation and / or shifting can be done in 2D or 1D, but generally such shifts can be represented as 3D shifts even if a shift in a particular direction is not required. Similarly, the predicted dose to an anatomical structure can be calculated as described herein and used during any of the re-optimization processes disclosed herein.

[0046] The process may include, at 360, performing a fast re-optimization of the original radiotherapy plan or optimizing the beam intensities of a previously existing treatment plan. The "fast" re-optimization can use the existing beam shapes and beam angles pre-calculated to predict the dose that is considered to be delivered by the preceding radiotherapy plan. In other implementations, a "complete" re-optimization can be performed that can include calculating beamlets, optimizing the fluence map, and re-optimizing the MLC leaf positions. Thus, the fast re-optimization may reduce the computational overhead and / or shorten the time taken to complete as compared to the complete re-optimization.

[0047] The process may include, at 370, generating one or more re-optimized radiation treatment plans based on modifications to treatment planning parameters. The system may be configured to receive an input that changes one or more characteristics of at least one re-optimized radiation treatment plan. In some cases, better realization of the radiation prescription can be achieved by changing one or more of the following characteristics: the position of the patient treatment table, the contoured anatomical structures, the RED structure override value, or the optimization objective function and constraints. Examples of optimization objective functions and constraints may include penalty functions for dose-volume objectives and weights for these objectives, in addition to minimum, maximum, average, median objectives, and operators such as >, ≧, <, ≦, or =. The system may then be configured to automatically re-calculate a re-optimized radiation treatment plan based on the changed characteristics.

[0048] The input for changing the radiation treatment plan can be provided based on user input (e.g., by using a graphical interface to change the contour, entering new values for target doses or tolerance values), but in some embodiments, such changes can be automatically implemented by the system software to generate a number of re-optimized radiation treatment plans. For example, one embodiment can have an automatic generation step for re-optimized radiation treatment plans, including generating a re-optimized radiation treatment plan based on modifications to treatment planning parameters. The step of generating a re-optimized radiation treatment plan can stop when one of the re-optimized treatment plans meets the treatment prescription, or when a predetermined number of re-optimized radiation treatment plans have been generated.

[0049] As an example of how parameters can be varied to generate different radiation treatment plans, first, the system can compare predicted statistical values (such as the dose to an anatomical structure) to a prescription. Next, for example, if the predicted dose is overly low, in the objective function attempting to deliver the dose prescribed to the target volume, the weighting, importance, or power (if using a power function penalty) can be increased. As another example, if an excessive dose is being administered to a critical organ, the weight, importance, or power of the objective of trying not to harm the organ can be increased. Such optimization can be performed iteratively to reach a target prescription or a convergence as close to the target as possible.

[0050] As mentioned above, any number of such re-optimized radiation treatment plans, such as 1, 2, 3, 5, 10, etc., can be generated. This predetermined number can be set or modified by the user as desired, or can also be hard-coded within the software. In some embodiments, the radiation treatment plans can be generated sequentially (i.e., when one is finished, a check against the prescription is made before starting another). In other embodiments, the radiation treatment plans can be generated in parallel. In some embodiments, the system can stop plan generation when it is determined that one of the plans meets the prescription. For example, five radiation treatment plans can be initiated, and if it is determined that the third plan is complete and meets the prescription, all ongoing unfinished plans can be aborted. Such an implementation may have the potential benefit of reducing unnecessary computational overhead and further shortening the time required to start treatment.

[0051] The process may include, at 380, selecting a radiotherapy plan re-optimized based on a planning criterion (e.g., a prescription). In some embodiments, the software may be configured such that a user can select from any number of re-optimized radiotherapy plans calculated as described herein. For example, in some embodiments, only one (best) plan may be generated, while in other embodiments, multiple plans may be generated, some of which may be different from others but still all satisfy the prescription. At this time, medical staff can have the option of selecting from these re-optimized radiotherapy plans. In other embodiments, based on an algorithm, for example, considering the prescription and optionally the relative importance of individual criteria in the prescription, the system can select the best radiotherapy.

[0052] The process may include, at 390, performing an independent dose calculation for the selected plan. In some embodiments, the quality assurance of radiotherapy planning may include the use of independent (i.e., using different algorithms and methods) dose calculation software that is different from that used to evaluate the validity of the creation / selection of re-optimized radiotherapy. For the purpose of ensuring safety, the dose can be recalculated with independent algorithms to ensure that multiple independent methods agree on the dose value. For example, the independent dose calculation can utilize specifically commissioned and verified software to accurately calculate the dose that will be delivered by the selected re-optimized radiotherapy plan. Independent dose calculations can be performed for different software modules of the disclosed system, or this calculation can be provided to an external computer, which will perform the independent dose calculation and return the results for storage and display to the user of the disclosed system.

[0053] As described herein, many embodiments include a comparison between a predicted dose and a prescribed dose for a particular radiation treatment plan. Such a comparison is entirely internal to the disclosed software (i.e., something that is never visible to the user), but in some embodiments, the system can be configured to perform calculations and simultaneously display the predicted dose and the prescribed dose and / or reference to anatomical structures. For example, there may be a table having columns representing the prescription and predicted doses for a radiation treatment plan. The table can have rows that further classify the doses displayed for each anatomical structure relative to the total dose to the patient. Similarly, some embodiments can include highlighting or other visual indicia, such as color coding, to indicate whether the predicted dose is above, below, or within the range or parameters defined by the prescription.

[0054] In certain situations, physicians and medical staff may wish to review aspects of one of the original or re-optimized treatment plans. For example, they may wish to shift the patient treatment couch or review the contours drawn around the target or other organs. As further described below, the disclosed software enables additional treatment plan re-optimization by allowing medical staff to examine aspects of one or more radiation treatment plans and modify them or control the software to perform re-optimization based on updated parameters. This step of providing additional treatment plan re-optimization can thus include generating a new re-optimized radiation treatment plan or modifying one of the automatically generated re-optimized radiation treatment plans. Examination / modification of the re-optimized radiation treatment plan can be facilitated by an interactive graphical user interface provided on a control console or any remote computer. Such an interface can enable changes to radiation treatment plan parameters, anatomical contours, patient prescriptions, and the like.

[0055] Figure 4 depicts an example of a re-optimization task 400 that can be performed in parallel to accelerate the creation of a final re-optimized radiotherapy plan. The present disclosure contemplates that software and systems can provide additional treatment plan re-optimization by enabling medical personnel to perform different re-optimization tasks simultaneously. While the specific re-optimization tasks described herein can be part of the parallel operations enabled by software, the present disclosure also contemplates general systems and software that enable the parallelization of various tasks related to radiotherapy planning processes.

[0056] The re-optimization process 400 can include, at 410, the software receiving an input from a first medical personnel regarding a 3D patient treatment couch shift. This can include not only the step of modifying the coordinates or orientation of the patient treatment couch, but also the analysis of the impact of a potential treatment couch shift on the quality of image registration (e.g., based on quantitative metrics such as the correlation of images, predicted dose, etc. for determining the effectiveness of the patient treatment couch shift).

[0057] At 420, the software can receive input from a second healthcare provider tasked with the step of adjusting the contour around the patient's biological structure. This includes, for example, the step of modifying the contouring performed by the software to edit / correct the contour that is preferably aligned by the anatomical structures depicted in the patient's image. Examples of such modifications can include steps of adding / removing portions of the area bounded by the contour. Such editing steps can be performed on a 2D image or on a certain number of 2D images that together form part of a 3D patient volume. In some embodiments, the step of providing additional treatment plan re-optimization includes steps that enable multiple healthcare providers to perform automatic contouring simultaneously. For example, there may be 20 anatomical structures to be contoured, and these anatomical structures may be divided among two (or more) remote computers such that the healthcare providers edit their assigned contours simultaneously. The contours can be stored on a server and may be continuously updated based on changes to the individual contours created on the remote computers and transmitted to the server.

[0058] At 430, the software can receive input from a third healthcare provider to generate a relative electron density map. The third healthcare provider can view and edit the relative density map to adjust the values to better represent certain features in the image (e.g., adjusting the electron density to be appropriate so that the area under consideration is bone, fat, cancerous tissue, etc.). Adjustments to the relative electron density can be reflected in the prediction dose calculations for various patient anatomical structures.

[0059] At 440, the software can receive input from a fourth healthcare provider tasked with performing radiation dose QA. Based on a radiation treatment plan (e.g., one being concurrently generated / modified by the aforementioned healthcare providers), the software can calculate predicted doses to anatomical structures and display them for the healthcare provider to evaluate. The healthcare provider can then determine whether the predicted doses are accurately calculated, for example, by comparing them to an independent dose calculation for the radiation treatment plan. The healthcare provider can then electronically advise another healthcare provider performing a re-optimization task to enable determination of whether the radiation treatment plan passes or fails the required quality assurance inspection.

[0060] The software provides additional treatment plan re-optimization by enabling healthcare providers to simultaneously attempt different re-optimization strategies. For example, for the purposes of both target coverage and sparing of critical organs to meet a prescription, different strategies by different healthcare providers can be used to set or modify IMRT treatment plan objectives. For example, the system can be configured to receive and process input from one healthcare provider to set a higher importance weight for critical organs while setting a lower importance weight for the target with other input from another healthcare provider, thus enabling efficient comparison of both approaches. One strategy if the prescription cannot be met is to change / relax the prescription to enable treatment. Another strategy could be to delay treatment until the patient's organ geometry is adjusted. For example, the patient can be moved around to settle / align the distribution of fluids or waste before returning the patient to the treatment table. Alternatively, the patient may be returned to treatment on another day, for example, to allow digestion of food that causes organ displacement.

[0061] At 450, the software can require approval of certain changes or approval of the final plan. Thus, in some embodiments, the software can be configured to receive input from a healthcare provider to approve a selected radiation treatment plan. For example, the healthcare provider may be required to approve the initial radiation treatment plan, the selected re-optimized radiation treatment plan, or the use of a plan re-optimized through the parallel interface described herein as shown in FIG. 4. Whether the plan is ready for delivery or requires further editing is determined based on the approval.

[0062] At 460, if approval is not given or is explicitly rejected, the system can, in accordance with any of the embodiments of the present disclosure, enable further editing of one or more aspects of an available radiation treatment plan (e.g., an original or re-optimized radiation treatment plan). For example, any of the above-described elements of 410 - 440, or others, can be edited or re-executed based on user input. In some embodiments, the system can display one or more images from an available radiation treatment plan on one or more remote computers. The system can receive user input to approve the images and / or the radiation treatment plan from any of these remote computers. Alternatively, the system can receive user input to modify or suggest modifications to one or more of the re-optimized radiation treatment plans. For example, the system can be configured to induce modification of the radiation treatment plan based on user input such as changes to the contours around anatomical structures, prescription parameters, location of imaging planes, etc.

[0063] For an example of the step of moving the imaging plane, the user input can specify that the imaging plane needs to be moved to a certain location in such a way that a particular anatomical structure (or a part thereof) is captured (or not captured) in the images acquired during treatment or used for generating a radiation treatment plan. In some embodiments, the system can update the re-optimized radiation treatment plan based on the user input. Since the radiation treatment plan is generated based on available imaging (e.g., the target and other anatomical structures are specific to a given image within the selected plane), any user input that changes / moves such an imaging plane can serve as the basis for the updated re-optimized radiation treatment plan. For example, assume that a given image plane passing through the patient shows the target but does not show nearby anatomical structures where radiation delivery avoidance is desired by prescription. In that case, the re-optimized radiation treatment plan may determine treatment parameters such as the number of beams, their delivery vectors, etc., so that the target receives radiation. However, since the structure to be avoided is not in the image, the re-optimized radiation treatment plan may not necessarily address nearby anatomical structures. However, when an input to move the imaging plane to another location is received, it is possible for the anatomical structure to now be within the imaging plane. Thus, the system can re-optimize the radiation treatment plan taking into account the nearby anatomical structures that should now be avoided and perhaps find a different solution for delivering radiation to the target. Similarly, the radiation treatment plan can include gating parameters, and by changing the imaging plane for gating, the treatment plan and delivery can be modified as a result.

[0064] In other embodiments, the imaging parameters can be modified by user input, and examples of such imaging parameters include the patient's orientation, field of view, number of imaging planes, planes to be tracked, location of the planes, and imaging resolution. Thus, any combination of changes to the imaging plane / parameters can similarly serve as a basis for the system to modify the re-optimized radiation treatment plan as described above.

[0065] In other embodiments, the system can be configured to receive user input that modifies one or more of the tracking parameters, dose parameters, structural shapes, or boundary parameters that the system uses when controlling a radiation therapy device to deliver radiation. Examples of tracking parameters include defining the degree of deformation of an anatomical structure, the field of view for imaging, and the imaging parameters (such as those described above), whether the anatomical structure is stationary or moving. Examples of dose parameters can include a prescription, which thus includes acceptable limits and ranges of radiation delivery. Structural shapes can potentially include contours around anatomical structures, such as contours defining a gross tumor volume (GTV) or any other arbitrary contour generated around a target anatomical structure. Boundary parameters can potentially include a specified region around an anatomical structure that may sometimes be used for treatment planning purposes, also known as a planning target volume (PTV). For example, for a given anatomical structure, the system can be enabled to set the boundary perimeter to enclose more than 5% of the area or volume and generate a perimeter slightly expanded around the identified anatomical structure, thereby making the acceptable region that can receive radiation larger.

[0066] At 470, if approval is given, the system may designate the selected radiation therapy plan as being ready for delivery. This may potentially also include automatically delivering the radiation therapy plan described herein, for example, to facilitate the system's ability to deliver radiation therapy in the shortest possible time.

[0067] In the following, further features, characteristics, and exemplary technical solutions of the present disclosure are described from the perspective of items that may optionally be claimed in any combination:

[0068] Item 1: A non-transitory machine-readable medium that stores instructions which, when executed by at least one programmable processor, cause the at least one programmable processor to perform operations including: controlling an MRI system to perform a treatment-day scan of a patient on a treatment table for the purpose of performing a scan prior to treatment; automatically initializing the treatment-day scan; controlling the MRI system to perform the treatment-day scan according to the called imaging parameters; automatically generating at least one re-optimized radiation treatment plan; displaying a predicted dose to the patient's anatomical structure based on the at least one re-optimized radiation treatment plan; and controlling a radiation therapy device to deliver radiation according to a selected radiation treatment plan. Item 2: The machine-readable medium according to Item 1, wherein the step of automatically initializing the treatment-day scan is based on a sensor indicating that the door to the treatment room is closed. Item 3: The machine-readable medium according to any one of Items 1 and 2, wherein the operations further include detecting that the patient is positioned at the isocenter, and the automatic initialization of the treatment-day scan is based on detecting that the patient is at the isocenter. Item 4: The machine-readable medium according to any one of Items 1 to 3, wherein the imaging parameters specify an imaging type including one or more of volumetric imaging, 4D volumetric imaging, and real-time 4D volumetric imaging. Item 5: The machine-readable medium according to any one of Items 1 to 4, wherein the imaging parameters specify one or more of contrast, dimensionality, frame rate, resolution, field of view, and scanning order. Item 6: The machine-readable medium according to any one of Items 1 to 5, wherein the step of automatically generating at least one re-optimized radiation treatment plan further includes automatically contouring the patient's anatomical structure, calculating a relative electron density map, calculating a 3D patient table shift, and calculating a predicted dose to the anatomical structure. Item 7: The automatic generation step of at least one re-optimized radiotherapy plan further comprises: generating a re-optimized radiotherapy plan based on modification of treatment plan generation parameters, and stopping when one of the re-optimized radiotherapy plans meets the treatment prescription or when a predetermined number of re-optimized radiotherapy plans have been generated; A machine-readable medium according to any one of Items 1 to 6. Item 8: The operation further comprises: receiving an input for changing one or more features of at least one re-optimized radiotherapy plan; and automatically recalculating at least one re-optimized radiotherapy plan based on the changed features; A machine-readable medium according to any one of Items 1 to 7. Item 9: The operation further comprises: displaying the prescribed dose for the anatomical structure simultaneously with the display step of the predicted dose; A machine-readable medium according to any one of Items 1 to 8. Item 10: The operation further comprises: imaging during treatment by an MRI system that performs one or more of 2D imaging, multi-planar 2D imaging, 3D imaging, 4D imaging, and real-time 4D volume imaging; wherein the control step of the radiotherapy device is further based on the imaging. A machine-readable medium according to any one of Items 1 to 9. Item 11: The operation further comprises: automatically calculating and displaying information for controlling the radiotherapy device based on the imaging. A machine-readable medium according to any one of Items 1 to 10. Item 12: The information includes one or more of imaging dimensionality, imaging parameters, tissue tracking boundary types and generation parameters, and tissue tracking algorithm parameters. A machine-readable medium according to any one of Items 1 to 11. Item 13: The operation further comprises providing additional treatment plan re-optimization. A machine-readable medium according to any one of Items 1 to 12. Item 14: A machine-readable medium according to any one of Items 1 to 13, wherein the step of providing additional treatment plan re-optimization includes generating a newly re-optimized radiation treatment plan or modifying one of the automatically generated re-optimized radiation treatment plans. Item 15: A machine-readable medium according to any one of Items 1 to 14, wherein the step of providing additional treatment plan re-optimization includes enabling a healthcare provider to perform different re-optimization tasks simultaneously. Item 16: A machine-readable medium according to any one of Items 1 to 15, wherein the step of providing additional treatment plan re-optimization includes enabling multiple healthcare providers to perform automatic contouring simultaneously. Item 17: A machine-readable medium according to any one of Items 1 to 16, wherein the step of providing additional treatment plan re-optimization includes enabling a healthcare provider to attempt different re-optimization strategies simultaneously. Item 18: A machine-readable medium according to any one of Items 1 to 17, wherein the step of providing additional treatment plan re-optimization includes the system receiving user input to modify one or more of the re-optimized radiation treatment plans. Item 19: A machine-readable medium according to any one of Items 1 to 18, wherein the operation further includes: moving an imaging plane included in one or more of the re-optimized radiation treatment plans based on user input; and updating one or more of the re-optimized radiation treatment plans based on the new location of the imaging plane. Item 20: A machine-readable medium according to any one of Items 1 to 19, further including the system receiving user input to modify one or more of the tracking parameters, dose parameters, structural shape, or boundary parameters used by the system when controlling a radiation therapy device to deliver radiation. Item 21: A machine-readable medium according to any one of Items 1 to 20, wherein the operation further includes receiving input from a healthcare provider who approves the selected radiation treatment plan. Item 22: A method comprising the operation recited in any one of Items 1 to 21. Item 23: A system comprising at least one programmable processor and a non-transitory machine-readable medium storing instructions that, when executed by the at least one programmable processor, cause the at least one programmable processor to perform an operation including those recited in any one of Items 1 to 21.

[0069] In the above, several embodiments have been detailed, but other modifications are possible. For example, the elements depicted in FIGS. 2 to 4 and described herein do not require the specific order or sequential order shown to achieve the desired result.

[0070] This disclosure contemplates that the calculations disclosed in the embodiments herein may be performed in many forms by applying the same concepts taught herein and that such calculations are equivalent to the disclosed embodiments.

[0071] One or more aspects or features of the subject matter described in this specification can be implemented in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), computer hardware, firmware, software, and / or combinations thereof. These various aspects or features can be included in one or more computer programs executable and / or interpretable within a programmable system including at least one programmable processor coupled to receive data and instructions from, and to transmit data and instructions to, a memory system, at least one input device, and at least one output device. The programmable system or computer system may include clients and servers. The clients and servers are generally remote from each other and typically interact over a communication network. The relationship of client and server arises by virtue of computer programs running on respective computers and having a client-server relationship to each other.

[0072] These computer programs, which may also be referred to as programs, software, software applications, applications, components or code, include machine instructions for a programmable processor and can be implemented in high-level procedural languages, object-oriented programming languages, functional languages, logic programming languages and / or assembly / machine languages. As used herein, the term "machine-readable medium" (or "computer-readable medium") refers to any computer program product, apparatus and / or device, such as magnetic disks, optical disks, memory and programmable logic devices (PLDs), used to provide machine instructions and / or data to a programmable processor, including a machine-readable medium that receives the machine instructions as a machine-readable signal. The term "machine-readable signal" (or "computer-readable signal") refers to any signal used to provide machine instructions and / or data to a programmable processor. A machine-readable medium can store such machine instructions non-transitorily, for example, as is thought to be done by a non-transitory solid state memory or a magnetic hard drive or any equivalent storage medium. A machine-readable medium can alternatively or additionally store such machine instructions temporarily, for example, as is thought to be done by a processor cache or other random access memory associated with one or more physical processor cores.

[0073] To provide interaction with a user, one or more aspects or features of the subject matter described herein can be implemented on a computer having a display device, such as a cathode ray tube (CRT), liquid crystal display (LCD), or light emitting diode monitor, for displaying information to the user, and a pointing device, such as a mouse or trackball, and a keyboard that enable the user to provide input to the computer. Other types of devices can also be used to provide interaction with the user. For example, the feedback provided to the user can be any form of sensory feedback, such as, for example, visual feedback, auditory feedback, or tactile feedback; and the input from the user can be received in any form, including, without limitation, acoustic input, voice input, or tactile input. Other input devices that can be contemplated include, without limitation, touchscreens or other touch sensor-based devices, such as single-point or multi-point resistive or capacitive trackpads, speech recognition hardware and software, optical scanners, optical pointers, digital image capture devices, and associated interpretation software, and the like.

[0074] In the above specification and claims, phrases such as "at least one of" or "one or more of" may be used following a list of connecting elements or features. The term "and / or" may likewise be used in a list of two or more elements or features. Unless otherwise expressly or implicitly contradicted by the context in which it is used, such phrases are intended to mean any of the listed elements or features individually or any of the listed elements or features in combination with any of the other listed elements or features. For example, the phrases "at least one of A and B," "one or more of A and B," and "A and / or B" are intended to mean "A alone, B alone, or A and B together," respectively. A similar interpretation is intended for lists containing more than two items. For example, the phrases "at least one of A, B, and C," "one or more of A, B and C," and "A, B, and / or C" are intended to mean "A alone, B alone, C alone, A and B together, A and C together, B and C together, or A, B and C together." Use of the term "based on" above and in the claims is intended to mean "based at least in part on," such that unrecited features or elements are permissible as well.

[0075] The subject matter described in this specification can be embodied in systems, apparatus, methods, computer programs, and / or articles, depending on the desired configuration. Any of the methods or logical flows depicted in the accompanying figures and / or described in this specification do not necessarily require the specific order or sequential order shown to achieve the desired result. The implementations described above do not represent all implementations that are consistent with the subject matter described in this specification. Rather, they are merely some examples that are consistent with aspects related to the described subject matter. Although only some variations have been detailed above, other modifications or additions are possible. In particular, additional features and / or variations can be provided in addition to those described in this specification. The implementations described above can also be directed to various combinations and sub-combinations of the disclosed features and / or combinations and sub-combinations of the additional features pointed out above. Furthermore, the advantages described above are not intended to limit the application of any of the published claims to processes and structures that achieve any or all of those advantages.

[0076] Furthermore, section headings do not limit or characterize the inventions presented in any claims that may be derived from this disclosure. Additionally, the description of the technology in "Background" should not be considered as an admission that such technology is prior art to any invention in this disclosure. Also, "Summary" should not be considered as characterizing the inventions presented in the published claims. Moreover, any reference indication in general to this disclosure, or the use of the singular term "invention", is not intended to imply any limitation to the scope of the claims presented below. In accordance with the limitations of the numerous claims derived from this disclosure, many inventions may be presented, and thus such claims define the inventions protected thereby and their equivalents.

Claims

**Claim 1** A non-transitory machine-readable medium that, when executed by at least one programmable processor, causes the at least one programmable processor to automatically retrieve imaging parameters from a computer memory for the purpose of controlling an MRI system to perform a treatment-day scan of a patient on a treatment table prior to treatment; automatically initialize the treatment-day scan; control the MRI system to perform the treatment-day scan according to the retrieved imaging parameters; automatically generate at least one re-optimized radiation treatment plan; display a predicted dose to the patient's anatomical structure based on the at least one re-optimized radiation treatment plan; control a radiation therapy device to deliver radiation according to a selected radiation treatment plan; A non-transitory machine-readable medium storing instructions that cause the above-described operations to be performed. **Claim 2** The machine-readable medium according to claim 1, wherein the step of automatically initializing the treatment-day scan is based on the sensor indicating that the door to the treatment room is closed. **Claim 3** The operations further include detecting that the patient is positioned at the isocenter, and the step of automatically initializing the treatment-day scan is based on the detection that the patient is at the isocenter. The machine-readable medium according to claim 1. **Claim 4** The machine-readable medium according to claim 1, wherein the imaging parameters specify an imaging type including one or more of volumetric imaging, 4D volumetric imaging, and real-time 4D volumetric imaging. **Claim 5** The machine-readable medium according to claim 1, wherein the imaging parameters specify one or more of contrast, dimensionality, frame rate, resolution, field of view, and scanning order. **Claim 6** The step of automatically generating the at least one re-optimized radiation treatment plan further includes automatically contouring the patient's anatomical structure; calculating a relative electron density map; calculating a 3D patient table shift; calculating the predicted dose to the anatomical structure; The machine-readable medium according to claim 1, including the above. **Claim 7** The step of automatically generating the at least one re-optimized radiation therapy plan further includes generating a re-optimized radiation therapy plan based on a modification of treatment plan generation parameters, and stopping when one of the re-optimized radiation therapy plans meets the treatment prescription or when a predetermined number of re-optimized radiation therapy plans have been generated. The machine-readable medium according to claim 1.

8. The operation further includes receiving an input for changing one or more characteristics of the at least one re-optimized radiation therapy plan; automatically recalculating the at least one re-optimized radiation therapy plan based on the changed characteristics; The machine-readable medium according to claim 1, comprising.

9. The operation further includes displaying the prescription dose for the anatomical structure simultaneously with the step of displaying the predicted dose. The machine-readable medium according to claim 1.

10. The operation further includes imaging during treatment by an MRI system that performs one or more of 2D imaging, multi-planar 2D imaging, 3D imaging, 4D imaging, and real-time 4D volume imaging. The step of controlling the radiation therapy device is further based on the imaging. The machine-readable medium according to claim 1.

11. The operation further includes automatically calculating and displaying information for controlling the radiation therapy device based on the imaging. The machine-readable medium according to claim 1.

12. The information includes one or more of imaging dimensionality, imaging parameters, tissue tracking boundary types and generation parameters, and tissue tracking algorithm parameters. The machine-readable medium according to claim 11.

13. The operation further includes providing additional treatment plan re-optimization. The machine-readable medium according to claim 1.

14. The step of providing the additional treatment plan re-optimization includes generating a new re-optimized radiation therapy plan or modifying one of the automatically generated re-optimized radiation therapy plans. The machine-readable medium according to claim 13.

15. The step of providing the additional treatment plan re-optimization includes enabling a healthcare provider to perform different re-optimization tasks simultaneously. The machine-readable medium according to claim 13.

16. The machine-readable medium of claim 13, wherein the step of providing the additional treatment plan re-optimization includes enabling a number of healthcare providers to perform automatic contouring simultaneously.

17. The machine-readable medium of claim 13, wherein the step of providing the additional treatment plan re-optimization includes enabling healthcare providers to simultaneously attempt different re-optimization strategies.

18. The machine-readable medium of claim 13, wherein the step of providing the additional treatment plan re-optimization includes the system receiving user input to modify one or more of the re-optimized radiation treatment plans.

19. The operation further includes moving an imaging plane included in one or more of the re-optimized radiation treatment plans based on the user input; and updating one or more of the re-optimized radiation treatment plans based on the new location of the imaging plane. The machine-readable medium of claim 18, comprising:

20. The machine-readable medium of claim 1, further comprising receiving user input to modify one or more of a tracking parameter, a dose parameter, a structural shape, or a boundary parameter that the system uses when controlling the radiation therapy device to deliver the radiation.

21. The machine-readable medium of claim 1, wherein the operation further includes receiving input from a healthcare provider who approves the selected radiation treatment plan.

Images