Parallel generation of Pareto optimal radiotherapy plans

Abstract

Systems and methods for dynamic adaptation of radiotherapy are disclosed. Example operations for radiotherapy planning include obtaining a radiotherapy problem (e.g., a multi-criterion optimization problem) for providing radiotherapy; performing treatment plan optimization for delivery of radiotherapy; and generating treatment plan data based on at least one of the plurality of solutions, wherein such treatment plan data is used to generate a radiation treatment plan for the particular human subject with the radiation treatment machine. In one example, treatment plan optimization includes identifying a parameterized linear programming equation from a radiation treatment problem; converting the parameterized linear programming equation for execution by parallel processing hardware; and solving the plurality of converted parameterized linear programming equations in parallel on parallel processing hardware to produce a plurality of solutions (e.g., including a Pareto surface) of the radiation therapy problem corresponding to the parameters defining the radiation therapy problem.

Description

Technical Field

[0001] Embodiments of the present disclosure generally relate to processing and optimization techniques used in conjunction with radiation therapy planning and treatment systems. Specifically, the present disclosure relates to methods for identifying an optimized plan for a radiation therapy session using a particular computing hardware configuration. Background Art

[0002] Radiation therapy (or "radiotherapy") can be used to treat cancer or other diseases in mammalian (e.g., human and animal) tissue. One such radiation therapy technique is provided using a Gamma Knife, by which the patient is irradiated with a large number of low-intensity gamma rays that are focused at a target (e.g., a tumor) with high intensity and precision. Another such radiation therapy technique is provided using a Linear Accelerator (Linac), whereby the tumor is irradiated with high-energy particles (e.g., electrons, protons, ions, high-energy photons, etc.). The placement and dose of the radiation beam must be accurately controlled to ensure that the tumor receives the prescribed radiation, and the placement of the beam should minimize damage to surrounding healthy tissue (commonly referred to as (one or more) organs at risk (Organ At Risk, OAR)).

[0003] In radiotherapy, treatment plans are usually generated by solving an optimization problem that balances various conflicting objectives, such as high dose to target, normal tissue sparing, and treatment complexity. It is therefore a multicriteria optimization (MCO) problem. Typically, different criteria are combined using a weighted sum, where each weight determines the relative importance of the criterion. For convex optimization problems, the optimization attempts to identify all Pareto optimal radiotherapy plans. In this context, a Pareto optimal plan refers to a radiotherapy plan in which no criterion can be improved without deteriorating another criterion.

[0004] Finding acceptable weights to develop a Pareto optimal radiation therapy plan is typically a manual and tedious trial-and-error process, especially because evaluating a single choice of parameters requires solving the full optimization problem for the radiation therapy. Depending on the application, solving the full optimization problem for a single plan can take from a few seconds to an hour to calculate and evaluate parameter combinations. Summary of the invention

[0005] Various embodiments, methods, systems, and computer-readable media are provided for generating radiation therapy plans by solving a radiation therapy problem that can be adjusted via parameters using an optimization method. The optimization method can produce multiple solutions, which are then used to identify parameter selections that result in a satisfactory radiation therapy plan.

[0006] The radiation therapy problem can be expressed as a multi-criteria optimization (MCO) problem, where the parameters correspond to clinical preferences. Multiple solutions can then be used to identify a Pareto surface (also called a Pareto frontier). As used herein, a Pareto optimal plan refers to a plan that is optimized so that no criterion can be improved without deteriorating another criterion. The set of all Pareto optimal plans constitutes a Pareto surface.

[0007] An extended method for radiation therapy plan optimization is provided below, which uses a special configuration of a linear programming (LP) solver to identify a Pareto surface. In one example, the LP solver is adapted to apply an alternating direction method of multipliers (ADMM) technique, which enables the LP solver to be executed on parallel processing hardware such as a GPU. As a result, the LP equations can be solved in parallel in a much faster manner than sequential solution.

[0008] In various examples, operations for such radiation therapy planning include: obtaining a radiation therapy problem for providing radiation therapy to a human subject, the radiation therapy problem being adjustable via parameters; performing treatment plan optimization for the delivery of the radiation therapy, the treatment plan optimization comprising: (i) identifying a parameterized linear programming equation from the radiation therapy problem; (ii) converting the parameterized linear programming equation for execution by parallel processing hardware; and (iii) solving a plurality of the converted parameterized linear programming equations in parallel on the parallel processing hardware to produce a plurality of solutions (e.g., Pareto optimal solutions) to the radiation therapy problem corresponding to the parameters defined by the radiation therapy problem; and generating treatment planning data based on at least one of the plurality of solutions, wherein such treatment planning data is used to generate a radiation therapy plan for a specific patient for radiation therapy via a specific radiation therapy machine.

[0009] In a further example, the radiation therapy problem is a multi-criteria optimization problem, and the parameters defined by the radiation therapy problem correspond to clinical preferences. Additionally, performing treatment plan optimization for delivery of radiation therapy can include receiving a request to solve the radiation therapy problem, and receiving a plurality of sets of parameters defined by the radiation therapy problem. For example, the parameters in the plurality of sets of parameters can relate to a particular anatomical region of a human subject receiving radiation therapy from a radiation therapy machine, or more specifically, the plurality of sets of parameters can include definitions of one or more organ-at-risk regions and one or more target regions.

[0010] As previously described, converting the linear programming equations may include applying an alternating direction method of multipliers (ADMM) technique. Specifically, the alternating direction method of multipliers technique may include transforming the linear programming equations into matrix and projection operations (e.g., as described below with reference to Equation 6). The parallel processing hardware may include multiple graphics processing units (GPUs) that are capable of performing matrix operations in parallel.

[0011] In a further example, a representation of a solution space for a radiation therapy problem (e.g., a Pareto surface including a set of Pareto optimal solutions) can be generated and output based on the generated multiple solutions. Other graphical representations can include generating a display of a graphical user interface (which is configured to provide functionality for configuring a treatment plan) and displaying information associated with a solution to the radiation therapy problem for a particular set of parameters within the graphical user interface. Such information associated with the displayed solution can be based on a representation of a solution space for the radiation therapy problem (e.g., a Pareto surface) or characteristics of individual solutions. In addition, such a graphical user interface can be used to obtain user interaction to modify a particular set of parameters.

[0012] In a further example, the operation for such radiation therapy plan optimization further includes: selecting a solution to the radiation therapy problem based on an evaluation of a plurality of solutions; wherein the treatment planning data is generated based on the selected solution to the radiation therapy problem. For example, the selected solution to the radiation therapy problem may provide an approximate solution, thereby allowing the operation for radiation therapy plan optimization to include: receiving an additional optimization of the selected solution; wherein the treatment planning data for the radiation therapy is generated based on the additional optimization of the selected solution.

[0013] Treatment planning data for radiation therapy may include a set of treatment delivery parameters corresponding to the capabilities of the radiation therapy machine. In one example, the radiation therapy is provided using a gamma knife, and the set of treatment delivery parameters includes a set of isocenters for the delivery of the radiation therapy. For example, the set of treatment delivery parameters also includes timing for the delivery of the radiation therapy and a collimator sequence for the delivery of the radiation therapy using the gamma knife. As another example, the radiation therapy is provided using volumetric-modulated arc therapy (VMAT) or intensity modulated radiation therapy (IMRT), for example, using a linear accelerator radiation therapy machine, and the set of treatment delivery parameters includes one or more of the following: a set of arc control points for one or more arcs, a fluence field, a gantry speed, and a dose rate along one or more arcs.

[0014] In a further example, the operations may then be operations to cause or effectuate delivery of the radiation therapy using a plurality of radiation therapy beams from a radiation therapy machine based on the treatment planning data for the radiation therapy.

[0015] The above summary is intended to provide an overview of the subject matter of this patent application. It is not intended to provide an exclusive or exhaustive explanation of the subject matter of the present invention. The detailed description is included to provide further information about this patent application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In the accompanying drawings (which are not necessarily drawn to scale), like numbers describe substantially similar components throughout the several views. Like numbers with different letter suffixes represent different instances of substantially similar components. The accompanying drawings generally illustrate various embodiments discussed in this document by way of example and not limitation.

[0017] Figure 1 Radiation therapy systems according to some examples are illustrated.

[0018] Figure 2A A radiation therapy system having an output configured to provide a therapy beam according to some examples is illustrated.

[0019] Figure 2B A system including a combined radiation therapy system and an imaging system (eg, a Cone Beam Computed Tomography (CBCT) imaging system) according to some examples is illustrated.

[0020] Figure 3 A partial cross-sectional view of a system including a combined radiation therapy system and an imaging system (eg, a Magnetic Resonance (MR) imaging (MRI) system) according to some examples is illustrated.

[0021] Figure 4 An example of a Lexell Gamma Knife radiotherapy device according to some examples is illustrated.

[0022] Figure 5 A radiation therapy planning workflow for radiation problem optimization using parallel processing according to some examples is illustrated.

[0023] Figure 6 A workflow for applying the alternating direction method of multipliers to parallelize the execution of linear or quadratic programming equations according to some examples is illustrated.

[0024] Figure 7 A flow chart illustrating a method of radiation therapy planning according to some examples.

[0025] Figure 8 An exemplary block diagram of a machine is illustrated upon which one or more of the methodologies discussed herein may be implemented. DETAILED DESCRIPTION

[0026] In the following detailed description, reference is made to the accompanying drawings, which form a part of the present description, and in which specific embodiments in which the present disclosure may be practiced are shown by way of example. These embodiments, also referred to herein as "examples," are described in sufficient detail to enable those skilled in the art to practice the present disclosure, and it is understood that these embodiments may be combined, or other embodiments may be utilized, and that structural, logical, and electrical changes may be made without departing from the scope of the present disclosure. Therefore, the following detailed description should not be understood in a limiting manner, and the scope of the present disclosure is defined by the appended claims and their equivalents.

[0027] Various implementations of planning and optimization techniques that can be used for radiotherapy or radiosurgery applications are discussed below. Such techniques can be used to generate a large number of solutions to a radiotherapy problem that can correspond to different parameter selections, and generate treatment planning data based on at least one of the solutions found. Such solutions can be solved in parallel on parallel processing hardware to efficiently and effectively generate multiple solutions to the radiotherapy problem.

[0028] In the examples discussed herein, the treatment planning problem is solved by using an LP solver that operates based on the alternating direction method of multipliers (ADMM). The LP solver is capable of solving a large number of problems in parallel on parallel processing hardware such as a graphics processing unit (GPU). The use of ADMM and parallel processing execution methods can solve all LPs much faster (approximately) than solving the LPs sequentially.

[0029] Considering the radiation therapy planning optimization problem as an LP problem, and the present technique for transforming the LP problem into a parallel processing space, provides significant technical and clinical benefits. Technical benefits include reduced computational processing time for generating radiation therapy plans, enhanced computational solutions to the radiation therapy planning optimization problem, and concomitant improvements in processing, memory, and network resources for generating radiation therapy.

[0030] As explained in the following section, the following techniques can be used to generate an entire Pareto surface of Pareto optimal treatment plans, which are then selected and further optimized or validated for use with radiotherapy. Because the goal is to navigate the Pareto surface to identify starting points for a more detailed radiotherapy plan, it is not necessary to solve the optimization problem with high accuracy. Therefore, in a radiotherapy planning setting (e.g., a plan for a Gamma Knife treatment), a sufficiently accurate approximation of a Pareto optimal plan can be generated much faster than conventional methods. This can enable the use of a workflow that performs planning and treatment on the same day.

[0031] Existing approaches that pre-compute a representative set of treatment plans using conventional processing techniques typically result in significant computational time and latency. The number of representative plans required to span the Pareto surface for Gamma Knife treatments is typically on the order of hundreds or thousands of plans, which means that very long computational times (typically overnight runs) are required to generate a complete representation of possible solutions. Some existing approaches also attempt to use AI-based methods to produce estimated solutions to optimization problems. However, such AI-based approaches require large amounts of training data to cover all edge cases and typically need to be integrated with a larger AI toolset to be deployed in a product, even if the Pareto predictions for new cases are approximate.

[0032] Some dose optimization software has been designed to solve optimization problems using a simplex solver for LP problems. A simplex solver is a mathematical modeling technique in which a linear function is maximized or minimized when subject to linear constraints. However, when using a simplex solver approach, when solving several closely related LP equations, the calculations cannot usually be batched together. This prevents the use of computing hardware designed for parallel execution, such as graphics processing units (GPUs).

[0033] These and other limitations are addressed in the following configuration. The following paragraphs provide an overview of an example radiation therapy system implementation and treatment use cases (see Figure 2A , Figure 2B , Figure 3 and Figure 4 ), including the use of computing systems and hardware implementations (reference Figure 1 and Figure 8 ). The following then continues with a discussion of example treatment planning and algorithm processing workflows (refer to Figure 5 and Figure 6 Finally, a discussion of radiation therapy planning is provided (ref. Figure 7 ), which illustrates an end-to-end approach to generating optimized treatment plans.

[0034] Figure 1An exemplary radiation therapy system 100 suitable for performing radiation therapy planning processing operations using one or more of the methods discussed herein is illustrated. These radiation therapy planning processing operations are performed to enable the radiation therapy system 100 to provide radiation therapy to a patient based on captured medical imaging data and treatment dose calculations or specific aspects of radiation therapy machine configuration parameters. Specifically, the following processing operations can be implemented as part of the radiation therapy planning logic 120 for developing a radiation therapy plan. However, it should be understood that many variations and use cases of the following planning logic 120 and optimization operations can be provided, such as in response to data validation, visualization, and other medical evaluation and diagnostic operations.

[0035] The radiation therapy system 100 includes a radiation therapy treatment computing system 110 that hosts radiation therapy planning logic 120. The radiation therapy treatment computing system 110 can be connected to a network (not shown), and such a network can be connected to the Internet. For example, the network can connect the radiation therapy treatment computing system 110 with one or more private and / or public medical information sources (e.g., a Radiology Information System (RIS), a medical record system (e.g., an Electronic Medical Record (EMR) / Electronic Health Record (EHR) system), an Oncology Information System (OIS)), one or more image data sources 150, an image acquisition device 170 (e.g., an imaging modality), a treatment device 180 (e.g., a radiation therapy device), and a treatment data source 160.

[0036] As an example, the radiation therapy treatment computing system 110 can be configured to receive a treatment goal for a subject (e.g., from one or more MR images) and generate a radiation therapy plan by executing instructions or data from the radiation therapy planning logic 120 as part of an operation to generate a treatment plan to be used by the treatment device 180 and / or output on the device 146. In one embodiment, the radiation therapy planning logic 120 solves an optimization problem to generate the radiation therapy plan. The radiation therapy planning logic 120 solves the radiation therapy optimization problem by estimating the optimization variables of the received optimization problem. Then, an optimization problem solver is used to solve the optimization problem. Such optimization problem solvers include, for example, the simplex method, interior point method, Newton's method, quasi-Newton method, Gauss-Newton method, Levenberg-Marquardt method, linear least squares method, gradient descent method, projected gradient method, conjugate gradient method, augmented Lagrangian method, Nelder-Mead method, branch and bound method, cutting plane method, simulated annealing and / or sequential quadratic programming, or as discussed below using ADMM applied on parallel processing circuit 118.

[0037] The general radiation therapy planning optimization problem can be defined as Equation 1:

[0038]

[0039] in, is the objective function, x∈X is the decision variable (also called optimization variable), and is the set of feasible variables. In general, the function f may be nonlinear and the set Ω is non-convex. Optimization problems are usually solved using some form of iterative scheme. For example, in the case where f is smooth and convex and Ω is convex, then a projected gradient scheme can be used to solve equation (1) and is paraphrased as follows:

[0040]

[0041] Among them, proj Ω :X→X is the projection onto Ω, is the step length, and is the gradient. While these algorithms are often provably convergent (e.g., given enough time (and the right choice of parameters), the algorithm will converge to a minimum), they are not always very fast and efficient. In fact, several algorithms may require hundreds or even thousands of iterations to achieve approximate convergence. Since each step can be computationally expensive, this can mean several minutes or even hours of runtime.

[0042] According to the disclosed technology, a solution to such an optimization problem is generated by using a parallel processing hardware application solver method to solve the optimization problem. In some scenarios, the optimization problem is solved within a deviation threshold of an expected or expected solution. The disclosed technology improves the speed and efficiency of solving the optimization problem by executing the solver method in parallel. As will be appreciated, the method for solving the optimization problem will often apply an accuracy exit criterion (deviation threshold). However, the use of ADMM as discussed herein, in addition to being easily parallelized, will also quickly generate reasonable and accurate solutions. As a result, the solution generated by ADMM may provide information that can be used to determine whether the solution is of clinical interest.

[0043] The radiation therapy treatment computing system 110 may include a processing circuit 112, a memory 114, a storage device 116, a parallel processing circuit 118, and other hardware and software operable features, such as a user interface 142, a communication interface (not shown), etc. The storage device 116 may store transient or non-transient computer executable instructions, such as an operating system, a radiation therapy plan, training data, software programs (such as image processing software, image or anatomical visualization software, artificial intelligence (AI) or ML implementations and algorithms, such as provided by deep learning models, ML models, and neural networks (NN), etc.), and any other computer executable instructions to be executed by the processing circuit 112.

[0044] In one example, the processing circuit 112 may include a processing device, such as one or more general processing devices, such as a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), etc. More specifically, the processing circuit 112 may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor that implements other instruction sets, or a processor that implements a combination of instruction sets. The processing circuit 112 may also be implemented by one or more special processing devices, such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), a system on a chip (SoC), etc.

[0045] As will be appreciated by those skilled in the art, in some examples, processing circuit 112 may be a dedicated processor rather than a general purpose processor. Processing circuit 112 may include one or more known processing devices, such as those from Intel. TM Pentium TM ), Core TM ), Xeon TM ) or Itanium Family, AMD TM Turion TM ), Athlon TM ), Sempron TM ), Opteron TM ), FX TM Phenom TM ) family of microprocessors, or any of a variety of processors manufactured by Sun Microsystems. Processing circuitry 112 may also include a graphics processing unit, such as a graphics processing unit from Nvidia TM) Leadtek Tesla family, by Intel TM ) made by GMA, Iris TM ) family or by AMD TM Radeon TM ) family of GPUs. The processing circuit 112 may also include an accelerated processing unit, such as an Intel TM Xeon Phi TM ) family. The disclosed embodiments are not limited to one or more processors of any type that are otherwise configured to meet the computational requirements of identifying, analyzing, maintaining, generating and / or providing large amounts of data or manipulating such data to perform the methods disclosed herein. In addition, the term "processor" may include more than one physical (circuit-based) or software-based processor (e.g., a multi-core design or multiple processors, each processor having a multi-core design). The processing circuit 112 can execute transient or non-transient computer program instruction sequences stored in the memory 114 and accessed from the storage device 116 to perform various operations, processes, and methods that will be explained in more detail below. It should be understood that any component in the system 100 can be implemented separately and operated as a stand-alone device, and can be coupled to any other component in the system 100 to perform the techniques described in the present disclosure.

[0046] The memory 114 may include a read-only memory (ROM), a phase-change random access memory (PRAM), a static random access memory (SRAM), a flash memory, a random access memory (RAM), a dynamic random access memory (DRAM) such as a synchronous DRAM (SDRAM), an electrically erasable programmable read-only memory (EEPROM), a static memory (such as a flash memory, a flash disk, a static random access memory), and other types of random access memory, a cache, a register, a compact disc read-only memory (CD-ROM), a digital versatile disc (Digital Versatile Disk), and a compact disc read-only memory (CD-ROM). Disc, DVD) or other optical storage, magnetic cassettes, other magnetic storage devices, or any other non-transitory medium that can be used to store information including images, training data, one or more ML models or technique parameters, data, or transient or non-transitory computer executable instructions (e.g., stored in any format) that can be accessed by processing circuit 112 or any other type of computer device. For example, computer program instructions can be accessed by processing circuit 112, read from ROM or any other suitable memory location, and loaded into RAM for execution by processing circuit 112.

[0047] The storage device 116 may constitute a driver unit including a transient or non-transitory machine-readable medium having stored thereon one or more sets of transient or non-transitory instructions and data structures (e.g., software) that implement or are utilized by any one or more of the methods or functions described herein (including, in various examples, the radiation therapy planning logic 120 and the user interface 142). The instructions may also reside, in whole or in part, within the memory 114 and / or within the processing circuitry 112 during their execution by the radiation therapy treatment computing system 110, wherein the memory 114 and the processing circuitry 112 also constitute transient or non-transitory machine-readable media. The instructions may also cause the parallel processing circuitry 118 to perform specific processing operations.

[0048] The memory 114 and the storage device 116 may constitute a non-transient computer-readable medium. For example, the memory 114 and the storage device 116 may store or load transient or non-transient instructions for one or more software applications on a computer-readable medium. The software applications stored or loaded in the memory 114 and the storage device 116 may include, for example, operating systems for common computer systems and software-controlled devices. The radiation therapy processing computing system 110 may also operate various software programs, including software code for implementing the radiation therapy planning logic 120 and the user interface 142. Further, the memory 114 and the storage device 116 may store or load the entire software application, a portion of the software application, or code or data associated with the software application, which may be executed by the processing circuit 112. In another example, the memory 114 and the storage device 116 may store, load, and manipulate one or more radiation therapy plans, imaging data, segmentation data, treatment visualization, histograms or measurements, one or more AI model data (e.g., weights and parameters of one or more ML models), training data, labels, and mapping data, etc. It is contemplated that the software program may be stored not only on storage device 116 and memory 114, but also on removable computer media, such as a hard drive, a computer disk, a CD-ROM, a DVD, a Blu-ray DVD, a USB flash drive, an SD card, a memory stick, or any other suitable media; such software programs may also be transmitted or received over a network.

[0049] The parallel processing circuitry 118 may include any of the processing circuitry described above arranged in a parallel processing configuration. For example, a set of graphics processing units (e.g., graphics processing units from Nvidia) may be arranged. TM ) Leadtek Tesla family, by Intel TM ) made by GMA, Iris TM ) family or by AMD TM Radeon TM ) family of GPUs) to perform highly parallel or repetitive computing tasks simultaneously. Other specialized parallel processing units or hardware capable of performing multiple calculations simultaneously may also be deployed. A GPU may include a single GPU "device" or "system" that operates or coordinates numerous (e.g., dozens, hundreds, or thousands) sub-processors; many of the examples provided herein involve the use of a single GPU device or system that uses each of its numerous sub-processors to process a corresponding set of parameters.

[0050] Although not described, the radiation therapy treatment computing system 110 may include communication interfaces, network interface cards, and communication circuits. Example communication interfaces may include, for example, network adapters, cable connectors, serial connectors, USB connectors, parallel connectors, high-speed data transmission adapters (e.g., such as optical fiber, USB 3.0, Thunderbolt, etc.), wireless network adapters (e.g., such as IEEE 802.11 / Wi-Fi adapters), telecommunication adapters (e.g., communicating with 3G, 4G / LTE, and 5G networks, etc.), etc. Such communication interfaces may include one or more digital and / or analog communication devices that allow the machine to communicate with other machines and devices (e.g., remotely located components) via a network. The network may provide the functionality of a local area network (LAN), a wireless network, a cloud computing environment (e.g., software as a service, platform as a service, infrastructure as a service, etc.), a client-server, a wide area network (WAN), etc. For example, the network may be a LAN or a WAN, which may include other systems (including additional image processing computing systems or image-based components associated with medical imaging or radiation therapy operations).

[0051] In one example, the radiation therapy treatment computing system 110 may obtain image data 152 from an image data source 150 (e.g., an MR image) for hosting on the storage device 116 and the memory 114. In yet another example, the software program may replace a function of a patient image (e.g., a signed distance function) or a processed version of the image that emphasizes a certain aspect of the image information. The radiation therapy treatment computing system 110 may obtain image data 152 from or transmit image data to the image data source 150. In another example, the treatment data source 160 receives or updates planning data 162 as a result of a treatment plan generated by the radiation therapy planning logic 120. The image data source 150 may also provide or host imaging data for use in the radiation therapy planning logic 120.

[0052] In one example, the computing system 110 can communicate with one or more treatment data sources 160, input device 148, and other data sources to generate optimization variables and parameters for multiple radiation treatment planning optimization problems. Such optimization variables and parameters are generated to identify multiple solutions to the radiation treatment problems. These solutions can approximate a solution and can be further evaluated and refined (e.g., using additional optimization) before using it in radiation treatment.

[0053] The processing circuitry 112 and the parallel processing circuitry 118 may be communicatively coupled to the memory 114 and the storage device 116, and the processing circuitry 112 and the parallel processing circuitry 118 may be configured to execute computer executable instructions stored thereon from the memory 114 or the storage device 116. In particular, the radiation therapy planning logic 120 receives an optimization problem derived from parameters for radiation therapy. The processing circuitry 112 and the parallel processing circuitry 118 may utilize a software program or implementation to optimize the radiation therapy dose for delivery to the patient as part of developing an optimization solution to the radiation therapy problem as discussed herein. Further, such a software program or implementation may utilize the radiation therapy planning logic 120 to generate new or updated treatment plan parameters using techniques further discussed herein for deployment to the treatment data source 160 and / or presentation on the output device 146. The processing circuitry 112 or the parallel processing circuitry 118 may then transmit the new or updated treatment plan details to the treatment device 180 via the communication interface and network, wherein the radiation therapy plan will be used to treat the patient using radiation via the treatment device 180 consistent with the results of the radiation therapy planning logic 120 (e.g., according to the process discussed below).

[0054] In one example, the image data 152 for defining a radiotherapy problem or indicating an anatomical region of a patient may include one or more MRI images (e.g., 2D MRI, 3D MRI, 2D streaming MRI, 4D MRI, 4D volume MRI, 4D cine MRI, etc.), functional MRI images (e.g., fMRI, DCE-MRI, diffusion MRI), computed tomography (CT) images (e.g., 2D CT, 2D cone beam CT, 3D CT, 3D CBCT, 4D CT, 4DCBCT), ultrasound images (e.g., 2D ultrasound, 3D ultrasound, 4D ultrasound), positron emission tomography (PET) images, X-ray images, fluorescence images, radiotherapy portal images, single-photon emission computed tomography (SPECT) images, computer-generated synthetic images (e.g., pseudo CT images), etc. Further, the image data 152 may also include or be associated with medical image processing data (e.g., training images, gold standard images, contour images, and dose images). In other examples, equivalent representations of anatomical regions may be represented in non-image formats (eg, coordinates, maps, etc.).

[0055] In one example, the image data 152 may be received from an image acquisition device 170 and stored in one or more image data sources 150 (e.g., a Picture Archiving and Communication System (PACS), a Vendor Neutral Archive (VNA), a medical record or information system, a data warehouse, etc.). Thus, the image acquisition device 170 may include an MRI imaging device, a CT imaging device, a PET imaging device, an ultrasound imaging device, a fluorescence device, a SPECT imaging device, an integrated linear accelerator and MRI imaging device, a CBCT imaging device, or other medical imaging devices for obtaining medical images of a patient. The image data 152 may be received and stored in any type of data or any type of format (e.g., Digital Imaging and Communications in Medicine (DICOM) format) that the image acquisition device 170 and the radiation therapy treatment computing system 110 can use to perform operations consistent with the disclosed embodiments. Further, in some examples, the models discussed herein may be trained to process raw image data formats or derivatives thereof.

[0056] In one example, the image acquisition device 170 can be integrated with the treatment device 180 into a single device (e.g., an MRI device combined with a linear accelerator, also referred to as an "MRI linear accelerator"). Such an MRI linear accelerator can be used, for example, to determine the location of a target organ or target tumor in a patient's body so that the radiotherapy treatment can be accurately directed to a predetermined target according to the radiotherapy plan. For example, the radiotherapy plan can provide information about the specific radiation dose to be applied to each patient. The radiotherapy plan can also include other radiotherapy information, including control points of the radiotherapy device, such as the position of the examination table, beam intensity, beam angle, dose histogram volume information, the number of radiation beams to be used during treatment, the dose of each beam, etc.

[0057] The radiotherapy treatment computing system 110 can communicate with an external database via a network to send / receive multiple various types of data related to image processing and radiotherapy operations. For example, the external database may include machine data (including equipment constraints) that provides information associated with the treatment device 180, the image acquisition device 170, or other machines related to radiotherapy or medical procedures. Machine data information (e.g., control points) may include radiation beam size, arc placement, beam on and off duration, machine parameters, segments, multi-leaf collimator (MLC) configuration, gantry speed, MRI pulse sequence, etc. The external database may be a storage device and may be equipped with an appropriate database management software program. Further, such a database or data source may include multiple devices or systems located in a centralized or distributed manner.

[0058] The radiation therapy treatment computing system 110 can collect and obtain data and communicate with other systems via a network using one or more communication interfaces that are communicatively coupled to the processing circuit 112 and the memory 114. For example, the communication interface can provide a communication connection between the radiation therapy treatment computing system 110 and components of the radiation therapy system (e.g., allowing data to be exchanged with external devices). For example, in some examples, the communication interface can have appropriate interface circuitry connecting from the output device 146 or the input device 148 to the user interface 142, which can be a hardware keyboard, keypad, or touch screen, through which a user can enter information into the radiation therapy system.

[0059] As an example, the output device 146 may include a display device that outputs a representation of the user interface 142 and one or more aspects, visualizations, or representations of medical images, treatment plans, and the status of training, generation, verification, or implementation of such plans. The output device 146 may include one or more display screens that display medical images, interface information, treatment plan parameters (e.g., contours, doses, beam angles, labels, maps, etc.), treatment plans, targets, positioning targets, and / or tracking targets, or any related information to a user. The input device 148 connected to the user interface 142 may be a keyboard, keypad, touch screen, or any type of device that a user may use with the radiation therapy system 100. Alternatively, the features of the output device 146, input device 148, and user interface 142 may be integrated into, for example, a smart phone or tablet computer (e.g., an Apple Lenovo Samsung etc.) in a single device.

[0060] In addition, any and all components of the radiation therapy system can be implemented as virtual machines (e.g., via a virtualization platform such as VMWare, Hyper-V, etc.) or stand-alone devices. For example, a virtual machine can be software used as hardware. Thus, a virtual machine can include at least one or more virtual processors, one or more virtual memories, and one or more virtual communication interfaces that are used together as hardware. For example, the radiation therapy processing computing system 110, the image data source 150, or similar components can be implemented as virtual machines or within a cloud-based virtualization environment.

[0061] The image acquisition device 170 may be configured to acquire one or more images of an area of ​​interest (e.g., a target organ, a target tumor, or both) of the patient's anatomical structure. Each image (typically a 2D image or slice) may include one or more parameters (e.g., 2D slice thickness, orientation, and position, etc.). In one example, the image acquisition device 170 may acquire 2D slices of any orientation. For example, the orientation of the 2D slice may include a sagittal orientation, a coronal orientation, or an axial orientation. The processing circuit 112 may adjust one or more parameters, such as the thickness and / or orientation of the 2D slice, to include the target organ and / or the target tumor. In one example, the 2D slice may be determined from information such as a 3D CBCT or CT or MRI volume. Such a 2D slice may be acquired by the image acquisition device 170 in "near real time" (where "near real time" means acquiring data in at least a few milliseconds or less) while the patient is undergoing radiation therapy (e.g., when using the treatment device 180).

[0062] The radiation therapy planning logic 120 in the radiation therapy treatment computing system 110 implements a radiation therapy optimization workflow 130 and a treatment plan generation workflow 140. The radiation therapy optimization workflow 130 may implement optimization operations for identifying and developing a radiation therapy plan, while the treatment plan generation workflow may implement operations for evaluating, selecting, and refining a radiation therapy plan. In a specific example, the radiation therapy optimization workflow 130 performs a radiation therapy problem process 132 of obtaining and identifying an optimization problem, a problem transformation process 134 of converting the optimization problem for more efficient or effective execution on hardware (e.g., converting the optimization problem for execution with parallel processing circuits 118), and a solution process 136 of identifying and outputting a solution to the optimization problem. Further details of the radiation therapy optimization workflow 130 are provided below with reference to Figure 5 and Figure 6 Provided, including the use of an alternating direction multiplication method to help transform equations for efficient execution on the parallel processing circuit 118. Again, more details of the treatment plan generation workflow 140 are provided below with reference to Figure 5 and Figure 7 Provides an indication of how the found solution can be used as a starting point for such a treatment plan to further evaluate, select, and optimize the treatment plan.

[0063] Figure 2A A radiotherapy device 202 is illustrated, which may include a radiation source, such as an x-ray source or a linear accelerator, a viewing table 216, an imaging detector 214, and a radiotherapy output 204. The radiotherapy device 202 may be configured to emit a radiation beam 208 to provide treatment to a patient. The radiotherapy output 204 may include one or more attenuators or collimators, such as an MLC. The MLC may be used to shape, guide, or modulate the intensity of the radiotherapy beam to a specified target site within the patient. For example, the leaves of the MLC may be automatically positioned to define an aperture close to a cross-section or projection of a tumor and cause modulation of the radiotherapy beam. For example, the leaves may include a metal plate, such as tungsten, wherein the long axis of the plate is oriented parallel to the beam direction, and the plate has an end oriented orthogonal to the beam direction. Further, the "state" of the MLC may be adaptively adjusted during the radiotherapy process to establish a treatment beam that better approximates the shape or position of the tumor or other target site.

[0064] Return to reference Figure 2A , a patient may be positioned in the area 212 and supported by a treatment table 216 to receive a radiation therapy dose in accordance with a radiation therapy plan. The radiation therapy output 204 may be mounted or attached to a gantry 206 or other mechanical support. When the table 216 is inserted into the treatment area, one or more housing motors (not shown) may rotate the gantry 206 and the radiation therapy output 204 around the table 216. In one example, the gantry 206 may continuously rotate around the table 216 when the table 216 is inserted into the treatment area. In another example, the gantry 206 may rotate to a predetermined position when the table 216 is inserted into the treatment area. For example, the gantry 206 may be configured to rotate the treatment output 204 around an axis ("A"). Both the table 216 and the radiation therapy output 204 may be independently moved to other positions around the patient, such as in a transverse direction ("T"), in a lateral direction ("L"), or may rotate around one or more other axes (e.g., around a horizontal axis (indicated as "R")). A controller communicatively connected to one or more actuators (not shown) can control the movement or rotation of the table 216 to properly position the patient in or out of the radiation beam 208 according to the radiation treatment plan. Both the table 216 and the gantry 206 can move independently of each other in multiple degrees of freedom, which allows the patient to be positioned so that the radiation beam 208 can be precisely aimed at the tumor. The MLC can be integrated and included in the gantry 206 to deliver a specific shape of the radiation beam 208.

[0065] Figure 2AThe coordinate system shown (including axes A, T, and L) can have an origin located at an isocenter 210. The isocenter can be defined as the location where the central axis of the radiation beam 208 intersects the origin of the coordinate axes so as to deliver a prescribed radiation dose to a location on or within a patient. Alternatively, the isocenter 210 can be defined as the location where the central axis of the radiation beam 208 intersects the patient for various rotational positions of the radiotherapy output 204 positioned by the gantry 206 about axis A. As discussed herein, the gantry angle corresponds to the position of the gantry 206 relative to axis A, but any other axis or combination of axes may be referenced and used to determine the gantry angle.

[0066] The gantry 206 may also have an attached imaging detector 214. The imaging detector 214 is preferably positioned opposite the radiation source, and in one example, the imaging detector 214 may be located within the field of the radiation beam 208. The imaging detector 214 may be mounted on the gantry 206 (preferably opposite the radiotherapy output 204) so ​​as to maintain alignment with the radiation beam 208. The imaging detector 214 rotates about the rotation axis as the gantry 206 rotates. In one example, the imaging detector 214 may be a flat panel detector (e.g., a direct detector or a scintillator detector). Thus, the imaging detector 214 may be used to monitor the radiation beam 208, or the imaging detector 214 may be used to image the patient's anatomical structure, such as portal imaging. The control circuitry of the radiotherapy device 202 may be integrated within the radiotherapy system 100 or remote therefrom.

[0067] In the illustrative example, one or more of the table 216, the treatment output 204, or the gantry 206 can be automatically positioned, and the treatment output 204 can establish the radiation beam 208 according to the specified dose for a particular treatment delivery instance. The sequence of treatment deliveries can be specified according to the radiation treatment plan (e.g., using one or more different orientations or positions of the gantry 206, the table 216, or the treatment output 204). The treatment deliveries can occur sequentially, but can intersect at a desired treatment site on or in the patient, such as at the isocenter 210. Thus, a prescribed cumulative radiation treatment dose can be delivered to the treatment site while reducing or avoiding damage to tissue near the treatment site.

[0068] Figure 2BA radiation therapy device 202 is illustrated that may include a combined linear accelerator and an imaging system (e.g., a CT imaging system). The radiation therapy device 202 may include an MLC (not shown). The CT imaging system may include an imaging X-ray source 218, for example, providing X-ray energy in the kiloelectronvolt (keV) energy range. The imaging X-ray source 218 may provide a fan-shaped and / or cone-shaped radiation beam 208 directed toward an imaging detector 222, such as a flat panel detector. The radiation therapy device 202 may be similar to the apparatus described above. Figure 2A The depicted system, for example, includes a radiation therapy output 204, a gantry 206, an examination table 216, and another imaging detector 214 (eg, a flat panel detector). An X-ray source 218 may provide a relatively low energy diagnostic X-ray beam for imaging.

[0069] exist Figure 2B In the illustrative example of , the radiation therapy output 204 and the x-ray source 218 can be mounted on the same rotating gantry 206, rotated 90 degrees apart from each other. In another example, two or more x-ray sources can be mounted along the circumference of the gantry 206, for example, each with its own detector arrangement to provide multiple angles of diagnostic imaging simultaneously. Similarly, multiple radiation therapy outputs 204 can be provided.

[0070] Figure 3 A radiation therapy system 300 is described that can combine a radiation therapy device 202 and an imaging system, such as a magnetic resonance (MR) imaging system consistent with the disclosed examples (e.g., referred to in the art as an MR linear accelerator). As shown, the system 300 can include a viewing table 216, an image acquisition device 320, and a radiation delivery device 330. The system 300 delivers radiation therapy to a patient according to a radiation therapy plan. In some examples, the image acquisition device 320 can correspond to Figure 1 The image acquisition device 170 in the image acquisition device can acquire an original image of a first modality (such as an MRI image) or a destination image of a second modality (such as a CT image).

[0071] The examination table 216 can support a patient (not shown) during a treatment session. In some implementations, the examination table 216 can move along a horizontal translation axis (labeled "I") so that the examination table 216 can move a patient lying on the examination table 216 into and / or out of the system 300. The examination table 216 can also rotate about a central vertical rotation axis that is transverse to the translation axis. To allow for such movement or rotation, the examination table 216 can have motors (not shown) that enable the examination table 216 to move in various directions and rotate along various axes. A controller (not shown) can control these movements or rotations so as to properly position the patient according to the treatment plan.

[0072] In some examples, the image acquisition device 320 may include an MRI machine for acquiring 2D or 3D MRI images of a patient before, during, and / or after a treatment session. The image acquisition device 320 may include a magnet 321 for generating a main magnetic field for magnetic resonance imaging. The magnetic field lines generated by the operation of the magnet 321 may extend approximately parallel to the central translation axis I. The magnet 321 may include one or more coils whose axes extend parallel to the translation axis I. In some examples, one or more coils in the magnet 321 may be spaced apart so that a central window 323 of the magnet 321 is free of coils. In other examples, the coils in the magnet 321 may be sufficiently thin or have a reduced density so that the radiation of the wavelength generated by the radiotherapy device 330 is approximately transparent to them. The image acquisition device 320 may also include one or more shielding coils that may generate a magnetic field of approximately equal magnitude and opposite polarity outside the magnet 321 so as to eliminate or reduce any magnetic field outside the magnet 321. As described below, the radiation source 331 of the radiation delivery device 330 may be positioned in a region where the magnetic field is eliminated (at least to a first order) or reduced.

[0073] The image acquisition device 320 may also include two gradient coils 325 and 326, which may generate a gradient magnetic field superimposed on the main magnetic field. The coils 325 and 326 may generate a gradient in the composite magnetic field, which allows for spatial encoding of protons so that their positions may be determined. The gradient coils 325 and 326 may be positioned around a central axis common to the magnet 321 and may be displaced along the central axis. The displacement may create a gap or window between the coils 325 and 326. In an example where the magnet 321 may also include a central window 323 between the coils, the two windows may be aligned with each other.

[0074] In some examples, the image acquisition device 320 may be an imaging device other than MRI, such as X-ray, CT, CBCT, spiral CT, PET, SPECT, optical tomography, fluorescence imaging, ultrasound imaging, radiation therapy portal imaging device, etc. As one of ordinary skill in the art will appreciate, the above description of the image acquisition device 320 relates to certain examples and is not intended to be limiting.

[0075] The radiation delivery device 330 may include a radiation source 331, such as an x-ray source or a linear accelerator, and an MLC 332. The radiation delivery device 330 may be mounted on a housing 335. When the examination table 216 is inserted into the treatment area, one or more housing motors (not shown) may rotate the housing 335 around the examination table 216. In one example, the housing 335 may continuously rotate around the examination table 216 when the examination table 216 is inserted into the treatment area. The housing 335 may also have an attached radiation detector (not shown), preferably positioned opposite the radiation source 331, and the rotation axis of the housing 335 is positioned between the radiation source 331 and the detector. Further, the device 330 may include control circuitry (not shown) for controlling, for example, one or more of the examination table 216, the image acquisition device 320, and the radiotherapy device 330. The control circuitry of the radiation delivery device 330 may be integrated within the system 300 or remote therefrom.

[0076] During a radiation therapy session, a patient may be positioned on the viewing table 216. The system 300 may then move the viewing table 216 into a treatment area defined by the magnet 321, coils 325, 326, and housing 335. The control circuitry may then control the radiation source 331, MLC 332, and one or more housing motors to deliver radiation to the patient through the window between the coils 325 and 326 according to the radiation therapy plan.

[0077] Figure 2A , Figure 2B and Figure 3 Examples of radiation therapy devices configured to provide radiation therapy to a patient are generally illustrated, using a configuration in which the radiation therapy output can rotate about a central axis (e.g., axis "A"). Other radiation therapy output configurations can be used. For example, the radiation therapy output can be mounted to a robotic arm or manipulator having multiple degrees of freedom. In yet another example, the treatment output can be fixed, such as located in an area laterally separated from the patient, and a platform supporting the patient can be used to align the radiation therapy isocenter with a specific target site in the patient's body.

[0078] Figure 4 A comparative example of a Lexell Gamma Knife radiotherapy device 430 is illustrated, which provides such radiotherapy with the aid of gamma radiation. As a brief overview of a gamma knife device, radiation is emitted from a large number of fixed radiation sources and is focused onto a defined target or treatment volume with the aid of a collimator (i.e., a channel or passage for obtaining a beam of limited cross-section). The individual sources provide a dose of gamma radiation that is insufficient to damage intervening tissue. However, tissue destruction can occur where the radiation beams from all or some of the radiation sources intersect or converge to cause the radiation to reach a tissue-destructive level. This point of convergence is hereinafter referred to as the "isocenter", but may also be referred to as the "focus".

[0079] like Figure 4 As shown, during a radiotherapy treatment, a patient 402 can wear a coordinate frame 420 to keep a patient's body part (e.g., head) that is undergoing surgery or radiotherapy stable. The coordinate frame 420 and the patient positioning system 422 can establish a spatial coordinate system that can be used when imaging a patient or during radiosurgery. The radiotherapy device 430 may include a protective shell 414 that is used to enclose a plurality of radiation sources 412. The radiation source 412 may generate a plurality of radiation beams (e.g., sub-beams) through a beam channel 416. The plurality of radiation beams may be configured to focus on the isocenter 310 from different directions. Although each individual radiation beam may have a relatively low intensity, when multiple doses from different radiation beams are accumulated at the isocenter 310, the isocenter 310 may receive a relatively high level of radiation. In some examples, the isocenter 310 may correspond to a target in surgery or treatment, such as a tumor.

[0080] Other types of radiotherapy devices (not illustrated) use protons and / or ions to deliver radiation therapy. The direction and shape of the radiation beam should be accurately controlled to ensure that the tumor receives the prescribed radiation dose, and the radiation from the beam should minimize damage to surrounding healthy tissue, essentially one or more organs at risk (OARs). Therefore, treatment plans are used to design and control radiation beam parameters, and the radiotherapy device achieves treatment by delivering a spatially varying dose distribution to the patient.

[0081] The purpose of treatment plan optimization for radiation therapy (e.g., for Gamma Knife radiosurgery) is to maximize the dose delivered to a target volume in a patient (e.g., in the treatment of a tumor) while minimizing the dose delivered to adjacent normal tissue. In treatment plan optimization, the delivered radiation dose is primarily limited by two competing factors: the first is the delivery of a high dose to the target volume, and the second is the delivery of a low dose to surrounding normal tissue. Treatment plan optimization is a process that includes optimizing the number of shots used, the sector collimator combination, the shot time, and the shot position (i.e., isocenter). Obviously, the irregularity and size of the target volume greatly affects the number of shots required and the shot size used to optimize the treatment. Therefore, for Gamma Knife radiotherapy, the selected isocenter positions and their corresponding shots for a given situation constitute the treatment plan.

[0082] Figure 5 A high-level view of the operation of a radiation therapy planning workflow is provided. Specifically, the workflow uses parallel processing for radiation therapy problem optimization, which can generate all or nearly all Pareto optimal solutions to the radiation therapy problem.

[0083] In more detail, Figure 5The operations in exemplify how radiation therapy problem information 510 for treating a human subject may be provided using definitions of information such as treatment target regions 512 and organ-at-risk regions 514. Other information related to the radiation therapy problem may include radiation therapy machine information 520, such as machine capabilities 522.

[0084] The radiation therapy problem optimization 530 described is then used to optimize and solve for the appropriate dose distribution to be delivered using the radiation therapy problem. Such optimization and solving can be performed using parallel processing hardware 535 and transformations or modifications to the radiation therapy problem used with the parallel processing hardware. As discussed, the parallel processing hardware can include multiple graphics processing units (GPUs), and the relevant transformation of the problem can include solving the linear programming equations using the alternating direction multiplier method technique. The alternating direction multiplier method can transform the linear programming equations into matrix and projection operations.

[0085] Optimization 530 produces a plurality of Pareto optimal radiation therapy solutions 540, which may be comprised of a Pareto surface or boundary of all (or approximately all) available Pareto optimal solutions. One or more of these solutions may be selected and refined using operation 550, and a particular radiation therapy plan generated using operation 560. The generation of the radiation therapy plan (and the associated selection or modification of the radiation therapy solution) using operation 560 may depend on machine capabilities 522. Finally, the generated treatment plan may be used to deliver radiation therapy.

[0086] Figure 6 An example workflow for applying the alternating direction method of multipliers to parallelize the execution of linear or quadratic programming equations is provided. In one example, the alternating direction method of multipliers (ADMM) follows the algorithmic approach discussed in Boyd et al., Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers, Now Publishers Inc. (2011) and applied as a batch LP solver in Nair et al., Solving Mixed Integer Programs Using Neural Networks, arXiv:2012.13349 (2020), both of which are incorporated by reference in their entirety.

[0087] The ADMM algorithm solves convex optimization problems by breaking them down into smaller chunks that are then easier to process. ADMM is well suited for use as a batch LP solver. In one example, the optimization problem can be expressed as:

[0088] Minimize f(x)+g(z)

[0089] Obey x=z

[0090] (Equation 3)

[0091] Considering this optimization problem, the ADMM solver can be expressed as:

[0092] For any ρ>0:

[0093]

[0094]

[0095] λ k+1 =λ k +x k+1 -z k+1

[0096] (Equation 4)

[0097] For LP problems, this can be reformulated as:

[0098] x k+1 =K(z k +λ k )+Γ ρ

[0099] z k+1 =Π w (x k+1 -λ k )

[0100] λ k+1 =λ k -(x k+1 -z k+1 )

[0101] (Equation 5)

[0102] Using this formulation,

[0103]

[0104]

[0105] Where A is the constraint matrix and c is the linear cost function vector. w is an operator that projects a point onto the feasible set and depends on the weights multiplied by the objective function term in the objective function. It projects each element in the vector onto a closed or half-open interval. Thus, each optimization is performed with its unique projection operator that is fast to compute. However, operator K is common to all optimizations but takes more time to compute.

[0106] In one example, using the ADMM algorithm to solve a radiation therapy problem can be done using Figure 6 The following operations described in this article summarize:

[0107] The K operator is calculated (operation 601) and represented, for example, explicitly or in a factorized form.

[0108] The K operator is transmitted to each node (operation 602).

[0109] An iterative scheme is run (operation 603), such as described with reference to Equation 5, until the difference in the variable between two consecutive iterations is less than a predefined threshold (operation 604). In one example, the iterative scheme includes matrix multiplication and projection.

[0110] The ADMM formulation can provide solutions that are as accurate as other solution methods, but if a particularly accurate solution is desired, longer processing time may be required. However, it will be appreciated that the ADMM provides a fairly accurate solution after a few iterations, which is useful for Pareto navigation. This selected plan can then be improved by other optimization methods (simplex, interior point, ADMM, ...).

[0111] Figure 7 A flowchart 700 is shown illustrating a method of radiotherapy treatment planning based on the above techniques. For example, the following features of flowchart 700 may be used in conjunction with reference to Figure 5 Optimization operations discussed and references Figure 6 The optimization solver operations discussed are integrated or adapted.

[0112] Operation 710 begins with the operation of obtaining a radiation therapy problem, wherein the radiation therapy problem defines various parameters for delivering radiation therapy from a radiation therapy machine. Such a radiation therapy problem may be adjusted via parameters, which are optionally received with a request to solve the radiation therapy problem.

[0113] Operation 720 proceeds with performing an operation of treatment plan optimization for the radiation therapy problem, which may be repeated for each problem until the entire Pareto surface or boundary (or a sufficient portion of the Pareto surface or boundary) of the solution is identified. Although not shown, the treatment plan optimization operations may be performed in parallel or simultaneously. The treatment plan optimization may be based on dose, geometry, imaging, machine learning, radiobiology, or other relevant factors.

[0114] Operation 730 continues with identifying linear programming equations from the radiation therapy problem. At operation 740, these linear programming equations are converted (e.g., changed, transformed, etc.) for execution on parallel processing hardware, such as using the alternating direction multiplier method described above. Then, at operation 750, multiple linear programming equations are solved in parallel on the parallel processing hardware.

[0115] At operation 760, a Pareto surface or boundary of a Pareto optimal radiation therapy solution is identified. At operation 770, the set of solutions can be used to provide a specific solution for use in radiation therapy. At operation 770, one of the multiple Pareto optimal solutions is selected, evaluated, and potentially improved. Finally, at operation 780, a treatment plan is generated based on the optimized (Pareto optimal) radiation therapy solution.

[0116] Although not directly depicted in the accompanying drawings, various forms of user interfaces or representations may be provided to enable representation of the solution space for a radiation therapy problem based on multiple Pareto optimal solutions. This may be provided in a graphical user interface having functionality for configuring a treatment plan and receiving and outputting data related to the treatment plan. For example, information associated with a solution to a radiation therapy problem for a particular set of parameters may be displayed. User interaction may be obtained in such a user interface in order to modify a particular set of parameters. As will be appreciated, various interactive Pareto navigation functions may be provided, such as an approximation of a Pareto surface that lets a user explore estimates of solutions corresponding to new or different parameter values ​​that have not yet been evaluated.

[0117] It will be appreciated that the Pareto optimal plans generated using this technique can be thought of as points on a Pareto surface. The more points generated, the better the description of the surface. As the user explores the Pareto surface, the user performs some type of interpolation between the existing calculated points in order to select and use a solution. It seems reasonable that the user will eventually develop and select a plan that is not necessarily one of the calculated points.

[0118] Thus, in some examples, all Pareto optimal solutions or at least a substantial subset of Pareto optimal solutions may be generated and evaluated before a user selects a particular plan or solution. Thus, the plan ultimately selected may be a plan "between" two generated points on the Pareto surface. Because all points on the Pareto surface may be generated using the ADMM techniques discussed herein, navigation of the Pareto surface can be performed quickly and efficiently.

[0119] Figure 8A block diagram of an example of a machine 800 is illustrated, on which one or more of the methods discussed herein may be implemented. In one or more examples, one or more items of the radiation therapy processing computing system 110 may be implemented by the machine 800. In an alternative example, the machine 800 operates as a standalone device or may be connected (e.g., networked) to other machines. In one or more examples, the radiation therapy processing computing system 110 may include one or more items of the machine 800. In a networked deployment, the machine 800 may operate in the capacity of a server or client machine in a server-client network environment, or as a peer machine in a peer (or distributed) network environment. The machine may be a personal computer (PC), a server, a tablet, a smart phone, a network appliance, an edge computing device, a network router, a switch or a bridge, or any machine capable of executing instructions (sequentially or otherwise), the instructions specifying actions to be taken by the machine. Further, while a single machine is illustrated, the term "machine" shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein.

[0120] The example machine 800 includes a processing circuit or processor 802 (e.g., a CPU, a graphics processing unit (GPU), an ASIC, a circuit such as one or more transistors, resistors, capacitors, inductors, diodes, logic gates, multiplexers, buffers, modulators, demodulators, radio devices (e.g., transmitting or receiving radio devices or transceivers), sensors 821 (e.g., transducers that convert one form of energy (e.g., light, heat, electricity, mechanical or other energy) into another form of energy), etc. or a combination thereof), a main memory 804 and a static memory 806, which communicate with each other via a bus 808. The machine 800 (e.g., a computer system) may also include a video display device 810 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)). The machine 800 also includes an alphanumeric input device 812 (e.g., a keyboard), a user interface (UI) navigation device 814 (e.g., a mouse), a disk drive or mass storage unit 816, a signal generating device 818 (e.g., a speaker), and a network interface device 820.

[0121] The disk drive unit 816 includes a machine-readable medium 822 on which is stored one or more sets of instructions and data structures (e.g., software) 824 that implement or are utilized by any one or more of the methods or functions described herein. The instructions 824 may also reside, completely or at least partially, within the main memory 804 and / or within the processor 802 during execution thereof by the machine 800, the main memory 804 and the processor 802 also constituting machine-readable media.

[0122] The machine 800 as illustrated includes an output controller 828. The output controller 828 manages the flow of data to / from the machine 800. The output controller 828 is sometimes referred to as a device controller, where software that interacts directly with the output controller 828 is referred to as a device driver.

[0123] Although the machine-readable medium 822 is shown as a single medium in the example, the term "machine-readable medium" may include a single medium or multiple media (e.g., centralized or distributed databases and / or associated caches and servers) that store one or more instructions or data structures. The term "machine-readable medium" should also be understood to include any tangible medium that is capable of storing, encoding, or carrying instructions that are executed by a machine and cause the machine to perform any one or more of the methods of the present disclosure, or capable of storing, encoding, or carrying data structures utilized by or associated with such instructions. The term "machine-readable medium" should therefore be understood to include, but is not limited to, solid-state memory and optical and magnetic media. Specific examples of machine-readable media include non-volatile memory, including, by way of example, semiconductor memory devices such as erasable programmable read-only memory (EPROM), EEPROM, and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks.

[0124] Instructions 824 may also be sent or received over a communication network 826 using a transmission medium. Instructions 824 may be sent using a network interface device 820 and any of a variety of well-known transmission protocols (e.g., HTTP). Examples of communication networks include LANs, WANs, the Internet, mobile phone networks, Plain Old Telephone Service (POTS) networks, and wireless data networks (e.g., Wi-Fi and 4G / 5G data networks). The term "transmission medium" should be understood to include any intangible medium capable of storing, encoding, or carrying instructions for execution by a machine, and includes digital or analog communication signals or other intangible media to facilitate communication of such software.

[0125] As used herein, "communicatively coupled between" means that entities on either of the couplings must communicate through an item therebetween, and the entities cannot communicate with each other without communicating through that item.

[0126] Additional Notes

[0127] The above detailed description includes reference to the accompanying drawings, which form a part of the detailed description. The accompanying drawings show specific embodiments in which the present disclosure can be practiced by way of illustration and not limitation. These embodiments are also referred to as "examples" in this article. Such examples may include elements other than the elements shown or described. However, the inventors also contemplate examples in which only these elements shown or described are provided. Moreover, the inventors also contemplate examples using any combination or arrangement of these elements (or one or more aspects thereof) shown or described with respect to a specific example (or one or more aspects thereof) or with respect to other examples (or one or more aspects thereof) shown or described herein.

[0128] All publications, patents, and patent documents cited in this document are incorporated herein by reference in their entirety, as if individually incorporated by reference. In the event of inconsistent usages between this document and those documents incorporated by reference, the usage in the incorporated reference(s) should be considered supplementary to that in this document; for irreconcilable inconsistencies, the usage in this document controls.

[0129] In this document, when introducing elements of aspects of the disclosure or embodiments thereof, the terms "a," "an," "the," and "said" are used, as is common in patent documents, to include one or more than one or more elements, regardless of any other instance or use of "at least one" or "one or more." In this document, the term "or" is used to refer to a non-exclusive or such that "A or B" includes "A but not B," "B but not A," and "A and B," unless otherwise indicated.

[0130] In the following claims, the terms "including" and "in which" are used as the plain-English equivalents of the respective terms "comprising" and "wherein." Furthermore, in the following claims, the terms "including," "comprising," and "having" are intended to be open-ended to mean that additional elements may be present in addition to the listed elements, such that elements following such a term (e.g., comprising, including, having) in a claim are still considered to fall within the scope of the claim. Furthermore, in the following claims, the terms "first," "second," and "third," etc. are used merely as labels, and are not intended to impose numerical requirements on their objects.

[0131] Embodiments of the present disclosure may be implemented with computer executable instructions. Computer executable instructions (e.g., software codes) may be organized into one or more computer executable components or modules. Aspects of the present disclosure may be implemented with such components or modules of any number and organization. For example, aspects of the present disclosure are not limited to specific computer executable instructions or specific components or modules illustrated in the drawings and described herein. Other embodiments of the present disclosure may include different computer executable instructions or components with more or less functions than those illustrated and described herein.

[0132] The method examples described herein (e.g., operations and functions) may be at least partially machine or computer implemented (e.g., implemented as software code or instructions). Some examples may include a computer-readable medium or machine-readable medium encoded with instructions, which may be operable to configure an electronic device to perform the methods described in the above examples. The implementation of these methods may include software code, such as microcode, assembly language code, high-level language code, etc. (e.g., "source code"). Such software code may include computer-readable instructions (e.g., "objects" or "executable code") for performing various methods. The software code may form part of a computer program product. The software implementation of the embodiments described herein may be provided via an article having codes or instructions stored thereon, or via a method of operating a communication interface to send data via a communication interface (e.g., wirelessly, via the Internet, via satellite communications, etc.).

[0133] Further, the software code may be tangibly stored on one or more volatile or non-volatile computer-readable storage media during execution or at other times. These computer-readable storage media may include any mechanism for storing information in a form accessible to a machine (e.g., a computing device, an electronic system, etc.), such as, but not limited to, a floppy disk, a hard disk, a removable disk, any form of disk storage media, a CD-ROM, a magneto-optical disk, a removable optical disk (e.g., a compact disk and a digital video disk), a flash memory device, a magnetic cassette, a memory card or stick (e.g., a secure digital card), a RAM (e.g., a CMOS RAM, etc.), a recordable / non-recordable medium (e.g., a read-only memory (ROM)), an EPROM, an EEPROM, or any type of medium suitable for storing electronic instructions, etc. Such computer-readable storage media may be coupled to a computer system bus to be accessible by the processor and other parts of the OIS.

[0134] In one embodiment, the computer readable storage medium may be encoded with a data structure for a treatment plan, wherein the treatment plan may be adaptive. The data structure for the computer readable storage medium may be at least one of a Digital Imaging and Communications in Medicine (DICOM) format, an extended DICOM format, an XML format, and the like. DICOM is an international communication standard that defines a format for transmitting medical image-related data between various types of medical devices. DICOM RT refers to a communication standard dedicated to radiation therapy.

[0135] In various embodiments of the present disclosure, the methods for creating components or modules can be implemented in software, hardware, or a combination thereof. For example, the methods provided by various embodiments of the present disclosure can be implemented in software using a standard programming language, such as C, C++, C#, Java, Python, CUDA programming, etc., and combinations thereof. As used herein, the terms "software" and "firmware" are interchangeable and include any computer program stored in a memory for execution by a computer.

[0136] The communication interface includes any mechanism that interfaces with any of the media such as hard wiring, wireless, light, etc. to communicate with another device, such as a memory bus interface, a processor bus interface, an Internet connection, a disk controller, etc. The communication interface can be configured by providing configuration parameters and / or sending signals to prepare the communication interface to provide data signals describing the software content. The communication interface can be accessed via one or more commands or signals sent to the communication interface.

[0137] The present disclosure also relates to a system for performing the operations herein. The system may be specially configured for the desired purpose, or it may include a general-purpose computer selectively activated or reconfigured by a computer program stored in the computer. Unless otherwise specified, the order in which the operations in the embodiments of the present disclosure illustrated and described herein are performed or performed is not required. That is, unless otherwise specified, the operations may be performed in any order, and the embodiments of the present disclosure may include more or less operations than the operations disclosed herein. For example, it is conceivable that performing or performing a specific operation before, simultaneously with, or after another operation is within the scope of the aspects of the present disclosure.

[0138] In view of the foregoing, it will be seen that the several objects of the present disclosure are achieved and other advantageous results are obtained. Having described various aspects of the present disclosure in detail, it will be apparent that modifications and variations are possible without departing from the scope of the various aspects of the present disclosure as defined in the appended claims. As various changes may be made to the above-described constructions, products and methods without departing from the scope of the various aspects of the present disclosure, it is intended that all matter contained in the above description and shown in the accompanying drawings shall be interpreted as illustrative and not restrictive.

[0139] The above description is intended to illustrate rather than to limit. For example, the above examples (or one or more aspects thereof) may be used in combination with each other. In addition, without departing from the scope of the present disclosure, many modifications may be made to adapt specific situations or materials to the teachings of the present disclosure. Although the sizes and types of the materials and coatings described herein are intended to limit the parameters of the present disclosure, they are by no means restrictive, but exemplary embodiments. After reviewing the above description, many other embodiments will be apparent to those skilled in the art. Therefore, the scope of the present disclosure should be determined with reference to the full scope of the equivalents authorized by the appended claims and these claims.

[0140] Moreover, in the above detailed description, various features may be grouped together to streamline the disclosure. This should not be interpreted as intending that unclaimed disclosed features are necessary for any claim. On the contrary, the subject matter of the invention may lie in less than all the features of a particular disclosed embodiment. Therefore, the following claims are hereby incorporated into the detailed description, with each claim independently serving as a separate embodiment. The scope of the present disclosure should be determined with reference to the appended claims and the full scope of equivalents to which these claims are authorized. Further, the limitations of the following claims are not written in a device-plus-function format and are not intended to be interpreted based on the sixth paragraph of 35 U.S.C. §112, unless and until such claim limitation explicitly uses the phrase "device for..." followed by a functional statement without additional structure.

[0141] The Abstract is provided to comply with 37 CFR §1.72(b), to allow the reader to quickly ascertain the nature of the technical disclosure, with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

Claims

1. A computer-implemented method for radiation therapy planning, the method comprising: obtaining a radiation therapy problem for providing radiation therapy to a human subject from a radiation therapy machine, the radiation therapy problem being a multi-criteria optimization problem adjustable via a plurality of parameters; performing a treatment plan optimization for delivery of the radiation therapy, the treatment plan optimization comprising: identifying a parameterized linear programming equation from the radiation therapy problem; converting the parameterized linear programming equations for execution by parallel processing hardware; and solving a plurality of transformed parameterized linear programming equations in parallel on the parallel processing hardware to produce a plurality of solutions to the radiation therapy problem corresponding to the plurality of parameters defining the radiation therapy problem; and Treatment planning data is generated based on at least one of the plurality of solutions, wherein the treatment planning data is used to generate a radiation treatment plan.

2. The method according to claim 1, wherein: The parameters defined by the radiation therapy problem correspond to clinical preferences.

3. The method according to claim 1, further comprising: A plurality of sets of the parameters defining the radiation therapy problem are received.

4. The method according to claim 3, wherein: Parameters in the plurality of sets of parameters relate to specific anatomical regions of the human subject receiving the radiation therapy from the radiation therapy machine.

5. The method according to claim 3, wherein: The plurality of sets of parameters include definitions of one or more organ-at-risk regions and one or more target regions.

6. The method according to claim 1, wherein: Transforming the parameterized linear programming equations includes applying an alternating direction method of multipliers technique.

7. The method according to claim 6, wherein: The alternating direction multiplier technique includes transforming the converted parameterized linear programming equations into matrix operations.

8. The method according to claim 1, wherein: The parallel processing hardware includes a plurality of graphics processing units (GPUs).

9. The method of claim 1 , further comprising generating a representation of a solution space based on the plurality of solutions to the radiation therapy problem, wherein: The solution space is a Pareto surface including a set of Pareto optimal solutions.

10. The method according to claim 1, further comprising: generating a display of a graphical user interface configured to provide functionality for configuring the radiation treatment plan; displaying within the graphical user interface information associated with a particular solution to the radiation therapy problem for the particular set of parameters; as well as A user interaction with the graphical user interface is obtained to modify the particular set of parameters.

11. The method according to claim 1, further comprising: selecting a solution to the radiation therapy problem based on an evaluation of the plurality of solutions; Therein, the treatment planning data is generated based on the selected solution to the radiation therapy problem.

12. The method according to claim 11, wherein: The selected solution to the radiation therapy problem provides an approximate solution, wherein the method further comprises: receiving an additional optimization of the selected solution; Wherein, the treatment planning data is generated based on the additional optimization of the selected solution.

13. The method according to claim 1, wherein: The treatment planning data for the radiation therapy comprises a set of treatment delivery parameters corresponding to the capabilities of the radiation therapy machine.

14. The method according to claim 13, wherein: The radiation therapy is to be delivered using a Gamma Knife, and wherein the set of treatment delivery parameters includes a set of isocenters for delivery of the radiation therapy.

15. The method according to claim 14, wherein: The set of treatment delivery parameters also includes timing for delivery of the radiation therapy and a collimator sequence for delivery of the radiation therapy.

16. The method according to claim 13, wherein: The radiation therapy will be delivered using a linear accelerator or a magnetic resonance (MR)-linac radiation therapy machine.

17. The method according to claim 16, wherein: The radiation therapy will be provided using volumetric modulation radiation therapy (VMAT) or intensity modulated radiation therapy (IMRT), and wherein the set of treatment delivery parameters includes: a set of arc control points for one or more arcs, a fluence field, a gantry speed, and a dose rate along the one or more arcs.

18. A non-transitory computer-readable storage medium comprising computer-readable instructions for radiation therapy planning, wherein: When the instructions are executed using a computer, the computer is caused to perform the method according to any one of claims 1 to 17.

19. A computing system configured for radiation therapy planning, the system comprising: one or more memory devices storing data for a radiation therapy problem for providing radiation therapy to a human subject from a radiation therapy machine, the radiation therapy problem being a multi-criteria optimization problem adjustable via a plurality of parameters; as well as One or more processors configured to: performing a treatment plan optimization for the delivery of the radiation therapy, the treatment plan optimization comprising the following operations: identifying a parameterized linear programming equation from the radiation therapy problem; converting the parameterized linear programming equations for execution by parallel processing hardware; as well as solving a plurality of transformed parameterized linear programming equations in parallel on the parallel processing hardware to produce a plurality of solutions to the radiation therapy problem corresponding to the plurality of parameters defining the radiation therapy problem; as well as Treatment planning data is generated based on at least one of the plurality of solutions, wherein the treatment planning data is used to generate a radiation treatment plan.

20. The computing system of claim 19, wherein: The parameters defined by the radiation therapy problem correspond to clinical preferences.

21. The computing system of claim 19, wherein the one or more processors are further configured to: A plurality of sets of the parameters defining the radiation therapy problem are received.

22. The computing system of claim 21, wherein: Parameters in the plurality of sets of parameters relate to specific anatomical regions of the human subject receiving the radiation therapy from the radiation therapy machine.

23. The computing system of claim 21, wherein: The plurality of sets of parameters include definitions of one or more organ-at-risk regions and one or more target regions.

24. The computing system of claim 19, wherein: The operation of converting the parameterized linear programming equation includes the operation of applying an alternating direction method of multipliers technique.

25. The computing system of claim 24, wherein: The alternating direction multiplier technique includes operations for transforming the converted parameterized linear programming equations into matrix operations.

26. The computing system of claim 19, wherein: The parallel processing hardware includes a plurality of graphics processing units (GPUs).

27. The computing system of claim 19, the one or more processors further configured to perform operations for generating a representation of a solution space based on the plurality of solutions to the radiation therapy problem, wherein: The solution space is a Pareto surface including a set of Pareto optimal solutions.

28. The computing system of claim 19, wherein the one or more processors are further configured to: generating a display of a graphical user interface configured to provide functionality for configuring the radiation treatment plan; displaying within the graphical user interface information associated with a particular solution to the radiation therapy problem for the particular set of parameters; and A user interaction with the graphical user interface is obtained to modify the particular set of parameters.

29. The computing system of claim 19, wherein the one or more processors are further configured to: selecting a solution to the radiation therapy problem based on an evaluation of the plurality of solutions; in, The treatment planning data is generated based on the selected solution to the radiation therapy problem.

30. The computing system of claim 19, wherein: The selected solution to the radiation therapy problem provides an approximate solution, the one or more processors are further configured to: receiving an additional optimization of the selected solution; Wherein, the treatment planning data is generated based on the additional optimization of the selected solution.

31. The computing system of claim 19, wherein: The treatment planning data for the radiation therapy comprises a set of treatment delivery parameters corresponding to the capabilities of the radiation therapy machine.

32. The computing system of claim 31, wherein: The radiation therapy is to be delivered using a Gamma Knife, and wherein the set of treatment delivery parameters includes a set of isocenters for delivery of the radiation therapy.

33. The computing system of claim 31, wherein: The set of treatment delivery parameters also includes timing for delivery of the radiation therapy and a collimator sequence for delivery of the radiation therapy.

34. The computing system of claim 31 , wherein: The radiation therapy will be delivered using a linear accelerator or a magnetic resonance (MR)-linac radiation therapy machine.

35. The computing system of claim 34, wherein: The radiation therapy will be provided using volumetric modulation radiation therapy (VMAT) or intensity modulated radiation therapy (IMRT), and wherein the set of treatment delivery parameters includes: a set of arc control points for one or more arcs, a fluence field, a gantry speed, and a dose rate along the one or more arcs.

Images