Adaptive dose accumulation algorithm

Abstract

A technique for adjusting a radiation therapy treatment for a patient in real time is provided. The technique includes operations including: obtaining one or more images of the patient at a first rate during delivery of a radiation therapy treatment segment to the patient; generating patient motion information at a second rate based on the one or more images obtained at the first rate; receiving radiation therapy treatment device settings at a third rate during delivery of the radiation therapy treatment segment; calculating a dose delivered to the patient with a first level of accuracy during delivery of the radiation therapy treatment segment based on the generated patient motion information and the radiation therapy treatment device settings; and determining a real-time measurement of a cumulative dose delivered to the patient with a second level of accuracy higher than the first level of accuracy using one or more previous dose calculations during delivery of the radiation therapy treatment segment.

Description

Technical Field

[0001] The present disclosure relates generally to radiation therapy or radiotherapy. More specifically, the present disclosure relates to systems and methods for calculating cumulative dose in real time during radiation therapy treatment fractions. Background Art

[0002] Radiotherapy is used to treat cancer and other diseases in mammalian (e.g., human and animal) tissues. Radiotherapy includes radiotherapy based on linear particle accelerator (LINAC) and circular particle accelerator (e.g., cyclotron, synchrotron and synchrocyclotron). The direction and shape of the radiation beam should be accurately controlled to ensure that the target tumor receives the prescribed radiation, and the arrangement of the beam should minimize the damage to the surrounding healthy tissue as much as possible, and the surrounding healthy tissue includes the particularly sensitive organs commonly referred to as organs at risk (OAR). Treatment planning can be used to control radiation beam parameters, and the radiotherapy device realizes treatment by delivering a spatially varying dose distribution to the patient according to the treatment plan. Summary of the invention

[0003] In some embodiments, a computer-implemented method, a transient or non-transitory computer-readable medium, and a system including a memory and a processor are provided for performing operations, the operations including: obtaining, by one or more processors, one or more images of a patient at a first rate during delivery of a radiotherapy treatment segment to the patient; generating patient motion information at a second rate based on the one or more images obtained at the first rate by sampling the one or more images at a second rate lower than the first rate; receiving radiotherapy treatment device settings at a third rate greater than the first rate during delivery of the radiotherapy treatment segment; calculating a dose delivered to the patient with a first level of accuracy based on the generated patient motion information and the radiotherapy treatment device settings during delivery of the radiotherapy treatment segment; and determining a real-time measurement of a cumulative dose delivered to the patient with a second higher level of accuracy than the first level of accuracy at a rate lower than the first rate using one or more previous dose calculations during delivery of the radiotherapy treatment segment.

[0004] In some embodiments, the operations further include determining a fourth rate at which dose is calculated and accumulated, the fourth rate being lower than the first rate; and setting the second rate at which the one or more images are sampled based on the fourth rate at which dose is calculated.

[0005] In some embodiments, generating the patient motion information includes adjusting a second rate at which the set of one or more images is sampled to ignore and exclude portions of the one or more images acquired at the first rate from the generated patient motion information.

[0006] In some embodiments, the dose is calculated using an advanced Monte Carlo dose calculation technique, resulting in a dose distribution having a noise level corresponding to a first level of accuracy.

[0007] In some embodiments, the dose is calculated at a fourth rate so that each of a plurality of dose calculations for a radiation therapy treatment segment is output at the fourth rate, each of the plurality of dose calculations respectively having a level of accuracy lower than the second level of accuracy, and the operation further comprises: converting each of the plurality of dose calculations to a same reference frame of the reference geometry, and accumulating each of the plurality of dose calculations in respective increments to determine a real-time measurement of the cumulative dose, wherein each increment in the accumulation increases the level of accuracy of a dosimetry index.

[0008] In some embodiments, the second rate is set to a value sufficient to resolve motion patterns of the patient, wherein the accuracy level of each individual dose calculation comprises an individual high-level Monte Carlo dose calculation, and wherein the second accuracy level comprises a cumulative three-dimensional (3D) Monte Carlo dose calculation.

[0009] In some embodiments, the dosimetric index comprises at least one of: a quantitative single measurement extracted from a 3D dose distribution, a near maximum dose, a near minimum dose, or a measure of consistency between the dose distribution and a target volume.

[0010] In some embodiments, the dosimetric index comprises a dose value histogram (DVH) or a DVH measurement.

[0011] In some embodiments, the operations further include calculating a dosimetry index by extracting a subset of the 3D portion in the cumulative 3D Monte Carlo dose calculation, the dosimetry index having a third level of accuracy higher than the first level of accuracy and the second level of accuracy.

[0012] In some embodiments, the operations further comprise compressing the radiation therapy treatment device settings into a single effective segment based on the second rate at which the patient motion information is generated, wherein the dose is calculated based on the compressed radiation therapy treatment device settings.

[0013] In some embodiments, the radiotherapy treatment device settings received at a third rate include a set of updates to the radiotherapy treatment device settings performed during a given time interval of the radiotherapy treatment segment corresponding to the third rate, and the method also includes aggregating the total fluence delivered by multiple beam delivery segments into a single effective segment.

[0014] In some embodiments, a single valid segment includes a starting position and a stopping position for each beam limiter (BLD) element pair, wherein calculating the valid segment includes: for each BLD element pair, including operations for performing the following: for each update in a set of updates, obtaining all positions of the BLD element pairs; identifying a maximum position of each BLD element pair in the current BLD element pair among the obtained positions in the set of updates; identifying a minimum position of each BLD element pair in the current BLD element pair among the obtained positions in the set of updates; designating the minimum position as the starting position of each BLD element pair in the current BLD element pair; and designating the maximum position as the stopping position of each BLD element pair in the current BLD element pair.

[0015] In some embodiments, the BLD element pair includes at least one of a clip pair of a multi-leaf collimator (MLC) or a leaf pair of the MLC, and the operation also includes: determining a number of monitoring units (MUs) delivered for each update in a set of updates; accumulating the determined number of MUs for a set of updates to calculate a total fluence; and allocating the accumulated MUs to active segments.

[0016] In some embodiments, the operations further include generating a visualization of dose accumulation at a fourth rate based on the determined real-time measurement of cumulative dose delivered to the patient during delivery of the radiation therapy treatment fractions.

[0017] In some embodiments, the visualization shows real-time progress of the radiotherapy treatment segments, and the operations further include: obtaining a reference dosimetry index calculated based on a reference radiotherapy treatment plan; and presenting the real-time progress in the visualization by graphically displaying the same dosimetry index based on the cumulative dose relative to the reference dosimetry index.

[0018] In some embodiments, the operations further comprise gating or adjusting radiation therapy treatment device settings during delivery of the radiation therapy treatment fraction based on real-time measurements of the determined dose and one or more additional factors.

[0019] In some embodiments, the patient motion information is generated by: applying a patient motion model to one or more reference images of the patient to create a motion estimate; and using the motion estimate to deform the patient anatomy to the current state.

[0020] In some embodiments, the calculated dose includes a first calculated dose corresponding to a first portion of a radiation therapy treatment segment, and the method further includes: denoising a differential dose volume histogram of the first calculated dose while calculating a second dose for a second portion of the radiation therapy treatment segment.

[0021] 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. Specific embodiments are included to provide additional information about this patent application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In the drawings, which are not necessarily drawn to scale, similar reference numerals describe substantially similar components throughout the several views. Similar reference numerals 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 by way of limitation.

[0023] Figure 1 is an illustrative radiation therapy system suitable for performing real-time dose calculations during radiation therapy treatment fractions according to some examples.

[0024] Figure 2 are illustrative image-guided radiation therapy devices according to some examples of the present disclosure.

[0025] Figure 3 are illustrative update rates for radiation therapy treatment device components according to some examples of the present disclosure.

[0026] Figure 4 are illustrative effective beam limiter segment representations according to some examples of the present disclosure.

[0027] Figure 5 are illustrative visualizations of dose accumulation according to some examples of the present disclosure.

[0028] Figure 6 A flow chart illustrating example operations for performing real-time dose calculations during a radiation therapy treatment fraction, according to some examples of the present disclosure. DETAILED DESCRIPTION

[0029] The present disclosure includes various techniques for improving and enhancing radiation therapy treatments by calculating dose accumulation in real time during radiation therapy treatment segments. Such real-time dose accumulation calculations can be used as a quality assurance (QA) measure during a radiation therapy treatment session to assure a user or operator that the treatment is proceeding according to the treatment plan. The disclosed techniques can be applicable to various medical treatment and diagnostic settings or radiation therapy treatment equipment and devices.

[0030] Due to the risk of severe injury and late effects, the dose to vital organs and healthy tissues in radiotherapy treatments should be minimized. However, treatment planning is usually performed based on one or some image sets of the patient (e.g., a snapshot in time of the patient) before the patient's first treatment session. Specifically, the conventional way to deliver radiotherapy is to image the patient using computed tomography (CT), magnetic resonance imaging (MRI), and / or positron emission tomography (PET) a few days or even weeks before the start of treatment. Based on a snapshot of the patient's anatomy, a treatment plan is created, and the same plan is used throughout the treatment. The treatment plan consists of a number of beam segments of different weights - cumulative dosing - that are delivered at discrete or continuous gantry angles using different multi-leaf collimators and clip settings (e.g., beam limiting devices) that shape the segment's fluence.

[0031] Based on the treatment plan, the treatment is delivered in several segments (usually 5 to 40 segments), most commonly once a day. One segment takes about a few minutes to deliver. The patient's anatomy can change between segments (inter-segment) due to, for example, weight loss or due to the fact that internal organs change shape and relative position, and the patient's anatomy can change within a segment (intra-segment) due to, for example, breathing. Despite these uncertainties, the standard approach to ensure adequate target dose coverage is to expand the irradiation volume with a certain margin. However, due to the large spatial uncertainty, the margin may result in a large amount of normal tissue being irradiated, resulting in an increased risk of normal tissue complications in the early (e.g., skin, bladder, or digestive tract inflammation) and late (e.g., fibrosis, atrophy, vascular damage, infertility, cognitive problems, or secondary cancers).

[0032] The introduction of sophisticated imaging possibilities at the treatment machine enables re-imaging of the patient in the treatment position just before delivery of each segment. The treatment plan can then be adjusted based on these daily images before delivery, which is called online adaptive radiotherapy. Thus, with online adaptive techniques, inter-segment variations in the anatomy can be taken into account and compensated. However, there is still a need to account for intra-segment variations by adding margins to the target (tumor) volume. These margins can be made smaller than those of conventional radiotherapy, where a single treatment plan is used for the entire course of treatment.

[0033] One way to achieve QA of clinical treatment plans is to deliver the plan on a phantom equipped with a detector that measures the deposited dose before treatment. The dose calculated based on the treatment plan is then compared to the measured dose, and if they agree within a certain tolerance, the plan is considered to be delivered as expected by the treatment machine. However, in online and real-time adaptive radiation therapy, it is not possible to measure the dose in advance, because the treatment plan is created or adjusted while the patient is on the treatment couch (online), or the treatment plan is continuously adjusted in real time in response to changing anatomy (real time). Given that measurement-based patient QA is not possible in online and real-time situations, dose calculation and accumulation can play a central role in patient QA. According to the disclosed technology, real-time imaging during the delivery of a treatment segment, together with access to the treatment machine settings, can be used offline (after the segment has been delivered) or in real time to calculate and accumulate the dose delivered to the patient during the delivery of the treatment segment. In order to speed up and improve the efficiency of real-time dose calculations, only a sufficient portion of the real-time imaging and treatment machine settings are considered at each dose calculation. That is, when calculating the dose, a subset of less than all patient imaging and treatment machine settings that is sufficient to resolve patient motion is considered. In this way, the calculated dose at each increment, although less accurate due to increased noise and a smaller set of information (e.g., imaging and machine settings), is still sufficient to account for patient movement and radiation delivered by the treatment machine. Furthermore, by accumulating multiple individual dose calculations with lower levels of accuracy, a real-time dose accumulation with a higher level of accuracy can be determined and used to accurately represent the dose delivered to the patient during the treatment segment.

[0034] The dose calculated in this manner can then be used as part of patient QA as verification of treatment delivery. According to some embodiments, different levels of action can occur based on real-time dose calculation and accumulation. For example, the treatment can simply be recorded for verification without additional action, and / or the radiation therapy treatment beam can be turned off or on based on the patient's organ motion and the calculated dose. In some cases, MLC can be used to follow or track patient motion.

[0035] In order to perform real-time dose calculation and accumulation, the disclosed embodiment obtains one or more images of the patient at a first rate during the delivery of a radiotherapy treatment segment to the patient, and generates patient motion information at a second rate based on the one or more images obtained at the first rate. During the delivery of the treatment segment, the radiotherapy treatment device settings are received at a third rate, and the dose delivered to the patient with a first level of accuracy is calculated based on the generated patient motion information and the radiotherapy treatment device settings. In some cases, the dose with the first level of accuracy is calculated using an advanced Monte Carlo dose calculation, which results in a dose distribution (e.g., a 3D dose distribution) with a relatively high noise level due to speed requirements. Such a 3D dose distribution with a first level of accuracy is not sufficient to determine the dose delivered to the patient by itself. The calculated dose is used to determine a real-time measurement of the cumulative dose delivered to the patient with a second higher level of accuracy during the delivery of the segment. The second level of accuracy can be due to the DVH metric and some of the 3D dose volume elements with the first level of accuracy are added. Then, by accumulating multiple individual dose calculations with a first level of accuracy, a real-time dose accumulation with a higher level of accuracy (e.g., a third level of accuracy that is higher than the second level of accuracy) can be determined and used to accurately represent the dose delivered to the patient during the treatment segment. As referred to herein, dose accumulation represents a continuous or periodic calculation of individual dose increments of treatment delivery, wherein changes in patient anatomy and treatment machine settings are taken into account and then mapped back to a common reference patient anatomy and summarized.

[0036] In some cases, dose calculations and accumulations are output at a rate (e.g., 2 Hz) that resolves patient motion (such as respiration, bowel movements, internal organ movement and deformation, etc.). That is, the temporal resolution of dose accumulation can be set to 2 Hz or any other suitable value that represents the patient motion of interest. In order to provide dose accumulation at such a rate that resolves patient motion, real-time images of the patient used in the dose calculations are acquired (e.g., sampled) at a rate that at least corresponds to the patient motion (e.g., 2 Hz).

[0037] Figure 1An exemplary radiation therapy system 100 is shown that is suitable for performing radiation therapy planning processing operations using one or more of the methods discussed herein. 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 specific aspects of therapy dose calculations or radiation therapy machine configuration parameters. In particular, the following processing operations can be implemented as part of a real-time dose calculation workflow 130 implemented by treatment processing logic 120. However, it should be understood that many variations and use cases of the following treatment processing logic 120 can be provided, including data validation, visualization, and other medical evaluation and diagnostic settings.

[0038] The radiation therapy system 100 includes a radiation therapy processing computing system 110 that hosts treatment processing logic 120. The radiation therapy processing 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 processing computing system 110 with one or more 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, also referred to herein as a radiation therapy device), and a treatment data source 160.

[0039] For example, the radiation therapy treatment computing system 110 can be configured to monitor the current patient geometry in real time to calculate the dose delivery to the subject within a given segment (e.g., based on one or more MR images captured at a first rate (such as 5 Hz)). In order to speed up and improve the efficiency of the dose calculation, the radiation therapy treatment computing system 110 samples a portion of the current patient geometry sufficient to resolve patient motion. That is, the radiation therapy treatment computing system 110 can sample one or more MR images at a second rate (such as 2.5 Hz) to skip every other MR image and reduce the amount of data processed by the dose calculation technique. Considering that the second rate of 2.5 Hz is still greater than 2 Hz of patient motion, the reduced number of MR images is still sufficient to resolve patient motion. Although patient images are obtained at a first rate during a given interval of a treatment segment (e.g., an increment of a segment), the radiation therapy treatment computing system 110 also obtains radiation therapy device settings or parameters at a third rate (e.g., the third rate is 25 Hz) that is faster than the first rate and the second rate at which the patient images are obtained. The radiation therapy treatment computing system 110 can calculate an effective representation of the radiation therapy device settings or parameters to reduce the amount of data processed by the dose calculation technique, the effective representation including less than all the information obtained at the third rate. In some cases, the effective representation can compress the radiation therapy device settings or parameters obtained at the third rate based on the second rate at which the patient images are sampled. The effective representation represents the total fluence delivered from the uncompressed radiation therapy device settings or parameters. At each interval or increment of the treatment segment, the radiation therapy treatment computing system 110 calculates individual doses by applying an advanced Monte Carlo dose calculation technique to a 3D patient model determined from the sampled images and the effective representation of the radiation therapy device settings to simulate the radiation transport of multiple incident particles and generate a dose distribution having a noise level corresponding to the first level of accuracy.

[0040] The radiation therapy processing computing system 110 similarly samples the patient's images during the second interval or increment of the treatment segment and calculates the effective radiation therapy device settings or parameters for the second interval or increment. The radiation therapy processing computing system 110 calculates another dose with a first accuracy level for the second interval and accumulates the dose with the previously calculated dose. The result is a real-time dose accumulation with a second higher accuracy level than the accuracy level of the individual dose calculation. The radiation therapy processing computing system 110 converts each of the multiple dose calculations to the same reference system of the patient's reference geometry and accumulates each of the multiple dose calculations in respective increments to determine a real-time measurement of the cumulative dose. In some cases, each increment in the accumulation increases the accuracy level of the dosimetry index. The dosimetry index includes at least one of the following: a quantitative single measurement extracted from, for example, a 3D dose distribution or a cumulative dose volume histogram (DVH), a near maximum dose DVH measurement, a near minimum dose DVH measurement, a differential DVH measurement, another DVH measurement, or a measurement of consistency between a dose distribution and a target volume.

[0041] The radiation therapy treatment computing system 110 may include a processing circuit system 112, a memory 114, a storage device 116, 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 treatment plan (e.g., training data, treatment planning strategies, patient movement models, patient deformation models, beam delivery segment information, 3D and / or 2D image information of the patient and device adjustment parameters, etc.), a software program (e.g., image processing software, image or anatomical visualization software, etc.), and any other computer executable instructions executed by the processing circuit system 112.

[0042] In an example, the processing circuit system 112 may include a processing device, such as one or more general-purpose 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 system 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 system 112 may also be implemented by one or more special-purpose processing devices such as an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), a system on a chip (SoC), etc.

[0043] As will be appreciated by those skilled in the art, in some examples, processing circuitry 112 may be a special purpose processor rather than a general purpose processor. Processing circuitry 112 may include one or more known processing devices, such as those provided by Intel. TM Pentium TM 、Core TM , Xeon TM or series of microprocessors, produced by AMD TM Made by Turion TM , Athlon TM 、Sempron TM 、Opteron TM FX TM 、Phenom TM series processors, or any of a variety of processors manufactured by Sun Microsystems. Processing circuit system 112 may also include a graphics processing unit, such as a graphics processing unit manufactured by Nvidia TM Manufactured series of GPUs, from Intel TM GMA, Iris TM Series or by AMD TM Made by Radeon TM The processing circuit system 112 may also include an accelerated processing unit such as an Intel TM Xeon Phi manufactured TM series. The disclosed embodiments are not limited to any type of processor that is 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 (circuitry-based) processor or a software-based processor, such as a multi-core design or multiple processors each having a multi-core design. The processing circuit system 112 can execute a sequence of transient or non-transient computer program instructions stored in the memory 114 and accessed from the storage device 116 to perform various operations, processes, methods that will be described in more detail below. It should be understood that any component in the radiation therapy system 100 can be implemented separately and operated as a stand-alone device, and can be coupled to any other component in the radiation therapy system 100 to perform the techniques described in the present disclosure.

[0044] The memory 114 may include read-only memory (ROM), phase-change random access memory (PRAM), static random access memory (SRAM), flash memory, random access memory (RAM), dynamic random access memory (DRAM) such as synchronous DRAM (SDRAM), electrically erasable programmable read-only memory (EEPROM), static memory (e.g., flash memory, flash disk, static random access memory), and other types of random access memory, cache memory, registers, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage device, cassette tape, other magnetic storage device, or any other non-transitory medium that can be used to store information including images, training data, ML technique parameters, device adaptation functions, data, or transient or non-transitory computer executable instructions (e.g., stored in any format) that can be accessed by the processor system 112 or any other type of computer device. For example, computer program instructions can be accessed by the processing circuit system 112, can be read from ROM or any other suitable memory location, and can be loaded into RAM for execution by the processing circuit system 112.

[0045] The storage device 116 may constitute a drive unit including a transitory or non-transitory machine-readable medium having stored thereon one or more transitory or non-transitory instruction sets and data structures (e.g., software) implemented or utilized by any one or more of the methods or functions described herein (including, in various examples, the treatment processing logic 120 and the user interface 142). During execution of the instructions by the radiation therapy treatment computing system 110, the instructions may also reside, in whole or in part, within the memory 114 and / or within the processing circuit system 112, wherein the memory 114 and the processing circuit system 112 also constitute transitory or non-transitory machine-readable media.

[0046] The memory 114 and the storage device 116 may constitute a non-transitory computer-readable medium. For example, the memory 114 and the storage device 116 may store or load transient or non-transitory instructions for one or more software applications on a computer-readable medium. Software applications stored or loaded using the memory 114 and the storage device 116 may include, for example, operating systems for general-purpose computer systems and software-controlled devices. The radiation therapy treatment computing system 110 may also operate various software programs including software codes for implementing the treatment treatment logic 120 and the user interface 142. In addition, 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 can be executed by the processing circuit system 112. In other examples, the memory 114 and the storage device 116 may store, load, and manipulate one or more radiation therapy treatment plans, imaging data, segmented data, treatment visualization, histograms, or measurement results, 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.

[0047] Although not depicted, the radiation therapy treatment computing system 110 may include communication interfaces, network interface cards, and communication circuit systems. 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, such as 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 WAN that may include other systems, including additional image processing computing systems or image-based components associated with medical imaging or radiation therapy operations.

[0048] In an example, the radiation therapy processing computing system 110 may obtain image data 152 from an image data source 150 (e.g., CT, PET, and / or MR images) to be hosted on the storage device 116 and the memory 114. In another example, a software program may replace a function of the patient image, such as a signed distance function or a processed version of the image that emphasizes some aspects of the image information.

[0049] In an example, the radiation therapy treatment computing system 110 may obtain image data 152 from or transmit image data 152 to the image data source 150. In other examples, the treatment data source 160 receives or updates planning data 162 as a result of radiation therapy device parameter adjustments or segment adaptations generated by the real-time dose calculation workflow 130; the image data source 150 may also provide or host the image data 152 for use in the real-time dose calculation workflow 130.

[0050] Processing circuitry 112 may be communicatively coupled to memory 114 and storage device 116, and processing circuitry 112 may be configured to execute computer-executable instructions stored thereon from memory 114 or storage device 116. Processing circuitry 112 may execute instructions to cause a medical image from image data 152 to be received or obtained in memory 114 and processed using treatment processing logic 120.

[0051] In addition, the processing circuit system 112 can utilize the software program to generate intermediate data, such as updated parameters to be used by, for example, a neural network model, a machine learning model, a real-time dose calculation workflow 130, or other aspects involved in the generation of device parameter adjustments or segment adaptations as discussed herein. In addition, using the techniques further discussed herein, such a software program can utilize the treatment processing logic 120 to implement the real-time dose calculation workflow 130 to generate updated radiation therapy parameters to provide to the treatment data source 160 to modify the dose delivered to the target within a given segment and / or for presentation on the output device 146. The processing circuit system 112 can then transmit the updated radiation therapy parameters to the treatment device 180 via the communication interface and network, where the updated parameters will be used to treat the patient with radiation via the treatment device 180, consistent with the results of the real-time dose calculation workflow 130. Other outputs and uses of the software program and the real-time dose calculation workflow 130 can occur in conjunction with the use of the radiation therapy processing computing system 110. Radiation therapy parameters (also called control points) may include MLC positions and settings for each segment or portion of a given treatment segment, gantry angle, amount of radiation dose (e.g., amount of monitoring units (MUs)), radiation therapy beam direction, radiation beam size, arc placement, beam switch duration, machine parameters, gantry speed, MRI pulse sequence, any combination thereof, and the like.

[0052] In an example, the image data 152 may include one or more MR images (e.g., 2D MRI, 3D MRI, 2D flow MRI, 4D MRI, 4D volume MRI, 4D imaging 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, fluoroscopic images, radiotherapy field images, single photon emission computed tomography (SPECT) images, computer-generated synthetic images (e.g., pseudo-CT images), radio beacons, laser scans of a patient's surface, etc. In addition, the image data 152 may also include or be associated with medical image processing data such as training images and ground truth 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.).

[0053] In an example, the image data 152 may be received from an image acquisition device 170 and may be stored in one or more of the 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 fluoroscope 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 data type or any format type (e.g., in Digital Imaging and Communications in Medicine (DICOM) format) that the image acquisition device 170 and the radiation therapy processing computing system 110 may use to perform operations consistent with the disclosed embodiments. Furthermore, in some examples, the models discussed herein may be trained to process the original image data format or a derivative thereof.

[0054] In an 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-Linac"). For example, such an MRI-Linac can be used to determine the location of a target in a patient's body, thereby accurately guiding the radiation beam to the predetermined target according to a radiation therapy treatment plan. For example, a radiation therapy treatment plan can provide information about a specific radiation dose to be applied to each patient. The radiation therapy treatment plan can also include other radiation therapy information and radiation therapy device parameters, such as beam angles, dose-volume histogram information, the number of radiation beams to be used during therapy, the dose of each beam, etc. MRI-Linac can be used to calculate, generate and / or update a patient deformation model to deform an image portion of a 3D or 2D image of the patient corresponding to a given beam delivery segment. MRI-Linac can be used to provide real-time patient images (or a subset of patient images) and machine settings or parameters at each increment / interval of the treatment segment to continuously or periodically calculate the dose for the increment / interval, and determine real-time dose accumulation based on the dose so calculated.

[0055] The radiation therapy processing computing system 110 can communicate with an external database over a network to send / receive a plurality of various types of data related to image processing and radiation therapy operations. For example, the external database may include machine data (including device constraints) that provides information associated with the treatment device 180, the image acquisition device 170, or other machines related to radiation therapy or medical procedures. The machine data information may include radiation beam size, arc placement, beam switch duration, machine parameters, segments, MLC configurations, gantry speeds, MRI pulse sequences, and the like. The external database may be a storage device and may be equipped with an appropriate database management software program. In addition, such a database or data source may include multiple devices or systems located in a central or distributed manner.

[0056] The radiation therapy treatment computing system 110 can collect and obtain data via a network and communicate with other systems using one or more communication interfaces that are communicatively coupled to the processing circuitry 112 and the memory 114. For example, the communication interface can provide a communication connection between the radiation therapy treatment computing system 110 and radiation therapy system components (e.g., allowing data to be exchanged with external devices). For example, in some examples, the communication interface can have appropriate interface circuitry with an output device 146 or an input device 148 to connect to a 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.

[0057] 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 the status of training, generation, verification, or implementation of a medical image, a treatment plan, and such a plan. The output device 146 may include one or more display screens that display medical images, interface information, treatment planning parameters (e.g., contours, doses, beam angles, labels, mappings, etc.), treatment plans, image portions identified and deformed for a given treatment segment, targets, positioning targets, and / or tracking targets, or any information related to the user. The output device 146 may provide a visualization of dose accumulation to the user based on real-time measurements of the dose delivered to the patient during the delivery of the radiation therapy treatment segment determined. The visualization shows the progress of the radiation therapy treatment segment. In some cases, the visualization is generated by obtaining a reference dosimetry index calculated based on a reference radiation therapy treatment plan, and presenting the progress in the visualization by graphically displaying the same dosimetry index based on the cumulative dose relative to the reference dosimetry index.

[0058] The input device 148 connected to the user interface 142 can be a keyboard, keypad, touch screen, or any type of device that a user can use to input information to the radiation therapy system 100. Alternatively, the output device 146, input device 148, and features of the user interface 142 can be integrated into a computer such as a smartphone or tablet computer (e.g., Apple Lenovo Samsung etc.) in a single device.

[0059] In addition, any and all components of the radiation therapy system 100 may be implemented as virtual machines (e.g., via VMWare, Hyper-V, and similar virtualization platforms) or standalone devices. For example, a virtual machine may be software that functions as hardware. Thus, a virtual machine may include at least one or more virtual processors, one or more virtual memories, and one or more virtual communication interfaces that function collectively as hardware. For example, the radiation therapy processing computing system 110, the image data source 150, or similar components may be implemented as virtual machines or within a cloud-based virtualization environment.

[0060] The image acquisition device 170 can be configured to acquire one or more images of the patient's anatomical structure for a region of interest (e.g., a target organ, a target tumor, or both). Each image, which is typically a 2D image or slice, can include one or more parameters (e.g., 2D slice thickness, orientation, and position, etc.). In an example, the image acquisition device 170 can acquire 2D slices of any orientation. For example, the orientation of the 2D slice can include a sagittal orientation, a coronal orientation, or an axial orientation. The processing circuit system 112 can 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 an example, the 2D slice can be determined based on information such as a 3D CBCT or CT or MRI volume. When the patient is undergoing radiation therapy treatment, such as when using the treatment device 180, such 2D slices can be acquired by the image acquisition device 170 in "near real time" (wherein, as known in the art, "near real time" means acquiring data without a lag (or with minimal lag) between image acquisition and treatment). In an example, a stack of one or more 2D slices may be used to generate a 3D volume representation of a region of interest.

[0061] Figure 2 An exemplary image-guided radiation therapy device 202 is shown, which includes a radiation source, such as an x-ray source or a linear accelerator, a bed 216, an imaging detector 214, and a radiation therapy output 204. The radiation therapy device 202 can be configured to emit a radiation therapy beam 208 to provide therapy to a patient. The radiation therapy output 204 can include one or more attenuators or collimators, such as a multi-leaf collimator (MLC).

[0062] As an example, a patient can be positioned in an area 212 supported by a treatment couch 216 to receive a radiation therapy dose according to a radiation therapy treatment plan. The radiation therapy output 204 can be mounted or attached to a gantry 206 or other mechanical support. When the couch 216 is inserted into the treatment area, one or more chassis motors (not shown) can rotate the gantry 206 and the radiation therapy output 204 around the couch 216. In an example, the gantry 206 can continuously rotate around the couch 216 when the couch 216 is inserted into the treatment area. In another example, the gantry 206 can rotate to a predetermined position when the couch 216 is inserted into the treatment area. For example, the gantry 206 can be configured to rotate the therapy output 204 around an axis ("A"). Both the couch 216 and the radiation therapy output 204 can be independently moved to other positions around the patient, for example, movable in a transverse direction ("T"), movable in a lateral direction ("L"), or rotated about one or more other axes, such as about a transverse axis (shown as "R"). A controller communicatively connected to one or more actuators (not shown) can control the movement or rotation of the couch 216 to appropriately position the patient in or out of the radiation therapy beam 208 according to the radiation therapy treatment plan. Both the couch 216 and the gantry 204 can be moved independently of each other in multiple degrees of freedom, which allows the patient to be positioned so that the radiation therapy beam 208 can be precisely aimed at the tumor.

[0063] The coordinate system (including axes A, T, and L) can have an origin located at an isocenter 210. The isocenter 210 can be defined as the location at which the central axis of the radiation therapy beam 208 intersects the origin of the coordinate axes, such as to deliver a prescribed radiation dose to a patient or a location within the body. Alternatively, the isocenter 210 can be defined as the location at which the central axis of the radiation therapy beam 208 intersects the patient for various rotational positions of the radiation therapy output 204 positioned by the gantry 206 about the axis A.

[0064] The gantry 206 may also have an attached imaging detector 214. The imaging detector 214 is preferably positioned opposite the radiation source (output 204), and in an example, the imaging detector 214 may be located within the field of the radiation therapy beam 208. The imaging detector 214 may preferably be mounted on the gantry 206 opposite the radiation therapy output 204, for example to maintain alignment with the radiation therapy beam 208. As the gantry 206 rotates, the imaging detector 214 rotates around the axis of rotation. In an example, the imaging detector 214 may be a flat panel detector (e.g., a direct detector or a scintillator detector). In this way, the imaging detector 214 may be used to monitor the radiation therapy beam 208, or the imaging detector 214 may be used to image the patient's anatomical structure, such as portal imaging. The control circuit system of the radiation therapy device 202 may be integrated within the radiation therapy system 100 or remote from the radiation therapy system 100.

[0065] In the illustrative example, one or more of the couch 216, therapy output 204, or gantry 206 may be automatically positioned, and the therapy output 204 may establish the radiation therapy beam 208 according to the specified dose for a particular therapy delivery instance. A sequence of therapy deliveries may be specified according to a radiation therapy treatment plan, for example, using one or more different orientations or positions of the gantry 206, couch 216, or therapy output 204. The therapy deliveries may occur sequentially, but may intersect at a desired treatment site on or within the patient, such as at an isocenter 210. Thus, a prescribed cumulative dose of radiation therapy may be delivered to the treatment site while reducing or avoiding damage to tissue near the treatment site.

[0066] therefore, Figure 2 In particular, an example of a radiation therapy device 202 is shown that is operable to provide radiation therapy treatment to a patient in accordance with or in accordance with a radiation therapy treatment plan and parameters of the device adjusted within a given segment, having a configuration in which a 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 another example, the therapy 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 specified target site in the patient's body. In another example, the radiation therapy device can be a combination of a linear accelerator and an image acquisition device. In some examples, the image acquisition device can be an MRI, X-ray, CT, CBCT, spiral CT, PET, SPECT, optical tomography, fluorescence imaging, ultrasound imaging, or a radiotherapy field imaging device, etc., as will be recognized by a person of ordinary skill in the art.

[0067] Return to reference Figure 1 , the real-time dose calculation workflow 130 includes patient image information 132, a 3D patient model constructed based on these images, radiation therapy device parameters 134, and a dose calculation and accumulation process 136. In an implementation, the processing implemented by the real-time dose calculation workflow 130 can be performed in real time during a given treatment segment (e.g., when each beam delivery segment begins or ends) and / or before or after the patient undergoes a given treatment segment.

[0068] In an example, the real-time dose calculation workflow 130 obtains a radiotherapy treatment plan for a given patient. A radiotherapy treatment plan can be generated by a clinician to deliver radiotherapy during one or more radiotherapy treatment segments. The radiotherapy treatment plan includes image information of the patient representing the OAR and the target to be irradiated. The image information can be a collection of 2D or 3D MR or CT images. The radiotherapy treatment plan also includes multiple radiotherapy beam delivery segments. Each beam delivery segment defines a set of radiotherapy device control points used throughout the radiotherapy treatment segment. In particular, a beam delivery segment defines a first set of control points used during a first time point or time interval of the treatment segment, and a second beam delivery segment defines a second set of control points used during a second time point or time interval of the treatment segment, the second time point or time interval being after, before and / or adjacent to the first time point. Multiple beam delivery segments define beam delivery parameters used throughout the treatment segment. The radiotherapy treatment plan also includes a depiction of one or more target volumes and / or one or more OARs.

[0069] In an example, the real-time dose calculation workflow 130 generates, obtains and / or updates a patient deformation model. The patient deformation model represents an estimated or predicted movement of a patient and / or a region of a patient during an upcoming, real-time and / or past treatment segment. In an embodiment, the patient deformation model is generated based on at least one of one or more descriptions of a patient captured before or during a radiotherapy treatment segment. One or more descriptions may be generated based on one or more magnetic resonance (MR) images, one or more computed tomography (CT) images, one or more cone beam computed tomography (CBCT) images, surface scans or radio beacons. The patient deformation model may represent actual and / or estimated (predicted) patient movement at specific times or time intervals during a treatment segment and / or throughout the treatment segment. The patient deformation model may be provided as one or more displacement vectors.

[0070] In some embodiments, the patient image information 132 monitors the current patient geometry in real time by capturing one or more MR images of the patient at a first rate (such as 5 Hz) within a given segment. The patient image information 132 samples a portion of the current patient geometry sufficient to resolve patient motion. In an example, the patient image information 132 samples one or more MR images of the patient at a second rate (such as 2.5 Hz) to skip every other MR image and reduce the amount of data processed by the dose calculation technique.

[0071] While patient images are acquired at a first rate during a given interval of a treatment segment (e.g., an increment of a segment), the radiation therapy device parameters 134 acquire radiation therapy device settings or parameters at a third rate (e.g., the third rate is 25 Hz) that is faster than the first rate and the second rate at which the patient images are acquired. The radiation therapy device parameters 134 can calculate an effective representation of the radiation therapy device settings or parameters to reduce the amount of data processed by the dose calculation technique, the effective representation including less information than all of the information acquired at the third rate. For example, the radiation therapy device parameters 134 compresses the radiation therapy device settings acquired at the third rate into an effective representation that represents the total fluence delivered from the radiation therapy device settings or parameters that were never compressed.

[0072] At each interval or increment of the treatment segment, the dose calculation and accumulation process 136 calculates individual doses by applying advanced Monte Carlo dose calculation techniques to the sampled images and an effective representation of the radiotherapy device settings to simulate the radiation transport of multiple incident particles and generate a dose distribution with a noise level corresponding to the first level of accuracy. In some cases, the dose calculation and accumulation process 136 implements a dose engine that uses a complete description of the patient's anatomy (geometry and tissue characterization) and machine settings or control points (MLC and / or clip positions, monitoring units, gantry angles) as input. In some implementations, the dose calculation and accumulation process 136 begins by acquiring and reconstructing 2D images from one or more MR patient images. The dose calculation and accumulation process 136 applies a patient motion model to the resulting 2D images to create a motion estimate used by the dose engine. In some cases, the output of the motion estimate describes the relative motion of the patient to a reference state I REF of patient movement.

[0073] In parallel with image acquisition and motion estimate creation, a dose calculation and accumulation process 136 receives treatment machine settings or control points based on the radiation delivered to the patient at a given interval of the treatment segment. The treatment machine settings are received as a stream of updates containing machine settings describing the state of the machine at that point in time or time interval of the treatment segment. The dose calculation and accumulation process 136 uses the motion estimate to deform the patient anatomy to its current state and combines the patient anatomy with the input received from the treatment machine to continuously calculate and accumulate dose in a reference representation of the patient anatomy. For the purpose of dose calculation, the patient is represented as a 3D matrix of volume elements, voxels. The dose to a given voxel depends on the current geometry of the patient and the treatment machine settings that define the current radiation field. The 3D motion of the patient can be estimated based on a stream of 2D MR images of the patient acquired in real time. In some cases, the 3D motion of the patient is estimated based on a sampled 2D image set (e.g., 2D images generated at a second rate corresponding to the patient's motion, such as 2.5 Hz).

[0074] Cumulative dose at position r in reference geometry is calculated as the sum in Equation 1 below:

[0075]

[0076] where N is the number of computational iterations during treatment, and is the dose increment for iteration i:. The superscript specifies in which anatomical structure the dose is expressed, and the subscript specifies for which iteration the dose is calculated (e.g. It is in I REF i: dose per iteration represented in the patient anatomy). Motion estimation provides I REF with I i The geometric transformation between and Radiation transfer during dose calculation is i to generate dose distributions in the anatomical structure of Calculated according to equation 2 below:

[0077]

[0078] and Both are represented as a deformation vector field (DVF) describing the motion of each individual voxel. In some cases, the cumulative dose is calculated based on a set of sampled patient images (sampled at a second rate of 2.5 Hz) and compression of the effective segments of multiple settings of the beam limiting device received at a third rate (e.g., 25 Hz). In this case, the value of each increment is calculated based on Equation 5 discussed below.

[0079] The dose calculation and accumulation process 136 then calculates relevant features such as a dosimetric index from the dose distribution and may generate a visualization that presents the relevant features to a user or operator. Figure 5 Illustrative visualizations are shown and described.

[0080] Figure 3 is an illustrative update rate for radiation therapy treatment device components according to some examples of the present disclosure. That is, Figure 3 As shown, each component of the radiotherapy system 100 can provide information at a different rate. For example, the MR device or image acquisition device 170 can acquire 2D / 3D images at 5Hz, and the subsequent motion modeling processes the images at the same (or higher) speed. In this case, the motion estimate is also generated at 5Hz. The machine settings (Linac control points) can be streamed or received at 25Hz. In some cases, the speed requirement for outputting and calculating dose accumulation is 2Hz. The GUI presented to the user with a diagram of dose accumulation provides updates to the user at a speed perceived as real-time, which in some cases is greater than or less than 2Hz. The disclosed embodiment responds to the rhythm of different components by sampling and using images less than all patient motion images (e.g., 2.5Hz patient images) and generating an effective segment representing the total fluence delivered by the radiotherapy device corresponding to the machine settings received at 25Hz.

[0081] In some cases, the dose calculation and accumulation process 136 uses the position of the MLC leaves and clips, the gantry angle, the MU delivered for the current radiation beam, and the DVF representing the motion estimate to calculate the dose at a given increment. Any other control point may be used to calculate the dose for a given increment. For notation purposes, the dose engine is defined as D(t) = D(I, TU), which calculates the dose given the patient anatomy I(t) and the treatment machine settings (control points) TU(t).

[0082] One way to process the various input data sources to calculate dose is to pair each update of the patient motion (received at 5 Hz) with the treatment machine setting associated with the same time slot of length t. i Each dose increment of the function is based on the amount delivered by the treatment machine in the corresponding time slot as defined in Equation 3 below:

[0083]

[0084] where TU(t) is the machine setting at time t, and I iis the patient motion state at the i-th time slot. In this case, one calculation is started for each patient motion update. In the case where the dose calculation is slower than the motion estimation update, the increasing queue of input data remains waiting to be processed by the dose accumulation, which causes a lag in presenting the results to the user in the GUI.

[0085] According to some embodiments, to address this problem, the sampling rate of the patient motion state is reduced by a given amount (such as by a factor of 2). This means that every other patient motion update is ignored, and each increment of the cumulative dose spanning a time slot of length 2Δt is calculated according to the following equation 4:

[0086]

[0087] This approximation reduces the number of iterations of dose calculation by half and reduces the overall lag of the final accumulated dose compared to the treatment progression. This enables a trade-off between adequate sampling of the patient state and accurate calculation of the dose at each iteration.

[0088] In some cases, instead of reducing the sampling rate, all dose increment calculations can be parallelized to reduce the queue of input data. In such a case, all patient motion updates are considered when calculating the dose at each increment, but the complexity of system resources will increase.

[0089] In some embodiments, a real-time stream containing machine settings or control points from a treatment device operates at a third rate (e.g., 25 Hz) that is greater than the rate at which patient motion estimates are generated. If the sampling rate of patient motion is a second rate of 2.5 Hz, each increment of dose accumulation will have ten updates of the treatment machine settings (segments). This will result in ten separate dose calculations, which would take too long in a real-time environment. In order to improve the efficiency of the dose calculations and the device and to speed up dose calculations and accumulation, all queued segments of machine settings or control points are compressed into a single active segment. To illustrate an embodiment, one blade pair (i.e., two opposing blades) of an MLC can be similarly compressed into an active segment, but any other pair of beam limiting devices (e.g., a pair of clips and / or other MLC blade pairs) can also be similarly compressed into an active segment.

[0090] The stream of treatment device settings may indicate the starting position of the leaf pair at time t=0 and provide five consecutive updates with the new positions and may also provide the number of MUs delivered in each update. Extension to an arbitrary number of updates is straightforward. The effective segment is calculated to accurately represent the total fluence delivered from all machine setting updates compressed against it from that effective segment. To generate an effective segment, the number of MUs for the effective segment is calculated as the sum of all MUs in the update. The effective segment S effis a dynamic section in which the start and stop positions of each leaf are not necessarily the same. Linear motion is assumed between the start and stop positions of each collimating element. The start position of each leaf is selected as the minimum of the positions in the update, and the stop position is selected as the maximum of the positions in the update. The dose expression for each increment of the cumulative dose is then provided as the following equation 5:

[0091]

[0092] Figure 4 The figure shows the creation of S based on five machine updates. eff A graphical illustration of S, including an indication of the effect of the approximation introduced by the method. eff The introduction of can lead to both overestimation and underestimation of dose, mainly in the penumbra region.

[0093] In some implementations, the radiotherapy device parameters 134 compresses the radiotherapy device parameters by analyzing the pair of beam limiting devices. For example, the radiotherapy device parameters 134 identifies a pair of leaves 410 and 412 in the radiotherapy device parameter set for a given increment or segment corresponding to time t0 to t5. The radiotherapy device parameters 134 searches for all positions of the first leaf 410 in the pair within a given time of the increment of the segment to identify the minimum extension position of the first leaf 410 and the maximum extension position of the first leaf 410. The radiotherapy device parameters 134 may determine that at time t3, the first leaf 410 is in the maximum extension position 430, and at time t5, the first leaf 410 is in the minimum extension position 420. In response, the radiotherapy device parameters 134 may generate a first effective leaf segment that begins at the minimum extension position 420 at time t0 440 and ends at the maximum extension position 430 at time t5 450 (corresponding to the last time point in the received parameter stream).

[0094] Similarly, the radiotherapy device parameters 134 search all positions of the second blade 412 in the pair within a given time of an increment of a segment to identify a minimum extended position of the second blade 412 and a maximum extended position of the second blade 412. The radiotherapy device parameters 134 may determine that at time t5, the second blade 412 is in the maximum extended position 422, and at time t4, the second blade 412 is in the minimum extended position 432. In response, the radiotherapy device parameters 134 may generate a second effective blade segment that begins at the minimum extended position 432 at time t0 440 and ends at the maximum extended position 422 at time t5 450 (corresponding to the last time point in the received parameter stream).

[0095] The radiation therapy device parameters 134 also obtain all MUs delivered within a given time of the increment of the segment at each time point. The radiation therapy device parameters 134 sum all MUs delivered during a given time of the increment of the segment to calculate the total MU for the active segment from t0 440 to time t5 450. Similar techniques can be similarly applied to any other type of beam limiting device pair (e.g., various combinations of clip pairs and / or leaf pairs) to calculate one or more active segments.

[0096] The radiation therapy device parameters 134 use the active segment with the total MU as the radiation therapy device settings when calculating the dose for a given increment, rather than using all settings received from time t0 to t5. This reduces the total amount of information used by the dose calculation technique and speeds up the output of dose calculations and accumulations.

[0097] In some cases, the dose calculation and accumulation process 136 implements a Monte Carlo (MC) dose calculation process to calculate dose and dose accumulation. The dose calculated by MC is inherently noisy, where the noise level (and therefore the accuracy of the calculated dose) is directly related to the number of simulated primary particles / histories used during the simulated radiation delivery. The dose calculation time increases linearly with the number of simulated particles. In MC, the patient is represented as a 3D matrix of voxels, where each voxel contains a material composition and a mass density. When the dose is calculated according to the i-th iteration , using the transformation described by the DVF from the motion model The patient's anatomical structure representation with material and density is transformed from I REF Transform to I i The patient anatomy I is calculated according to Equation 6 below i The density in

[0098]

[0099] Among them, trilinear interpolation is used to calculate the density This is because density can be considered a continuous quantity. Material composition is considered a discrete quantity and is calculated according to Equation 7:

[0100]

[0101] and the material composition is implemented using nearest neighbor interpolation. Then, the dose per voxel is calculated as and function.

[0102] The noise in a given voxel depends on the number of dose deposits in that voxel. The DVH metric is usually used to evaluate 3D dose distributions, rather than doses to individual voxels, and considers doses to many voxels (such as D 2％ or D 98％ The DVH metric of the OAR is inherently less noisy than the base dose distribution. Therefore, given the same noise level in the DVH metric, a large target will have more noise per voxel than a small target. Because a uniform dose is usually delivered to the target, the differential DVH will be a spike around the prescribed target dose. In the case of OARs, the situation will be different because the differential DVH will have a larger spread. As a result of the uniform dose, the dose to the target D will be higher than the OAR metric. 2％ or D 98％ More sensitive to noise. According to the disclosed embodiments, the noise level of the cumulative dose decreases (i.e., the accuracy level of the dose accumulation increases) as the dose is accumulated according to Equations 1 and 2, because accumulation is equivalent to increasing the number of particles in the simulation. That is, as each individual dose calculation (with a high noise level) is accumulated with the previous dose calculation (with a similar high noise level), the overall cumulative dose calculation noise decreases. In this way, the cumulative dose D 2％ or D 98％ The noise in starts at a high level and becomes significantly lower after many iterations (eg, as more and more individual dose calculations are performed and accumulated).

[0103] In some embodiments, after calculating and accumulating individual doses using previous dose calculations, the cumulative dose and / or individual dose calculations are denoised to enhance or improve the accuracy level of the cumulative dose. The cumulative dose and / or individual doses are denoised in parallel with subsequent doses calculated in subsequent iterations. In this way, while doses are calculated for subsequent iterations, previous dose accumulations are denoised and improved to further reduce noise in cumulative dose calculations performed for subsequent iterations. Specifically, as mentioned above, each iteration of dose calculations performed in real time during a treatment segment produces a very noisy dose distribution The noise is due to the fact that far fewer particles are simulated compared to conventional dose calculations. The total dose is then accumulated according to Equation 1, which results in a significant reduction in the noise in the accumulated dose, since each increment in the accumulation enables more particles to be simulated per voxel. That is, very noisy dose distributions can be considered, since the noise in the dose distribution decreases as the accumulation increases. Furthermore, instead of calculating and evaluating the complete 3D dose distribution, a cumulative DVH measure or a differential DVH measure extracted from the accumulated dose obtained according to Equation 1 is calculated and evaluated.

[0104] According to some embodiments, the differential DVH is denoised before extracting the relevant DVH measurements to enable increased speed and efficiency of dose calculation and accumulation. This is possible if the noise per dose level in the differential DVH is known or can be modeled. For this purpose, the noisy differential DVH f noise can be understood as the following equation 8a:

[0105]

[0106] Where f0 is the noise-free differential DVH, and k is a mathematical function that models the uncertainty of each dose level in the differential DVH. If k in each dose bin is known or can be modeled, the noise-free DVH f0 can be reconstructed by solving Equation 8a. In some embodiments, k is according to the following Equation 8b:

[0107]

[0108] where σ is a function proportional to the square root of the dose level.

[0109] According to the disclosed embodiments, the noise-free DVH is reconstructed by employing an optimization problem where bounds are placed on the differentiated DVH to ensure non-negativity.

[0110] The optimization problem is set as a least squares minimization problem, in which the fuzzy estimated noise-free signal (Equation 8a is discretized into dose bins) is represented by the following equation 10:

[0111]

[0112] (Equation 10)

[0113] Among them, f j is the discrete f0. The error function to be minimized is expressed by Equation 11:

[0114]

[0115] Instead of using an iterative approach to solve the optimization problem, we solve the least squares minimization problem according to Equation 12:

[0116]

[0117] Use which can set f jThe optimization of the bound on (e.g., L-BFGS-B method) is used to ensure the non-negativity of the resulting denoised differential DVH. In some embodiments, patient QA can be performed on the delivered treatment segment using offline intra-segment dose accumulation after the treatment segment has been delivered. Offline intra-segment dose accumulation can be a complete MC of the recorded patient movement information and machine parameters applied to the delivered treatment segment. That is, after the treatment segment is delivered, all patient movement information and all corresponding machine parameters in the entire treatment segment can be obtained from the log file. Then, conventional MC can be applied to calculate the cumulative dose with a high level of accuracy using the obtained patient movement information and machine parameters to obtain the cumulative dose of the treatment segment. That is, after the treatment segment is delivered, it is not necessary to perform an approximation of the patient movement information and machine parameters (e.g., the effective segmentation of the beam limiting device), but all such information can be considered. This is because time is not important and a complete calculation can be performed to obtain a very accurate dose accumulation, as long as such calculation is completed before delivering another treatment segment. In some cases, the log file storing the machine parameters is updated every 40 milliseconds during treatment for offline dose accumulation. Additionally, patient motion can be reconstructed using a log of 2D or 3D images captured during a treatment segment. Pairing the machine settings with concurrent patient motion constitutes the dose accumulation input for each increment. The total summed dose for all increments of that segment can then be compared to the dose calculated based on the online treatment plan and can be used as a patient QA method to verify that the dose delivered to the patient corresponds to the expected dose.

[0118] In some cases, the total dose for a given increment or all increments can be compared to an estimated dose accumulation calculated in real time based on an approximation of patient geometry and machine parameters. This enables a QA that is made to an approximation made during real-time dose accumulation during a previous treatment segment, and potentially used to change the approximation of patient geometry and machine parameters considered during the delivery of a subsequent treatment segment. That is, the 3D distribution of offline intra-segment and inter-segment dose accumulations of dose accumulation can be used to adjust subsequent segments (e.g., used as a basis for offline adjustments). For example, the user can be provided with the opportunity to compensate for any hot spots or cold spots in the current total dose distribution (e.g., a smaller set of voxels where the dose deviates from the desired uniform spacing).

[0119] In some embodiments, during the delivery of a treatment segment, a real-time dose accumulation is presented to the user in a graphical user interface to inform the user about the progress of the treatment. Figure 5is an illustrative visualization of dose accumulation according to some examples of the present disclosure. The visualization may include two parts. For example, the first part on the left side of the visualization may graphically depict the target projection and beam limiter (e.g., MLC) position in real time according to the beam-eye-view. At the same time, in the second part on the right side of the visualization, the cumulative dose of the reference geometry is presented as a function of MU. This enables the user to visually see how the cumulative dose calculation compares to the target dose according to the treatment plan as the treatment progresses. In some cases, the dosimetry measurements displayed are the same measurements used to evaluate the treatment plan during planning or are a subset of the measurements used to evaluate the treatment plan during planning. In some implementations, the second part of the visualization presents the dosimetry measurements D calculated for a static reference treatment plan based on a reference patient geometry. 98％ (MU), allowing comparison and validation of treatment progress.

[0120] In some embodiments, the beam can be automatically or manually gated (turned on / off) based on a comparison of the current calculated real-time cumulative dose to the dosimetry measurements calculated based on the static reference plan and patient geometry. That is, if the real-time cumulative dose exceeds the reference dosimetry measurement by more than a threshold amount, the beam for a given portion of the treatment segment can be automatically or manually turned off. Additionally or alternatively, MLC tracking can be performed based on a comparison of the current calculated real-time cumulative dose to the dosimetry measurements calculated based on the static reference plan and patient geometry. In some cases, MLC tracking can use only geometric input.

[0121] Figure 6 600 when executing the process 600. The process 600 may be implemented in computer-readable instructions for execution by one or more processors, such that the operations of the process 600 may be performed in part or in whole by functional components of the treatment processing logic 120; therefore, the process 600 is described below by way of example with reference thereto. However, in other embodiments, at least some of the operations of the process 600 may be deployed on various other hardware configurations. Therefore, the process 600 is not intended to be limited to the treatment processing logic 120 and may be implemented in whole or in part by any other component. Some or all of the operations of the process 600 may be parallel, out of order, or omitted entirely.

[0122] At operation 610 , the treatment processing logic 120 acquires one or more images of a patient at a first rate during delivery of radiation therapy treatment fractions to the patient.

[0123] At operation 620 , the therapy processing logic 120 generates patient motion information at a second rate based on the one or more images acquired at the first rate.

[0124] At operation 630, the treatment processing logic 120 receives radiation therapy treatment device settings at a third rate during delivery of the radiation therapy treatment segments.

[0125] At operation 640 , the treatment processing logic 120 calculates a dose delivered to the patient with a first level of accuracy based on the generated patient motion information and the radiation therapy treatment device settings during delivery of the radiation therapy treatment segment.

[0126] At operation 650 , the treatment processing logic 120 determines a real-time measurement of cumulative dose delivered to the patient having a second higher level of accuracy than the first level of accuracy during delivery of the radiation therapy treatment fraction using one or more previous dose calculations.

[0127] As previously discussed, various electronic computing systems or devices can implement one or more of the methods or functional operations discussed herein. In one or more embodiments, the radiation therapy processing computing system 110 can be configured, adapted or used to control or operate the image-guided radiation therapy device 202, perform or implement the operation of process 600, or perform any one or more of the other methods discussed herein. In various embodiments, such an electronic computing system or device operates as a standalone device or can be connected (e.g., networked) to other machines. For example, such a computing system or device can operate in the capacity of a server or client machine in a server-client network environment, or operate as a peer machine in a peer-to-peer (or distributed) network environment. The features of the computing system or device can be implemented by a personal computer (PC), a tablet PC, a personal digital assistant (PDA), a cellular phone, a web device, or any machine capable of executing instructions (sequentially or otherwise) specifying actions to be taken by the machine.

[0128] As also indicated above, the functionality discussed above may be implemented by instructions, logic, or other information stored on a machine-readable medium. Although a machine-readable medium may have been described in various examples with reference to a single medium, the term "machine-readable medium" may include a single medium or multiple media (e.g., a centralized or distributed database and / or associated cache memories and servers) storing one or more transient or non-transient instructions or data structures. The term "machine-readable medium" should also be considered to include any tangible medium that is capable of storing, encoding, or carrying transient or non-transient instructions for execution by a machine and causing the machine to perform any one or more of the methods of the subject matter of the present invention, or any tangible medium that is capable of storing, encoding, or carrying data structures utilized by or associated with such instructions.

[0129] The above detailed description includes reference to the accompanying drawings, which form a part of the detailed description. The accompanying drawings show the specific embodiments in which the subject matter of the present invention can be practiced by way of explanation rather than by way of limitation. These embodiments are also referred to as "examples" in this article. Such examples may include elements other than those shown or described. However, the present disclosure also contemplates examples that only provide those elements shown or described. In addition, the present disclosure also contemplates examples of any combination or arrangement of those elements (or one or more aspects of those elements) shown or described with respect to a specific example (or one or more aspects of a specific example) or with respect to other examples (or one or more aspects of other examples) shown or described in this article.

[0130] All publications, patents, and patent documents cited in this document are incorporated herein by reference in their entirety, as if individually incorporated by reference. If there is an inconsistent usage between this document and those documents incorporated by reference, the usage in the incorporated reference should be considered supplementary to that of this document; for conflicting inconsistencies, the usage in this document controls.

[0131] In this document, the terms "a," "an," "the," and "said" are used when introducing elements of various aspects of the present subject matter or elements in embodiments thereof to include one or more than one or more of the elements as is common in patent documents, independent of any other instances or uses of "at least one" or "one or more." In this document, unless otherwise indicated, the term "or" is used to refer to a non-exclusive or such that "A or B" includes "including A but not B," "including B but not A," and "A and B."

[0132] In the following claims, the terms "including" and "in which" are used as the plain-English equivalents of the respective terms "comprising" and "wherein." Further, in the following claims, the terms "comprising," "including," and "having" are intended to be open-ended, to mean that there may be additional elements in addition to the listed elements, such that anything following such a term in a claim (e.g., comprising, including, having) is still considered to fall within the scope of the claim. Moreover, 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.

[0133] The subject matter of the present invention also relates to a computing system suitable for, configured to, or operated to perform the operations herein. The system may be specially constructed for the desired purpose, or the system may include a general-purpose computer selectively activated or reconfigured by a computer program (e.g., instruction, code, etc.) stored in a computer. Unless otherwise specified, the order of implementation or execution of the operations in the embodiments of the present invention shown and described herein is not necessary. That is, unless otherwise specified, operations may be performed in any order, and embodiments of the present invention may include additional or fewer operations compared to the operations disclosed herein. For example, it is contemplated that it is within the scope of the aspects of the subject matter of the present invention to implement or perform a specific operation before, simultaneously with, or after another operation, another operation.

[0134] In view of the above, it will be seen that the several objects of the inventive subject matter are achieved and other beneficial results are obtained. Having described aspects of the inventive subject matter in detail, it will be apparent that modifications and variations are possible without departing from the scope of aspects of the inventive subject matter as defined in the appended claims. As various changes may be made in the above-described constructions, products and methods without departing from the scope of aspects of the inventive subject matter, it is intended that all matter contained in the above description and shown in the accompanying drawings shall be interpreted as illustrative and not in a limiting sense.

[0135] The examples described herein may be implemented in various embodiments. For example, one embodiment includes a computing device including processing hardware (e.g., a processor or other processing circuit system) and memory hardware (e.g., a storage device or volatile memory) including instructions implemented thereon, such that the instructions, when executed by the processing hardware, cause the computing device to implement, execute, or coordinate electronic operations for these technologies and system configurations. Another embodiment discussed herein includes a computer program product, which may be implemented, for example, by a machine-readable medium or other storage device, that provides transient or non-transient instructions for implementing, executing, or coordinating electronic operations for these technologies and system configurations. Another embodiment discussed herein includes a method that is capable of operating on the processing hardware of a computing device to implement, execute, or coordinate electronic operations for these technologies and system configurations.

[0136] In other embodiments, the logic, commands, or transient or non-transient instructions that implement various aspects of the above-described electronic operations may be provided in a distributed or centralized computing system, including any number of form factors for computing systems such as desktop or notebook personal computers, mobile devices such as tablet computers, netbooks and smart phones, client and server-hosted machine instances, etc. Another embodiment discussed herein includes incorporating the techniques discussed herein into other forms, including other forms of programmed logic, hardware configurations, or dedicated components or modules, including devices having corresponding means for performing the functions of such techniques. The corresponding algorithms for implementing the functions of such techniques may include sequences of some or all of the above-described electronic operations or other aspects depicted in the accompanying drawings and the following detailed description.

[0137] The above description is intended to be illustrative, rather than restrictive. For example, the examples described above (or one or more aspects of the examples) can be used in combination with each other. In addition, without departing from the scope of the present disclosure, many modifications can be made to adapt specific situations or materials to the teachings of the present disclosure. Although the size, type, and example parameters, functions, and implementations of the materials described herein are intended to limit the parameters of the subject matter of the present invention, they are by no means restrictive embodiments, 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 subject matter of the present invention should be determined with reference to the full range of equivalents given by the attached claims and such claims.

[0138] In addition, in the above detailed description, various features can be combined together to simplify the present disclosure. This should not be interpreted as meaning that: unclaimed disclosed features are essential to any claim. Instead, the subject matter of the present invention may lie in less than all the features of a particular disclosed embodiment. Therefore, the attached claims are thus incorporated into the detailed description, wherein each claim itself independently serves as a separate embodiment. The scope of the subject matter of the present invention should be determined with reference to the attached claims and the full range of equivalents given to such claims.

Claims

1. A method comprising: acquiring, by one or more processors, one or more images of a patient at a first rate during delivery of radiation therapy treatment fractions to the patient; generating patient motion information at a second rate based on the one or more images acquired at the first rate by sampling the one or more images at the second rate which is lower than the first rate; receiving radiation therapy treatment device settings at a third rate greater than the first rate during delivery of the radiation therapy treatment fraction; calculating a first measure of cumulative dose delivered to the patient during delivery of the radiation therapy treatment fraction, the first measure of cumulative dose being calculated to have a first amount of noise, the first measure of cumulative dose being calculated based on the generated patient motion information and the radiation therapy treatment device settings; as well as During delivery of the radiation therapy treatment fraction, a second measurement of a cumulative dose delivered to the patient having a lower amount of noise than the first measurement of the cumulative dose is determined at a rate lower than the first rate using one or more previous dose calculations including a first measurement of the cumulative dose having the first amount of noise, wherein as each individual measurement of cumulative dose is accumulated with previous dose measurement calculations, an overall cumulative dose calculation noise decreases.

2. The method according to claim 1, further comprising: determining a fourth rate for calculating and accumulating the dose, the fourth rate being lower than the first rate; as well as The second rate at which the one or more images are sampled is set based on the fourth rate at which the dose is calculated.

3. The method according to claim 2, wherein: Generating the patient motion information includes adjusting the second rate at which the set of one or more images is sampled to ignore and exclude portions of the one or more images obtained at the first rate from the generated patient motion information.

4. The method according to any one of claims 1 to 3, wherein: The dose is calculated using an advanced Monte Carlo dose calculation technique, thereby generating a dose distribution having a noise level corresponding to the first amount of noise.

5. The method according to any one of claims 1 to 3, wherein: calculating the dose at a fourth rate such that each of a plurality of dose calculations for the radiation therapy treatment segment is output at the fourth rate, each of the plurality of dose calculations having a lower noise level than a previous dose calculation, the method further comprising: Each of the plurality of dose calculations is transformed to a same frame of reference of the reference geometry and each of the previous dose calculations is accumulated in respective increments to determine a real-time measurement of the accumulated dose, wherein each increment in the accumulation reduces noise present in the dosimetric index.

6. The method according to claim 5, wherein: The second rate is set to a value sufficient to discern movement patterns of the patient.

7. The method according to claim 5, wherein: The dosimetric index comprises at least one of: a quantitative single measurement extracted from a 3D dose distribution, a near maximum dose, a near minimum dose, or a measure of consistency between the dose distribution and a target volume.

8. The method according to claim 5, wherein: The dosimetry index comprises a dose value histogram DVH or a DVH measurement.

9. The method according to claim 6, further comprising: The dosimetric index is calculated by extracting a subset of the 3D portion in the 3D Monte Carlo dose calculation.

10. The method according to any one of claims 1 to 3, further comprising: The radiation therapy treatment device settings are compressed into a single effective segment based on the second rate at which the patient motion information is generated, wherein the dose is calculated based on the compressed radiation therapy treatment device settings.

11. The method according to claim 10, wherein: The radiotherapy treatment device settings received at the third rate include a set of updates to the radiotherapy treatment device settings performed during a given time interval of the radiotherapy treatment segment corresponding to the third rate, and the method also includes aggregating the total fluence delivered by multiple beam delivery segments into the single effective segment.

12. The method according to claim 11, wherein: The single effective section includes the starting position and the stopping position of each beam limiter BLD element pair, wherein calculating the effective section includes: performing the following operations for each BLD element pair: For each update in the set of updates, obtaining all positions of the BLD element pairs; identifying a maximum position of each BLD element pair in the current BLD element pair among the obtained positions in the set of updates; identifying a minimum position of each BLD element pair in the current BLD element pair among the obtained positions in the set of updates; designating the minimum position as the starting position of each BLD element pair in the current BLD element pair; and The maximum position is designated as a stop position for each of the current BLD element pairs.

13. The method according to claim 12, wherein: The BLD element pair comprises at least one of a clip pair of a multi-leaf collimator MLC or a leaf pair of the MLC, and the method further comprises: determining a number of monitoring units MU to deliver for each update in the set of updates; accumulating the number of determined MUs for the set of updates to calculate a total fluence; and The accumulated MUs are allocated to the active section.

14. The method according to any one of claims 1 to 3, further comprising: Based on the second measure of the cumulative dose, a visualization of the dose accumulation is generated at a fourth rate.

15. The method according to claim 14, wherein: The visualization shows real-time progress of the radiation therapy treatment segment, the method further comprising: obtaining a reference dosimetry index calculated based on a reference radiotherapy treatment plan; and The real-time progression is presented in the visualization by graphically displaying the same dosimetric index based on the cumulative dose relative to the reference dosimetric index.

16. The method according to any one of claims 1 to 3, further comprising: The radiation therapy treatment device settings are gated or adjusted during delivery of the radiation therapy treatment fractions based on real-time measurements of the determined dose and one or more additional factors.

17. The method according to any one of claims 1 to 3, wherein: The patient motion information is generated by the following operations: applying a patient motion model to one or more reference images of the patient to create a motion estimate; and The patient anatomy is deformed to a current state using the motion estimate.

18. The method according to any one of claims 1 to 3, wherein: The calculated dose includes a first calculated dose corresponding to a first portion of the radiation therapy treatment segment, and the method further includes: denoising a differential dose volume histogram of the first calculated dose while calculating a second dose for a second portion of the radiation therapy treatment segment.

19. A system for real-time adjustment of radiation therapy treatment for a patient, the system comprising: One or more processors configured to perform operations including: acquiring one or more images of a patient at a first rate during delivery of radiation therapy treatment fractions to the patient; generating patient motion information at a second rate based on the one or more images acquired at the first rate; receiving radiation therapy treatment device settings at a third rate during delivery of the radiation therapy treatment fraction; calculating a first measure of cumulative dose delivered to the patient during delivery of the radiation therapy treatment fraction, the first measure of cumulative dose being calculated to have a first amount of noise, the first measure of cumulative dose being calculated based on the generated patient motion information and the radiation therapy treatment device settings; as well as During delivery of the radiation therapy treatment fraction, a second measurement of a cumulative dose delivered to the patient having a lower amount of noise than the first measurement of the cumulative dose is determined using one or more previous dose calculations including a first measurement of the cumulative dose having the first amount of noise, wherein as each individual measurement of the cumulative dose is accumulated with previous dose measurement calculations, the overall cumulative dose calculation noise decreases.

20. The system of claim 19, wherein: The operations also include: determining a fourth rate for calculating and accumulating the dose, the fourth rate being lower than the first rate; sampling the set of one or more images at a second rate lower than the first rate; and The second rate at which the one or more images are sampled is set based on the fourth rate at which the dose is calculated.

Images