Dose monitoring method, system and storage medium

Abstract

The present specification discloses a dose monitoring method, system and storage medium, the method comprising: acquiring at least one acquisition image of a target object, the acquisition image corresponding to at least a portion of a radiation field; acquiring a predicted image based on radiotherapy plan information of the target object; and monitoring the dose received by the target object based on at least one acquisition image and the predicted image.

Description

Technical Field

[0001] The present invention relates to the field of radiotherapy technology, and in particular to a dose monitoring method. Background Art

[0002] The portal imaging system is a device that collects images of the target object in the direction of the radioactive beam of the radiotherapy equipment, and its functions include portal verification and dose monitoring. The portal range in the image acquired by the portal imaging system is determined by the detector area of ​​the portal imaging system and the distance between the detector of the portal imaging system and the radiation source of the radiotherapy equipment. However, the distance between the detector of the portal imaging system and the radiation source of the radiotherapy equipment may be limited by the architecture of the radiotherapy equipment (for example, the aperture of the radiotherapy equipment guided by nuclear magnetic resonance images is small, which limits the distance between the detector and the radiation source). At the same time, the area of ​​the detector cannot be infinitely enlarged, resulting in the detection area of ​​the portal imaging system being smaller than the portal area, making the acquired image of the target object incomplete, and thus making it impossible to perform accurate dose monitoring.

[0003] Therefore, it is hoped to provide a dose monitoring method that can improve the accuracy of dose monitoring. Summary of the invention

[0004] One aspect of the present specification provides a dose monitoring method, which includes: acquiring at least one acquisition image of a target object, wherein the acquisition image corresponds to at least a portion of a radiation field; acquiring a predicted image based on radiotherapy planning information of the target object; and monitoring the dose received by the target object based on at least one acquisition image and the predicted image.

[0005] In some embodiments, the method includes: determining at least one dose difference result based on at least one acquired image and a predicted image; and monitoring a dose received by the target object based on the at least one dose difference result.

[0006] In some embodiments, the method further includes: determining at least one dose difference result based on at least one acquisition image and at least one sub-prediction image in the prediction image; or obtaining a full-field acquisition image based on at least one acquisition image, and determining at least one dose difference result based on the full-field acquisition image and the prediction image. In some embodiments, the method further includes obtaining a full-field acquisition image based on at least one acquisition image and radiotherapy plan information. In some embodiments, the method further includes inputting at least one acquisition image and radiotherapy plan information into an image prediction model to obtain a full-field acquisition image.

[0007] In some embodiments, the method further includes: performing three-dimensional dose reconstruction based on the full-field acquisition image. In some embodiments, the method further includes adjusting the current radiotherapy dose and / or the remaining fractionated radiotherapy dose based on the result of the three-dimensional dose reconstruction and the radiotherapy plan information. In some embodiments, the method further includes: judging whether the dose currently received by the target object meets a preset range based on at least one acquisition image and a predicted image; in response to the dose currently received by the target object not meeting the preset range, sending a prompt message to the terminal device.

[0008] Another aspect of the present specification provides a dose monitoring system, the system comprising: an image acquisition module for acquiring at least one acquired image of a target object, wherein the acquired image corresponds to at least a portion of a radiation field; a predicted image acquisition module for acquiring a predicted image based on radiotherapy plan information of the target object; and a dose monitoring module for monitoring the dose received by the target object based on at least one acquired image and a predicted image.

[0009] Another aspect of the present specification provides a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a dose monitoring method.

[0010] Some embodiments of the present specification acquire a full-field acquisition image based on an acquisition image corresponding to at least a portion of the beam field, and then perform dose monitoring based on the full-field acquisition image and the predicted image, so that when the detection area of ​​the beam field imaging system is smaller than the beam field area, dose monitoring can be achieved based on the determined dose difference result; the predicted image is segmented based on the acquisition image, a sub-prediction image corresponding to the acquisition image is acquired, and then dose monitoring is performed based on the acquisition image and the sub-prediction image, and the dose difference result of the full-field acquisition image is replaced with the dose difference result corresponding to the acquisition image corresponding to a portion of the beam field to achieve dose monitoring, thereby improving computational efficiency; based on the acquired full-field acquisition image, three-dimensional dose reconstruction can be further performed, the radiotherapy plan can be modified online, and online adaptive radiotherapy can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0012] Figure 1 is a schematic diagram of an application scenario of a dose monitoring system according to some embodiments of this specification;

[0013] Figure 2 is an exemplary module diagram of a dose monitoring system according to some embodiments of the present specification;

[0014] Figure 3 is an exemplary flow chart of a dose monitoring method according to some embodiments of this specification;

[0015] Figure 4a is a schematic diagram of obtaining a sub-prediction image according to some embodiments of this specification;

[0016] Figure 4b is a schematic diagram of obtaining a full-field acquisition image according to some embodiments of this specification;

[0017] Figure 5 is an exemplary flow chart of a method for monitoring a dose received by a target object based on at least one dose difference result of at least one acquired image and / or predicted image according to some embodiments of the present specification;

[0018] Figure 6 is a schematic diagram of a method for optimizing a radiotherapy plan based on full-field acquisition images according to some embodiments of this specification;

[0019] Figure 7 It is an exemplary flow chart of a method for online monitoring of radiotherapy plans based on full-field acquisition images according to some embodiments of this specification. DETAILED DESCRIPTION

[0020] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0021] It should be understood that the "system", "device", "unit" and / or "module" used in this specification is a method for distinguishing different components, elements, parts, parts or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0022] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0023] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0024] Figure 1 It is a schematic diagram of an application scenario of a dose monitoring system according to some embodiments of this specification.

[0025] The dose monitoring system 100 can monitor the dose received by the target object by implementing the method and / or process disclosed in this specification.

[0026] like Figure 1 As shown, the dose monitoring system 100 may include: a radiotherapy device 110, a portal imaging system 160, a processing device 120, a terminal device 130, a network 140 and / or a storage device 150, etc.

[0027] The components of the dose monitoring system 100 may be connected in one or more of a variety of ways. By way of example only, Figure 1 As shown, the radiotherapy device 110 can be connected to the processing device 120 through the network 140. For another example, the radiotherapy device 110 can be directly connected to the processing device 120 (as shown by the dotted double-headed arrow connecting the radiotherapy device 110 and the processing device 120). As a further example, the storage device 150 can be connected to the processing device 120 directly or through the network 140. As a further example, the terminal device 130 can be connected to the processing device 120 directly (as shown by the dotted double-headed arrow connecting the terminal device 130 and the processing device 120) and / or through the network 140.

[0028] The radiotherapy device 110 can treat the target object using one or more radioactive beams. In some embodiments, the radiotherapy device 110 may include an imaging device. The imaging device may be a device that collects image information of the target object to guide the positioning of the target object. In some embodiments, the imaging device may include, but is not limited to, a combination of one or more of an X-ray imaging device, a nuclear magnetic resonance imaging device, an ultrasonic imaging device, a nuclear imaging device, and a computer tomography (CT) imaging device. In some embodiments, the guide image may be an image acquired by the imaging device.

[0029] The portal imaging system 160 may be a device for acquiring an image of a target object in the direction of the radioactive beam emission of the radiotherapy device. In some embodiments, the portal imaging system may receive energy released by the target object and absorbed during the radiotherapy process, convert the received energy into an electrical signal, and generate an image based on the electrical signal. In some embodiments, the acquired image may be an image acquired by the portal imaging system 160. In some embodiments, the portal imaging system 160 may acquire the dose distribution received by the target object based on the acquired image, thereby verifying the treatment plan of the target object.

[0030] The processing device 120 can process data and / or information obtained from the radiotherapy device 110, the terminal device 130 and / or the storage device 150. For example, the processing device 120 can obtain a predicted image based on the radiotherapy plan information of the target object. For another example, the processing device 120 can determine the dose received by the target object based on at least one acquired image and / or predicted image. For another example, the processing device 120 can adjust the radiotherapy dose received by the target object based on the result of three-dimensional dose reconstruction. In some embodiments, the processing device 120 may include a central processing unit (CPU), a digital signal processor (DSP), a system on a chip (SoC), a microcontroller unit (MCU), etc. and / or any combination thereof. In some embodiments, the processing device 120 may include a computer, a user console, a single server or a server group, etc. The server group may be centralized or distributed. In some embodiments, the processing device 120 may be local or remote. For example, the processing device 120 can access information and / or data stored in the radiotherapy device 110, the terminal device 130 and / or the storage device 150 via the network 140. For another example, the processing device 120 can be directly connected to the radiotherapy device 110, the terminal device 130 and / or the storage device 150 to access the stored information and / or data. In some embodiments, the processing device 120 can be implemented on a cloud platform. As an example only, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, etc., or any combination thereof. In some embodiments, the processing device 120 or a portion of the processing device 120 can be integrated into the radiotherapy device 110.

[0031] The terminal device 130 can display the collected image and / or the full-field image to the user, and / or receive parameters such as a pass rate threshold and a similarity threshold input by the user. The terminal device 130 can include a mobile device 131, a tablet computer 132, a notebook computer 133, etc., or any combination thereof. In some embodiments, the terminal device 130 can be a part of the processing device 120.

[0032] The network 140 may include any suitable network that facilitates information and / or data exchange of the dose monitoring system 100. In some embodiments, one or more components of the dose monitoring system 100 (e.g., the radiotherapy device 110, the processing device 120, the storage device 150, the terminal device 130) may communicate information and / or data with one or more other components of the dose monitoring system 100 via the network 140. For example, the processing device 120 may receive user instructions from the terminal device via the network. For another example, the radiotherapy device 110 may obtain ultrasound emission parameters from the processing device 120 via the network 140. The network 140 may be and / or include a public network (e.g., the Internet), a private network (e.g., a local area network (LAN), a wide area network (WAN)), a wired network (e.g., an Ethernet network), a wireless network (e.g., an 802.11 network, a Wi-Fi network), a cellular network (e.g., a long term evolution (LTE) network), a frame relay network, a virtual private network (“VPN”), a satellite network, a telephone network, a router, a hub, a switch, a server computer, and / or any combination thereof. By way of example only, the network 140 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth™ network, a ZigBee™ network, a near field communication (NFC) network, etc., or any combination thereof. In some embodiments, the network 140 may include one or more network access points. For example, the network 140 may include wired and / or wireless network access points such as base stations and / or Internet exchange points, and one or more components of the dose monitoring system 100 may be connected to the network 140 through these access points to exchange data and / or information.

[0033] The storage device 150 may store data, instructions and / or any other information. In some embodiments, the storage device 150 may store data obtained from the radiotherapy device 110, the terminal device 130 and / or the processing device 120. In some embodiments, the storage device 150 may store data and / or instructions, and the processing device 120 may execute or use the data and instructions to execute the exemplary method / system described in the present application. In some embodiments, the storage device 150 may include a large-capacity memory, a removable memory, a volatile read-write memory, a read-only memory (ROM), etc. or any combination thereof. Exemplary large-capacity memory may include a disk, an optical disk, a solid-state disk, etc. Exemplary removable memory may include a flash drive, a floppy disk, an optical disk, a memory card, a compressed disk, a tape, etc. Exemplary volatile read-write memory may include a random access memory (RAM). Exemplary RAM may include a dynamic random access memory (DRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), a static random access memory (SRAM), a thyristor random access memory (T-RAM), and a zero-capacitance random access memory (Z-RAM), etc. Exemplary ROMs may include mask read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (eePROM), compact disk read-only memory (CD-ROM), and digital versatile disk read-only memory, etc. In some embodiments, the storage device 150 may be executed on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof.

[0034] In some embodiments, the storage device 150 may be connected to the network 140 to communicate with one or more other components of the dose monitoring system 100 (e.g., the radiotherapy device 110, the processing device 120, the terminal device 130). One or more components of the dose monitoring system 100 may access data or instructions stored in the storage device 150 through the network 140. In some embodiments, the storage device 150 may be directly connected to or communicate with one or more other components of the dose monitoring system 100 (e.g., the radiotherapy device 110, the processing device 120, the storage device 150, the terminal device 130). In some embodiments, the storage device 150 may be part of the processing device 120.

[0035] Figure 2 is an exemplary module diagram of a dose monitoring system according to some embodiments of the present specification.

[0036] In some embodiments, the processing device 120 may include an acquisition image acquisition module 210 , a prediction image acquisition module 220 , and a dose detection module 230 .

[0037] The acquisition image acquisition module 210 can be used to acquire at least one acquisition image of the target object. In some embodiments, the acquisition image can correspond to at least a portion of the portal. In some embodiments, the acquisition image can be acquired by a portal imaging system. For a detailed description of the acquisition image acquisition module 210, please refer to step 310, which will not be repeated here.

[0038] The predicted image acquisition module 220 can be used to acquire a predicted image based on the radiotherapy plan information of the target object. A detailed description of the predicted image acquisition module 220 can be found in step 320, which will not be repeated here.

[0039] The dose monitoring module 230 may be used to monitor the dose received by the target object based on at least one acquired image and the predicted image. In some embodiments, the dose monitoring module 230 may determine at least one dose difference result based on at least one acquired image and the predicted image; and monitor the dose received by the target object based on at least one dose difference result. In some embodiments, the dose monitoring module 230 may determine at least one dose difference result based on at least one acquired image and at least one sub-predicted image in the predicted image; or acquire a full-field acquired image based on at least one acquired image, and determine at least one dose difference result based on the full-field acquired image and the predicted image. In some embodiments, the sub-predicted image may correspond to the acquired image.

[0040] In some embodiments, the dose monitoring module 230 can obtain a full-field acquisition image based on at least one acquisition image and radiotherapy plan information. In some embodiments, the dose monitoring module 230 can input at least one acquisition image and radiotherapy plan information into a trained image prediction model to obtain a full-field acquisition image.

[0041] In some embodiments, the dose monitoring module 230 can perform three-dimensional dose reconstruction based on the full-field acquisition image. In some embodiments, the dose monitoring module 230 can determine whether the dose currently received by the target object meets the preset range based on at least one acquisition image and the predicted image; in response to the dose currently received by the target object not meeting the preset range, a prompt message is sent to the terminal device. In some embodiments, the dose monitoring module 230 can adjust the current radiotherapy dose and / or the remaining fractionated radiotherapy dose based on the results of the three-dimensional dose reconstruction and the radiotherapy plan information. For a detailed description of the dose monitoring module 230, please refer to step 330, which will not be repeated here.

[0042] Figure 3 is an exemplary flow chart of a dose monitoring method according to some embodiments of the present specification.

[0043] like Figure 3 As shown, the method 300 may include:

[0044] Step 310: Acquire at least one captured image of the target object.

[0045] Specifically, step 310 may be performed by the image acquisition module 210 .

[0046] Radiotherapy can be the treatment of a target object using one or more radioactive beams. In some embodiments, the target object can be a human body, an organ, an organism, an object, a phantom, a region of interest, a lesion, a tumor, etc. In some embodiments, the radioactive beam can include but is not limited to a combination of one or more of a radioisotope (such as β, γ) ray beam, an X-ray, a photon, a heavy particle (such as an electron, a proton, a neutron) ray beam, etc. Correspondingly, in some embodiments, the radiotherapy equipment can include but is not limited to a combination of one or more of a 60 cobalt therapy machine, an X-ray therapy machine, a heavy particle accelerator, etc.

[0047] In some embodiments, the radiotherapy device may further include an imaging device. The imaging device may be a device that collects images of a target object to guide the positioning of the target object. In some embodiments, the imaging device may include, but is not limited to, a combination of one or more of an X-ray imaging device, a nuclear magnetic resonance imaging device, an ultrasonic imaging device, a nuclear imaging device, and a computer tomography (CT) imaging device.

[0048] The guide image may be an image acquired by an imaging device. Corresponding to the imaging device, in some embodiments, the guide image may include, but is not limited to, a combination of one or more of an X-ray image, a computed tomography (CT) image, a positron emission tomography (PET) image, a single photon emission computed tomography (SPECT), a magnetic resonance image (MRI), an ultrasound scan (US) image, a digital subtraction angiography (DSA) image, a magnetic resonance angiography (MRA) image, a time-of-flight magnetic resonance image (TOF-MRI), a magnetoencephalogram (MEG), and the like.

[0049] Exemplarily, the imaging device may be a nuclear magnetic resonance imaging device. After the nuclear magnetic resonance imaging device transmits radio frequency pulses to a target object in a magnetic field, the hydrogen nuclei of the target object absorb the energy and may release the energy after stopping transmitting the radio frequency pulses. The imaging device may convert the received energy into electrical signals and generate a guidance image based on the electrical signals.

[0050] In some embodiments, the radiotherapy device 110 can better monitor the target object before and during treatment based on the guidance image obtained by the imaging device, so as to adjust the position of the target object in time, so that the radioactive beam of the radiotherapy device 110 can be concentrated on the target area of ​​the target object. For example, the contrast of soft tissue in the magnetic resonance image is very clear, and the radiotherapy device 110 can better distinguish the tumor from soft tissues such as muscle, fat and fascia based on the magnetic resonance image, so as to adjust the position of the target object in time so that the radioactive beam can be irradiated on the tumor area.

[0051] The portal imaging system may be a device for acquiring an image of a target object in the direction of the radiation beam emitted by the radiotherapy device. The portal may be the irradiation range of the radiotherapy device when the radiation beam irradiates the target object. Figure 4a As shown, the irradiation range of the radioactive beam X-ray when irradiating the target object on the treatment bed can be the radiation field AB.

[0052] In some embodiments, the portal imaging system 160 may include a detector and an image processing unit. The detector may receive energy released by the target object based on the radiotherapy device, and the image processing unit may convert the received energy into an electrical signal and generate an image based on the electrical signal.

[0053] The acquired image may be an image acquired by a portal imaging system. In some embodiments, the portal imaging system 160 may acquire the dose distribution of the radioactive beam received by the target object based on the acquired image, thereby adjusting the radiotherapy dose of the target object and / or adjusting the inter-fractional radiotherapy dose of the target object in real time according to the treatment plan. For a detailed description of adjusting the radiotherapy dose of the target object, see Figure 6 , Figure 7 And the related description will not be repeated here.

[0054] Corresponding to the radiotherapy equipment, in some embodiments, the acquired images may include but are not limited to a combination of one or more of X-ray images, computed tomography (CT) images, positron emission tomography (PET) images, and single photon emission computed tomography (SPECT) images. In some embodiments, the acquired images may be two-dimensional (2D) images or three-dimensional (3D) images. In some embodiments, the three-dimensional images may be composed of a series of two-dimensional slices or two-dimensional layers.

[0055] Exemplarily, the radiotherapy device can be an X-ray radiotherapy device. After the X-ray radiotherapy device emits X-rays to the target object, and the target object absorbs part of the energy of the X-rays, the detector can receive the remaining X-ray energy from the target object, and the image processing unit can convert the remaining X-ray energy into electrical signals and generate an acquisition image based on the electrical signals.

[0056] In some embodiments, the acquired image may correspond to at least a portion of the portal. As previously described, the portal range in the acquired image is determined by the detector area of ​​the portal imaging system and the distance between the detector of the portal imaging system and the radiation source of the radiotherapy device. The distance between the detector of the portal imaging system and the radiation source of the radiotherapy device may be limited by the architecture of the radiotherapy device (for example, the aperture of the radiotherapy device guided by nuclear magnetic resonance images is small, which limits the distance between the detector and the radiation source). At the same time, the area of ​​the detector cannot be infinitely enlarged, resulting in the detection area of ​​the portal imaging system being smaller than the portal area, making the portal in the acquired image incomplete, and thus making it impossible to perform accurate dose monitoring. Some embodiments of the present description may perform dose monitoring on a target object based on an acquired image corresponding to a portion of the portal.

[0057] Specifically, the detector with a smaller area can receive part of the energy released by the target object, and the image processing unit can convert the received part of the energy into an electrical signal, and generate a captured image corresponding to a part of the radiation field based on the electrical signal. Figure 4a As shown, the detector area of ​​the portal imaging system is smaller than the area of ​​the portal AB, and a portion of the portal AB may include A1B1.

[0058] In some embodiments, the image acquisition module 210 may move the position of the detector to acquire at least one image of the target object. Figure 4a As shown, the detector can obtain an image of a portion A1B1 of the field of view at position a, and can obtain an image of another portion A2B2 of the field of view AB at position b.

[0059] In some embodiments, at least one of the collected images may overlap or may not overlap. Figure 4a As shown, the acquired image of a portion A1B1 of the field and the acquired image of a portion A2B2 of the field may have an overlapping portion A2B1 in the x-axis direction.

[0060] Step 320: acquiring a predicted image based on the radiotherapy plan information of the target object.

[0061] Specifically, step 320 may be performed by the predicted image acquisition module 220 .

[0062] A radiotherapy plan (also known as a radiotherapy plan) may be a radioactive ray irradiation plan for a target object. In some embodiments, the purpose of the radiotherapy plan may be to irradiate a target area of ​​the target object with a high dose, thereby irreversibly destroying the target area while minimizing the impact on the normal tissue of the target object.

[0063] The radiotherapy plan information may be information related to the radiotherapy plan. In some embodiments, the radiotherapy plan information may include basic information of the target object, morphological information of the target object, equipment parameters, number of radiotherapy sessions, dose of each radiotherapy session, field position of each radiotherapy session, number of target areas of each radiotherapy session, position of each target area, and / or dose of each target area.

[0064] The basic information of the target object may include the target object's age, occupation, and medical history. The morphological information of the target object may describe information about the shape and position of the target object. In some embodiments, the morphological information of the target object may include, but is not limited to, the position, height, weight, and / or outline of the target object.

[0065] The device parameters may include the dose response characteristics of the portal imaging system. As previously described, the portal imaging system may receive energy released by the target object and absorbed during radiotherapy, convert the received energy into electrical signals, and generate images based on the electrical signals. The dose response characteristics of the portal imaging system may be the influence of the characteristics of the particles incident on the portal imaging system on the electrical signals generated by the portal imaging system. In some embodiments, the characteristics of the particles may include, but are not limited to, the angle at which the particles enter the detector, the type of particles, and the energy of the particles. The predicted image may be an image of the target object in the direction of the emission of the radioactive beam predicted based on the radiotherapy plan information. In some embodiments, the type and format of the predicted image may be the same as the acquired image.

[0066] In some embodiments, the predicted image acquisition module 220 may generate a predicted image based on the radiotherapy plan information using a prediction model. Specifically, the predicted image acquisition module 220 may input the radiotherapy plan information into the prediction model, and the prediction model may perform modeling based on the radiotherapy plan information and output a predicted image.

[0067] In some embodiments, the prediction model may include but is not limited to a combination of one or more of a Fully Convolutional Networks (FCN) model, a Visual Geometry Group Network (VGG Net) model, an Efficient Neural Network (ENet) model, a Full-Resolution Residual Networks (FrrN) model, a Mask Region-based Convolutional Neural Network (Mask R-CNN) model, a Multi-Dimensional Recurrent Neural Networks (MDRNNs) model, and the like.

[0068] In some embodiments, the prediction model can be trained based on a large number of first training samples with a first identifier. Specifically, the first training samples with the first identifier are input into the prediction model, and the parameters of the prediction model are updated through training. In some embodiments, the first training sample may include historical radiotherapy plan information, and the first identifier may be a historical full-field image obtained by radiotherapy based on the historical radiotherapy plan information.

[0069] Step 330 , monitoring the dose received by the target object based on at least one acquired image and / or predicted image.

[0070] Specifically, step 330 may be performed by the dose monitoring module 230 .

[0071] The dose received by the target object may be the energy of the radioactive beam absorbed by the target object.

[0072] In some embodiments, the dose monitoring module 230 may determine at least one dose difference result based on at least one acquired image and the predicted image, and detect the dose received by the target object based on the at least one dose difference result.

[0073] The dose difference result may represent the difference between the calculated dose of the radiation therapy plan and the actual dose delivered by the radiation therapy device.

[0074] A detailed description of monitoring the dose received by the target object based on at least one acquired image and / or predicted image can be found in Figure 5 And the related description will not be repeated here.

[0075] Figure 5 The present invention is an exemplary flow chart of a method for monitoring a dose received by a target object based on at least one dose difference result of at least one acquired image and / or predicted image according to some embodiments of the present specification.

[0076] Specifically, Figure 5 It may be performed by the dose monitoring module 230 .

[0077] like Figure 5 As shown, method 500 may include:

[0078] Step 510, determining at least one dose difference result based on at least one acquired image and / or predicted image.

[0079] As described above, the dose difference result can represent the difference between the calculated dose of the radiotherapy plan and the actual dose of the radiotherapy device. In some embodiments, each dose difference result can be evaluated by a combination of one or more of at least one pass rate, at least one similarity, and / or at least one dose distribution difference rate of at least one acquired image and / or predicted image.

[0080] The pass rate can be a parameter calculated based on the dose difference and distance difference of pixels in two images, and can be an indicator of the consistency between the dose of the radioactive beam actually received by the target object and the dose of the radioactive beam predicted to be received. In some embodiments, the pass rate can reflect whether the dose received by the target object is appropriate. In some embodiments, the larger the pass rate, the closer the dose of the radioactive beam actually received by the target object is to the dose of the radioactive beam predicted to be received, that is, the dose received by the target object is more appropriate.

[0081] In some embodiments, the target object may correspond to multiple spatial points, and each spatial point may further correspond to a pixel in the acquired image and / or the predicted image. In some embodiments, the pass rate may be determined based on the first dose of the radioactive beam actually received by each spatial point corresponding to the target object, the second dose of the radioactive beam predicted to be received, and the positional relationship.

[0082] In some embodiments, the first dose of the radioactive beam actually received by each spatial point of the target object can be obtained based on the acquired image. Specifically, the dose monitoring module 230 can obtain the first dose of the radioactive beam received by the spatial point of the target object corresponding to each pixel of the acquired image based on the EPID-dose scale method based on the pixels of each acquired image.

[0083] In some embodiments, the second dose of the radioactive beam predicted to be received by each spatial point of the target object can be obtained based on the predicted image. Specifically, the dose monitoring module 230 can obtain the second dose of the radioactive beam predicted to be received by the spatial point of the target object corresponding to each pixel of the predicted image based on the EPID-dose scale method based on the pixels of each predicted image.

[0084] In some embodiments, the positional relationship between each spatial point can be characterized based on the distance between each spatial point.

[0085] In some embodiments, the dose monitoring module 230 can calculate the pass rate corresponding to each spatial point by formula (1):

[0086]

[0087] Where, Δd max and ΔD max The distance limit criterion and the dose difference limit criterion can be selected by the user, for example, Δd max Can be 3mm, ΔD maxcan be 3%; Δd can represent the distance between the corresponding spatial point i in the acquired image and the corresponding arbitrary spatial point in the predicted image that meets the restriction standard; ΔD can represent the dose difference between the corresponding spatial point i in the acquired image and the corresponding arbitrary spatial point in the predicted image that meets the restriction standard; G i It can represent the passing rate of the corresponding spatial point i in the acquired image.

[0088] In some embodiments, further, the dose monitoring module 230 may obtain the pass rate corresponding to each acquired image and predicted image based on the average pass rate of all spatial points of the corresponding target object in the acquired image and / or predicted image.

[0089] As mentioned above, the detection area of ​​the detector may be smaller than the field area, and the number of spatial points of the target object corresponding to the acquired image is correspondingly smaller than the number of spatial points of the target object corresponding to the predicted image. In some embodiments, the dose monitoring module 230 can make a one-to-one correspondence between the multiple spatial points corresponding to each acquired image and the multiple spatial points corresponding to the predicted image, thereby obtaining at least one pass rate based on at least one acquired image and the predicted image in the same imaging range.

[0090] In some embodiments, the dose monitoring module 230 may determine at least one pass rate based on at least one acquired image and the at least one predicted sub-image in the predicted image.

[0091] A sub-prediction image can be a part of a prediction image. Figure 4a As shown, the sub-prediction images P1 and P2 may be part of the prediction image P. In some embodiments, the sub-prediction images may correspond to the acquisition image. Specifically, the imaging range of the sub-prediction images may correspond to the imaging range of the acquisition image, and both correspond to the same part of the field of view, so that multiple spatial points on the target object corresponding to the sub-prediction images may correspond one-to-one with multiple spatial points on the target object corresponding to the acquisition image.

[0092] Specifically, the dose monitoring module 230 may acquire the at least one predicted sub-image in the predicted image based on the at least one acquired image.

[0093] In some embodiments, the dose monitoring module 230 can obtain the imaging range corresponding to the predicted image based on the position of the treatment bed and / or the parameters of the radioactive beam, and then obtain the imaging range corresponding to each acquired image (i.e., a part of the radiation field) based on the position of the treatment bed, the parameters of the radioactive beam, the detection area of ​​the detector and / or the position of the detector each time, and further obtain the range correspondence between each acquired image and the predicted image, thereby intercepting a sub-predicted image of the corresponding range of each acquired image from the predicted image.

[0094] like Figure 4a As shown, the dose monitoring module 230 can determine that the imaging range AB corresponding to the predicted image P in the x-axis direction and the imaging range (not shown) corresponding to the predicted image P in the y-axis direction are based on the parameters of the radioactive beam and the position of the treatment bed, and based on the position of the treatment bed, the parameters of the radioactive beam, the detection area of ​​the detector and the positions a and b of the detector, respectively obtain the imaging range A1B1 in the x-axis direction and the imaging range (not shown) in the y-axis direction of the acquired image M1, and the imaging range A2B2 in the x-axis direction and the imaging range (not shown) in the y-axis direction of the acquired image M2, and obtain the correspondence between the imaging range of the acquired image M1 and the imaging range of the acquired image M2 and the imaging range of the predicted image P, thereby intercepting the sub-predicted image P1 corresponding to M1 and the sub-predicted image P2 corresponding to M2 from the predicted image P.

[0095] In some embodiments, the dose monitoring module 230 may segment a corresponding portion of at least one acquired image from the predicted image based on at least one acquired image by using a segmentation model, thereby acquiring at least one sub-prediction image.

[0096] In some embodiments, the segmentation model may include but is not limited to a combination of one or more of traditional segmentation algorithm models (e.g., traditional threshold method, region growing method, edge detection method), image segmentation algorithm models combined with specific tools (e.g., genetic algorithm, wavelet analysis, wavelet transform, active contour model, etc.) and neural network models (e.g., full convolutional network model, visual geometry group network model, efficient neural network model, full-resolution residual network model, mask area convolutional neural network model, multidimensional recurrent neural network model, etc.).

[0097] like Figure 4a As shown, the segmentation model can segment the predicted image P into sub-prediction image P1 and sub-prediction image P2 based on the image features of the acquired image M1 and the image features of the acquired image M2, respectively.

[0098] In some embodiments, the segmentation model can be trained based on a large number of second training samples with second identifiers. Specifically, the second training samples with the second identifier are input into the segmentation model, and the parameters of the segmentation model are updated through training. In some embodiments, the second training samples may include a sample image to be segmented (corresponding to the predicted image) and a sample segmented image (corresponding to the acquired image), and the second identifier may be a partial image (corresponding to the sub-predicted image) selected from the sample image to be segmented based on the sample segmented image.

[0099] Further, the dose monitoring module 230 can obtain N pass rates corresponding to N spatial points based on the N first doses corresponding to N spatial points in the acquisition image M1, the N second doses corresponding to N spatial points in the sub-prediction image P1, and the positional relationship between the spatial points, and then obtain the pass rate G1 corresponding to the acquisition image M1 and the sub-prediction image P1 based on the average value of the N pass rates. Similarly, the dose monitoring module 230 can also obtain the pass rate G2 corresponding to the acquisition image M2 and the sub-prediction image P2.

[0100] Some embodiments of the present specification segment a predicted image based on an acquired image corresponding to a portion of the radiation field, obtain a sub-predicted image corresponding to the acquired image, and then perform dose monitoring based on the acquired image and the sub-predicted image. The pass rate corresponding to the acquired image is used instead of the pass rate of the acquired image of the entire field to achieve dose monitoring, thereby improving computational efficiency.

[0101] In some embodiments, the dose monitoring module 230 may acquire a full-field acquisition image based on at least one acquisition image, and determine at least one pass rate based on the full-field acquisition image and the predicted image.

[0102] The full-field acquisition image may be an acquisition image corresponding to the entire field of view. In some embodiments, the imaging range of the full-field acquisition image may correspond to the imaging range of the predicted image, so that the multiple spatial points corresponding to the full-field acquisition image may correspond one-to-one with the multiple spatial points corresponding to the predicted image. Figure 4b As shown, the full-field acquisition image M may correspond to the predicted image P. In some embodiments, the dose monitoring module 230 may perform three-dimensional dose reconstruction based on the full-field acquisition image. For a detailed description of performing three-dimensional dose reconstruction based on the full-field acquisition image, see Figure 6 And the related description will not be repeated here.

[0103] Specifically, the dose monitoring module 230 may acquire a full-field acquisition image based on at least one acquisition image and radiotherapy plan information.

[0104] In some embodiments, the dose monitoring module 230 may infer a full-field acquisition image based on at least one acquisition image, radiotherapy plan information, and a guidance image of the target object.

[0105] In some embodiments, the dose monitoring module 230 can determine the intensity distribution error based on the intensity distribution of at least one acquired image and the intensity distribution of the sub-prediction image corresponding to the acquired image in the radiotherapy plan information, and then determine the intensity distribution of the full-field acquired image based on the prediction image of the target object in the radiotherapy plan information and the intensity distribution error; then obtain the response morphology error based on the historical acquired image acquired by the electronic field conversion device and the corresponding historical guidance image, and then determine the shape of the full-field acquired image based on the morphological information of the target object, the guidance image and the response morphology error; finally, obtain the full-field acquired image based on the intensity distribution of the full-field acquired image and the shape of the full-field acquired image. Figure 4b As shown, the dose monitoring module 230 can acquire the full-field acquisition image M based on the acquisition images M1 and M2.

[0106] In some embodiments, the dose monitoring module 230 can input at least one acquisition image, radiotherapy planning information (including predicted images, morphological information of the target object and dose response characteristics of the portal imaging system, etc.) and / or a guidance image of the target object into a trained image prediction model to obtain a full-field acquisition image output by the trained image prediction model.

[0107] The image prediction model can be a model that predicts the image of the entire target object based on the image of a portion of the target object. In some embodiments, the image prediction model can include, but is not limited to, a combination of one or more of a traditional algorithm model (such as a genetic algorithm) and a machine learning model (such as a neural network model, a convolutional neural network model, a recurrent neural network model, etc.).

[0108] In some embodiments, the image prediction model can be trained based on a large number of training samples with identifiers. Specifically, the training samples with identifiers are input into the image prediction model, and the parameters of the image prediction model are updated through training. In some embodiments, the training samples may include a sample image corresponding to a portion of the radiation field segmented from a sample full-field image and / or historical radiotherapy plan information, and the identifier may be the sample full-field image.

[0109] Furthermore, the dose monitoring module 230 can obtain S pass rates corresponding to the S spatial points based on the S first doses of the S spatial points corresponding to the acquired image M, the S second doses of the S spatial points corresponding to the predicted image P, and the positional relationship between the spatial points, and then obtain the pass rate G corresponding to the acquired image M and the predicted image P based on the average value of the S pass rates.

[0110] Some embodiments of the present specification acquire a full-field acquisition image based on an acquisition image corresponding to a portion of the portal, and then perform dose monitoring based on the full-field acquisition image and the predicted image, thereby achieving dose monitoring based on a determined pass rate when the detector area of ​​the portal imaging system is smaller than the portal area.

[0111] The similarity can be an indicator of the consistency between the pixels corresponding to each spatial point of the target object in the acquired image and the pixels corresponding to the predicted image. It can be understood that the closer the dose of the radioactive beam actually received by the target object is to the dose of the radioactive beam predicted to be received, the closer the corresponding acquired image is to the predicted image.

[0112] In some embodiments, when the detection area of ​​the detector is equal to the field area, the pixels in the acquired image and the pixels in the predicted image may correspond to each other, and the dose monitoring module 230 may directly obtain the similarity between the acquired image and the predicted image.

[0113] In some embodiments, the dose monitoring module 230 may obtain the similarity between the acquired image and the predicted image based on the similarity model. Specifically, the phase velocity model may include a feature extraction layer and a similarity calculation layer.

[0114] In some embodiments, the input of the feature extraction layer may include a captured image and a predicted image, and the output may include a captured image feature vector and a predicted image feature vector. Specifically, the feature extraction layer may first obtain multiple image features of the captured image and the predicted image, respectively, and then fuse the multiple image features of the captured image and the multiple image features of the predicted image, respectively, to obtain a captured image feature vector and a predicted image feature vector.

[0115] In some embodiments, image features include but are not limited to: Haar features, Histogram of Oriented Gridients (HOG) features, Local Binary Patterns (LBP) features, Edgelet features, Color-Self Similarity (CSS) features, Integral Chaneel Feature features, and Census Transform Histogram (CENTRIST) features, etc.

[0116] In some embodiments, the feature extraction layer can be a feature extraction algorithm model. In some embodiments, the feature extraction algorithm can include but is not limited to a histogram of oriented gradients (HOG), a local binary pattern (Local Binary Pattern, LBP) algorithm, a scale invariant feature transform matching (Scale Invariant Feature Transform, SIFT) algorithm, a Haar feature (Haar-like) algorithm, a gray-level co-occurrence matrix method (GLCM, Gray-level co-occurrence matrix), a Hough transform (Hough transform), a Fourier transform (Fourier transform), a Fourier shape descriptor method (Fourier shape deors), a shape parameter method (shape factor), a finite element method (Finite Element Method, FEM), a rotation function (Turning) and a wavelet descriptor (Wavelet Deor) and the like. One or more combinations.

[0117] In some embodiments, the feature extraction layer may be a neural network model. In some embodiments, the neural network model may include but is not limited to a combination of one or more of a convolutional neural network (CNN) and a fully convolutional neural network (FCN) model.

[0118] In some embodiments, the input of the similarity calculation layer may include a captured image feature vector and a predicted image feature vector, and the output may include the similarity between the captured image and the predicted image. Specifically, the similarity calculation layer may determine the similarity by calculating the distance between the captured image feature vector and the predicted image feature vector. The similarity is negatively correlated with the distance.

[0119] In some embodiments, when the detection area of ​​the detector is smaller than the field area, the pixels in the acquired image are correspondingly less than the pixels in the predicted image, and the dose monitoring module 230 can obtain at least one similarity based on at least one acquired image and predicted image in the same imaging range.

[0120] In some embodiments, the dose monitoring module 230 may determine at least one similarity based on at least one acquired image and at least one corresponding sub-prediction image in the prediction image.

[0121] Exemplarily, the dose monitoring module 230 may obtain the similarity S1 between the acquired image M1 and the sub-predicted image P1 based on the acquired image M1 and the sub-predicted image P1; similarly, the dose monitoring module 230 may obtain the similarity S2 between the acquired image M2 and the sub-predicted image P2.

[0122] In some embodiments, the dose monitoring module 230 may acquire a full-field acquisition image based on at least one acquisition image, and determine at least one similarity based on the full-field acquisition image and the predicted image.

[0123] Exemplarily, the dose monitoring module 230 may obtain the similarity S between the full-field acquisition image M and the predicted image P based on the full-field acquisition image M and the predicted image P.

[0124] A dose volume histogram (DVH) may be a graph that statistically represents the relationship between the dose and volume received by a target object. The horizontal axis of the dose volume histogram may represent the dose received by the target object, and the vertical axis may represent the percentage of the volume exceeding the dose on the horizontal axis to the total volume of the target object.

[0125] In some embodiments, the dose monitoring module 230 can obtain the first dose of the radioactive beam received by the spatial point of the target object corresponding to each pixel of each acquisition image (or full-field acquisition image) and the second dose of the radioactive beam received by the spatial point of the target object corresponding to each pixel of each sub-prediction image (or prediction image) based on the EPID-dose scale method. Further, the dose monitoring module 230 can respectively count each first dose volume histogram corresponding to each acquisition image (or full-field acquisition image) and the second dose volume histogram corresponding to each prediction image (or sub-prediction image). For example, in the first dose volume histogram corresponding to the acquisition image M1, the volume percentages of the horizontal axis 0Gy, 1Gy, 2GY...6Gy corresponding to the horizontal axis dose are: 100%, 93%, 70%...10% respectively; in the second dose volume histogram corresponding to the sub-prediction image P1, the volume percentages of the horizontal axis 0Gy, 1Gy, 2GY...6Gy corresponding to the horizontal axis dose are: 100%, 90%, 72%...5% respectively.

[0126] The dose distribution difference rate can be an indicator to characterize the distribution consistency of doses in two images.

[0127] In some embodiments, the dose monitoring module 230 may process the difference in volume percentage corresponding to each dose in the dose volume histograms corresponding to the two images to obtain the dose distribution difference rate. In some embodiments, the processing method may include but is not limited to summing, averaging, and variance.

[0128] For example, the differences in volume percentages corresponding to 0Gy, 1Gy, 2GY...6Gy of the acquisition image M1 and the sub-prediction image P1 are 0, 3%, 2%...5% respectively, then the dose distribution difference rate between the acquisition image M1 and the sub-prediction image P1 can be an average value of 0, 3%, 2%...5% (such as X1=3%).

[0129] In some embodiments, the dose monitoring module 230 may determine at least one dose distribution difference rate based on at least one acquired image and at least one corresponding sub-prediction image in the prediction image.

[0130] Exemplarily, the dose monitoring module 230 can obtain the dose distribution difference rate X1 between the acquired image M1 and the sub-predicted image P1 based on the acquired image M1 and the sub-predicted image P1; similarly, the dose monitoring module 230 can obtain the dose distribution difference rate X2 between the acquired image M2 and the sub-predicted image P2.

[0131] In some embodiments, the dose monitoring module 230 may acquire a full-field acquisition image based on at least one acquisition image, and determine at least one dose distribution difference rate based on the full-field acquisition image and the predicted image.

[0132] Exemplarily, the dose monitoring module 230 may obtain a dose distribution difference rate X between the full-field acquisition image M and the predicted image P based on the full-field acquisition image M and the predicted image P.

[0133] Step 520, monitoring the dose received by the target object based on the at least one dose difference result. In some embodiments, it can be determined whether the dose received by the target object is appropriate based on the at least one dose difference result and a dose difference threshold.

[0134] The dose difference threshold may be a value for evaluating whether the dose received by the target object is appropriate based on the dose difference result. In some embodiments, the dose difference threshold may be set from a user terminal based on user input. In some implementations, the dose difference threshold may also be automatically set based on historical data.

[0135] Corresponding to the dose difference result, the dose difference threshold may include but is not limited to a pass rate threshold, a similarity threshold, a difference rate threshold, and the like.

[0136] The pass rate threshold may be a value for evaluating whether the dose received by the target object is appropriate based on the pass rate. In some embodiments, the dose monitoring module 230 may determine whether the dose received by the target object is appropriate based on any one of the pass rates and the pass rate threshold.

[0137] Specifically, when any one of the pass rates is greater than the pass rate threshold, it indicates that the dose received by the target object is appropriate; otherwise, it indicates that the dose received by the target object is inappropriate.

[0138] For example, if the pass rate G corresponding to the full-field acquisition image M and the predicted image P is 80%, which is less than the pass rate threshold of 92%, it means that the dose of the radioactive beam received by the target object is not appropriate. For another example, the dose monitoring module 230 can select the pass rate G1 of the acquisition image M1 and the corresponding sub-prediction image P1 to represent the pass rate corresponding to the full-field acquisition image M and the predicted image P. If the pass rate G1 is 95%, which is greater than the pass rate threshold of 92%, it means that the dose of the radioactive beam received by the target object is appropriate.

[0139] In some embodiments, the dose monitoring module 230 may determine whether the dose received by the target object is appropriate based on an average of a plurality of pass rates and a pass rate threshold.

[0140] Specifically, the dose monitoring module 230 may be based on the average value of multiple pass rates corresponding to multiple acquired images acquired by the detector at multiple positions. When the pass rate average value is greater than the pass rate threshold, it indicates that the dose received by the target object is appropriate, otherwise it indicates that the dose received by the target object is inappropriate.

[0141] like Figure 4a As shown, the pass rate G1 of the acquisition image M1 and the corresponding sub-prediction image P1 acquired by the detector at position a is 95%, and the pass rate G2 of the acquisition image M2 and the corresponding sub-prediction image P2 acquired by the detector at position b is 85%. The dose monitoring module 230 can obtain an average pass rate of 90% based on the pass rate G1 and the pass rate G2, which is less than the pass rate threshold of 92%, indicating that the dose of the radioactive beam received by the target object is inappropriate.

[0142] The similarity threshold may be a value for evaluating whether the dose received by the target object is appropriate based on the similarity. In some embodiments, the similarity threshold may be set from a user terminal based on user input. In some implementations, the similarity threshold may also be automatically set based on historical data.

[0143] Specifically, when the similarity is greater than the similarity threshold, it indicates that the dose received by the target object is not appropriate, otherwise it indicates that the dose received by the target object is appropriate.

[0144] For example, if the similarity threshold is 0.8 and the similarity S1 is 0.9, which is greater than 0.8, it means that the dose of the radioactive beam of the acquired image M1 corresponding to S1 is appropriate; if the similarity S2 is 0.78, which is less than 0.8, it means that the dose of the radioactive beam of the acquired image M2 corresponding to S2 is inappropriate; if the similarity S is 0.85, which is greater than 0.8, it means that the dose of the radioactive beam of the acquired image M corresponding to S is appropriate.

[0145] The difference rate threshold may be a value for evaluating whether the dose received by the target object is appropriate based on the dose distribution difference rate. In some embodiments, the difference rate threshold may be set from a user terminal based on user input. In some implementations, the difference rate threshold may also be automatically set based on historical data.

[0146] Specifically, when the dose distribution difference rate is greater than the difference rate threshold, it indicates that the dose received by the target object is not appropriate; otherwise, it indicates that the dose received by the target object is appropriate.

[0147] For example, if the difference rate threshold is 2% and the dose distribution difference rate X1 is 3%, which is greater than 2%, it means that the dose of the radioactive beam of the acquired image M1 corresponding to X1 is inappropriate; if the dose distribution difference rate X2 is 1% and is less than 2%, it means that the dose of the radioactive beam of the acquired image M2 corresponding to X2 is appropriate; if the dose distribution difference rate X is 5% and is greater than 2%, it means that the dose of the radioactive beam of the acquired image M corresponding to X is inappropriate.

[0148] Figure 6 It is a schematic diagram of a method for optimizing radiotherapy plan based on full-field acquisition images according to some embodiments of this specification.

[0149] In some embodiments, the dose monitoring module 230 may perform three-dimensional dose reconstruction based on the full-field acquisition image in response to the inappropriate dose received by the target object.

[0150] The three-dimensional dose reconstruction may be a process of obtaining the dose distribution of the target object in the three-dimensional space. Specifically, the dose monitoring module 230 may obtain the full-field dose distribution map based on the full-field acquisition image.

[0151] The full-field dose distribution map can characterize the dose of the radioactive beam received by each spatial point of the target object corresponding to the full-field image. In some embodiments, the dose monitoring module 230 can convert each pixel in the full-field acquisition image into the dose of the radioactive beam received by the corresponding spatial point of the target object based on the EPID-dose calibration method, thereby obtaining the full-field dose distribution map.

[0152] Further, the dose monitoring module 230 can obtain the three-dimensional spatial dose distribution of the target object based on the full-field dose distribution map. In some embodiments, the dose monitoring module 230 can obtain the radiation source intensity distribution through the dose deposition kernel function based on the full-field dose distribution map, and then obtain the three-dimensional spatial dose distribution of the target object based on the radiation source intensity distribution and the morphological information of the target object.

[0153] In some embodiments, the dose monitoring module 230 may optimize the radiotherapy plan at different radiotherapy stages based on the results of three-dimensional dose reconstruction of the full-field acquisition images.

[0154] As mentioned above, a radiotherapy plan (also known as a radiotherapy plan) can be a radioactive ray irradiation plan for a target object. In some embodiments, the radiotherapy plan can be divided into multiple executions, so that the normal tissue of the target object can be restored within the interval between each radiotherapy after being irradiated with a small amount of radioactive beams. The inter-fraction radiotherapy dose can be the dose of the radioactive beam received by the target object in a single radiotherapy plan. In some embodiments, the total dose of a radiotherapy plan divided into multiple executions can be equal to the sum of multiple inter-fraction radiotherapy doses. For example, in a radiotherapy plan divided into 4 executions, the total dose of the radiotherapy plan for the target area is 80Gy, and the corresponding 4 inter-fraction radiotherapy doses are 14Gy, 16Gy, 20Gy and 30Gy respectively; the total dose of the radiotherapy plan for organs at risk is 17Gy, and the corresponding 4 inter-fraction radiotherapy doses are 3Gy, 4Gy, 5Gy and 5Gy respectively.

[0155] In some embodiments, the dose monitoring module 230 can optimize the radiotherapy plan based on the three-dimensional dose reconstruction result of the full-field acquisition image of the patient's phantom before the patient is radiotreated.

[0156] Specifically, before the patient undergoes radiotherapy, the dose monitoring system 100 can irradiate the phantom corresponding to the patient with a radioactive beam according to the radiotherapy plan, and obtain at least one full-field acquisition image of the phantom through the portal imaging system. The dose monitoring module 230 can obtain the total radiotherapy dose distribution and / or the inter-fraction radiotherapy dose distribution of the phantom based on at least one full-field acquisition image of the phantom, and then optimize the information and / or parameters in the radiotherapy plan (such as radiotherapy equipment parameters, target area position and target area dose, etc.) based on the dose distribution of at least one radiotherapy in the radiotherapy plan information.

[0157] For example, after the radiotherapy equipment completes the irradiation of the phantom according to the radiotherapy equipment parameters in the first fractionated radiotherapy of the radiotherapy plan (such as including "irradiating area A for t1 second"), the dose monitoring module 230 can obtain the actual dose distribution of the phantom in the first fractionated radiotherapy based on the full-field acquisition image corresponding to the first fractionated radiotherapy of the phantom, including the actual received dose of area A of 2Gy, and then adjust the radiotherapy equipment parameters of "irradiating area A for t1 second" to "irradiating area A for t2 seconds" based on the planned radiotherapy dose of "3Gy" of area A in the first fractionated radiotherapy in the radiotherapy plan.

[0158] In some embodiments, the dose monitoring module 230 can monitor the operation of the radiotherapy plan online based on the three-dimensional dose reconstruction results of the patient's full-field acquisition images acquired in real time during the radiotherapy process. For a detailed description of the online monitoring of the operation of the radiotherapy plan, please refer to Figure 7 And the related description will not be repeated here.

[0159] In some embodiments, the dose monitoring module 230 may adjust the current radiotherapy dose and / or the remaining fractionated radiotherapy doses after a single radiotherapy session based on the results of the three-dimensional dose reconstruction and the radiotherapy plan information.

[0160] Specifically, the dose monitoring module 230 can determine the cumulative three-dimensional dose distribution corresponding to the current single radiotherapy based on the three-dimensional dose reconstruction results of the patient's full-field image, and then adjust the inter-fraction radiotherapy dose of the radiotherapy plan information based on the cumulative three-dimensional dose distribution and the radiotherapy plan information.

[0161] The cumulative three-dimensional dose distribution corresponding to the current single radiotherapy may be the cumulative three-dimensional dose of the region of interest in the single radiotherapy that has been performed before the current single radiotherapy (including the current single radiotherapy). The region of interest may include the patient's target area and organs at risk. The target area may be the target area where the radiotherapy equipment irradiates the radioactive beam, including malignant lesion tissue. In some embodiments, the target area may take into account the patient's breathing, movement and error, and appropriately expand the range based on the malignant lesion tissue. It is understood that the target area receives an appropriate dose of the radioactive beam to ensure the destructive effect of radiotherapy on malignant lesion tissue. Organs at risk may be important tissues and / or organs within the field of view. It is understood that receiving an appropriate dose of the critical organ can prevent the radiotherapy plan from causing irreversible damage to the patient's normal tissue.

[0162] In some embodiments, the dose monitoring module 230 can obtain the cumulative three-dimensional dose distribution corresponding to the current single radiotherapy by accumulating the results of the three-dimensional dose reconstruction corresponding to the single radiotherapy that has been performed. Exemplarily, in a radiotherapy plan that is divided into 4 times, after the second single treatment is completed, the cumulative three-dimensional dose distribution corresponding to the current second single radiotherapy can be obtained based on the results of the three-dimensional dose reconstruction of the first single radiotherapy and the results of the three-dimensional dose reconstruction of the second single radiotherapy. For example, based on the results of the three-dimensional dose reconstruction of the first single radiotherapy, it can be obtained that the dose actually received by the target area in the first single radiotherapy is 12Gy, and the dose actually received by the organ at risk is 4Gy; based on the results of the three-dimensional dose reconstruction of the second single radiotherapy, it can be obtained that the dose actually received by the target area in the second single radiotherapy is 14Gy, and the dose actually received by the organ at risk is 4Gy; thereby, the cumulative three-dimensional dose distribution corresponding to the second single radiotherapy is obtained as follows: target area 12+14=26Gy, organ at risk 4+4=8Gy.

[0163] As mentioned above, the radiotherapy planning information may be information related to the radiotherapy plan. In some embodiments, the radiotherapy planning information may include the planned inter-fraction radiotherapy doses of the target area and / or the organ at risk.

[0164] Further, the dose monitoring module 230 can obtain the cumulative planned radiotherapy dose corresponding to the current single radiotherapy of each region of interest based on the radiotherapy plan information. Continuing with the above example, the cumulative planned radiotherapy dose corresponding to the second single radiotherapy of the target area is the sum of the first single radiotherapy dose and the second single radiotherapy dose: 14+16=30Gy. Similarly, the cumulative planned radiotherapy dose corresponding to the second single radiotherapy of the organ at risk is 3+4=7Gy.

[0165] In some embodiments, if the difference between the cumulative three-dimensional dose corresponding to the current single radiotherapy of the region of interest and the corresponding cumulative planned radiotherapy dose is greater than a first threshold, it is judged that the dose received by the region of interest is in excess; if the difference between the cumulative planned radiotherapy dose corresponding to the current single radiotherapy of the region of interest and the corresponding cumulative three-dimensional dose is greater than a second threshold, it is judged that the dose received by the region of interest is in short supply.

[0166] For example, if the difference between the cumulative three-dimensional dose of 8Gy corresponding to the current single radiotherapy of the organ at risk and the corresponding cumulative planned radiotherapy dose of 7Gy is 1Gy, which is greater than the first threshold value "0.5Gy", it is judged that the dose received by the organ at risk is excessive. For another example, if the difference between the cumulative planned radiotherapy dose of 30Gy corresponding to the current single radiotherapy of the target area and the corresponding cumulative three-dimensional dose of 26Gy is 4Gy, which is greater than the second threshold value "2Gy", it is judged that the dose received by the target area is insufficient.

[0167] In order to ensure that the region of interest receives the total dose of the radiotherapy plan, the dose monitoring module 230 can adjust the unexecuted inter-fraction radiotherapy dose. Continuing the above example, the doses actually received by the target area in the first and second radiotherapy are 12Gy and 14Gy, respectively. In order to ensure that the total dose received by the target area is 80Gy, the inter-fraction radiotherapy doses of the third and fourth times can be adjusted to 20Gy and 34Gy.

[0168] In some embodiments, the patient achieves a treatment effect beyond expectations after performing part of the single radiotherapy, and the dose monitoring module 230 can adjust the unperformed inter-fraction radiotherapy dose based on the reduced total dose of the radiotherapy plan. Continuing with the above example, after the target area has undergone the second radiotherapy, the total dose of the radiotherapy plan is modified to 70Gy, and the dose monitoring module 230 can adjust the third and fourth inter-fraction radiotherapy doses to 20Gy and 24Gy.

[0169] Figure 7 is an exemplary flow chart of a method for online monitoring of radiotherapy plans based on full-field acquisition images according to some embodiments of this specification. Specifically, Figure 7 It can be performed by the dose monitoring module 230. Figure 7 As shown, method 700 may include:

[0170] Step 710 , triggering a monitoring condition, and determining whether the dose currently received by the target object meets a preset range based on at least one acquired image and a predicted image.

[0171] The monitoring condition may be a condition for initiating dose monitoring during radiotherapy. In some embodiments, the monitoring condition may include that the time interval between the current moment and the last monitoring moment meets the set time interval. For example, the monitoring condition may be that the time interval "30 seconds" between the current moment "16:0:30 on the same day" and the last monitoring moment "16:0:00 on the same day" meets the set time interval "30 seconds". In some embodiments, the monitoring condition may include receiving a monitoring request sent by the terminal device 130. For example, the monitoring condition may be receiving a monitoring request sent by a user through the terminal device 130 to monitor the dose received by the target object at the current moment. In some embodiments, the monitoring condition may also include that the current radiotherapy process is a specified process. For example, the monitoring condition may be when the current radiotherapy process is 1 / 4 process, 2 / 4 process and 3 / 4 process of the current single radiotherapy process.

[0172] In some embodiments, after the monitoring condition is triggered, the system 100 can obtain at least one captured image and a predicted image at the current moment. For a detailed description of obtaining at least one captured image and a predicted image, please refer to step 310 and step 320, which will not be repeated here.

[0173] The dose currently received by the target object may be a real-time 3D reconstructed dose of the target object at the current moment. In some embodiments, the dose monitoring module 230 may acquire a full-field acquisition image of the target object at the current moment based on at least one acquisition image and a predicted image of the target object at the current moment. For a description of acquiring a full-field acquisition image, see Figure 5 In some embodiments, the dose monitoring module 230 can obtain the dose currently received by the target object through three-dimensional dose reconstruction based on the full-field acquisition image of the target object at the current moment. For a detailed description of three-dimensional dose reconstruction, please refer to Figure 6 And the related description will not be repeated here.

[0174] The preset range is the appropriate dose range corresponding to the current radiotherapy process. In some embodiments, the dose monitoring module 230 can determine the preset range based on the current radiotherapy process and the radiotherapy plan dose. Exemplarily, the dose monitoring module 230 can first determine the appropriate dose range corresponding to the current single radiotherapy plan based on the radiotherapy plan dose and the first threshold and the second threshold, and then determine the preset range based on the current radiotherapy process and the appropriate dose range corresponding to the current single radiotherapy plan.

[0175] For example, the current single radiotherapy planned dose of the target area is 20 Gy, the first threshold is 0.5 Gy, and the second threshold is 2 Gy. Then the appropriate dose of the current single radiotherapy plan is (20-2)~(20+0.5)=18~20.5 Gy, and the preset range is 9~10.25 Gy.

[0176] In some embodiments, the dose monitoring module 230 can compare the dose currently received by the target object with a preset range. If the dose currently received by the target object is greater than the upper limit of the preset range, it indicates that the dose currently received by the target object is excessive; if the dose currently received by the target object is less than the lower limit of the preset range, it indicates that the dose currently received by the target object is insufficient; when the dose currently received by the target object is within the preset range, it indicates that the dose currently received by the target object is appropriate.

[0177] Step 720: In response to the dose currently received by the target object not satisfying the preset range, a prompt message is sent to the terminal device.

[0178] The prompt information may include information that prompts the user that the online dose monitoring result is abnormal. For example, the prompt information may include "the current dose may be excessive" or "the current dose may be insufficient".

[0179] In some embodiments, the dosage monitoring module 230 may send prompt information to the terminal device 130 via the network 140 .

[0180] In some embodiments, after receiving the prompt information sent by the terminal device, the user can choose to manually adjust the current radiotherapy dose, or can choose to have the dose monitoring module 230 automatically adjust the current radiotherapy dose.

[0181] In some embodiments, when the target object receives an excessive dose in the current single radiotherapy, the dose monitoring module 230 may automatically close the leaves of the multi-leaf collimator relative to the target object so that the radioactive beam does not continue to irradiate the target object.

[0182] In some embodiments, when the target object receives insufficient dose in the current single radiotherapy, the dose monitoring module 230 may automatically open more leaves of the multi-leaf collimator relative to the target object so that more radioactive beams can irradiate the target object.

[0183] For example, in the second radiotherapy in the radiotherapy plan, the planned doses of the target area and the organ at risk are 8 Gy and 3 Gy respectively, and the three-dimensional reconstructed doses of the target area and the organ at risk are 5 Gy and 4 Gy respectively. The dose monitoring module 230 can open the leaves of the multi-leaf collimator relative to the target area, and close the leaves of the multi-leaf collimator relative to the organ at risk, so that more radioactive beams irradiate the target area, while preventing the radioactive beams from continuing to irradiate the organ at risk.

[0184] In some embodiments, in response to the target subject's current dose not meeting the preset range, the dose monitoring module 230 can directly and automatically adjust the remaining fractionated radiotherapy dose. For detailed description of adjusting the remaining fractionated radiotherapy dose, see Figure 6 And the related description will not be repeated here.

[0185] In some embodiments, the prompt information may also include an instruction to directly trigger stopping treatment, and the instruction to stop treatment may instruct the radiotherapy device 110 to stop treatment through the network 140 .

[0186] The beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) based on the acquisition image corresponding to a part of the field, the acquisition image of the whole field is obtained, and then the dose monitoring is performed based on the acquisition image of the whole field and the predicted image, so that when the detection area of ​​the field imaging system is smaller than the field area, the dose monitoring can be achieved based on the determined dose difference result; (2) based on the acquisition image corresponding to a part of the field, the predicted image is segmented, and the sub-prediction image corresponding to the acquisition image is obtained, and then the dose monitoring is performed based on the acquisition image and the sub-prediction image, and the dose difference result corresponding to the acquisition image is replaced with the dose difference result of the acquisition image of the whole field, so as to achieve dose monitoring, thereby improving the calculation efficiency; (3) based on the acquired full-field acquisition image, three-dimensional dose reconstruction can be further performed, the radiotherapy plan can be modified online, and online adaptive radiotherapy can be achieved. It should be noted that different embodiments may have different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained.

[0187] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0188] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0189] In addition, it will be understood by those skilled in the art that various aspects of this specification may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of this specification may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of this specification may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0190] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0191] The computer program code required for the operation of each part of this specification can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0192] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing processing device or mobile device.

[0193] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0194] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0195] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0196] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A dose monitoring method, the method comprising: Acquire at least one acquired image of the target object based on a detector, wherein the detection area of ​​the detector is smaller than the area of ​​the radiation field, and the acquired image corresponds to a part of the radiation field; acquiring a predicted image based on the radiotherapy plan information of the target object; Inputting the at least one acquired image and the radiotherapy plan information into an image prediction model to obtain a full-field acquired image; Determining at least one dose difference result based on the full-field acquisition image and the predicted image; Based on the at least one dose difference result, a dose received by the target object is monitored.

2. The method of claim 1, further comprising: Based on the full-field acquisition images, three-dimensional dose reconstruction is performed.

3. The method of claim 2, further comprising: Based on the result of the three-dimensional dose reconstruction and the radiotherapy plan information, the current radiotherapy dose and / or the remaining fractionated radiotherapy dose are adjusted.

4. The method of claim 1, further comprising: Based on the at least one acquired image and the predicted image, determining whether a dose currently received by the target object meets a preset range; In response to the dose currently received by the target object not satisfying a preset range, a prompt message is sent to the terminal device.

5. A dose monitoring system, comprising: An acquisition image acquisition module, used to acquire at least one acquisition image of the target object based on a detector, wherein the detection area of ​​the detector is smaller than the area of ​​the radiation field, and the acquisition image corresponds to a part of the radiation field; A predicted image acquisition module, used to acquire a predicted image based on the radiotherapy plan information of the target object; Dose monitoring module for: Inputting the at least one acquired image and the radiotherapy plan information into an image prediction model to obtain a full-field acquired image; Determining at least one dose difference result based on the full-field acquisition image and the predicted image; Based on the at least one dose difference result, a dose received by the target object is monitored.

6. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the dose monitoring method according to any one of claims 1 to 4.

Images