Target region tracking method, apparatus, device, and medium

Abstract

The application provides a target region tracking method, device, equipment and medium. The method comprises: in the process of extracorporeal radiotherapy, performing projection processing on a guide image collected for a target region to obtain a guide image projection; in the process of scanning a human body by using a megavoltage ray matched with a target treatment plan, based on a kilovoltage ray matched with the target treatment plan and used for guide image collection and separated from the megavoltage ray, a treatment region projection corresponding to a treatment region is obtained; according to the guide image projection, a blocked projection in the treatment region projection is corrected to obtain a corrected projection; according to the guide image projection and the corrected projection, the guide image is updated to obtain an updated guide image; and based on the updated guide image and a target region positioning image matched with the target treatment plan, a tracking result of the target region is determined. In this way, real-time tracking of the target region in the radiotherapy process is effectively realized, and the risk of not timely terminating beam output due to off-target is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer vision, in particular to a target region tracking method and device, equipment and medium. BACKGROUND

[0002] Radiotherapy is a tumor treatment method, which uses high-dose ionizing radiation (commonly X-rays, gamma rays or protons, etc.) to kill cancer cells and reduce tumors. According to the source mode, it is divided into external radiotherapy (external irradiation), brachytherapy (intracavitary / tissue interstitial radiotherapy) and radionuclide systemic treatment, and is widely used in tumor comprehensive treatment. When radiotherapy is performed on a tumor, the position of the target region needs to be determined. The target region is the anatomical volume that needs to receive a sufficient dose for the purpose of treatment.

[0003] In radiotherapy, the position of the target region is usually predicted before the treatment beam is emitted. Then megavoltage X-rays are emitted to the target region. However, the tumor may move due to patient breathing and other reasons during treatment, which may cause off-target during treatment, thereby affecting the radiotherapy effect. SUMMARY

[0004] Therefore, the present application provides a target region tracking method, device, equipment and medium. During external radiotherapy, the guide image can be updated in real time, and compared with the target treatment plan matched target region positioning image, effectively realizing real-time tracking of the target region and improving the accuracy of the target region tracking.

[0005] Specifically, the present application is realized by the following technical solutions:

[0006] According to a first aspect of the present application, a target region tracking method is provided, the method comprising:

[0007] During external radiotherapy, the guide image collected for the target region is projected to obtain a guide image projection;

[0008] During scanning of the human body by megavoltage rays matched with the target treatment plan, based on the kilovoltage rays separated from the megavoltage rays and matched with the target treatment plan for guide image collection, a treatment region projection corresponding to the treatment region is obtained, the treatment region being a ray irradiation region indicated by the target treatment plan;

[0009] According to the guide image projection, the occluded projection in the treatment region projection is corrected to obtain a corrected projection;

[0010] According to the guide image projection and the corrected projection, the guide image is updated to obtain an updated guide image;

[0011] determine a tracking result of the target volume based on the updated scout image and a target volume localization image matched with the target treatment plan.

[0012] In an alternative embodiment, the treatment region projection is obtained from kilovoltage rays separated from megavoltage rays used to scan the human body in a process matched with the target treatment plan, including:

[0013] In a process of scanning the human body using megavoltage rays matched with the target treatment plan, the kilovoltage rays matched with the target treatment plan are separated from the megavoltage rays by a target device with photon counting acquisition function according to a separation limit value used to distinguish the energy range of the megavoltage rays and the kilovoltage rays.

[0014] The kilovoltage ray separation projection corresponding to the kilovoltage rays is projected and corrected using a projection value adjustment matrix to obtain the treatment region projection.

[0015] In an alternative embodiment, the separation limit value includes a separation upper limit and a separation lower limit, and the separation limit value is determined by the following steps:

[0016] The separation upper limit is determined based on the energy required when using kilovoltage rays for image guidance according to the target treatment plan.

[0017] The separation lower limit is determined based on the minimum energy of the kilovoltage rays that can be received by the target device.

[0018] In an alternative embodiment, the projection value adjustment matrix is obtained by the following steps:

[0019] Obtain the megavoltage ray spectrum corresponding to the megavoltage rays and the kilovoltage ray spectrum corresponding to the kilovoltage rays;

[0020] Extract the kilovoltage separation spectrum corresponding to the separation limit value from the megavoltage ray spectrum;

[0021] Normalize the kilovoltage ray spectrum and the kilovoltage separation spectrum to obtain the normalized kilovoltage ray spectrum and the normalized kilovoltage separation spectrum;

[0022] Scan a plurality of waters with different lengths using the normalized kilovoltage ray spectrum to obtain a kilovoltage ray spectrum projection corresponding to each water, and scan the plurality of waters with different lengths using the normalized kilovoltage separation spectrum to obtain a kilovoltage separation spectrum projection corresponding to each water;

[0023] Determine the projection value adjustment matrix based on the kilovoltage spectrum projection and the kilovoltage separate spectrum projection corresponding to each water.

[0024] In an alternative embodiment, the step of projecting the guide image to obtain the modified projection comprises:

[0025] Determine the fusion matrix based on the values of each pixel in the treatment region projection.

[0026] Fuse the guide image projection and the treatment region projection at the current circumferential beam-out angle using the fusion matrix to obtain the modified projection.

[0027] In an alternative embodiment, the values of each pixel in the treatment region projection are determined by:

[0028] Binary process the treatment region projection to determine the blocked region and the unblocked region.

[0029] Determine the value of each pixel in the blocked region as 1 and the value of each pixel in the unblocked region as 0.

[0030] In an alternative embodiment, the method further comprises:

[0031] Select a boundary transition region inward from the boundary of the unblocked region.

[0032] Determine the value of each pixel in the boundary transition region according to a target transition algorithm, wherein the value of each pixel in the boundary transition region is greater than 0 and less than 1.

[0033] In an alternative embodiment, the step of updating the guide image based on the guide image projection and the modified projection to obtain an updated guide image comprises:

[0034] Perform filter back-projection processing on the guide image projection and the modified projection at the current circumferential beam-out angle to obtain a back-projection guide image and a back-projection modified image.

[0035] Update the guide image based on the back-projection guide image and the back-projection modified image to obtain an updated guide image.

[0036] In an alternative embodiment, the step of determining the tracking result of the target region based on the updated guide image and a simulated positioning image matching the target treatment plan comprises:

[0037] Perform position matching on the updated guide image and the simulated positioning image to obtain a matching result.

[0038] determine whether to continue the treatment according to the matching result;

[0039] In a case where it is determined to continue the treatment, the original guide image is replaced by the updated guide image, and the guide image projection is replaced by the corrected projection, and the kilovoltage scanned human body matched with the target treatment plan is re-used for projection correction until the treatment ends.

[0040] According to a second aspect of the present application, a target region tracking device is provided, the device comprising:

[0041] a guide projection module, configured to perform projection processing on a guide image collected for a target region during extracorporeal radiotherapy, to obtain a guide image projection;

[0042] a treatment projection module, configured to obtain a treatment region projection corresponding to a treatment region during the use of a megavoltage scanned human body matched with a target treatment plan, the treatment region being a radiation irradiation region indicated by the target treatment plan, based on kilovoltage rays separated from the megavoltage rays and used for guide image collection and matched with the target treatment plan;

[0043] a projection correction module, configured to correct a blocked projection in the treatment region projection according to the guide image projection, to obtain a corrected projection;

[0044] an image updating module, configured to update the guide image according to the guide image projection and the corrected projection, to obtain an updated guide image;

[0045] a target region tracking module, configured to determine a tracking result of the target region based on the updated guide image and a target region positioning image matched with the target treatment plan.

[0046] According to a third aspect of the present application, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the target region tracking method of the first aspect when executing the program.

[0047] According to a fourth aspect of the present application, a computer readable storage medium is provided, having a computer program stored thereon, the program implementing the steps of the target region tracking method of the first aspect when executed by a processor.

[0048] The target region tracking method, device, equipment and medium provided by the embodiments of the present application can correct the blocked projection in the treatment region projection according to the guide image projection in the process of external radiotherapy, thereby updating the guide image in real time according to the guide image projection and the corrected projection, and comparing the updated guide image with the target region positioning image matched with the target treatment plan, so that the target region tracking in the radiotherapy process is effectively realized, the accuracy of the target region tracking is improved, the risk of not terminating the beam in time due to off-target is reduced, and the effect of radiotherapy is improved.

[0049] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, but not limiting the technical solutions of the present disclosure.

[0050] In order to make the above-mentioned purposes, features and advantages of the present disclosure more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 is a flowchart of a target region tracking method according to an example embodiment of the present application;

[0052] Figure 2 is a process schematic diagram of target region tracking according to an example embodiment of the present application;

[0053] Figure 3 is another process schematic diagram of target region tracking according to an example embodiment of the present application;

[0054] Figure 4 is a schematic diagram of a data query device according to an example embodiment of the present application;

[0055] Figure 5 is a structural schematic diagram of a computer equipment according to an example embodiment of the present application.

[0056] In the drawings: 400-target region tracking device; 401-guide projection module; 402-treatment projection module; 403-projection correction module; 404-image update module; 405-target region tracking module; 500-computer equipment; 510-processor; 520-memory; 530-bus; 521-internal memory; 522-external memory. DETAILED DESCRIPTION

[0057] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The description of the exemplary embodiments is intended to apply to any exemplary embodiment, unless specified otherwise. It is understood that features of one exemplary embodiment are applicable to other exemplary embodiments as appropriate. Unless otherwise defined, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an overly literal or overly formal sense unless expressly so defined herein.

[0058] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0059] It is to be understood that the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. It is to be further understood that the term "or" as used herein encompasses both exclusive and inclusive or unless otherwise indicated herein. It is to be understood that the terms "comprises", "comprising", "includes", and / or "including" as used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0060] For the purpose of promoting an understanding of the principles of the present disclosure, reference will now be made to the embodiments illustrated in the drawings.

[0061] A medical linear accelerator (LINAC) is the most commonly used treatment machine for external beam radiotherapy. It accelerates electrons to high energy and forms a treatment beam in one of two ways: electrons are directly used for treatment (electron beam, suitable for superficial lesions); electrons hit a high-Z metal target to produce megavoltage X-rays for deep tumor treatment. Modern LINACs can also precisely shape the beam and work with image guidance to achieve high-precision treatment.

[0062] LINAC working principle and key components:

[0063] Electron gun: Produces electrons. Microwave / radio frequency source (magnetron or klystron) with acceleration structure / waveguide: Accelerates electrons to desired energy with microwave electric field. Beam transport and deflection (bending magnets, etc.): Directs electrons to target location. Target / flattening filter or scatter foil: Braking radiation produced by electron bombardment of metal target when irradiating X-rays; flattening filter traditionally used to make dose distribution more uniform at certain depths; scatter foil or magnetic scanning spread used when irradiating electron beam. Collimation and shaping: Primary / secondary collimator + multi-leaf collimator (MLC) dynamically opens and closes according to planned shape, shaping and intensity modulation. Monitor ionization chamber: Online monitors dose, beam stability and interlocks. Gantry / treatment couch / imaging: Gantry rotates around isocenter, treatment couch has three or six degrees of freedom for positioning; equipped with kilovoltage (KV) or megavoltage (MV) imaging or cone beam computed tomography (CBCT) for image-guided radiation therapy (IGRT).

[0064] LINAC typically provides multiple banks of megavoltage X-rays (about 4-25 MV) and electron beams (a few MeV to over 20 MeV) for different depths of target volume. Through de-flattening filter beam, the central axis dose rate is significantly improved after removing the flattening filter, and the scattering and head secondary radiation are reduced, which is often used for stereotactic radio surgery (SRS) / stereotactic body radiation therapy (SBRT) and other high-efficiency delivery. Three-dimensional conformal radiation therapy (3D-CRT), intensity-modulated radiation therapy (IMRT), volumetric modulated arc therapy (VMAT), spiral volumetric modulated arc therapy (SVMAT), stereotactic radiotherapy (SRS / SBRT) and other treatments can be achieved by LINAC; IGRT can be used before / after treatment to correct the position of the target volume and organs, improve accuracy and reduce normal tissue dose.

[0065] In radiotherapy, the position of the target volume needs to be determined. The target volume is the anatomical volume that needs to receive a sufficient dose for the treatment to be successful. It is not a single volume, but a hierarchy of standard volumes (gross tumor volume / clinical target volume / internal target volume / planning target volume) used to define the prescription, planning and evaluation. The gross tumor volume (GTV) is the extent of the tumor and metastasis visible on imaging, physical examination or biopsy. It is the basis for all subsequent volumes. The clinical target volume (CTV) is the GTV plus the subclinical spread of tumor (e.g. along the anatomical structures, lymphatic drainage pathways). It is a clinical / anatomical concept representing the "tumor-related tissue that must be adequately irradiated". The internal target volume (ITV) is the CTV plus an internal margin (IM) to account for internal organ motion (e.g. due to respiration). For sites with little motion (e.g. head and neck), the ITV can not be defined separately. The planning target volume (PTV) is the CTV (or ITV) plus a safety margin (SM) to account for setup / geometric uncertainties. It is the geometric volume used for planning optimization and dose evaluation. The PTV is intended to ensure that the CTV receives the prescribed dose in the presence of small errors.

[0066] Tumors / organs move in treatment due to respiration and other reasons. The long target volume is more significant in movement. When high dose and steep dose gradient are used to "hit the target and hit it hard", the margin is often expanded (CTV→PTV). However, this will involve more normal tissue in the high dose region. Real-time tracking of the target volume is to solve the problem of "the target is moving and the irradiation is still accurate", so as to cover, reduce the margin, reduce toxicity and improve efficiency.

[0067] In order to realize target area tracking, first, real-time position information of the tumor target area is obtained, and common methods include infrared markers, body surface imaging, implanted metal markers combined with X-ray imaging, etc. After obtaining the position of the target area, in order to achieve the purpose of "hitting accurately", there are mainly three methods. Free breathing gating: the beam is turned on in a certain interval of the breathing cycle, and the beam is turned off at other times; It can also be triggered by an external breathing signal, or an internal marker signal; The end-expiratory pause is usually selected as the gating window. Deep inspiration breath hold (DIBH) / active breathing coordinator (ABC): the patient actively holds his breath to stop the chest and abdominal movement. Usually, after deep inspiration, the patient holds his breath, so that the lungs are filled and the heart is away from the dangerous area. Each breath hold lasts for 15-30 seconds to complete partial irradiation; The ABC device measures the lung capacity and uses a mechanical air valve to achieve repeated breath holding. Real-time target area tracking irradiation: real-time adjustment of beam aiming / shaping to follow tumor movement. For example, the robot adjusts the machine head or the high-speed MLC changes the field shape, and the bed moves to compensate. The mechanical lag is solved by a prediction algorithm. This method can achieve accurate aiming and irradiation of the tumor at all times. This method has a larger duty cycle and higher treatment efficiency than free breathing gating; Compared with DIBH / ABC, it has better treatment experience, wider applicability and better patient compliance.

[0068] It is found through research that during radiotherapy, the position of the target area is usually predicted before the beam treatment, and then a laser is emitted to the target area, without confirming the accuracy of the actual beam position. However, the tumor may move during treatment due to patient breathing and other reasons, and there may be a situation of off-target during treatment, which may bring great risks if the beam is not terminated in time, thereby affecting the effect of radiotherapy.

[0069] Based on the above research, the present application provides a target area tracking method, device, equipment and medium, which can update the guide image in real time during extracorporeal radiotherapy, and compare it with the target area positioning image matched with the target treatment plan, effectively realizing real-time tracking of the target area during radiotherapy and improving the accuracy of target area tracking.

[0070] In order to facilitate the understanding of the present embodiment, first, a target area tracking method disclosed by the present embodiment is introduced in detail. The execution subject of the target area tracking method provided by the present embodiment is generally an electronic device with certain computing power. The electronic device can be a server, which can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud storage, big data and artificial intelligence platform. In some possible implementation manners, the target area tracking method can be realized by calling computer readable instructions stored in the memory by the processor.

[0071] The target region tracking method provided by the embodiment of the present application is described below with reference to the accompanying drawings.

[0072] Referring to Figure 1 FIG. 1 is a flowchart of a target region tracking method according to an example embodiment of the present application. As shown in FIG. 1, the target region tracking method provided by the embodiment of the present application includes steps S101-S105. Figure 1

[0073] S101: In the process of performing external radiotherapy, a guide image collected for a target region is subjected to projection processing to obtain a guide image projection.

[0074] In this step, in the process of performing external radiotherapy, a guide image can be collected for a target region by using a LINAC, and KV CT or KV CBCT. A guide image projection Prj can be obtained by subjecting the guide image to orthographic projection. IGRT .

[0075] Here, in the process of performing external radiotherapy, a guide image is collected for a target region in real time at each circumferential beam-out angle. In actual application, the circumferential beam-out angle refers to the angle of incidence of a ray beam relative to the surface of a patient's body when a treatment machine (accelerator rotating part) performs 360° rotation irradiation around the patient's body. The circumferential beam-out angle directly affects the distribution of the ray beam and the dose coverage range. Correspondingly, each guide image projection corresponds to a circumferential beam-out angle.

[0076] S102: In the process of scanning a human body by using a megavoltage ray matched with a target treatment plan, a kilovoltage ray matched with the target treatment plan and used for guide image collection is separated from the megavoltage ray to obtain a treatment region projection corresponding to a treatment region, the treatment region being a ray irradiation region indicated by the target treatment plan.

[0077] Here, before performing external radiotherapy, a target region positioning image can be collected for a target region by using a device for formulating a treatment plan, such as a computed tomography (CT) device, and a target treatment plan can be formulated in combination with a tumor shape indicated by the target region positioning image, for example, including treatment of the treatment region by using a certain amount of ray at a certain circumferential beam-out angle.

[0078] In this step, in the process of scanning a human body by using a megavoltage ray matched with a target treatment plan, a kilovoltage ray matched with the target treatment plan and used for guide image collection can be separated from the megavoltage ray to obtain a treatment region projection corresponding to a treatment region based on the kilovoltage ray.

[0079] ​In some possible implementation manners, the treatment region projection corresponding to the treatment region is obtained based on kilo-voltage rays separated from the mega-voltage rays and matched with the guide image for guide image acquisition in the process of scanning the human body by using the mega-voltage rays matched with the target treatment plan, comprising:

[0080] In the process of scanning the human body by using the mega-voltage rays matched with the target treatment plan, the kilo-voltage rays matched with the target treatment plan for guide image acquisition are separated from the mega-voltage rays by a target device with a photon counting acquisition function according to a separation limit value for distinguishing the energy ranges of the mega-voltage rays and the kilo-voltage rays.

[0081] The kilo-voltage ray separation projection corresponding to the kilo-voltage rays is projected and corrected by using a projection value adjustment matrix to obtain the treatment region projection.

[0082] Here, when performing IGRT, mega-voltage electrons and kilo-voltage electrons, that is, mega-voltage rays and kilo-voltage rays, are often generated, and the emitted rays are often multi-order mixed rays. In the process of scanning the human body by using the mega-voltage rays matched with the target treatment plan, the kilo-voltage rays matched with the target treatment plan for guide image acquisition can be separated from the mega-voltage rays by a target device with a photon counting acquisition function, such as a flat panel lamp, according to a separation limit value. MVKV .

[0083] The kilo-voltage rays are air corrected to obtain the kilo-voltage ray separation projection PrjT mvkv . Specifically, the kilo-voltage ray separation projection can be obtained by the following formula (1):

[0084] PrjT mvkv = ln(I0) - ln(I) (1)

[0085] Wherein, PrjT mvkv represents the kilo-voltage ray separation projection, I0 represents the beam intensity without scanning objects, I represents the beam intensity with scanning objects, and the beam intensities corresponding to I0 and I are consistent. Here, the scanning objects can be the human body, and I can take the value I MVKV .

[0086] The kilo-voltage ray separation projection PrjT mvkv is projected and corrected by using a projection value adjustment matrix M(r, c) to obtain the treatment region projection Prj mvkv . Here, the projection value adjustment matrix M includes r rows and c columns, and each element in the projection value adjustment matrix can be used to perform polynomial fitting on the kilo-voltage ray separation projection to obtain the treatment region projection.

[0087] Specifically, the treatment region projection corresponding to the treatment region can be obtained by formula (2) as follows:

[0088] Prj mvkv (r,c)=polyval(M(r,c),PrjT mvkv (r,c)) (2)

[0089] Wherein, Prj mvkv (r,c) represents the treatment region projection, polyval represents the polynomial calculation, M(r,c) represents the projection value adjustment matrix, PrjT mvkv (r,c) represents the kilovoltage ray separation projection.

[0090] In this way, the target device with photon counting acquisition function is used to separate the kilovoltage ray matched with the treatment plan from the megavoltage ray, so as to realize accurate scanning of the treatment region, correct the kilovoltage ray separation projection by using the projection value adjustment matrix, and generate high-precision treatment region projection, thereby helping to improve the ray energy separation and projection correction capability, effectively reducing the error caused by ray energy aliasing, and improving the target area positioning accuracy in the external radiotherapy process and the execution accuracy of the treatment plan.

[0091] Before the external radiotherapy is performed, preliminary parameter preparation can be performed. Specifically, the separation limit value and the projection value adjustment matrix can be determined first.

[0092] In some possible embodiments, the separation limit value includes a separation upper limit and a separation lower limit, and the separation limit value is determined by the following steps:

[0093] The separation upper limit is determined based on the energy required when image guidance is performed using the kilovoltage ray according to the target treatment plan;

[0094] The separation lower limit is determined based on the minimum energy of the kilovoltage ray that can be received by the target device.

[0095] In the above steps, the ray energy required for imaging when image guidance is performed using the kilovoltage ray according to the target treatment plan can be determined, and the separation upper limit is determined according to the ray energy. For example, the separation upper limit corresponding to the ray energy of 125kV is 125keV.

[0096] In actual application, if the energy of the kilovoltage ray is small, the photons can be consumed, and the photons are difficult to be received by the target device, thereby causing difficulty in imaging. The minimum energy of the kilovoltage ray that can be received by the target device can be determined, and the separation lower limit is determined based on the minimum energy. For example, the minimum energy of the kilovoltage ray that can be received by the target device ranges from 25keV to 40keV, and the separation lower limit can be any value in the range, for example, 30keV.

[0097] In this way, by combining the energy requirements for kilovolt X-ray image guidance in the target treatment plan to determine the upper limit of separation, and by determining the lower limit of separation based on the minimum energy of kilovolt X-rays received by the target equipment, the energy separation range between megavolt X-rays and kilovolt X-rays can be accurately defined. This helps to ensure the targeting and equipment compatibility of energy separation, reduce the risk of image quality degradation or equipment overload caused by energy aliasing, and improve the stability and reliability of kilovolt X-ray separation.

[0098] In some possible implementations, the projection value adjustment matrix is ​​obtained through the following steps:

[0099] Obtain the megavolt radiation spectrum corresponding to the megavolt radiation and the kilovolt radiation spectrum corresponding to the kilovolt radiation;

[0100] Extract the kilovolt separation spectrum corresponding to the separation limit from the megavolt radiation spectrum;

[0101] The kilovolt radiation spectrum and the kilovolt separation spectrum are normalized to obtain the normalized kilovolt radiation spectrum and the normalized kilovolt separation spectrum.

[0102] The normalized kilovolt X-ray spectrum was used to scan multiple water bodies of different lengths to obtain the kilovolt X-ray spectral projection corresponding to each water body. The normalized kilovolt separation spectrum was also used to scan the multiple water bodies of different lengths to obtain the kilovolt separation spectral projection corresponding to each water body.

[0103] The projection value adjustment matrix is ​​determined based on the kilovolt X-ray spectral projection and kilovolt separation spectral projection corresponding to each water.

[0104] In the above steps, Monte Carlo simulation can be used to obtain the megavolt spectral spectra corresponding to the megavolt rays matching the target treatment plan by simulating the transport of photons and electrons in the medium. MV and the kilovolt radiation spectrum Spectrum corresponding to the kilovolt radiation matched with the stated treatment plan KV Then, it is possible to obtain the megavolt-ray spectral spectra from the spectra. MV Extract the kilovolt separation spectrum corresponding to the separation limit. MVKV For example, if the separation limit is 125keV-30keV, then Spec... MVKV =Spec MVKV (30:125). Next, the kilovolt X-ray spectrum can be analyzed. KV and the kilovolt separation spectrum Spec MVKV After normalization, the normalized kilovolt X-ray spectrum Spectrum is obtained. ’ KV and the normalized kilovolt separation spectrum Spec’ MVKV , thereby eliminating dimensional differences.

[0105] Since most of the human tissue is water, water is used here to simulate the effect of human body scanning. A plurality of water of different lengths can be taken, for example, 5:5:500mm, starting from 5mm and taking 5mm intervals to 500mm. The normalized kilovoltage ray spectrum Spec ’ KV A plurality of water of different lengths are scanned respectively to obtain the kilovoltage ray spectrum projection PrjW KV corresponding to each water, and the normalized kilovoltage separation spectrum Spec ’ MVKV The plurality of water of different lengths are scanned respectively to obtain the kilovoltage separation spectrum projection PrjW MVKV corresponding to each water. The projection value represents the attenuation of the ray after passing through the object (i.e. water), and the projection value is the product of the attenuation value and the path length (i.e. the length of the water).

[0106] For each water, based on the kilovoltage ray spectrum projection PrjW KV and the kilovoltage separation spectrum projection PrjW MVKV corresponding to the water, polynomial fitting is performed to obtain the projection value adjustment matrix M(r,c), each element in the projection value adjustment matrix corresponds to one of the plurality of water of different lengths, and each element in the projection value adjustment matrix is obtained by performing polynomial fitting on the kilovoltage ray spectrum projection PrjW KV and the kilovoltage separation spectrum projection PrjW MVKV corresponding to the water corresponding to the element.

[0107] In this way, the kilovoltage ray energy difference of the treatment region is compensated by the above-mentioned manner, the correction accuracy of the treatment region projection is effectively improved, reliable data support is provided for subsequent target tracking, and the stability of the radiotherapy process and the accuracy of target positioning are enhanced.

[0108] S103: According to the guide image projection, the occluded projection in the treatment region projection is corrected to obtain a corrected projection.

[0109] In actual application, there is often an occluded part in the treatment region projection, for example, a part occluded by the MLC. In this step, the occluded projection in the treatment region projection Prj IGRT can be corrected according to the guide image projection Prj mvkv to obtain a corrected projection PrjFix.

[0110] S104: According to the guide image projection and the corrected projection, the guide image is updated to obtain an updated guide image.

[0111] In this step, the guide image projection Prj can be used. IGRT The guide image is updated using the corrected projection PrjFix to obtain an updated guide image. The guide image projection Prj... IGRT Both the corrected projection PrjFix and the kilovolt radiation matched to the target treatment plan ensure the fusion quality of the guided image update.

[0112] S105: Based on the updated guidance image and the target area localization image matched with the target treatment plan, determine the target area tracking result.

[0113] In this step, the target area position at the time of beam exit can be reconstructed in real time through the updated guide image. The accuracy of target area positioning is detected by comparing the updated guide image with the target area positioning image that matches the target treatment plan, and the target area tracking result is determined.

[0114] For example, see [link / reference] Figure 2 This is a schematic diagram illustrating a target area tracking process, as shown in an exemplary embodiment of this application. Figure 2 As shown, preliminary parameter preparation can be performed before external beam radiotherapy. During external beam radiotherapy, projection correction is performed. Specifically, based on the guidance image projection, any obstructed projections in the treatment area projection are corrected to obtain the corrected projection. Then, image updating is performed. Based on the guidance image projection and the corrected projection, the guidance image is updated to obtain an updated guidance image. Based on the updated guidance image and the target area localization image matched with the target treatment plan, the target area tracking result is determined, achieving real-time target area monitoring. Specific steps are described in the aforementioned embodiments and will not be repeated here.

[0115] The following will further explain the content of each step in conjunction with specific implementation methods.

[0116] In some possible implementations, the step of correcting the occluded projection in the treatment area projection based on the guided image projection to obtain a corrected projection includes:

[0117] The fusion matrix is ​​determined based on the values ​​of each pixel in the projection of the treatment area;

[0118] The fusion matrix is ​​used to fuse the projection of the guide image and the projection of the treatment area at the current circumferential beam exit angle to obtain the corrected projection.

[0119] In the above step, the fusion matrix W (r, c) can be determined according to the values of each pixel in the treatment region projection, the fusion matrix W including r rows and c columns, and each element in the fusion matrix corresponding to the value of each pixel in the treatment region projection.

[0120] The guide image projection Prj IGRT (β, r, c) and the treatment region projection Prj mvkv (β, r, c) at the current circumferential beam-out angle β to obtain the corrected projection. Correspondingly, with the rotation of the treatment machine, the corresponding corrected projection can be obtained at each circumferential beam-out angle by the embodiment.

[0121] Specifically, the corrected projection can be obtained by the following formula (3):

[0122] Prj Fix (β, r, c) = Prj mvkv (β, r, c) x W (r, c) + Prj IGRT (β, r, c) x (1-W (r, c)) (3)

[0123] Wherein, Prj Fix (β, r, c) represents the corrected projection, Prj mvkv (β, r, c) represents the treatment region projection, Prj IGRT (β, r, c) represents the guide image projection, and W (r, c) represents the fusion matrix.

[0124] In this way, the fusion matrix is constructed according to the values of each pixel in the treatment region projection, and the guide image projection and the treatment region projection at the current circumferential beam-out angle are dynamically fused by using the fusion matrix, so as to realize the accurate correction of the occluded region in the treatment region projection, effectively improve the physical consistency and geometric precision of the corrected projection, and provide a more reliable image basis for subsequent target tracking.

[0125] In some possible embodiments, the values of each pixel in the treatment region projection are determined by the following steps:

[0126] The treatment region projection is binarized to determine the occluded region and the non-occluded region.

[0127] The values of each pixel in the occluded region are determined as 1, and the values of each pixel in the non-occluded region are determined as 0.

[0128] Here, because the projection value represents the attenuation of the ray after passing through the object, if the region is blocked, the attenuation will be larger, and if the region is not blocked, the attenuation will be smaller. Thus, the projection of the treatment region is binarized, that is, the blocked region and the non-blocked region are distinguished. It can be understood that the blocked region is the invalid beam-out region, and the non-blocked region is the valid beam-out region. The values of each pixel in the blocked region are uniformly set to 1, and the values of each pixel in the non-blocked region are uniformly set to 0, so that the region classification is directly reflected.

[0129] In this way, by binarizing the projection of the treatment region, the blocked region and the non-blocked region are clearly distinguished, and the rapid classification of the pixel values in the projection of the treatment region is realized, which simplifies the processing complexity of the projection data, provides a clear numerical basis for the subsequent construction of the fusion matrix, and effectively improves the generation efficiency and accuracy of the corrected projection, thereby enhancing the real-time and reliability of the target tracking in the radiotherapy process.

[0130] In some possible implementation manners, the method further includes:

[0131] selecting a boundary transition region inward from the region boundary of the non-blocked region;

[0132] determining the values of the pixels in the boundary transition region according to a target transition algorithm, the values of the pixels in the boundary transition region being greater than 0 and less than 1.

[0133] In the above step, for the non-blocked region, a preset number of pixels n are expanded inward from the region boundary of the non-blocked region as a boundary transition region, and the values of the pixels in the boundary transition region are determined according to a target transition algorithm, so that the pixels in the boundary transition region gradually transition from 1 to 0 in the direction from the non-blocked region to the blocked region.

[0134] The specific value of the preset number is determined according to actual needs, which is not limited here. The target transition algorithm can be, for example, linear transition.

[0135] In this way, on the basis of the binarization, the boundary transition region is demarcated inward from the region boundary of the non-blocked region, and the target transition algorithm is used to give the pixels in the region a gradual value between 0 and 1, which realizes the smooth transition between the non-blocked region and the blocked region, reduces the edge sawtooth effect caused by binarization, reduces the abruptness of the fusion of the guide image projection and the treatment region projection, and improves the spatial continuity of the corrected projection.

[0136] In some possible implementation manners, the updating of the guide image according to the guide image projection and the corrected projection to obtain an updated guide image includes:

[0137] The guided image projection and the corrected projection are respectively filtered back projection processed at the current circumferential beam-out angle to obtain a back projection guided image and a back projection corrected image;

[0138] Based on the back projection guided image and the back projection corrected image, the guided image is updated to obtain an updated guided image.

[0139] In the above steps, the guided image projection Prj IGRT (β, r, c) at the current circumferential beam-out angle β can be filtered back projection processed to obtain a back projection guided image img0 β (x, y, z), and the corrected projection Prj Fix (β, r, c) at the current circumferential beam-out angle β can be filtered back projection processed to obtain a back projection corrected image img1 β (x, y, z). Here, the back projection guided image img0 β (x, y, z) and the back projection corrected image img1 β (x, y, z) are only position projection images at the current circumferential beam-out angle β, and are in the form of multiple lines rather than complete images.

[0140] The back projection guided image in the original guided image is deleted and the back projection corrected image is added, that is, the back projection corrected image is used to replace the back projection guided image to obtain an updated guided image corresponding to the current beam-out.

[0141] Here, the coverage range of the circumferential beam-out angle of the image replacement can be determined according to actual needs, which is not limited here. For example, if the coverage range of the circumferential beam-out angle reaches a set beam-out angle region, such as 200°, it indicates that the iteration replacement of each circumferential beam-out angle in the original guided image is completed at this time, and the updated image is obtained.

[0142] Specifically, the updated guided image can be obtained by the following formula (4):

[0143] img ’ (x, y, z) = img(x, y, z) - img0 β (x, y, z) + img1 β (x, y, z) (4)

[0144] Wherein, img ’ (x, y, z) represents the updated guided image, img(x, y, z) represents the guided image before updating, img0 β (x, y, z) represents the back projection guided image, and img1 β (x, y, z) represents the back projection corrected image.

[0145] Thus, by filtering back-projection technology, the noise and artifacts in the projection data are effectively eliminated, the spatial resolution and detail retention capability of the back-projection image are improved, and the actual state of the treatment region is accurately reflected by the updated guide image through the dual-image fusion mechanism, thereby significantly enhancing the real-time and robustness of the target region tracking in the radiotherapy process, and providing a reliable image-guided basis for precise treatment.

[0146] In some possible embodiments, the tracking result of the target region is determined based on the updated guide image and a simulation positioning image matched with the target treatment plan, and the tracking result of the target region comprises:

[0147] The updated guide image and the simulation positioning image are positionally matched to obtain a matching result.

[0148] Whether to continue the treatment is determined according to the matching result.

[0149] In a case where it is determined to continue the treatment, the updated guide image is used to replace the original guide image, the corrected projection is used to replace the guide image projection, a kilovoltage radiography of the human body matched with the target treatment plan is re-used for projection correction until the treatment ends.

[0150] In the above steps, the updated guide image img ’ (x,y,z) can be used to replace the original guide image img(x,y,z), and the simulation positioning image img Simu is positionally matched to obtain a matching result. If the matching result indicates that the positional deviation is less than a first preset threshold, the subsequent ART treatment process can be continued after the patient position is adjusted according to the positional deviation; if the matching result indicates that the positional deviation is greater than or equal to the first preset threshold, it is determined to stop the treatment.

[0151] In other embodiments, the updated guide image can also be displayed in real time for a user to manually determine the accuracy of the target region position at any time according to the updated guide image, and the treatment process can be manually intervened to determine whether to continue the treatment.

[0152] In a case where it is determined to continue the treatment, the updated guide image img ’ (x,y,z) can be used to replace the original guide image img(x,y,z), and the corrected projection Prj Fix (β,r,c) is used to replace the guide image projection Prj IGRT (β,r,c), a kilovoltage radiography of the human body matched with the target treatment plan is re-used for projection correction until the treatment ends.

[0153] Here, if the matching result indicates that the position deviation is less than the first preset threshold and greater than a second preset threshold, the second preset threshold is less than the first preset threshold, a target treatment plan can be re-established according to the updated guide image, a kilovoltage ray scanned human body matched with the re-established target treatment plan is adopted and projection correction is performed, and the above steps are repeated until the treatment ends. If the matching result indicates that the position deviation is less than or equal to the second preset threshold, the original target treatment plan can be continued to be adopted, and the above steps are repeated until the treatment ends.

[0154] In this way, by matching the position of the real-time updated guide image and the simulation positioning image, the accuracy of target area positioning is dynamically evaluated and the treatment continuity is intelligently decided, the updated guide image is adopted to replace the original guide image when it is confirmed to continue the treatment, and the guide image projection is synchronously replaced, the image guidance reliability in the whole treatment process is ensured through the data updating mechanism, and the prediction-treatment-monitoring full closed loop process can be formed by combining target area prediction, the real-time performance of target area tracking and the accuracy of treatment execution are significantly improved, and the effect of radiotherapy is improved.

[0155] For example, refer to Figure 3 Another process diagram of target area tracking is shown in an example embodiment of the present application. As shown in Figure 3 In the process of external radiotherapy, the guide image projection is determined, the kilovoltage ray matched with the target treatment plan is separated from the megavoltage ray matched with the target treatment plan for performing guide image acquisition, the kilovoltage ray separation projection corresponding to the kilovoltage ray is determined, the treatment area projection is obtained by performing projection correction on the kilovoltage ray separation projection, the fusion matrix is determined, the occluded projection in the treatment area projection is corrected by using the fusion matrix and the guide image projection to obtain the corrected projection, the guide image projection under the current circumferential beam-out angle is processed by filter back projection to obtain the back projection guide image, the corrected projection under the current circumferential beam-out angle is processed by filter back projection to obtain the back projection correction image, the guide image is updated based on the back projection guide image and the back projection correction image to obtain the updated guide image corresponding to the current beam-out, and the updated guide image and the guide image projection are updated. Through automatic monitoring or manual intervention, it is determined whether to continue the treatment, and in the case of determining to continue the treatment, the kilovoltage ray matched with the target treatment plan is re-separated from the megavoltage ray matched with the target treatment plan, and the above steps are continued, otherwise the treatment is stopped. For specific step description, refer to the foregoing embodiments, which will not be repeated here.

[0156] The target region tracking method provided in the embodiments of the present application can correct the blocked projection in the treatment region projection according to the guide image projection in the process of external radiotherapy, thereby updating the guide image in real time according to the guide image projection and the corrected projection, and comparing the updated guide image with the target region positioning image matched with the target treatment plan, so that the target region tracking in the process of radiotherapy is effectively realized, the accuracy of target region tracking is improved, the risk of not terminating the beam in time due to off-target is reduced, and the effect of radiotherapy is improved.

[0157] Those skilled in the art can understand that, in the above method of the specific implementation, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process, and the specific execution order of each step should be determined according to its function and possible internal logic.

[0158] Corresponding to the above-mentioned embodiments of the target region tracking method, the present application also provides an embodiment of a target region tracking device.

[0159] Please refer to Figure 4 Fig. 1 is a schematic diagram of a target region tracking device according to an example embodiment of the present application. As shown in Figure 4 The target region tracking device 400 provided in the embodiments of the present application comprises:

[0160] The guide projection module 401 is configured to perform projection processing on the guide image collected for the target region in the process of external radiotherapy, to obtain a guide image projection.

[0161] The treatment projection module 402 is configured to obtain a treatment region projection corresponding to a treatment region in the process of scanning a human body by megavoltage rays matched with a target treatment plan, based on kilovoltage rays separated from the megavoltage rays and matched with the target treatment plan and used for guide image collection.

[0162] The projection correction module 403 is configured to correct the blocked projection in the treatment region projection according to the guide image projection, to obtain a corrected projection.

[0163] The image updating module 404 is configured to update the guide image according to the guide image projection and the corrected projection, to obtain an updated guide image.

[0164] The target region tracking module 405 is configured to determine a tracking result of the target region based on the updated guide image and a target region positioning image matched with the target treatment plan.

[0165] In some possible implementation manners, the treatment projection module 402 is specifically configured to:

[0166] In the process of scanning a human body by megavoltage rays matched with a target treatment plan, a target device with photon counting acquisition function is used to separate kilovoltage rays for guided image acquisition from the megavoltage rays according to a separation limit value, which is used to distinguish the energy range of megavoltage rays and kilovoltage rays, and the kilovoltage rays are matched with the target treatment plan.

[0167] The kilovoltage ray separation projection corresponding to the kilovoltage rays is projected and corrected by using a projection value adjustment matrix to obtain the treatment region projection.

[0168] In some possible implementation manners, the separation limit value includes a separation upper limit and a separation lower limit, and the treatment projection module 402 determines the separation limit value by the following steps.

[0169] The separation upper limit is determined based on the energy required when image guidance is performed by using kilovoltage rays according to the target treatment plan.

[0170] The separation lower limit is determined based on the minimum energy of kilovoltage rays that can be received by the target device.

[0171] In some possible implementation manners, the treatment projection module 402 obtains the projection value adjustment matrix by the following steps.

[0172] The megavoltage ray spectrum corresponding to the megavoltage rays and the kilovoltage ray spectrum corresponding to the kilovoltage rays are obtained.

[0173] A kilovoltage separation spectrum corresponding to the separation limit value is extracted from the megavoltage ray spectrum.

[0174] The kilovoltage ray spectrum and the kilovoltage separation spectrum are normalized to obtain a normalized kilovoltage ray spectrum and a normalized kilovoltage separation spectrum.

[0175] The normalized kilovoltage ray spectrum is used to scan a plurality of waters with different lengths respectively to obtain a kilovoltage ray spectrum projection corresponding to each water, and the normalized kilovoltage separation spectrum is used to scan the plurality of waters with different lengths respectively to obtain a kilovoltage separation spectrum projection corresponding to each water.

[0176] The projection value adjustment matrix is determined based on the kilovoltage ray spectrum projection and the kilovoltage separation spectrum projection corresponding to each water.

[0177] In some possible implementation manners, the projection correction module 403 is specifically configured to:

[0178] A fusion matrix is determined based on the numerical value of each pixel in the treatment region projection.

[0179] The fusion matrix is used to fuse the guide image projection and the treatment region projection at the current circumferential beam-out angle, to obtain the corrected projection.

[0180] In some possible implementation manners, the projection correction module 403 determines the value of each pixel in the treatment region projection by the following steps:

[0181] The treatment region projection is binarized to determine the blocked region and the unblocked region.

[0182] The value of each pixel in the blocked region is determined as 1, and the value of each pixel in the unblocked region is determined as 0.

[0183] In some possible implementation manners, the projection correction module 403 is further configured to:

[0184] A boundary transition region is selected inward from the region boundary of the unblocked region.

[0185] The value of each pixel in the boundary transition region is determined according to a target transition algorithm, and the value of each pixel in the boundary transition region is greater than 0 and less than 1.

[0186] In some possible implementation manners, the image updating module 404 is specifically configured to:

[0187] The guide image projection and the corrected projection are respectively filtered and back-projected at the current circumferential beam-out angle, to obtain a back-projected guide image and a back-projected corrected image.

[0188] The guide image is updated based on the back-projected guide image and the back-projected corrected image, to obtain an updated guide image.

[0189] In some possible implementation manners, the target region tracking module 405 is specifically configured to:

[0190] The updated guide image and the simulated positioning image are positionally matched to obtain a matching result.

[0191] Whether to continue treatment is determined according to the matching result.

[0192] In a case where it is determined to continue treatment, the updated guide image is used to replace the original guide image, and the corrected projection is used to replace the guide image projection, a kilovoltage (kV) radiation scan of the human body matched with the target treatment plan is re-performed and corrected until the treatment ends.

[0193] The functions and effects of the modules in the above apparatus are specifically described in the implementation process of the corresponding steps in the above method, and will not be described here again.

[0194] For the device embodiment, since it basically corresponds to the method embodiment, the relevant part can be seen from the part of the method embodiment. The device embodiment described above is only illustrative, wherein the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the application scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0195] Based on the same technical concept, the application also provides a computer device 500, as shown in Figure 5 Fig. 1 is a structural schematic diagram of a computer device according to an example embodiment of the application, which comprises:

[0196] a processor 510, a memory 520, and a bus 530. The memory 520 is used to store execution instructions, including an internal memory 521 and an external memory 522; the internal memory 521 is also called an internal storage, used to temporarily store operation data in the processor 510 and exchange data with the external memory 522 such as a hard disk, and the processor 510 exchanges data with the external memory 522 through the internal memory 521.

[0197] In the application embodiment, the memory 520 is specifically used to store application program codes for executing the application scheme, and is controlled to execute by the processor 510. That is, when the electronic device 500 is running, the processor 510 communicates with the memory 520 through the bus 530, or the processor 510 communicates with the memory 520 through other ways, so that the processor 510 executes the application program codes stored in the memory 520, and further executes the steps of the target area tracking method described in any of the preceding embodiments.

[0198] The memory 520 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0199] The processor 510 can be an integrated circuit chip having a processing capability for signals. The processor described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; or can be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed by the processor. The general processor can be a microprocessor or the processor can also be any conventional processor.

[0200] It can be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the electronic device 500. In some other embodiments of the present application, the electronic device 500 can include more or fewer components than those illustrated, or combine certain components, or split certain components, or different arrangement of components. The illustrated components can be implemented in hardware, software or a combination of software and hardware.

[0201] The embodiments of the present disclosure further provide a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program is run by a processor, the steps of the target area tracking method described in the method embodiments are executed. The storage medium can be a volatile or non-volatile computer readable storage medium.

[0202] The embodiments of the present disclosure further provide a computer program product, and the computer program product stores a computer program. When the computer program is run by a processor, the steps of the target area tracking method provided by any of the embodiments of the present disclosure are executed. For details, refer to the method embodiments described above, which will not be repeated here.

[0203] The computer program product can be specifically implemented by hardware, software or a combination thereof. In an optional embodiment, the computer program product is specifically embodied as a computer storage medium, which can be a volatile or non-volatile computer readable storage medium. In another optional embodiment, the computer program product is specifically embodied as a software product, such as a software development kit (Software Development Kit, SDK) and the like.

[0204] Moreover, embodiments of the subject matter described in this specification can be implemented in digital electronic circuitry, in tangibly-embodied computer software or firmware, in computer hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible non-transitory program carrier for execution by, or to control the operation of, data processing apparatus. Alternatively or additionally, the program instructions can be encoded on an artificially generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal that is generated to encode information for transmission to suitable receiver apparatus for execution by a data processing apparatus. The computer storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0205] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit), and the apparatus can be implemented as special purpose logic circuitry.

[0206] Computers suitable for the execution of a computer program include, by way of example, general and / or special purpose microprocessors, or any other kind of central processing unit. Generally, a central processing unit will receive instructions and data from a read-only memory and / or a random access memory. The essential elements of a computer are a central processing unit for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. However, a computer need not have such devices. Moreover, a computer can be embedded in another device, e.g., a mobile telephone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device (e.g., a universal serial bus (USB) flash drive), to name just a few.

[0207] Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0208] While the specification contains many specifics, these should not be construed as limiting the scope of any invention or of what can be claimed, but as merely providing illustrations of some of the embodiments of the inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features can be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination and the claimed combination can be directed to a subcombination or variation of a subcombination.

[0209] Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring such order, nor that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing can be advantageous. Moreover, the separation of various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0210] Accordingly, particular embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In some implementations, multitasking and parallel processing can be advantageous.

[0211] The above description is merely illustrative of the application and does not limit the scope of the application as determined by the appended claims.

Claims

1. A target area tracking method characterized by, The method comprises: During the process of performing external radiotherapy, projection processing is performed on a guide image collected for a target region to obtain a guide image projection; During the process of scanning a human body by using megavoltage rays matched with a target treatment plan, a treatment region projection corresponding to a treatment region is obtained based on kilovoltage rays matched with the target treatment plan and separated from the megavoltage rays, the treatment region being a ray irradiation region indicated by the target treatment plan; According to the guide image projection, a blocked projection in the treatment region projection is corrected to obtain a corrected projection; According to the guide image projection and the corrected projection, the guide image is updated to obtain an updated guide image; Based on the updated guide image and a target region positioning image matched with the target treatment plan, a tracking result of the target region is determined; During the process of scanning a human body by using megavoltage rays matched with a target treatment plan, a treatment region projection corresponding to a treatment region is obtained based on kilovoltage rays matched with the guide image and separated from the megavoltage rays, the treatment region being a ray irradiation region indicated by the target treatment plan; During the process of scanning a human body by using megavoltage rays matched with a target treatment plan, kilovoltage rays matched with the target treatment plan and separated from the megavoltage rays for performing guide image collection are separated from the megavoltage rays by using a target device with a photon counting collection function according to a separation limit value, the separation limit value being used to distinguish the energy ranges of the megavoltage rays and the kilovoltage rays; A projection value adjustment matrix is used to perform projection correction on kilovoltage ray separation projections corresponding to the kilovoltage rays to obtain the treatment region projection, the kilovoltage ray separation projections being obtained by performing air correction on the kilovoltage rays.

2. The method of claim 1, wherein, The separation limit value comprises a separation upper limit and a separation lower limit, and the separation limit value is determined by the following steps: The separation upper limit is determined based on the energy required when performing image guidance by using kilovoltage rays according to the target treatment plan; The separation lower limit is determined based on the minimum energy of the kilovoltage rays that can be received by the target device.

3. The method of claim 1, wherein, The projection value adjustment matrix is obtained by the following steps: The megavoltage ray spectrum corresponding to the megavoltage rays and the kilovoltage ray spectrum corresponding to the kilovoltage rays are obtained; A kilovoltage separation spectrum corresponding to the separation limit value is extracted from the megavoltage ray spectrum; Normalization processing is performed on the kilovoltage ray spectrum and the kilovoltage separation spectrum to obtain a normalized kilovoltage ray spectrum and a normalized kilovoltage separation spectrum; The normalized kilovoltage ray spectrum is used to scan a plurality of waters with different lengths respectively to obtain a kilovoltage ray spectrum projection corresponding to each water, and the normalized kilovoltage separation spectrum is used to scan the plurality of waters with different lengths respectively to obtain a kilovoltage separation spectrum projection corresponding to each water; The projection value adjustment matrix is determined based on the kilovoltage ray spectrum projection and the kilovoltage separation spectrum projection corresponding to each water.

4. The method of claim 1, wherein, The correction of the blocked projection in the treatment region projection based on the guide image projection to obtain the corrected projection comprises: A fusion matrix is determined based on the numerical values of each pixel in the treatment region projection; The fusion matrix is used to fuse the guide image projection and the treatment region projection at the current circumferential beam-out angle, to obtain the corrected projection.

5. The method of claim 4, wherein, The value of each pixel in the treatment region projection is determined by the following steps: The treatment region projection is binarized to determine the blocked region and the unblocked region; The value of each pixel in the blocked region is determined as 1, and the value of each pixel in the unblocked region is determined as 0.

6. The method of claim 5, wherein, The method further comprises: A boundary transition region is selected inward from the boundary of the unblocked region; The value of each pixel in the boundary transition region is determined according to a target transition algorithm, and the value of each pixel in the boundary transition region is greater than 0 and less than 1.

7. The method of claim 1, wherein, The updating of the guide image based on the guide image projection and the corrected projection to obtain an updated guide image comprises: The guide image projection and the corrected projection are respectively filtered and back-projected at the current circumferential beam-out angle to obtain a back-projected guide image and a back-projected corrected image; The guide image is updated based on the back-projected guide image and the back-projected corrected image to obtain an updated guide image.

8. The method of claim 1, wherein, The determination of the tracking result of the target region based on the updated guide image and the simulated positioning image matching the target treatment plan comprises: The position matching of the updated guide image and the simulated positioning image is performed to obtain a matching result; It is determined whether to continue treatment according to the matching result; In the case of determining to continue treatment, the updated guide image is used to replace the original guide image, and the corrected projection is used to replace the guide image projection, and a kilovoltage ray scanning human body matching the target treatment plan is used again for projection correction until the treatment is completed.

9. A target area tracking device, characterized by, The device comprises: A guide projection module is configured to perform projection processing on a guide image collected for a target region during extracorporeal radiotherapy to obtain a guide image projection. A treatment projection module is configured to obtain a treatment region projection corresponding to a treatment region during the process of using a megavoltage ray scanning human body matching a target treatment plan, based on a kilovoltage ray separated from the megavoltage ray and used for guide image collection. A projection correction module is configured to correct the blocked projection in the treatment region projection according to the guide image projection to obtain a corrected projection. An image updating module is configured to update the guide image according to the guide image projection and the corrected projection to obtain an updated guide image. A target region tracking module is configured to determine a tracking result of a target region based on the updated guide image and a target region positioning image matching the target treatment plan. The treatment projection module is specifically configured to: In the process of scanning a human body by megavoltage rays matched with a target treatment plan, a target device with photon counting acquisition function is used to separate kilovoltage rays matched with the target treatment plan for guided image acquisition from the megavoltage rays according to a separation limit value for distinguishing the energy ranges of the megavoltage rays and the kilovoltage rays. A projection value adjustment matrix is used to project and correct kilovoltage ray separation projections corresponding to the kilovoltage rays to obtain the treatment region projections, wherein the kilovoltage ray separation projections are obtained by air correction of the kilovoltage rays.

10. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the steps of the target region tracking method of any one of claims 1 to 8.

11. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the target region tracking method of any one of claims 1 to 8.

Images