Dose error type determination method, apparatus, computer device, and storage medium

Abstract

The application relates to a dose error type determination method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining a predicted EPID image of a to-be-tested object in current fraction treatment; the predicted EPID image comprises a first predicted EPID image and a second predicted EPID image; the first predicted EPID image is obtained based on an initial medical scanning image of the to-be-tested object; the second predicted EPID image is obtained based on a medical scanning image of the to-be-tested object in the current fraction treatment; an actual EPID image of the to-be-tested object in the current fraction treatment is obtained; and the dose error type of the current fraction treatment is determined according to the first predicted EPID image, the second predicted EPID image and the actual EPID image. Different dose error types of the to-be-tested object are determined based on the predicted EPID images and the actual EPID image obtained in different states, the source of the dose error is determined, and the accuracy of the dose error type judgment is improved.

Description

Technical Field

[0001] This application relates to the field of radiotherapy plan quality verification technology, and in particular to a method, apparatus, computer equipment, and storage medium for determining dose error type. Background Technology

[0002] Quality Assurance (QA) is a crucial part of radiotherapy. It involves comparing the planned theoretical dose with the actual measured dose to evaluate the effectiveness of the treatment plan.

[0003] Traditionally, during fractionated treatment, an Electronic Portal Imaging Device (EPID) is used to measure the image of the patient after radiation penetration, obtaining an actual EPID image. This actual EPID image characterizes the image on the EPID after the treatment radiation penetrates the patient during the fractionated treatment. Then, by comparing this actual EPID image with a planned EPID image calculated based on the planned CT images, the dose error corresponding to the fractionated treatment is determined.

[0004] However, dosage errors are of various types, and traditional methods cannot determine the specific type of error in fractionated treatment. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining dose error type, which can accurately determine the error type of each treatment session for different types of dose errors.

[0006] Firstly, this application provides a method for determining the type of dose error. The method includes:

[0007] Obtain the predicted EID image of the subject in the current treatment session; the predicted EID image includes a first predicted EID image and a second predicted EID image; the first predicted EID image is obtained based on the initial medical scan image of the subject; the second predicted EID image is obtained based on the medical scan image of the subject in the current treatment session;

[0008] Obtain the actual EPID image of the subject during the current treatment session;

[0009] Based on the first predicted EID image, the second predicted EID image, and the actual EID image, determine the dosage error type of the current fractionated treatment.

[0010] In one embodiment, the dose error type includes a first type of dose error and a second type of dose error; determining the dose error type of the current fractionated treatment based on the first predicted EID image, the second predicted EID image, and the actual EID image includes:

[0011] Based on the first and second predicted EID images, determine whether the current fractionated treatment dose error type is a type I dose error.

[0012] Based on the second predicted EPID image and the actual EPID image, determine whether the current fractionated treatment dose error type is a type II dose error.

[0013] In one embodiment, determining whether the dose error type of the current fractionated treatment is a type I dose error based on the first predicted EID image and the second predicted EID image includes:

[0014] A preset evaluation algorithm is used to compare the first predicted EID image and the second predicted EID image to obtain a first evaluation result; wherein, the first evaluation result is used to characterize the similarity between the first predicted EID image and the second predicted EID image;

[0015] Based on the first assessment results, determine whether the current fractionated treatment dose error type is a type I dose error; type I dose error is used to characterize the dose error caused by different body postures and positions of the test subject.

[0016] In one embodiment, determining whether the dose error type of the current fractionated treatment is a type II dose error based on the second predicted EID image and the actual EID image includes:

[0017] A pre-defined evaluation algorithm is used to compare the second predicted EID image and the actual EID image to obtain a second evaluation result; wherein, the second evaluation result is used to characterize the similarity between the second predicted EID image and the actual EID image;

[0018] Based on the second assessment results, the dosage error type of the current fractionated treatment is determined to be Type II dosage error; Type II dosage error is used to characterize the dosage error caused by the different operating parameters of the treatment accelerator in the current fractionated treatment.

[0019] In one embodiment, the method further includes:

[0020] Based on the current dose error type of the fractionated treatment and the preset error adjustment strategy, determine the target error adjustment strategy corresponding to the dose error type of the current fractionated treatment; the preset error adjustment strategy includes error adjustment strategies corresponding to different dose error types;

[0021] The target error adjustment strategy is used to treat the subjects in stages.

[0022] In one embodiment, acquiring the predicted EPID image of the subject in the current treatment fraction includes:

[0023] Acquire the first and second medical scan images of the subject during the current treatment session, as well as the initial treatment plan for the subject; the first medical scan image is the initial medical scan image of the subject used to formulate the initial treatment plan; the second medical scan image is the medical scan image of the subject acquired before the current treatment session.

[0024] The first medical scan image and the initial treatment plan are input into the preset EPID algorithm to obtain the first predicted EPID image of the subject in the current treatment session;

[0025] The second medical scan image and the initial treatment plan are input into the preset EPID algorithm to obtain the second predicted EPID image of the subject in the current treatment session.

[0026] In one embodiment, the method further includes:

[0027] Based on the first medical scan image, the theoretical three-dimensional dose reconstruction result of the subject is obtained;

[0028] Three-dimensional dose reconstruction is performed based on the second medical scan image and the actual EPID image of the current fractionated treatment to obtain the actual three-dimensional dose reconstruction result of the subject under test.

[0029] By comparing and analyzing the theoretical three-dimensional dose reconstruction results with the actual three-dimensional dose reconstruction results, the dose analysis results of the target object are determined.

[0030] Secondly, this application also provides a dose error type determination device. The device includes:

[0031] The first acquisition module is used to acquire the predicted EID image of the subject in the current treatment session; the predicted EID image includes a first predicted EID image and a second predicted EID image; the first predicted EID image is obtained based on the initial medical scan image of the subject; the second predicted EID image is obtained based on the medical scan image of the subject in the current treatment session.

[0032] The second acquisition module is used to acquire the actual EPID image of the subject in the current treatment session;

[0033] The first determining module is used to determine the dosage error type of the current fractionated treatment based on the first predicted EID image, the second predicted EID image, and the actual EID image.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the dose error type determination method in the first aspect.

[0035] Fourthly, this application also provides a computer-readable storage medium. This computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the dose error type determination method in the first aspect.

[0036] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the dose error type determination method in the first aspect.

[0037] The aforementioned method, apparatus, computer device, storage medium, and computer program product for determining dose error types involve the computer device acquiring a first predicted EID image and a second predicted EID image of the subject during the current fraction of treatment. The first predicted EID image is obtained based on the initial medical scan image of the subject, and the second predicted EID image is obtained based on the medical scan image of the subject during the current fraction of treatment. Next, the actual EID image of the subject during the current fraction of treatment is acquired. Furthermore, the dose error type of the current fraction of treatment is determined based on the first predicted EID image, the second predicted EID image, and the actual EID image. In other words, in this embodiment, the computer device can determine different dose error types of the subject based on predicted EID images and actual EID images obtained under different states. Since the predicted EID images and actual EID images under different states can characterize different states of the subject and different states of the radiotherapy equipment, it is possible to accurately determine what factors caused the dose error, i.e., determine the source of the dose error, thereby obtaining the specific dose error type and improving the accuracy and rationality of dose error type determination. Furthermore, since the method proposed in this application can accurately locate the source of dosage error, it can also adjust the error in a timely manner after determining the source of the dosage error, thereby reducing the error and improving the accuracy of fractionated treatment. Attached Figure Description

[0038] Figure 1 This is a diagram illustrating the application environment of a dose error type determination method in one embodiment;

[0039] Figure 2 This is a flowchart illustrating a method for determining the type of dose error in one embodiment;

[0040] Figure 3This is a flowchart illustrating the method for determining the type of dose error in another embodiment;

[0041] Figure 4 This is a flowchart illustrating the method for determining the type of dose error in another embodiment;

[0042] Figure 5 This is a flowchart illustrating the method for determining the type of dose error in another embodiment;

[0043] Figure 6 This is a flowchart illustrating the method for determining the type of dose error in another embodiment;

[0044] Figure 7 This is a flowchart illustrating the method for determining the type of dose error in another embodiment;

[0045] Figure 8 This is a schematic diagram of the complete process of a dose error type determination method in one embodiment;

[0046] Figure 9 This is a schematic diagram illustrating the determination of the first type of dose error in one embodiment;

[0047] Figure 10 This is a schematic diagram illustrating the determination of the second type of dose error in one embodiment;

[0048] Figure 11 This is a schematic diagram illustrating the dosage analysis of fractionated treatment in one embodiment;

[0049] Figure 12 This is a structural block diagram of a dose error type determination device in one embodiment;

[0050] Figure 13 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0052] Quality Assurance (QA), also known as patient-specific QA, is an important part of radiotherapy. A common method is to use dose verification equipment to measure point dose, area dose, etc., during the execution of the plan. By comparing the measured dose with the theoretically calculated dose, the effectiveness of the plan execution can be evaluated.

[0053] For example, plan quality verification can typically be achieved using methods such as ionization chambers, semiconductor probes to measure point doses in phantoms, and dose verification equipment to measure surface doses. However, because patient positioning and posture vary during each fraction of treatment, and accelerator execution also introduces errors, such methods cannot perform online plan verification during actual treatment.

[0054] With the development of medical technology, in vivo dose monitoring of patients during radiotherapy has been widely used. The existing in vivo methods for radiotherapy mainly include the following two:

[0055] 1. Patient surface point dose measurement typically uses thermoluminescent dosimeters (TLDs) and diodes to measure point doses on the surface of the patient receiving and exiting radiation. However, this method results in a limited number of measurement points, providing only limited information and lacking spatial distribution.

[0056] 2. Electronic Portal Imaging Device (EPID) measures images of radiation transmitted through the patient. EPID measures sequences of radiation images transmitted through the patient, allowing for dose verification during treatment. This method requires calibration of the EPID-acquired images, and accurate modeling of the EPID response is also necessary.

[0057] During treatment, EPID measures the sequence of X-ray images transmitted through the patient and compares them with the expected image (or baseline image) to verify the in vivo dose during treatment. The expected image (or baseline image) of EPID can be obtained by combining the patient's image information (CT, MR, etc.) acquired at the beginning of treatment with dose calculation. Using the gamma pass rate method to assess the degree of consistency between the two sets of images, the consistency between the EPID measured image and the expected image (or baseline image) can be quantitatively evaluated, thereby obtaining the evaluation results, and then determining the effectiveness of the treatment plan based on the evaluation results.

[0058] However, in actual treatment, due to factors such as patient positioning deviation, changes in patient posture, and accelerator execution error, the dose received by the patient often deviates from the expected dose. Moreover, this deviation is caused by different factors. Therefore, the types of dose errors received by the patient are diverse, and traditional methods cannot determine the type of dose error in the fractionated treatment process.

[0059] Based on this, the embodiments of this application propose a method for determining the type of dose error, which can serve as an effective method for online quality verification of the treatment plan. This method can further distinguish the sources of deviation in the dose received by the patient and provide guidance for subsequent fractionated treatment.

[0060] The dosage error type determination method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, computer equipment 120 may include, but is not limited to, radiotherapy equipment, control terminals or servers communicating with the radiotherapy equipment; the radiotherapy equipment may be conventional radiotherapy equipment or integrated radiotherapy equipment with image scanning capabilities; the control terminal communicating with the radiotherapy equipment may be, but is not limited to, various personal computers, laptops, smartphones, tablets and portable wearable devices, such as smartwatches, smart bracelets, head-mounted devices; the server communicating with the radiotherapy equipment may be a standalone server or a server cluster composed of multiple servers, and may be a local server or a cloud server.

[0061] In one embodiment, such as Figure 2 As shown, a method for determining the type of dose error is provided, which can be applied to... Figure 1 Taking a computer device as an example, the explanation includes the following steps:

[0062] Step 201: Obtain the predicted EPID image of the subject in the current treatment session.

[0063] The predicted EPID image includes a first predicted EPID image and a second predicted EPID image; the first predicted EPID image is obtained based on the initial medical scan image of the subject; the second predicted EPID image is obtained based on the medical scan image of the subject during the current fractional treatment.

[0064] A typical radiotherapy procedure may include the following steps: performing medical imaging scans on the subject to obtain initial medical scan images (including but not limited to CT images, MR images, etc.); delineating the target area and organs at risk based on the initial medical scan images; developing an initial treatment plan based on the initial medical scan images (the initial treatment plan includes multiple fractionated treatments and relevant parameters for each fractionated treatment, i.e., a treatment plan that includes multiple fractionated treatments); quality assurance (QA); and implementation of the fractionated treatments. The initial medical scan images are the medical scan images of the subject that are collected before radiotherapy to develop an initial treatment plan for radiotherapy.

[0065] After obtaining the initial treatment plan, for each treatment session, a first predicted EID image can be obtained based on the treatment plan for each session and the initial medical scan image of the subject. That is, the first predicted EID image is a theoretical EID image characterizing the radiation received by the subject during each treatment session, calculated based on the initial medical scan image of the subject and the radiation dose in the treatment plan. Furthermore, after obtaining the first predicted EID images for each treatment session, these images can be saved so that they can be directly retrieved during subsequent treatment sessions.

[0066] Additionally, it should be noted that when the relevant parameters for each treatment session are consistent, the first preset EID image corresponding to each treatment session can also be the same; that is, when determining the first predicted EID image corresponding to each treatment session based on the initial treatment plan and the initial medical scan image, the first predicted EID image corresponding to any treatment session in the initial treatment plan and the initial medical scan image can also be obtained based on the treatment plan of any treatment session in the initial treatment plan and the initial medical scan image, and the first predicted EID image can be used as the first predicted EID image corresponding to each of the other treatment sessions.

[0067] When implementing fractionated therapy, for the current fractionated therapy, a medical image scan can be performed on the subject to obtain the medical scan image of the subject during the current fractionated therapy. Based on the medical scan image of the current fractionated therapy and the radiation dose applied in the current fractionated therapy, the second predicted EPID image of the subject corresponding to the current fractionated therapy can be calculated. The radiation dose applied in the current fractionated therapy can be obtained from the initial treatment plan. Of course, if the initial treatment plan is updated, the treatment plan for the current fractionated therapy can also be determined based on the latest treatment plan for the subject, and the radiation dose applied in the current fractionated therapy can be further determined.

[0068] Optionally, if the subject has not undergone medical image scanning for the current treatment session, a medical scan image from the previous treatment session can be used as the medical scan image for the current treatment session. That is, if the subject has not undergone medical image scanning for the current treatment session, a recently scanned medical scan image of the subject can be used as the medical scan image for the current treatment session. The recently scanned medical scan image can include a medical scan image from the previous treatment session, the one before that, or a medical scan image collected during a non-treatment session. This application does not specifically limit this, as long as the medical scan image can characterize the subject's recent posture, positioning, and other relevant information.

[0069] Step 202: Obtain the actual EPID image of the subject during the current treatment session.

[0070] For example, during the current fractionation of treatment for the subject, an EPD device can be used to measure the radiation transmitted through the patient image of the subject, obtaining the actual EPD image of the subject during the current fractionation of treatment. This actual EPD image is used to characterize the image on the EPD of the actual radiation dose received by the subject during the current fractionation of treatment after transmission through the patient.

[0071] Step 203: Determine the dosage error type of the current fractionated treatment based on the first predicted EID image, the second predicted EID image, and the actual EID image.

[0072] During fractionated therapy, the patient's posture and positioning may vary due to the time interval between each fraction. Furthermore, the accelerator used to deliver radiation in radiotherapy equipment can also develop errors over long-term use. Therefore, under the influence of various factors, the radiation dose received by the subject during fractionated therapy may deviate from the planned radiation dose. To ensure accurate treatment of the subject, the type of dose deviation must be clearly identified so that the treatment plan can be adjusted accordingly, or the accelerator parameters in the radiotherapy equipment can be adjusted.

[0073] Since the first predicted EPID image is obtained based on the subject's initial treatment plan, which is determined based on the subject's initial medical scan images, if the subject's posture and positioning remain unchanged throughout the treatment process, the predicted EPID image for each treatment session will likely remain consistent. However, during the intervals between treatment sessions, the subject's posture often undergoes subtle or even significant changes; moreover, it is difficult to guarantee that the subject's positioning will be completely consistent each time a treatment session is performed. Therefore, for each treatment session, there will be a deviation between the second predicted EPID image determined based on the subject's medical scan image at the current treatment session and the first predicted EPID image determined based on the initial treatment plan. This deviation can be used to characterize changes in the subject's posture and positioning.

[0074] Furthermore, since the second predicted EPID image of the subject is obtained based on the medical scan image of the subject during the current fractionation treatment, the second predicted EPID image can more accurately characterize the predicted EPID image of the subject; combined with the actual EPID image of the subject during the current fractionation treatment, it is possible to further determine whether there is a deviation in the accelerator of the radiotherapy equipment.

[0075] Based on this, the type of dose error can include at least a first type of dose error and a second type of dose error. The first type of dose error can be used to characterize the dose error caused by different body postures and positions of the subject being tested; the second type of dose error can be used to characterize the dose error caused by different operating parameters of the treatment accelerator for the current fractionated treatment.

[0076] Furthermore, the computer device can determine whether the current dose error type of the fractionated treatment is a type I dose error based on the first predicted EID image and the second predicted EID image of the subject under test; and determine whether the current dose error type of the fractionated treatment is a type II dose error based on the second predicted EID image and the actual EID image of the subject under test.

[0077] It should be noted that the first type of dose error can also be used to characterize dose errors caused by different operating parameters of the treatment accelerator in the current fractionation treatment; the second type of dose error can also be used to characterize dose errors caused by different body postures and positions of the test subject. Based on this, the computer equipment can determine whether the dose error type of the current fractionation treatment is a first type of dose error based on the second predicted EID image and the actual EID image of the test subject; and determine whether the dose error type of the current fractionation treatment is a second type of dose error based on the first predicted EID image and the second predicted EID image of the test subject.

[0078] In the aforementioned method for determining the type of dose error, the computer device acquires a first predicted EID image and a second predicted EID image of the subject during the current fraction of treatment. The first predicted EID image is obtained based on the initial medical scan image of the subject, and the second predicted EID image is obtained based on the medical scan image of the subject during the current fraction of treatment. Next, the actual EID image of the subject during the current fraction of treatment is acquired. Furthermore, the type of dose error for the current fraction of treatment is determined based on the first predicted EID image, the second predicted EID image, and the actual EID image. In other words, in this embodiment, the computer device can determine different types of dose errors for the subject based on predicted EID images and actual EID images obtained under different states. Since the predicted EID images and actual EID images under different states can characterize different states of the subject and the radiotherapy equipment, it is possible to accurately determine what factors caused the dose error, i.e., determine the source of the dose error, thereby obtaining the specific type of dose error and improving the accuracy and rationality of the dose error type determination. Furthermore, since the method proposed in this application can accurately locate the source of dosage error, it can also adjust the error in a timely manner after determining the source of the dosage error, thereby reducing the error and improving the accuracy of fractionated treatment.

[0079] In one embodiment, such as Figure 3 As shown, the computer device determines whether the dose error type of the current fractionated treatment is a type I dose error based on the first predicted EPID image and the second predicted EPID image, which may include:

[0080] Step 301: Using a preset evaluation algorithm, the first predicted EPID image and the second predicted EPID image are compared to obtain the first evaluation result.

[0081] The first evaluation result is used to characterize the similarity between the first predicted EPID image and the second predicted EPID image. The preset evaluation algorithm can be used to quantify the similarity between the two images, thereby obtaining the similarity evaluation result between the two images.

[0082] For example, a computer device can input a first predicted EPID image and a second predicted EPID image into a preset evaluation algorithm to perform a similarity evaluation and obtain the first evaluation result.

[0083] In one implementation, the preset evaluation algorithm can be a gamma pass evaluation algorithm. This algorithm uses a gamma function to compare two images and calculate the gamma pass rate, which is then used to evaluate the degree of similarity between the two images. Accordingly, in this embodiment, the gamma pass evaluation algorithm can be used to compare the first predicted EPID image and the second predicted EPID image to obtain the gamma pass rate, which characterizes the degree of similarity between the two images. Then, this gamma pass rate can be used as the first evaluation result between the first and second predicted EPID images. In other words, in this implementation, the gamma pass rate can be used to characterize the similarity between two images, and the gamma pass rate is used as the first evaluation result.

[0084] The principle of the gamma pass evaluation algorithm is as follows: For each corresponding pixel in the first and second predicted EID images, the corresponding pixel is input into the gamma function to calculate the image gamma value corresponding to that pixel; according to the gamma evaluation criteria, if the image gamma value is less than or equal to 1, it means that the corresponding pixel has passed the evaluation; if the image gamma value is greater than 1, it means that the corresponding pixel has failed the evaluation; then, the ratio of the pixels that have passed the evaluation to the total number of pixels in the EID image is calculated, that is, the quotient of the number of pixels that have passed the evaluation to the total number of pixels in the EID image is calculated, and the quotient is used as the gamma pass rate of the first and second predicted EID images.

[0085] In addition, the gamma function includes multiple preset evaluation parameters. Different combinations of these evaluation parameters can be used to characterize different evaluation conditions. For example, the evaluation parameters may include the dose tolerance and distance tolerance between two pixel values, such as a dose tolerance of 2% and a distance tolerance of 2mm. When the settings of each evaluation parameter are different, the resulting image gamma values ​​between the two pixels will be different, which also indicates that the degree of matching between the two images will be different under different evaluation conditions.

[0086] For example, when the evaluation conditions are a dose tolerance of 2% and a distance tolerance of 2mm, a gamma pass rate of 95% (including or equal to 95%) can be considered to indicate good agreement between the two. It should be noted that the settings for each evaluation parameter in this embodiment are not specifically limited; in practical applications, users can flexibly adjust the values ​​of each evaluation parameter.

[0087] In another implementation, after obtaining the gamma pass rate, a first evaluation result can be further obtained based on the gamma pass rate. For example, the gamma pass rate can be compared with a preset gamma pass rate threshold to obtain a first evaluation result that characterizes whether the first predicted EPID image and the second predicted EPID image match. The first evaluation result can be a specific number, character, string, or a combination thereof. For example, if the gamma pass rate is greater than or equal to the preset gamma pass rate threshold (such as 95% mentioned above), a first evaluation result that characterizes the two images matching can be obtained, such as the character 1. If the gamma pass rate is less than the preset gamma pass rate threshold (such as 95% mentioned above), a first evaluation result that characterizes the two images not matching can be obtained, such as the character 0.

[0088] In this implementation, if the degree of matching between two images reaches a certain threshold, the two images can be considered to be in agreement, and a first evaluation result can be obtained to characterize the matching between the two images.

[0089] Additionally, it should be noted that the gamma evaluation algorithm described above is only an example of one of the preset evaluation algorithms. This preset evaluation algorithm may also include other algorithms used to determine the similarity between two images, such as relative dose deviation, distance to agreement (DTA), etc. Of course, image similarity and other evaluation indicators can also be used to determine the similarity between two images.

[0090] Step 302: Based on the first assessment result, determine whether the current dose error type of the fractionated treatment is a type I dose error.

[0091] The first type of dose error is used to characterize the dose error caused by different body postures and positions of the test subject.

[0092] For example, if the first evaluation result is the similarity between the first predicted EID image and the second predicted EID image (such as the gamma pass rate mentioned above), the similarity can be compared with a first similarity threshold. If the similarity is less than or equal to the first similarity threshold, it indicates that the similarity between the first predicted EID image and the second predicted EID image is low, which in turn indicates that there is a type I dose error in the current fractionated treatment due to the different body posture and positioning of the test subject. Thus, the type of dose error in the current fractionated treatment can be determined to be a type I dose error.

[0093] Conversely, if the first evaluation result indicates that the similarity between the first predicted EID image and the second predicted EID image is greater than the first similarity threshold, it can be determined that the current fractionated treatment does not have a type I dose error caused by the different body posture and positioning of the subject, that is, it can be determined that the dose error type of the current fractionated treatment is not a type I dose error.

[0094] For example, if the first evaluation result is a number, character, or combination thereof characterizing whether the first predicted EID image and the second predicted EID image are similar or match, it can be determined whether the first evaluation result is a preset evaluation result. If the first evaluation result is a preset evaluation result, it can be determined that the dosage error type of the current fractionated treatment is a type I dosage error. For example, if the first evaluation result is the character 0, it can be indicated that the first predicted EID image and the second predicted EID image do not match, thus indicating that there is a dosage error in the current fractionated treatment, and the dosage error type is a type I dosage error caused by the different body posture and positioning of the test subject.

[0095] In this embodiment, the computer device compares the first predicted EID image and the second predicted EID image using a preset evaluation algorithm to obtain a first evaluation result; and if the first evaluation result indicates that the similarity between the first predicted EID image and the second predicted EID image is less than or equal to a first similarity threshold, the dosage error type of the current fractionated treatment is determined to be a first type of dosage error, which is used to characterize the different body posture and positioning of the subject; thereby realizing the detection and identification of the first type of dosage error and improving the accuracy of the determination of the dosage error type.

[0096] In one embodiment, such as Figure 4 As shown, the computer device described above determines whether the dose error type of the current fractionated treatment is a type II dose error based on the second predicted EID image and the actual EID image, which may include:

[0097] Step 401: Using a preset evaluation algorithm, the second predicted EID image and the actual EID image are compared to obtain the second evaluation result.

[0098] The second evaluation result is used to characterize the similarity between the second predicted EID image and the actual EID image.

[0099] Referring to the above embodiments, the computer device can input the second predicted EID image and the actual EID image into a preset evaluation algorithm for similarity evaluation to obtain the second evaluation result. The method for determining the second evaluation result and the preset evaluation algorithm can be referred to the above. Figure 3 The relevant descriptions in the illustrated embodiments will not be repeated here.

[0100] Step 402: Based on the second assessment results, determine whether the current dose error type of the fractionated treatment is a type II dose error.

[0101] The second type of dose error is used to characterize the dose error caused by the different operating parameters of the treatment accelerator for the current fractionation treatment.

[0102] For example, when the second type of dose error is the similarity between the second predicted EID image and the actual EID image, the similarity can be compared with a second similarity threshold. If the similarity is less than or equal to the second similarity threshold, it indicates that the similarity between the second predicted EID image and the actual EID image is low, which in turn indicates that there is a second type of dose error in the current fractionation treatment due to different operating parameters of the treatment accelerator. Thus, the dose error type of the current fractionation treatment can be determined to be the second type of dose error.

[0103] Conversely, if the second evaluation result indicates that the similarity between the second predicted EID image and the actual EID image is greater than the second similarity threshold, it can be determined that the current fractionated treatment does not have a type II dose error caused by different operating parameters of the treatment accelerator, that is, it can be determined that the dose error type of the current fractionated treatment is not a type II dose error.

[0104] Optionally, the second similarity threshold may be the same as or different from the first similarity threshold mentioned above, and this application embodiment does not specifically limit this.

[0105] Of course, the second evaluation result can also be in other forms besides similarity, such as an evaluation result used to characterize whether the second predicted EID image is similar to or matches the actual EID image. This evaluation result can be represented by numbers, characters or a combination thereof. Accordingly, the method for determining the dosage error type of the current fractionated treatment based on the second evaluation result can also be adaptively set according to the specific form of the second evaluation result.

[0106] In this embodiment, the computer device compares the second predicted EID image and the actual EID image using a preset evaluation algorithm to obtain a second evaluation result. If the second evaluation result indicates that the similarity between the second predicted EID image and the actual EID image is less than or equal to a second similarity threshold, the dosage error type of the current fractionated treatment is determined to be a second type of dosage error, which is used to characterize the different operating parameters of the treatment accelerator for the current fractionated treatment. This enables the detection and identification of the second type of dosage error and improves the accuracy of the dosage error type judgment.

[0107] In one embodiment, if the type of dose error in the current fractionated treatment is determined, the current fractionated treatment or subsequent fractionated treatments can be optimized and adjusted based on the determined specific type of dose error; based on the above embodiment, such as Figure 5 As shown, the above method also includes:

[0108] Step 501: Based on the current dose error type of fractionated treatment and the preset error adjustment strategy, determine the target error adjustment strategy corresponding to the dose error type of the current fractionated treatment.

[0109] The preset error adjustment strategy includes error adjustment strategies corresponding to different types of dose error. For example, it may include a first error adjustment strategy corresponding to a first type of dose error and a second error adjustment strategy corresponding to a second type of dose error. For instance, when the first type of dose error represents a dose error caused by different body postures and positioning of the test subject, and the second type of dose error represents a dose error caused by different operating parameters of the treatment accelerator used in the current fractionated treatment, the first error adjustment strategy may include whether to continue treatment or modify the treatment plan; the second error adjustment strategy may include whether to interrupt treatment or adjust accelerator parameters.

[0110] Based on this, in this embodiment, when the dosage error type of the current fractionated treatment is determined, a target error adjustment strategy corresponding to the dosage error type of the current fractionated treatment can be determined from the preset error adjustment strategies according to the dosage error type of the current fractionated treatment.

[0111] Step 502: Perform treatment on the subject in stages based on the target error adjustment strategy.

[0112] After determining the target error adjustment strategy, the current fractionation treatment, subsequent treatment plan, or operating parameters of the treatment accelerator in the radiotherapy equipment can be adaptively adjusted according to the target error adjustment strategy to achieve precise fractionation treatment of the subject.

[0113] In this embodiment, after determining the type of dose error in the current fractionated treatment, the computer device can further determine a target error adjustment strategy corresponding to the type of dose error in the current fractionated treatment and a preset error adjustment strategy. Based on the target error adjustment strategy, the device can then perform fractionated treatment on the subject under test. That is, this embodiment can not only accurately locate the source of the dose error and clarify the type of dose error, but also further perform targeted dose error adjustment based on the precise type of dose error. This enables adaptive adjustment of the treatment plan according to the different states of the subject under test and the different states of the radiotherapy equipment, achieving precise treatment of the subject under test and reducing unnecessary radiation exposure received by the subject under test.

[0114] In one embodiment, a method is also provided for a computer device to acquire a predicted EPID image of the subject in the current treatment session; based on the above embodiments, such as Figure 6 As shown, step 201 above may include:

[0115] Step 601: Obtain the first and second medical scan images of the subject in the current treatment session, as well as the initial treatment plan for the subject.

[0116] The first medical scan image is the initial medical scan image of the subject to be tested, used to formulate the initial treatment plan; the second medical scan image is the medical scan image of the subject to be tested, collected before the current fractional treatment.

[0117] In other words, the initial medical scan image of the subject taken before the initial treatment plan is formulated is the first medical scan image, which is used to formulate the initial treatment plan. This initial treatment plan includes the number of treatment sessions and the treatment plan for each session. The treatment plan for each session may include relevant treatment parameters. While the subject is undergoing treatment based on this initial plan, another medical scan image can be acquired, and this newly acquired image can be used as the second medical scan image for the current session. Compared to the first medical scan image, this second medical scan image can more accurately characterize the subject's posture and positioning during the current session.

[0118] Since the first medical scan image of the subject is the medical scan image of the subject before the initial treatment plan, the computer device can obtain the first medical scan image of the subject from the database or the medical image storage system. In addition, since the second medical scan image of the subject is the medical scan image of the subject acquired before the current fractional treatment, the computer device can obtain the second medical scan image of the subject from the medical imaging scanning device (such as an imaging scanning simulator) or an integrated radiotherapy device with imaging scanning function. Optionally, if the medical imaging device or the integrated radiotherapy device with imaging scanning function sends the second medical scan image of the subject to the database or the medical image storage system, the computer device can also obtain the second medical scan image of the subject from the database or the medical image storage system.

[0119] In addition, the initial treatment plan for the subject of the test can be obtained from a database, a server, or the computer device's local storage.

[0120] Step 602: Input the first medical scan image and the initial treatment plan into the preset EPID algorithm to obtain the first predicted EPID image of the subject in the current treatment session.

[0121] Step 603: Input the second medical scan image and the initial treatment plan into the preset EPID algorithm to obtain the second predicted EPID image of the subject in the current treatment session.

[0122] The preset EPID algorithm is used to convert medical scan images into predicted EPID images, which are used to characterize the dose distribution of the object under a certain radiation dose.

[0123] For example, when a computer device acquires a first medical scan image of the subject before the initial treatment plan and a second medical scan image acquired before the current treatment session, it can input the first medical scan image and the initial treatment plan, and the second medical scan image and the initial treatment plan, respectively, into a preset EPID algorithm for image conversion processing, thereby obtaining a first predicted EPID image corresponding to the first medical scan image and a second predicted EPID image corresponding to the second medical scan image. That is, it obtains the first predicted EPID image of the subject under the initial body posture and initial positioning corresponding to the initial treatment plan, and the second predicted EPID image of the subject under the current body posture and current positioning corresponding to the current treatment session.

[0124] In this embodiment, when the computer device acquires the predicted EID image of the subject in the current treatment session, it acquires the first medical scan image of the subject before the initial treatment plan, the second medical scan image of the subject acquired before the current treatment session, and the initial treatment plan. Then, the first medical scan image and the initial treatment plan, as well as the second medical scan image and the initial treatment plan, are respectively input into a preset EID algorithm to obtain the first predicted EID image and the second predicted EID image of the subject in the current treatment session. That is, by using the method of inputting the medical scan image and the treatment plan into the preset EID algorithm for image conversion processing, the first predicted EID image and the second predicted EID image of the current treatment session can be obtained respectively, which can improve the accuracy and efficiency of acquiring the first predicted EID image and the second predicted EID image, thereby improving the efficiency of dose error type judgment.

[0125] In one embodiment, based on the above embodiments, the computer device, after acquiring the first medical scan image, the second medical scan image, and the actual EPID image of the current fractionated treatment of the subject, can further determine the total dose received by the subject after the current fractionated treatment, and determine whether the dose received by the subject is excessive or insufficient, providing guidance for subsequent treatment. Figure 7 As shown, the above method may further include:

[0126] Step 701: Based on the first medical scan image, obtain the theoretical three-dimensional dose reconstruction result of the object to be tested.

[0127] For example, a computer device can input the first medical scan image into a preset reconstruction algorithm model to perform three-dimensional dose reconstruction and obtain the theoretical three-dimensional dose reconstruction result of the test object. The theoretical three-dimensional dose reconstruction result is used to characterize the theoretical dose distribution received by the test object after the current fractional treatment. The theoretical dose distribution may include the theoretical dose values ​​corresponding to different treatment sites of the test object.

[0128] Step 702: Perform three-dimensional dose reconstruction based on the second medical scan image and the actual EPID image of the current fractionated treatment to obtain the actual three-dimensional dose reconstruction result of the subject.

[0129] For example, the computer device can input the second medical scan image and the actual EPID image acquired during the current fractionated treatment into a preset reconstruction algorithm model to perform three-dimensional dose reconstruction, thereby obtaining the actual three-dimensional dose reconstruction result of the test object; the actual three-dimensional dose reconstruction result is used to characterize the actual dose distribution received by the test object after the current fractionated treatment, and the actual dose distribution may include the actual dose values ​​corresponding to different treatment sites of the test object.

[0130] Step 703: Compare and analyze the theoretical three-dimensional dose reconstruction results and the actual three-dimensional dose reconstruction results to determine the dose analysis results of the object to be tested.

[0131] The dose analysis results of the test subject may include at least one of the following: the analysis results of overdose or underdose corresponding to different treatment sites of the test subject, and the analysis results of overdose or underdose of the total dose received by the test subject.

[0132] For example, the computer device can compare and analyze the theoretical dose values ​​of each treatment site in the theoretical three-dimensional dose reconstruction results with the actual dose values ​​of each treatment site in the actual three-dimensional dose reconstruction results to obtain the dose analysis results corresponding to each treatment site of the test subject; it can also determine the theoretical total dose value of the test subject based on the theoretical three-dimensional dose reconstruction results, and determine the actual total dose value of the test subject based on the actual three-dimensional dose reconstruction results, and then determine the relationship between the theoretical total dose value and the actual total dose value to determine whether there is an analysis result of overdose or underdose of the total dose received by the test subject.

[0133] In this embodiment, the computer device acquires the theoretical three-dimensional dose reconstruction result of the test subject based on the first medical scan image; and performs three-dimensional dose reconstruction based on the second medical scan image and the actual EPID image of the current fractionated treatment to obtain the actual three-dimensional dose reconstruction result of the test subject; then, the theoretical three-dimensional dose reconstruction result and the actual three-dimensional dose reconstruction result are compared and analyzed to determine the dose analysis result of the test subject; the dose analysis result is used to characterize whether the dose received by the test subject is excessive or insufficient, thereby providing data support for subsequent treatment, so as to monitor the treatment process and adaptively adjust the subsequent treatment plan according to the actual treatment situation, thereby improving the accuracy of fractionated treatment.

[0134] In one embodiment, a method for determining the type of dose error is provided, which is applied to an integrated radiotherapy device, such as... Figure 8 As shown, it includes the following steps:

[0135] Step 801: Obtain the first medical scan image of the subject to be tested for formulating an initial treatment plan from the medical image storage system, and input the first medical scan image and the current treatment plan into the preset EPID algorithm to obtain the first predicted EPID image of the subject to be tested in the current treatment.

[0136] The current treatment plan for fractionated treatment can be obtained from the initial treatment plan or from the latest treatment plan; the latest treatment plan is the updated treatment plan based on the initial treatment plan.

[0137] Step 802: Control the integrated radiotherapy device to perform a medical scan on the subject to be tested, obtain a second medical scan image of the subject to be tested during the current fractionation treatment, and input the second medical scan image and the treatment plan of the current fractionation treatment into the preset EPID algorithm to obtain a second predicted EPID image of the subject to be tested during the current fractionation treatment.

[0138] Step 803: Control the integrated radiotherapy device to perform the current fraction of treatment on the subject and acquire the actual EPID image of the subject during the current fraction of treatment.

[0139] Step 804a: Using a preset evaluation algorithm, the first predicted EPID image and the second predicted EPID image are compared to obtain the first evaluation result.

[0140] Step 805a: Determine whether the first evaluation result indicates that the similarity between the first predicted EPID image and the second predicted EPID image is less than or equal to the first similarity threshold; if yes, proceed to step 806a; if no, proceed to step 809.

[0141] Step 806a: Determine the dosage error type of the current fractionated treatment as Type I dosage error; Type I dosage error is used to characterize dosage errors caused by differences in the body posture and positioning of the test subject. (Reference) Figure 9 As shown.

[0142] Step 807a: Determine the target error adjustment strategy corresponding to the first type of dose error from the preset error adjustment strategies. Then proceed to step 808.

[0143] Step 804b: Using a preset evaluation algorithm, the second predicted EPID image and the actual EPID image are compared to obtain the second evaluation result.

[0144] Step 805b: Determine whether the second evaluation result indicates that the similarity between the second predicted EID image and the actual EID image is less than or equal to the second similarity threshold; if yes, proceed to step 806b; if no, proceed to step 809.

[0145] Step 806b: Determine the dose error type of the current fractionation treatment as Type II dose error; Type II dose error is used to characterize the dose error caused by different operating parameters of the treatment accelerator in the current fractionation treatment. (Reference) Figure 10 As shown.

[0146] Step 807b: Determine the target error adjustment strategy corresponding to the second type of dose error from the preset error adjustment strategies. Then proceed to step 808.

[0147] Step 808: Based on the target error adjustment strategy, the subject is treated in multiple sessions. Then, step 810 is executed.

[0148] Step 809: Execute the current fractionated treatment based on the current fractionated treatment plan. Then proceed to step 810.

[0149] Step 810: Based on the first medical scan image, obtain the theoretical three-dimensional dose reconstruction result of the object to be tested.

[0150] Step 811: Perform three-dimensional dose reconstruction based on the second medical scan image and the actual EPID image of the current fractionated treatment to obtain the actual three-dimensional dose reconstruction result of the subject.

[0151] Step 812: Compare and analyze the theoretical three-dimensional dose reconstruction results with the actual three-dimensional dose reconstruction results to determine the dose analysis results for the target object. (Reference) Figure 11 As shown.

[0152] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0153] Based on the same inventive concept, this application also provides a dose error type determination apparatus for implementing the dose error type determination method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more dose error type determination apparatus embodiments provided below can be found in the limitations of the dose error type determination method described above, and will not be repeated here.

[0154] In one embodiment, such as Figure 12 As shown, a dose error type determination device is provided, comprising: a first acquisition module 1201, a second acquisition module 1202, and a first determination module 1203, wherein:

[0155] The first acquisition module 1201 is used to acquire the predicted EID image of the subject in the current treatment session; the predicted EID image includes a first predicted EID image and a second predicted EID image; the first predicted EID image is obtained based on the initial medical scan image of the subject; the second predicted EID image is obtained based on the medical scan image of the subject in the current treatment session.

[0156] The second acquisition module 1202 is used to acquire the actual EPID image of the subject in the current treatment session.

[0157] The first determining module 1203 is used to determine the dosage error type of the current fractionated treatment based on the first predicted EID image, the second predicted EID image and the actual EID image.

[0158] In one embodiment, the dose error type includes a first type of dose error and a second type of dose error; the first determining module 1203 includes a first determining submodule and a second determining submodule; wherein, the first determining submodule is used to determine whether the dose error type of the current fractionated treatment is a first type of dose error based on the first predicted EID image and the second predicted EID image; the second determining submodule is used to determine whether the dose error type of the current fractionated treatment is a second type of dose error based on the second predicted EID image and the actual EID image.

[0159] In one embodiment, the first determining submodule includes a first comparison unit and a first determining unit; wherein, the first comparison unit is used to compare the first predicted EID image and the second predicted EID image using a preset evaluation algorithm to obtain a first evaluation result; the first determining unit is used to determine the dosage error type of the current fractionated treatment as a first type of dosage error based on the first evaluation result; wherein, the first evaluation result is used to characterize the similarity between the first predicted EID image and the second predicted EID image; and the first type of dosage error is also used to characterize the dosage error caused by the different body posture and positioning of the subject.

[0160] In one embodiment, the second determining submodule includes a second comparison unit and a second determining unit; wherein the second comparison unit is used to compare the second predicted EID image and the actual EID image using a preset evaluation algorithm to obtain a second evaluation result; the second determining unit is used to determine the dose error type of the current fractionated treatment as a second type of dose error based on the second evaluation result; wherein the second evaluation result is used to characterize the similarity between the second predicted EID image and the actual EID image; and the second type of dose error is also used to characterize the dose error caused by the different operating parameters of the treatment accelerator in the current fractionated treatment.

[0161] In one embodiment, the device further includes a second determining module and a fractionated treatment module; wherein, the second determining module is used to determine a target error adjustment strategy corresponding to the dose error type of the current fractionated treatment based on the dose error type of the current fractionated treatment and a preset error adjustment strategy; the preset error adjustment strategy includes error adjustment strategies corresponding to different dose error types; the fractionated treatment module is used to perform fractionated treatment on the test subject based on the target error adjustment strategy.

[0162] In one embodiment, the first acquisition module 1201 includes an acquisition submodule and a processing submodule. The acquisition submodule is used to acquire a first medical scan image and a second medical scan image of the subject in the current treatment session, as well as the initial treatment plan of the subject. The first medical scan image is the initial medical scan image of the subject used to formulate the initial treatment plan. The second medical scan image is the medical scan image of the subject acquired before the current treatment session. The processing submodule is used to input the first medical scan image and the initial treatment plan into a preset EPID algorithm to obtain a first predicted EPID image of the subject in the current treatment session. The processing submodule is used to input the second medical scan image and the initial treatment plan into the preset EPID algorithm to obtain a second predicted EPID image of the subject in the current treatment session.

[0163] In one embodiment, the device further includes a third acquisition module, a reconstruction module, and a third determination module; wherein, the third acquisition module is used to acquire the theoretical three-dimensional dose reconstruction result of the test object based on the first medical scan image; the reconstruction module is used to perform three-dimensional dose reconstruction based on the second medical scan image and the actual EPID image of the current fractionated treatment to obtain the actual three-dimensional dose reconstruction result of the test object; the third determination module is used to compare and analyze the theoretical three-dimensional dose reconstruction result and the actual three-dimensional dose reconstruction result to determine the dose analysis result of the test object.

[0164] The modules in the aforementioned dose error type determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0165] In one embodiment, a computer device is provided. This computer device may be a radiotherapy device, or a control terminal or server communicatively connected to the radiotherapy device. Its internal structure diagram may be as follows: Figure 13As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for determining the type of dose error. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0166] Those skilled in the art will understand that Figure 13 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0167] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the dose error type determination method in any of the above embodiments.

[0168] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the dose error type determination method in any of the above embodiments.

[0169] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the dose error type determination method in any of the above embodiments.

[0170] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0171] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based reconstruction result databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0172] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0173] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining the type of dose error, characterized in that, The method includes: Acquire a predicted EID image of the subject in the current treatment session; the predicted EID image includes a first predicted EID image and a second predicted EID image; the first predicted EID image is obtained based on the initial medical scan image of the subject; the second predicted EID image is obtained based on the medical scan image of the subject in the current treatment session; Acquire the actual EPID image of the subject during the current treatment session; Based on the first predicted EID image, the second predicted EID image, and the actual EID image, the dose error type of the current fractionated treatment is determined; the dose error type includes a first type of dose error and a second type of dose error, the first type of dose error is used to characterize the dose error caused by different body postures and positions of the subject, and the second type of dose error is used to characterize the dose error caused by different operating parameters of the treatment accelerator in the current fractionated treatment.

2. The method according to claim 1, characterized in that, The step of determining the dose error type of the current fractionated treatment based on the first predicted EID image, the second predicted EID image, and the actual EID image includes: Based on the first predicted EID image and the second predicted EID image, determine whether the dose error type of the current fractionated treatment is a type 1 dose error; Based on the second predicted EID image and the actual EID image, determine whether the dose error type of the current fractionated treatment is a type II dose error.

3. The method according to claim 2, characterized in that, The step of determining whether the dosage error type of the current fractionated treatment is a type I dosage error based on the first predicted EID image and the second predicted EID image includes: A preset evaluation algorithm is used to compare the first predicted EID image and the second predicted EID image to obtain a first evaluation result; Based on the first evaluation result, determine whether the dosage error type of the current fractionated treatment is a type I dosage error.

4. The method according to claim 2 or 3, characterized in that, The step of determining whether the dose error type of the current fractionated treatment is a type II dose error based on the second predicted EID image and the actual EID image includes: A preset evaluation algorithm is used to compare the second predicted EID image and the actual EID image to obtain a second evaluation result; Based on the second assessment result, determine whether the current dose error type of the fractionated treatment is a type II dose error.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Based on the current dose error type of the fractionated treatment and the preset error adjustment strategy, a target error adjustment strategy corresponding to the dose error type of the current fractionated treatment is determined; the preset error adjustment strategy includes error adjustment strategies corresponding to different dose error types. The target object is treated in stages based on the target error adjustment strategy.

6. The method according to any one of claims 1 to 4, characterized in that, The acquisition of the predicted EPID image of the subject in the current treatment session includes: The system acquires a first medical scan image and a second medical scan image of the subject during the current fractionated treatment, as well as the initial treatment plan for the subject; the first medical scan image is the initial medical scan image of the subject used to formulate the initial treatment plan; the second medical scan image is the medical scan image of the subject acquired before the current fractionated treatment. The first medical scan image and the initial treatment plan are input into a preset EPID algorithm to obtain the first predicted EPID image of the subject in the current treatment session; The second medical scan image and the initial treatment plan are input into the preset EPID algorithm to obtain the second predicted EPID image of the subject in the current treatment session.

7. The method according to claim 6, characterized in that, The method further includes: Based on the first medical scan image, the theoretical three-dimensional dose reconstruction result of the object under test is obtained; Three-dimensional dose reconstruction is performed based on the second medical scan image and the actual EPID image of the current fractionated treatment to obtain the actual three-dimensional dose reconstruction result of the subject under test; The theoretical three-dimensional dose reconstruction results and the actual three-dimensional dose reconstruction results are compared and analyzed to determine the dose analysis results of the test object.

8. A device for determining the type of dose error, characterized in that, The device includes: The first acquisition module is used to acquire the predicted EID image of the subject in the current treatment session; the predicted EID image includes a first predicted EID image and a second predicted EID image; the first predicted EID image is obtained based on the initial medical scan image of the subject; the second predicted EID image is obtained based on the medical scan image of the subject in the current treatment session. The second acquisition module is used to acquire the actual EPID image of the subject under test during the current fractionated treatment. The first determining module is used to determine the dose error type of the current fractionated treatment based on the first predicted EID image, the second predicted EID image, and the actual EID image; the dose error type includes a first type of dose error and a second type of dose error, the first type of dose error is used to characterize the dose error caused by different body postures and positions of the subject under test, and the second type of dose error is used to characterize the dose error caused by different operating parameters of the treatment accelerator in the current fractionated treatment.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images