Medical image-based QA evaluation method, system, and medical equipment

Abstract

The present invention provides a QA (Quality Assurance) evaluation method, system and medical equipment based on medical images. The QA evaluation method includes the following steps: obtaining a medical reference image and a medical comparison image; normalizing the medical comparison image with the medical reference image as a reference according to a preset normalization evaluation strategy; obtaining evaluation parameter information based on the medical reference image and the normalized medical comparison image; and obtaining an evaluation result based on the evaluation parameter information. The QA evaluation method, system and medical equipment for medical images provided by the present invention can avoid the randomness of image point selection and can achieve more accurate evaluation. Furthermore, it can be used for dose verification before radiotherapy to ensure that tumors or abnormalities receive the prescribed dose while surrounding normal tissues are not damaged; and it can also be used for quantitative evaluation of the treatment effect of patients after treatment, so that doctors can adjust the patient's treatment plan at any time.

Description

Technical Field

[0001] The present invention relates to the field of medical verification, and in particular to a QA (Quality Assurance) evaluation method, system and medical equipment based on medical images. Background Art

[0002] In radiotherapy, due to the complexity and irregularity of target volumes, Intensity Modulated Radiotherapy (IMRT) and Volumetric Modulated ARC Therapy (VMAT) have become the most commonly used treatment techniques for tumor radiotherapy. However, during the execution of the plan, potential mechanical system motion accuracy, dose delivery instability, and the actual placement of the multi-leaf collimator (MLC) affect the patient's treatment outcome. Therefore, pre-treatment dose verification and post-treatment evaluation and confirmation of patient treatment outcomes are necessary.

[0003] Using an electronic portal imaging device (EPID) to measure portal imaging data before and during treatment, pre-treatment dose verification and post-treatment analysis of treatment outcomes can be performed. Generally, pre-treatment dose verification is referred to as pre-treatment verification, while post-treatment treatment outcome assessment, which can be analyzed offline, is referred to as invivo verification. Quality assurance (QA) evaluations for these two modalities typically use conventional methods such as dose deviation (DD), distance to agreement (DTA), or gamma analysis based on a specific point in the dose image, such as the maximum value, a given value, and / or a selected point in the image. While these methods can meet the needs of treatment outcome analysis to a certain extent, due to the high degree of randomness in this selection process, they fail to reflect the true image state. For more detailed comparisons, such as comparing the impact of different angles in VMAT technology and highlighting the dose impact of specific regions of interest (ROIs) in invivo analysis, these existing evaluation methods are insufficient.

[0004] Therefore, how to provide a QA evaluation method based on medical images to overcome the above-mentioned defects in the existing technology has become one of the technical problems that those skilled in the art need to solve urgently.

[0005] It should be noted that the information disclosed in the background technology section of the invention is only intended to deepen the understanding of the general background technology of the invention, and should not be regarded as an admission or any form of implication that the information constitutes prior art already known to those skilled in the art. Summary of the Invention

[0006] The purpose of the present invention is to address the above-mentioned defects in the prior art and propose a QA evaluation method, system, medical device and storage medium based on medical images to effectively avoid the randomness of point selection at locations with large dose gradients and facilitate doctors to quantitatively analyze the treatment effect of specific ROIs.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: A QA evaluation method based on medical images, comprising:

[0008] acquiring medical reference images and medical comparison images;

[0009] Normalizing the medical comparison image based on a preset normalization evaluation strategy and taking the medical reference image as a reference;

[0010] acquiring evaluation parameter information according to the medical reference image and the normalized medical comparison image;

[0011] An evaluation result is obtained according to the evaluation parameter information.

[0012] Optionally, the medical reference image and the medical comparison image are both portal images; the medical reference image includes a dose calculation image, and the medical comparison image includes a dose measurement image.

[0013] Optionally, the method for normalizing the medical comparison image according to a preset normalization evaluation strategy and taking the medical reference image as a reference includes:

[0014] Obtaining a normalized reference dose value of the medical reference image and a normalized comparative dose value of the medical comparison image according to a preset isodose line normalization strategy or a preset region of interest normalization strategy;

[0015] The medical comparison image is normalized according to a ratio of the normalized reference dose value to the normalized comparison dose value.

[0016] Optionally, the method for obtaining the normalized reference dose value of the medical reference image and the normalized comparative dose value of the medical comparison image according to a preset isodose line normalization strategy includes:

[0017] determining a percentage isodose line according to the dose gradient information of the medical reference image or the dose gradient information of the medical comparison image;

[0018] Counting a first average value of the medical reference image within the percentage isodose line range, and using the first average value as the normalized reference dose value;

[0019] A second average value of the medical comparison image within the percentage isodose line range is calculated, and the second average value is used as the normalized comparison dose value.

[0020] Optionally, the method for determining percentage isodose lines based on the dose gradient information of the medical reference image or the dose gradient information of the medical comparison image includes:

[0021] According to the dose gradient information of the medical reference image or the dose gradient information of the medical comparison image, a percentage isodose line of the maximum value of the entire dose field of the medical reference image or the medical comparison image is selected as the percentage isodose line.

[0022] Optionally, the method for obtaining the normalized reference dose value of the medical reference image and the normalized comparative dose value of the medical comparison image according to a preset region of interest normalization strategy includes:

[0023] Determine at least one region of interest based on a preset evaluation region selection factor;

[0024] Calculating the dose value of the medical reference image according to the volume dose correspondence relationship corresponding to the region of interest to obtain the normalized reference dose value;

[0025] The dose value of the medical comparison image is calculated according to the volume dose correspondence relationship corresponding to the region of interest to obtain the normalized comparison dose value.

[0026] Optionally, acquiring the medical reference image and the medical comparison image includes:

[0027] Acquiring dose information of a plurality of reference points on the medical reference image, as well as three-dimensional spatial position information and angle information of the reference points;

[0028] Dose information of a plurality of evaluation points on the medical comparison image, as well as three-dimensional spatial position information and angle information of the evaluation points are obtained.

[0029] Optionally, the evaluation parameter information includes:

[0030] The dose difference between the reference point on the medical reference image and the evaluation point on the normalized medical comparison image, the distance between the evaluation point and the reference point in three-dimensional space, and the angular deviation between the evaluation point and the reference point.

[0031] Optionally, the method for obtaining the evaluation result according to the evaluation parameter information includes:

[0032] The evaluation result is obtained by using the Gamma evaluation method according to the dose difference between the reference point on the medical reference image and the evaluation point on the normalized medical comparison image, the distance between the evaluation point and the reference point in three-dimensional space, and the angular deviation between the evaluation point and the reference point.

[0033] In order to achieve the above object, the present invention further provides a QA evaluation system based on medical images, the QA evaluation system comprising a portal imaging device and an image evaluation device that are communicatively connected;

[0034] The portal imaging device is configured to: acquire a medical comparison image;

[0035] The image evaluation device is configured to: obtain an evaluation result of the medical comparison image based on the medical reference image and the medical comparison image;

[0036] The image evaluation device includes an image normalization module, a parameter information acquisition module and an evaluation result acquisition module;

[0037] The image normalization module is configured to: normalize the medical comparison image based on a preset normalization evaluation strategy with the medical reference image as a reference; wherein the preset normalization evaluation strategy includes a preset isodose line normalization strategy or a preset region of interest normalization strategy;

[0038] The parameter information acquisition module is configured to: acquire evaluation parameter information according to the medical reference image and the normalized medical comparison image;

[0039] The evaluation result acquisition module is configured to acquire the evaluation result according to the evaluation parameter information.

[0040] To achieve the above-mentioned object, the present invention further provides a medical device, comprising a radiotherapy device, a portal imaging device, and an electronic device connected in communication, wherein the electronic device comprises a memory and a processor;

[0041] The radiotherapy apparatus is configured to: generate a radiation beam;

[0042] The portal imaging device is configured to: acquire a medical comparison image based on the radiation beam;

[0043] The electronic device is configured to: obtain an evaluation result of the medical comparison image based on the medical reference image and the medical comparison image;

[0044] The processor is adapted to implement various instructions, the memory is adapted to store a plurality of instructions, and the instructions are adapted to be loaded by the processor to execute the following steps to obtain an evaluation result of the medical comparison image:

[0045] Normalizing the medical comparison image with the medical reference image as a reference according to a preset normalization evaluation strategy; wherein the preset normalization evaluation strategy includes a preset isodose line normalization strategy or a preset region of interest normalization strategy;

[0046] acquiring evaluation parameter information according to the medical reference image and the normalized medical comparison image;

[0047] An evaluation result is obtained according to the evaluation parameter information.

[0048] In order to achieve the above-mentioned objectives, the present invention also provides a computer-readable storage medium, on which computer-executable instructions are stored. When the computer-executable instructions are executed, the steps of any one of the above-mentioned medical image-based QA evaluation methods are implemented.

[0049] Compared with the existing technology, the medical image-based QA evaluation method, system, medical device and storage medium provided by the present invention have the following beneficial effects:

[0050] The medical image-based QA evaluation method provided by the present invention includes obtaining a medical reference image and a medical comparison image; normalizing the medical comparison image with the medical reference image as a reference according to a preset normalization evaluation strategy; obtaining evaluation parameter information based on the medical reference image and the normalized medical comparison image; and obtaining an evaluation result based on the evaluation parameter information. Thus configured, the medical image-based QA evaluation method, system, medical device, and storage medium provided by the present invention can avoid the randomness of image point selection, thereby effectively reflecting the true situation of the image and achieving a more accurate evaluation. Furthermore, the medical image-based QA evaluation method, system, and medical device provided by the present invention can be used for dose verification before radiotherapy to ensure that tumors or abnormalities receive the prescribed dose while surrounding normal tissues are not damaged; and can also be used for quantitative evaluation of the treatment effect on patients after treatment, making it convenient for doctors to adjust the patient's treatment plan at any time.

[0051] Furthermore, the medical image-based QA evaluation method provided by the present invention determines percentage isodose lines according to a preset isodose line normalization strategy based on the dose gradient information of the medical reference image or the dose gradient information of the medical comparison image; calculates a first average value of the medical reference image within the percentage isodose line range, and uses the first average value as the normalized reference dose value; calculates a second average value of the medical comparison image within the percentage isodose line range, and uses the second average value as the normalized comparison dose value. With such a configuration, the medical image-based QA evaluation method, system, medical device, and storage medium provided by the present invention adopt an isodose line-based normalization method based on statistical laws, thereby avoiding the randomness of point selection in high-dose gradient areas, avoiding repeated attempts to select points, and reducing the adverse effects of dose jitter on evaluation (analysis) results. It can fully reflect the true situation of the image and achieve a more accurate evaluation.

[0052] Furthermore, the medical image-based QA evaluation method provided by the present invention utilizes a preset region of interest normalization strategy: determining at least one region of interest based on a preset evaluation region selection factor; calculating the dose value of the medical reference image based on the volume dose correspondence corresponding to the region of interest to obtain the normalized reference dose value; and calculating the dose value of the medical comparison image to obtain the normalized comparison dose value. Thus configured, the medical image-based QA evaluation method, system, medical device, and storage medium provided by the present invention overcome the existing art's inability to effectively analyze the dose impact of specific regions of interest. This allows physicians to quantitatively analyze the treatment effects of specific regions of interest, assess the treatment effects on patients' organs at risk and target areas, and facilitate the adjustment of patient treatment plans at any time.

[0053] Furthermore, the medical image-based QA evaluation method provided by the present invention utilizes a gamma evaluation method to obtain an evaluation result based on the dose difference between a reference point on the medical reference image and an evaluation point on the normalized medical comparison image, the distance between the evaluation point and the reference point in three-dimensional space, and the angular deviation between the evaluation point and the reference point. Thus configured, the medical image-based QA evaluation method, system, medical device, and storage medium provided by the present invention enhance the contribution of angular dimensions to the overall algorithm, enabling analysis of the machine's actual performance at different angles. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram of a flow chart of a medical image-based QA evaluation method provided by one embodiment of the present invention;

[0055] Figure 2 A schematic diagram of a region of interest normalization strategy provided by one embodiment of the present invention;

[0056] Figure 3 A schematic diagram of the structure of a medical image-based QA evaluation system provided by one embodiment of the present invention;

[0057] Figure 4 A schematic structural diagram of a medical device provided in one embodiment of the present invention;

[0058] The description of the accompanying drawings is as follows:

[0059] 100 - portal imaging device, 200 - image evaluation device, 210 - image normalization module, 220 - parameter information acquisition module, 230 - evaluation result acquisition module;

[0060] 300 - Radiotherapy device, 310 - Gantry, 320 - Radiation module, 330 - Treatment bed, 400 - Electronic device, 410 - Memory, 420 - Processor, 500 - Controller, 600 - Patient. DETAILED DESCRIPTION

[0061] To make the objectives, advantages, and features of the present invention more clear, the medical image-based QA evaluation method, system, and medical device proposed in the present invention are further described in detail below with reference to the accompanying drawings. It should be noted that the drawings are all in a very simplified form and are not in exact proportions, and are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention. It should be understood that the drawings in the specification do not necessarily show the specific structure of the present invention to scale, and the illustrative features used in the drawings to illustrate certain principles of the present invention may also be slightly simplified. The specific design features of the present invention disclosed herein, including, for example, specific dimensions, directions, positions, and shapes, will be determined in part by the specific application and use environment. In addition, in the embodiments described below, the same figure mark is sometimes used in different figures to represent the same part or parts with the same function, and their repeated description is omitted. In this specification, similar numbers and letters are used to represent similar items. Therefore, once an item is defined in one figure, it does not need to be further discussed in subsequent figures.

[0062] Where appropriate, these terms used in this manner are interchangeable. Similarly, if a method described herein comprises a series of steps, the order in which the steps are presented herein is not necessarily the only order in which the steps may be performed, and some of the steps described may be omitted and / or other steps not described herein may be added to the method.

[0063] Before specifically introducing the medical image-based QA evaluation method, system, medical device, and storage medium proposed in the present invention, the basic principles of the present invention are described as follows.

[0064] In order to overcome the defects in the existing technology, the inventors have conducted extensive analysis and research on the dose evaluation methods in the existing technology, including the dose deviation method, position deviation method and Gamma algorithm. After a lot of investigation and practice and continuous in-depth research, practice and repeated demonstration, they creatively proposed a QA evaluation method, system and medical equipment based on graphics and medical images.

[0065] Specifically, for the dose deviation (DD) method, it is usually evaluated by the following formula for the selected evaluation points:

[0066] DD(r)=D c (r)-D m (r)

[0067] Among them, D c (r) is the dose value of the evaluation point, D m (r) is the dose at the reference point, r is the evaluation point in three-dimensional space, DD(r) is the difference between the dose at the evaluation point, m and the reference point r. If the difference is within the allowable range, it is considered that the evaluation at this reference point has passed. The allowable range is generally set to ±3% of the prescribed dose at the reference point. It can be understood that the specific verification values ​​in this article are only exemplary and can be set according to actual working conditions. They are not limitations of the present invention and should be understood in conjunction with the context. They will not be explained one by one. This method is only based on a certain point in the dose image (maximum value, given value, selected point in the image). The pass rate is closely coupled with the selection of evaluation points and reference points, and has great randomness. It is not only difficult to reflect the true situation of the image, but also involves the tedious operation of repeatedly taking points, which is inefficient.

[0068] For the position deviation (DTA) method, the selected evaluation points are usually evaluated using the following formula:

[0069] The reference formula is as follows:

[0070]

[0071] Here, Δr(r, r′) is the distance between the evaluation point r and the reference point r′ in three-dimensional space. DTA searches for the minimum distance between an evaluation point and a reference point that has the same dose value as the reference point within a preset allowable distance range. The allowable distance is generally set to 3mm. The pass rate of this method is closely related to the dose at the selected evaluation and reference points. From the perspective of high and low dose gradients: in the high dose gradient region, the dose difference between points is large, and a small spatial error will cause a large dose deviation; in the low dose gradient region, a small dose difference between two identical points will result in a large increase in distance. It also has a high degree of randomness, not only making it difficult to reflect the true situation of the image, but also involving the aforementioned operation of repeatedly selecting points, which is inefficient.

[0072] For the Gamma evaluation method, the selected evaluation points are usually evaluated by the following formula:

[0073]

[0074]

[0075]

[0076]

[0077] in, R is the evaluation point m and reference point r c the distance between them; R is the evaluation point m and reference point r c The dose difference between m is the preset maximum tolerated dose deviation percentage, Δd m is the preset maximum tolerance position deviation percentage, when γ(r m )≤1, the reference point evaluation passes. According to the above formula, it can be seen that the Gamma evaluation method is a method for quantitatively evaluating the degree of consistency between the predicted dose image and the measured dose image distribution. It combines the two standards of dose deviation DD and position deviation DTA into a single Gamma index value, and uses the Gamma index to evaluate the consistency of the two dose image distributions. However, it only considers the impact of the entire dose field. When executing the VMAT plan in Pre_Treatment, data are calculated and measured at each angle. In this case, directly accumulating the calculated and measured data on a single image can easily lose information about intermediate details.

[0078] Based on the above research, the core idea of ​​the present invention is to overcome the defects existing in the existing technology, reduce the attempts of repeated point acquisition, use specific statistical principles to find the best normalized dose, and reduce the impact of dose jitter on the analysis results under point normalization.

[0079] In order to realize the above ideas, the present invention exemplarily gives strategies based on isodose line normalization and region of interest normalization. In the isodose line normalization method, normalization is performed based on the average dose within the isodose line, which can reduce the impact of dose jitter on the analysis results under point normalization. In the region of interest normalization method, normalization is performed based on the dose-volume correspondence corresponding to the region of interest, which is more convenient for statistical analysis of the treatment effect of a specific ROI and convenient for the doctor's next stage of treatment plan. The present invention also further improves the Gamma analysis method and increases the contribution to the entire algorithm in the angular direction. The improved Gamma method can assist in analyzing the actual execution effect of the machine at different angles.

[0080] Specifically, the following first describes the medical image-based QA evaluation method proposed in the present invention, and then introduces the medical image-based QA evaluation system, medical equipment, and storage medium proposed in the present invention one by one.

[0081] This embodiment provides a QA evaluation method based on medical images. Figure 1 , Figure 1 The flowchart of the QA evaluation method based on medical images provided in this embodiment is as follows. Figure 1 It can be seen that the QA evaluation method based on medical images proposed in the present invention includes the following steps:

[0082] Step 1: Obtain medical reference images and medical comparison images.

[0083] Step 2: According to a preset normalization evaluation strategy, the medical comparison image is normalized with the medical reference image as a reference.

[0084] Step 3: Acquire evaluation parameter information based on the evaluation reference image and the evaluation comparison image.

[0085] Specifically, in step 2, the preset normalization evaluation strategy normalizes the medical comparison image with reference to the medical reference image, including: normalizing the medical comparison image according to a preset ratio relationship to obtain the evaluation parameter information. In this embodiment, normalizing the medical comparison image to the medical reference image can be normalizing the medical comparison image with reference to the medical reference image. Of course, it is also possible to normalize the medical reference image with reference to the medical comparison image. The two methods are essentially the same, with only slight differences in expression, and both are within the scope of protection of the present invention. Then, as described in step 3, the evaluation parameter information is determined using the evaluation reference image and the normalized evaluation comparison image. Among them, the preset ratio relationship includes but is not limited to the dose value ratio relationship obtained based on the preset isodose line normalization strategy or the preset region of interest normalization strategy described below.

[0086] Preferably, as one of the preferred embodiments, the evaluation parameter information includes but is not limited to: the dose difference between the reference point on the medical reference image and the evaluation point on the normalized medical comparison image, the distance between the evaluation point and the reference point in three-dimensional space, and the angular deviation between the evaluation point and the reference point.

[0087] Step 4: Obtain evaluation results based on the evaluation parameter information.

[0088] It should be noted that, although the description below is based on the evaluation results of one evaluation point, those skilled in the art should be able to understand that in actual applications, it is better to select the appropriate distribution and number of evaluation points according to actual needs, and finally obtain the corresponding pass rate results, rather than using the evaluation results of one or several evaluation points as the overall final evaluation results.

[0089] With such configuration, the QA evaluation method based on medical images provided by the present invention can avoid the randomness of image point selection, thereby effectively reflecting the true situation of the image and achieving a more accurate evaluation. Furthermore, the QA evaluation method based on medical images provided by the present invention can be used for dose verification before radiotherapy to ensure that the tumor or abnormality receives the prescribed dose while protecting the surrounding normal tissue from damage; and can also be used for quantitative evaluation of the treatment effect on the patient after treatment, making it convenient for doctors to adjust the patient's treatment plan at any time. Furthermore, the QA evaluation method based on medical images provided by the present invention overcomes the randomness of image point selection because it adopts a preset normalization evaluation strategy and uses the medical reference image as a reference to normalize the medical comparison image. Therefore, when obtaining the evaluation results based on the evaluation parameter information, both the traditional dose deviation method or the position deviation method and the traditional Gamma evaluation method can be used. The present invention does not impose any restrictions on the specific means of obtaining the evaluation results.

[0090] As one of the preferred implementations, in step 1, the medical reference image and the medical comparison image are both portal images; the medical reference image includes a dose calculation image, and the medical comparison image includes a dose measurement image. The dose calculation image includes a portal image acquired before the start of the patient's treatment under the same conditions as the actual treatment, for example, the medical reference image is generated by simulating radiotherapy planning data. The dose measurement image is a portal image acquired during the patient's actual treatment (including during and / or after treatment). It can be understood that this is only a description of a preferred implementation, and the present invention does not limit the acquisition method and specific form of the medical reference image and the medical comparison image.

[0091] Furthermore, in step S1, the obtaining of the medical reference image and the medical comparison image includes: obtaining the dose information of several reference points on the medical reference image, and the three-dimensional spatial position information and angle information of the reference points; obtaining the dose information of several evaluation points on the medical comparison image, and the three-dimensional spatial position information and angle information of the evaluation points.

[0092] Preferably, in step 2, the method of normalizing the medical comparison image based on a preset normalization evaluation strategy and taking the medical reference image as a reference comprises:

[0093] Step 21: Acquire a normalized reference dose value of the medical reference image and a normalized comparative dose value of the medical comparative image according to a preset isodose line normalization strategy or a preset region of interest normalization strategy.

[0094] Step 22: Normalizing the medical comparison image according to the ratio of the normalized reference dose value to the normalized comparison dose value.

[0095] Preferably, in one exemplary embodiment, in step 21, the method of obtaining the normalized reference dose value of the medical reference image and the normalized comparative dose value of the medical comparison image according to a preset isodose line normalization strategy includes:

[0096] Step S2111: determining a percentage isodose line according to the dose gradient information of the medical reference image or the dose gradient information of the medical comparison image;

[0097] Step S2112: Counting the first average value of the medical reference image within the range of the percentage isodose line, and using the first average value as the normalized reference dose value; and counting the second average value of the medical comparison image within the range of the percentage isodose line, and using the second average value as the normalized comparison dose value.

[0098] Furthermore, the method for determining the percentage isodose line based on the dose gradient information of the medical reference image or the dose gradient information of the medical comparison image includes: selecting the percentage isodose line of the maximum value of the entire dose field of the medical reference image or the medical comparison image as the percentage isodose line based on the dose gradient information of the medical reference image or the dose gradient information of the medical comparison image.

[0099] With this configuration, the medical image-based QA evaluation method provided by the present invention utilizes a statistically based normalization approach based on isodose lines, thereby avoiding the randomness of point selection in high-dose gradient regions, avoiding repeated point selection attempts, and reducing the adverse effects of dose jitter on evaluation (analysis) results. This method can fully reflect the true state of the image and achieve more accurate assessments.

[0100] Preferably, in another exemplary embodiment, in step 21, the method of obtaining the normalized reference dose value of the medical reference image and the normalized comparative dose value of the medical comparison image according to a preset region of interest normalization strategy comprises the following steps:

[0101] Step S2121: determining at least one region of interest according to a preset evaluation region selection factor;

[0102] Step S2122: Calculate the dose value of the medical reference image according to the volume dose correspondence corresponding to the region of interest to obtain the normalized reference dose value; and calculate the dose value of the medical comparison image according to the volume dose correspondence corresponding to the region of interest to obtain the normalized comparison dose value.

[0103] Specifically, see Figure 2 , Figure 2 Schematic diagram of the normalization strategy of the region of interest according to one embodiment of the present invention. Figure 2 It can be seen that for the comparison of the original plan and the reconstructed three-dimensional dose field, in order to facilitate doctors to evaluate the treatment effect of the patient's organs at risk and target area, this embodiment proposes a QA evaluation scheme in relative mode based on the ROI selection evaluation region selection factor H and the ROI dose volume histogram (DVH). This scheme requires additional input (i.e., based on the ROI selection evaluation region selection factor H): one or more ROIs (head, body, etc.). The algorithm finds the corresponding position in the reference image based on the absolute position information of the ROI and defines the calculation range. When analyzing a certain target area or organ at risk separately, when there is a significant difference in the DVH of the two dose images in the ROI, a statistical analysis based on the ROI normalization method can be selected. It can be seen from the figure: first, according to the preset evaluation region selection factor H and the input ROI absolute position information, the calculation range of the reference image I1 and the comparison image I2 are obtained respectively, that is, the corresponding position I′1=I1*H of the reference image I1 and the corresponding position I′2=I2*H of the comparison image I2 are obtained; then, according to the ratio relationship The medical reference image I1 is used as a reference to normalize the comparison image I2. In the above formula, D 1_X For the case of the same volume percentage, the dose value corresponding to the ROI selected in the reference image I1; D 2_X For the same volume fraction, the comparison image I2 selects a dose value corresponding to the ROI. Preferably, the dose value corresponding to the selected ROI can be determined based on the DVH of the ROI. Finally, an evaluation result γ is obtained based on the evaluation parameter information. As will be understood by those skilled in the art, the volume-dose correspondence can be a dose-volume histogram, and the volume fraction can be input data (i.e., known data).

[0104] As can be seen, the medical image-based QA evaluation method provided by the present invention selects the same volume ratio for a specific ROI, calculates the dose values ​​corresponding to the reference image and the comparison image respectively, then normalizes the comparison image to the reference image using a second ratio relationship. Finally, gamma analysis is performed based on other input conditions to obtain the corresponding pass rate result. This allows doctors to quantitatively analyze the treatment effect of a specific ROI and adjust the patient's treatment plan at any time.

[0105] In particular, those skilled in the art will appreciate that the above-mentioned normalization method based on isodose lines and the preset region of interest normalization method are merely descriptions of preferred embodiments and are not limitations of the present invention. In other embodiments, other normalization methods commonly used in statistics may also be adopted, which will not be described in detail.

[0106] With such a configuration, the medical image-based QA evaluation method provided by the present invention overcomes the problem in the prior art that it is impossible to effectively analyze the dose impact on a specific region of interest. It can facilitate doctors to quantitatively analyze the treatment effect of a specific region of interest, evaluate the treatment effect of the patient's organs at risk and target areas, and facilitate the adjustment of the patient's treatment plan at any time.

[0107] Preferably, in step 4, the method for obtaining the evaluation result based on the evaluation parameter information includes: obtaining the evaluation result using the Gamma evaluation method based on the dose difference between the reference point on the medical reference image and the evaluation point on the normalized medical comparison image, the distance between the evaluation point and the reference point in three-dimensional space, and the angular deviation between the evaluation point and the reference point.

[0108] In one preferred embodiment, the dose difference between the reference point on the medical reference image and the evaluation point on the normalized medical comparison image, the distance between the evaluation point and the reference point in three-dimensional space, and the angular deviation between the evaluation point and the reference point are evaluated using a Gamma evaluation method to obtain an evaluation result, including:

[0109] For any evaluation point, the evaluation result is obtained by the following formula:

[0110]

[0111]

[0112]

[0113]

[0114]

[0115] Where, is the evaluation point on the medical comparison image The evaluation results, is the distance between the evaluation point and the reference point in three-dimensional space, is the dose difference between the evaluation point and the reference point, Δd is the angle difference between the evaluation point and the reference point. m is the preset maximum tolerance position deviation percentage, ΔD m is the preset maximum tolerated dose deviation percentage, Δθ m It is the preset maximum tolerance angle deviation percentage. and They are respectively the dose information of the evaluation point, and the three-dimensional spatial position information and angle information of the reference point. and are the dose information of the reference point, and the three-dimensional spatial position information and angle information of the reference point. Specifically, θ is usually measured in radians, which is not limited in the present invention. m ), when γ(r m )≤1, the reference point is calculated as passed. By reasonably selecting a certain number and distribution of reference points and evaluation points, the pass rate of the QA evaluation can be obtained.

[0116] This demonstrates that the present invention improves upon the prior art gamma evaluation method by increasing the weight of the angles of influence. The medical image-based QA evaluation method provided by the present invention overcomes the drawback of prior art gamma evaluation methods that only consider the current control point. In particular, in pre-treatment assessments, the QA evaluation method provided by the present invention fully considers the impact of the angles before and after the measurement data on the reference point at the current angle, enabling more accurate analysis of the VMAT plan's calculated data at each angle.

[0117] With such configuration, the medical image-based QA evaluation method provided by the present invention can assist in analyzing the actual execution effect of the machine at different angles by increasing the contribution of the angular direction to the entire algorithm.

[0118] Another embodiment of the present invention provides a QA evaluation system based on medical images, see Figure 3 , Figure 3 The QA evaluation system based on medical images provided in this embodiment. Figure 3 It can be seen that the QA evaluation system includes a portal imaging device 100 and an image evaluation device 200 that are communicatively connected.

[0119] Specifically, the portal imaging device 100 is configured to acquire a medical comparison image; and the image evaluation device 200 is configured to acquire an evaluation result of the medical comparison image based on a medical reference image and the medical comparison image. As previously mentioned, as a preferred embodiment, the medical reference image is a portal image generated by simulating planning data before the patient's treatment begins. Furthermore, the image evaluation device 200 includes an image normalization module 210, a parameter information acquisition module 220, and an evaluation result acquisition module 230. The image normalization module 210 is configured to normalize the medical comparison image based on a preset normalization evaluation strategy, using the medical reference image as a reference. The preset normalization evaluation strategy may include a preset isodose line normalization strategy or a preset region of interest normalization strategy. The parameter information acquisition module 220 is configured to acquire evaluation parameter information based on the medical reference image and the normalized medical comparison image. The evaluation result acquisition module 230 is configured to acquire an evaluation result based on the evaluation parameter information. With this configuration, the medical image-based QA evaluation system provided by the present invention shares the same inventive concept as the medical image-based evaluation methods provided in the aforementioned embodiments. This system can avoid randomness in image point selection, effectively reflecting the true image state and enabling more accurate evaluation. Furthermore, the medical image-based QA evaluation system can be used for both pre-radiotherapy dose verification, ensuring that tumors or abnormalities receive the prescribed dose while minimizing damage to surrounding normal tissue, and post-treatment quantitative assessment of patient treatment outcomes, enabling physicians to adjust treatment plans at any time.

[0120] In particular, it will be understood by those skilled in the art that the devices and methods disclosed in the embodiments of this document may also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the devices, methods, and computer program products according to the various embodiments of this document. In this regard, each box in the flowchart or block diagram may represent a module, program, or portion of code, wherein the module, program segment, or portion of code contains one or more executable instructions for implementing a specified logical function, and the module, program segment, or portion of code contains one or more executable instructions for implementing a specified logical function. In particular, in some alternative implementations, the functions marked in the boxes may also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes may actually be executed substantially in parallel, or they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified function or action, or may be implemented by a combination of dedicated hardware and computer instructions.

[0121] In addition, the functional modules in the various embodiments of this document may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0122] Another embodiment of the present invention provides a medical device, see Figure 4 , Figure 4This is a schematic diagram of the structure of the medical device provided in this embodiment. The medical device provided in this example can provide radiotherapy to a patient 600 and allows for various pre-treatment field dose verifications and post-treatment confirmation of the patient's treatment effects. Radiotherapy treatments may include photon-based radiotherapy, particle therapy, electron beam therapy, or any other type of therapeutic treatment. The medical device provided in this embodiment includes a radiotherapy device 300, a portal imaging device 100, and an electronic device 400 that are communicatively connected. The electronic device 400 includes a memory 410 and a processor 420. Preferably, the radiotherapy device 300 is configured to generate a radiation beam for treating a patient; the portal imaging device 100 is configured to obtain a medical comparison image based on the radiation beam; and the electronic device 400 is configured to obtain an evaluation result of the medical comparison image based on a medical reference image and the medical comparison image. As previously mentioned, as a preferred embodiment, the medical reference image is a portal image generated by simulation of planning data before the patient treatment begins. The processor 420 is adapted to execute various instructions, and the memory 410 is adapted to store a plurality of instructions, wherein the instructions are adapted to be loaded by the processor 420 and executed by the following steps to obtain an evaluation result of the medical comparison image: normalizing the medical comparison image according to a preset normalization evaluation strategy with the medical reference image as a reference; wherein the preset normalization evaluation strategy includes a preset isodose line normalization strategy or a preset region of interest normalization strategy; obtaining evaluation parameter information based on the medical reference image and the normalized medical comparison image; and obtaining an evaluation result based on the evaluation parameter information. With such a configuration, the medical device provided by the present invention shares the same inventive concept as the medical image-based QA evaluation system and the medical image-based evaluation method provided in the aforementioned embodiments, and can avoid randomness in image point selection, thereby effectively reflecting the true state of the image and achieving more accurate evaluation. Furthermore, the medical device can be used for both pre-radiotherapy dose verification to ensure that tumors or abnormalities receive the prescribed dose while avoiding damage to surrounding normal tissue; and post-treatment quantitative evaluation of patient treatment efficacy, facilitating physicians to adjust treatment plans at any time.

[0123] Specifically, in one preferred embodiment, the radiotherapy apparatus 300 (such as, but not limited to, a radiotherapy or radiosurgery device) may include a gantry 310 supporting a radiation module 320. The radiation module 320 includes one or more radiation sources (not shown) and a linear accelerator (not shown) operable to generate a kV or MV X-ray radiation beam. The gantry 310 may be an annular gantry (i.e., extending through a full 360-degree arc to form a complete ring or circle), but other mounting arrangements may also be employed. For example, a C-shaped, partial annular gantry, or a robotic arm may be employed. Any other framework capable of positioning the radiation module 320 in various rotational and / or axial positions relative to the patient 600 may also be employed. The radiation module 320 may also include a modulation device (not shown) operable to modulate the radiation beam and direct the therapeutic radiation beam toward the patient 600 and toward a region of the patient desired to be irradiated. The region desired to be irradiated is referred to as a target, target region, or region of interest. The patient 600 may have one or more regions of interest that are desired to be irradiated. A calibration device (not shown) may be included in the modulation device to define and adjust the size of the aperture through which the radiation beam passes from the radiation source to the patient 600. The calibration device may be controlled by an actuator (not shown), which may be controlled by the electronic device 400 and / or the controller 500.

[0124] In some embodiments, the radiotherapy device 300 is a kV or MV intensity modulated radiotherapy (IMRT) device or a volumetric modulated ARC therapy (VMAT) device. The intensity distribution in such a system is adapted to the treatment requirements of a single patient. The intensity modulated radiotherapy field is delivered using a multi-leaf collimator (MLC), which is a computer-controlled mechanical beam shaping device attached to the head of the linear accelerator and includes an assembly of metal fingers or leaves. For each beam direction, an optimized intensity distribution is achieved by sequentially delivering various subfields with optimized shapes and weights. From one subfield to the next, the leaves can move with the radiation beam turned on (i.e., dynamic multi-leaf calibration (DMLC)) or with the radiation beam turned off (i.e., segmented multi-leaf calibration (SMLC)). In other embodiments, the radiotherapy device 300 can also be a tomotherapy device, in which intensity modulation is achieved using a binary collimator that is turned on and off under computer control. Because the gantry rotates continuously around the patient, the exposure time of the small width of the beam can be adjusted by opening and closing the binary collimator, so that radiation can be delivered to the tumor through the patient's most preferred direction and position. Furthermore, in some embodiments, the radiotherapy device 300 can also be a helical tomotherapy device including a slip ring rotating gantry. In short, it will be understood by those skilled in the art that any type of intensity modulated radiation therapy (IMRT) device can be used. Each type of radiotherapy device 300 is accompanied by a corresponding radiation plan and radiation delivery program.

[0125] The portal imaging device 100 can be an electronic portal dosimetry device (EPID). Depending on the purpose of the QA assessment, whether non-radioactive pre-treatment, non-radioactive treatment, or transradioactive treatment dosimetry is used, the portal imaging device 100 can be placed in different locations, such as on top of the treatment couch 300 or attached to the accelerator head. The portal imaging device 100 can generate direct portal images that include data from different projection angles (0≤θ<360°) from the gantry 310. In some embodiments, it can be a camera-based device, such as a CCD camera-based EPID or an amorphous silicon-based detector. In other embodiments, it can also be a flat-panel imager that provides good image quality, high light transmission efficiency, a large imaging area, and radiation resistance. Flat-panel imagers are typically composed of picture elements (pixels), which register the amount of radiation falling on them and convert the received radiation into a corresponding number of electrons. The electrons are converted into electrical signals, which are further processed using the portal imaging device 100 or the electronic device 400.

[0126] The medical device provided by the present invention may also include multiple modules containing programming instructions that communicate with each other and, when executed, cause the medical device to perform various functions related to radiotherapy / surgery as discussed herein. For example, in some embodiments, the medical device may include: a treatment planning module (not shown) operable to generate a treatment plan for the patient 600 based on multiple data input into the system by a medical professional, the treatment plan including a predicted radiation dose distribution; a patient positioning module (not shown) operable to position and align the patient 600 relative to the isocenter of the gantry 310 for a specific radiotherapy treatment; a patient image acquisition module (not shown) operable to instruct the radiotherapy device 300 to acquire images (i.e., in vivo images) of the patient 600 before and / or during the radiotherapy treatment; and a treatment delivery module (not shown) operable to instruct the radiotherapy device 300 to deliver the treatment plan to the patient 600.

[0127] Those skilled in the art will appreciate that the electronic device 400 provided herein includes, but is not limited to, a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device. Furthermore, the instructions may be written in the C or C++ programming languages. The computer program code for performing the operations of the present invention as described herein may also be written in other programming languages. The electronic device 400 includes, but is not limited to, conventional hardware such as a memory 410 and a processor 420, as well as an operating system for running various software programs and / or communication applications. The electronic device 400 may include software programs capable of communicating with the radiotherapy device 300 and the portal imaging device 100, and these software programs may receive data from any external software programs and hardware. The electronic device 400 may also include any suitable input / output devices and I / O interfaces, memory devices, storage, a keyboard, a mouse, a monitor, a printer, a scanner, etc., suitable for access by medical personnel. The electronic device 400 may also be networked with other computers and radiotherapy systems. Both the radiotherapy device 300 and the electronic device 400 may communicate with a network, as well as databases and servers.

[0128] Another embodiment of the present invention provides a computer-readable storage medium having computer-executable instructions stored thereon. When the computer-executable instructions are executed, the steps of any of the above-described medical image-based QA evaluation methods are implemented: obtaining a medical reference image and a medical comparison image; normalizing the medical comparison image with the medical reference image as a reference according to a preset normalization evaluation strategy; obtaining evaluation parameter information based on the medical reference image and the normalized medical comparison image; and obtaining an evaluation result based on the evaluation parameter information. With such a configuration, the computer-readable storage medium provided by the present invention and the medical image-based QA evaluation method and system provided by the present invention are of the same inventive concept, can avoid the randomness of image point selection, thereby effectively reflecting the true condition of the image and achieving a more accurate evaluation.

[0129] The readable storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer hard disk, a hard disk, a random access memory (RAM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this article, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0130] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0131] Computer program code for performing the operations of the present invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet using an Internet service provider). In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features. In the description of the present invention, "multiple" means at least two, such as two, three, etc., unless

[0132] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0133] In summary, the above embodiments provide detailed descriptions of different configurations of medical image-based QA evaluation methods, systems, medical devices, and storage media. Of course, the above description is only a description of the preferred embodiments of the present invention and does not limit the scope of the present invention. The present invention includes but is not limited to the configurations listed in the above embodiments. Those skilled in the art can draw inferences based on the contents of the above embodiments. Any changes and modifications made by ordinary technicians in the field of the present invention based on the above disclosure are within the scope of protection of the claims.

Claims

1. A QA evaluation method based on medical images, characterized in that: include: acquiring medical reference images and medical comparison images; Obtaining a normalized reference dose value of the medical reference image and a normalized comparative dose value of the medical comparison image according to a preset isodose line normalization strategy or a preset region of interest normalization strategy, wherein the preset region of interest is a part of the patient desired to be irradiated; normalizing the medical comparison image according to a ratio of the normalized reference dose value to the normalized comparison dose value; acquiring evaluation parameter information according to the medical reference image and the normalized medical comparison image; An evaluation result is obtained according to the evaluation parameter information.

2. The QA evaluation method according to claim 1, characterized in that: The medical reference image and the medical comparison image are both portal images; the medical reference image includes a dose calculation image, and the medical comparison image includes a dose measurement image.

3. The QA evaluation method according to claim 1, characterized in that: The method for obtaining the normalized reference dose value of the medical reference image and the normalized comparative dose value of the medical comparison image according to a preset isodose line normalization strategy includes: determining a percentage isodose line according to the dose gradient information of the medical reference image or the dose gradient information of the medical comparison image; Counting a first average value of the medical reference image within the percentage isodose line range, and using the first average value as the normalized reference dose value; A second average value of the medical comparison image within the percentage isodose line range is calculated, and the second average value is used as the normalized comparison dose value.

4. The QA evaluation method according to claim 3, characterized in that: The method for determining the percentage isodose line based on the dose gradient information of the medical reference image or the dose gradient information of the medical comparison image includes: According to the dose gradient information of the medical reference image or the dose gradient information of the medical comparison image, a percentage isodose line of the maximum value of the entire dose field of the medical reference image or the medical comparison image is selected as the percentage isodose line.

5. The QA evaluation method according to claim 1, characterized in that: The method for obtaining the normalized reference dose value of the medical reference image and the normalized comparative dose value of the medical comparison image according to a preset region of interest normalization strategy includes: Determine at least one region of interest based on a preset evaluation region selection factor; Calculating the dose value of the medical reference image according to the volume dose correspondence relationship corresponding to the region of interest to obtain the normalized reference dose value; The dose value of the medical comparison image is calculated according to the volume dose correspondence relationship corresponding to the region of interest to obtain the normalized comparison dose value.

6. The QA evaluation method according to claim 1, characterized in that: The evaluation parameter information includes: The dose difference between the reference point on the medical reference image and the normalized evaluation point on the medical comparison image, the distance between the evaluation point and the reference point in three-dimensional space, and the angular deviation between the evaluation point and the reference point.

7. The QA evaluation method according to claim 1, characterized in that: The method for obtaining the evaluation result according to the evaluation parameter information includes: The evaluation result is obtained by using the Gamma evaluation method according to the dose difference between the reference point on the medical reference image and the evaluation point on the normalized medical comparison image, the distance between the evaluation point and the reference point in three-dimensional space, and the angular deviation between the evaluation point and the reference point.

8. A QA evaluation system based on medical images, characterized by: including a portal imaging device and an image evaluation device connected in communication; The portal imaging device is configured to: acquire a medical comparison image; The image evaluation device is configured to: obtain an evaluation result of the medical comparison image based on the medical reference image and the medical comparison image; The image evaluation device includes an image normalization module, a parameter information acquisition module and an evaluation result acquisition module; The image normalization module is configured to: obtain a normalized reference dose value of the medical reference image and a normalized comparative dose value of the medical comparison image according to a preset isodose line normalization strategy or a preset region of interest normalization strategy, wherein the preset region of interest is a part of the patient that is desired to be irradiated; normalizing the medical comparison image according to a ratio of the normalized reference dose value to the normalized comparison dose value; The parameter information acquisition module is configured to: acquire evaluation parameter information according to the medical reference image and the normalized medical comparison image; The evaluation result acquisition module is configured to acquire the evaluation result according to the evaluation parameter information.

9. A medical device, characterized in that comprising a radiotherapy device, a portal imaging device, and an electronic device in communication with each other, wherein the electronic device comprises a memory and a processor; The radiotherapy apparatus is configured to: generate a radiation beam; The portal imaging device is configured to: acquire a medical comparison image based on the radiation beam; The electronic device is configured to: obtain an evaluation result of the medical comparison image based on the medical reference image and the medical comparison image; The processor is adapted to implement various instructions, the memory is adapted to store a plurality of instructions, and the instructions are adapted to be loaded by the processor to execute the following steps to obtain an evaluation result of the medical comparison image: Obtaining a normalized reference dose value of the medical reference image and a normalized comparative dose value of the medical comparison image according to a preset isodose line normalization strategy or a preset region of interest normalization strategy, wherein the preset region of interest is a part of the patient desired to be irradiated; normalizing the medical comparison image according to a ratio of the normalized reference dose value to the normalized comparison dose value; acquiring evaluation parameter information according to the medical reference image and the normalized medical comparison image; An evaluation result is obtained according to the evaluation parameter information.

Images