Recommended method and device of field angle, processor and electronic equipment

Abstract

The application discloses a field angle recommendation method and device, a processor and an electronic device, relates to the technical field of radiotherapy, and comprises the following steps: acquiring a multi-layer target medical image, wherein the multi-layer target medical image at least includes delineation information of a radiotherapy target region and delineation information of a radiotherapy organ at risk; performing feature extraction on the delineation information of a radiotherapy organ at risk image in the multi-layer target medical image to obtain first target feature information; calculating the similarity values of the first target feature information and second target feature information corresponding to a plurality of historical cases stored in a target database to obtain a plurality of similarity values; and determining a target field angle of the multi-layer target medical image from the field angles corresponding to the plurality of historical cases according to the plurality of similarity values. Through the application, the problem that the efficiency of determining a field angle is relatively low due to the determination of the field angle by relying on artificial experience in the related art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of radiotherapy, in particular to a method and device for recommending a field angle, a processor and an electronic device. BACKGROUND

[0002] The purpose of radiotherapy is to give the target area a required dose to eliminate tumors, while the normal tissue and the OAR (OAR) around the target area are protected as much as possible, at least cannot be irradiated beyond the dose limit value. In clinical practice, two methods are currently used, the first method is to make the shape of the ray projected on the clinical target volume (CTV) consistent with the projection of the clinical target volume in this direction, and the intensity of the ray beam does not change in the plane perpendicular to the central axis of the ray beam, or a wedge-shaped plate is used to make it linearly change in one direction, which is called classic (traditional) conformal therapy (CCRT); the second method is similar to the first method, except that the intensity of the ray can change as needed in the plane perpendicular to the central axis of the ray beam, which is called intensity-modulated conformal radiotherapy (IMRT).

[0003] In the process of designing a treatment plan, there are many parameters that can be selected and adjusted, such as the type of rays, the number of fields, the field weight, whether to use a wedge-shaped plate and the angle and direction of the wedge-shaped plate, the field incidence angle, etc. In the past 20 years, in order to obtain a better treatment plan, various computer optimization techniques have been developed, including optimization of field weight, optimization of wedge-shaped plate direction and angle, and if it is an intensity-modulated plan, optimization of field intensity distribution can also be performed. At the beginning of designing a treatment plan, the plan designer first determines the type and energy of the rays. Generally speaking, the types and energies of rays that can be provided by a treatment unit of a treatment unit are limited and are pre-set. The traditional approach is that the plan designer must first determine the number of fields and the incidence angle of the fields according to experience, and then determine the shape and dose weight of the fields as needed; the number of fields and the direction selected are completely dependent on the experience of the plan designer. If the final calculated dose distribution cannot meet the requirements, the plan designer needs to change some field directions or change the number of fields and the corresponding dose weight at the same time, and then perform a new round of calculation. If the relationship between the CTV and the OAR is complex, this trial and error process may need to be performed many times to achieve a clinically acceptable, but not the best, solution. Therefore, it is necessary to study the setting of field direction and field dose weight. The current manual adjustment of parameters is through multiple attempts and modifications, although a set of field angles can be obtained eventually, but the process consumes a lot of time and effort of the physicist.

[0004] In view of the problem in the related art that the field angle is determined by relying on manual experience, resulting in low efficiency of determining the field angle, no effective solution has been proposed so far. SUMMARY

[0005] The main purpose of the present application is to provide a field angle recommendation method and device, a processor and an electronic device to solve the problem of low efficiency of determining the field angle by relying on artificial experience in the related art.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a field angle recommendation method is provided. The method comprises: acquiring a multi-layer target medical image, wherein the multi-layer target medical image at least includes delineation information of a radiotherapy target area and delineation information of a radiotherapy organ at risk; performing feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain first target feature information; calculating the similarity values of the first target feature information and the second target feature information corresponding to a plurality of historical cases stored in a target database to obtain a plurality of similarity values; and determining a target field angle of the multi-layer target medical image from the field angles corresponding to the plurality of historical cases according to the plurality of similarity values.

[0007] Further, the feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain the first target feature information comprises: reading a target center point in the multi-layer target medical image, wherein the target center point is a center point of a historical field or a center point calculated according to the delineation information of the radiotherapy target area; dividing each target medical image according to the target center point and a preset interval angle to obtain a plurality of groups of target medical sub-images, wherein the plurality of groups of target medical sub-images are composed of a plurality of layers of target medical sub-images; and calculating the relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images to the target center point to obtain the first target feature value.

[0008] Further, the calculation of the relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images to the target center point to obtain the first target feature value comprises: calculating the volume value of the radiotherapy organ at risk image in each group of target medical sub-images according to the relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images to the target center point; and taking the minimum distance value of the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images to the target center point and the volume value of the radiotherapy organ at risk image in each group of target medical sub-images as the first target feature value.

[0009] Further, the volume value of the radiotherapy OAR image in each group of target medical sub-images is calculated according to the relative position of the delineation information of the radiotherapy OAR image in each group of target medical sub-images and the target center point, including: taking the target center point as a starting point, calculating the distance value between the pixel coordinates in the delineation information of the radiotherapy OAR image in each group of target medical sub-images and the target center point to obtain a plurality of distance values; determining the maximum distance value between the pixel coordinates in the delineation information of the radiotherapy OAR image in each group of target medical sub-images and the target center point and the minimum distance value between the pixel coordinates in the delineation information of the radiotherapy OAR image in each group of target medical sub-images and the target center point from the plurality of distance values; performing sector area calculation according to the maximum distance value, the minimum distance value and the interval angle to obtain the area value of the radiotherapy OAR image of each layer of target medical sub-images; and calculating the volume value of the radiotherapy OAR image in each group of target medical sub-images according to the area value of the radiotherapy OAR image of each layer of target medical sub-images.

[0010] Further, before calculating the similarity values of the first target feature information and the second target feature information corresponding to a plurality of historical cases stored in the target database to obtain a plurality of similarity values, the method further comprises: obtaining a plurality of medical images corresponding to each historical case, and performing feature extraction on the delineation information of the radiotherapy OAR image in the plurality of medical images corresponding to each historical case to obtain the second target feature information; and storing the second target feature information and the historical case corresponding to the second target feature information in the target database in the form of a key-value pair.

[0011] Further, calculating the similarity values of the first target feature information and the second target feature information corresponding to a plurality of historical cases stored in the target database to obtain a plurality of similarity values comprises: reading all the second target feature information from the target database; calculating the Euclidean distance between each feature value in the first target feature information and each feature value of the second target feature information to obtain the plurality of similarity values.

[0012] Further, according to the plurality of similarity values, the target field angle of the plurality of target medical images is determined from the field angles corresponding to the plurality of historical cases, including: determining the historical case corresponding to the maximum similarity value as a target historical case; obtaining the field angle corresponding to the target historical case, and taking the field angle corresponding to the target historical case as the target field angle of the plurality of target medical images.

[0013] In order to achieve the above object, according to another aspect of the present application, a field angle recommendation device is provided. The device comprises: a first acquisition unit configured to acquire a multi-layer target medical image, wherein the multi-layer target medical image comprises at least delineation information of a radiotherapy target region and delineation information of a radiotherapy organ at risk; an extraction unit configured to perform feature extraction on the delineation information of a radiotherapy organ at risk image in the multi-layer target medical image to obtain first target feature information; a calculation unit configured to calculate similarity values of the first target feature information and second target feature information corresponding to a plurality of historical cases stored in a target database to obtain a plurality of similarity values; and a determination unit configured to determine a target field angle of the multi-layer target medical image from field angles corresponding to the plurality of historical cases according to the plurality of similarity values.

[0014] Further, the extraction unit comprises: a reading subunit configured to read a target center point in the multi-layer target medical image, wherein the target center point is a center point of a historical field irradiation or a center point calculated according to the delineation information of the radiotherapy target region; a uniform division subunit configured to uniformly divide each layer of the target medical image according to the target center point and a preset interval angle to obtain a plurality of groups of target medical sub-images, wherein the plurality of groups of target medical sub-images are composed of a plurality of layers of target medical sub-images; and a first calculation subunit configured to calculate relative positions of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point to obtain the first target feature value.

[0015] Further, the first calculation subunit comprises: a calculation module configured to calculate a volume value of the radiotherapy organ at risk image in each group of target medical sub-images according to the relative positions of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point; and a determination module configured to take a minimum distance value between pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point and the volume value of the radiotherapy organ at risk image in each group of target medical sub-images as the first target feature value.

[0016] Further, the computing module comprises: a first computing submodule, configured to take the target center point as a starting point, calculate distance values between pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point, and obtain a plurality of distance values; a determining submodule, configured to determine a maximum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point and a minimum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point from the plurality of distance values; a second computing submodule, configured to perform sector area calculation according to the maximum distance value, the minimum distance value and the interval angle, and obtain an area value of the radiotherapy organ at risk image of each layer of target medical sub-images; and a third computing submodule, configured to calculate a volume value of the radiotherapy organ at risk image in each group of target medical sub-images according to the area value of the radiotherapy organ at risk image of each layer of target medical sub-images.

[0017] Further, the device further comprises: a second acquisition unit, configured to, before obtaining a plurality of similarity values by calculating the first target feature information and second target feature information corresponding to a plurality of historical cases stored in a target database, acquire a plurality of medical images corresponding to each historical case, and perform feature extraction on the delineation information of the radiotherapy organ at risk image in the plurality of medical images corresponding to each historical case to obtain the second target feature information; and a storage unit, configured to store the second target feature information and the historical case corresponding to the second target feature information in the target database in the form of a key-value pair.

[0018] Further, the computing unit comprises: a reading submodule, configured to read all the second target feature information from the target database; and a second computing submodule, configured to calculate Euclidean distances between each feature value in the first target feature information and each feature value of the second target feature information to obtain the plurality of similarity values.

[0019] Further, the determining unit comprises: a determining submodule, configured to determine that a historical case corresponding to a maximum similarity value is a target historical case; and an acquisition submodule, configured to acquire a field angle corresponding to the target historical case and take the field angle corresponding to the target historical case as a target field angle of the plurality of target medical images.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a processor is also provided, wherein the processor is used to run a program, wherein the program performs the field angle recommendation method of any one of the above-mentioned aspects when running.

[0021] To achieve the above object, according to another aspect of the present application, there is further provided an electronic device, comprising one or more processors and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any of the above-mentioned field angle recommendation methods.

[0022] According to the present application, the following steps are adopted: obtaining a multi-layer target medical image, wherein the multi-layer target medical image at least comprises delineation information of a radiotherapy target region and delineation information of a radiotherapy organ at risk; performing feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain first target feature information; calculating a similarity value of the first target feature information and second target feature information corresponding to a plurality of historical cases stored in a target database to obtain a plurality of similarity values; and determining a target field angle of the multi-layer target medical image from the field angles corresponding to the plurality of historical cases according to the plurality of similarity values, thereby solving the problem in the related art that the field angle is determined by relying on artificial experience, resulting in relatively low efficiency of determining the field angle. In the present solution, the feature extraction is performed on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain the first target feature information corresponding to the radiotherapy organ at risk, and the field angle most similar to the first target feature information is obtained from the field angles corresponding to the plurality of historical cases as the recommended field angle, which can effectively reduce the large amount of time and effort required by the physicist for trial and error, and the historical field is a feasible field proven by practice, thus the quality of the radiotherapy plan can be improved, and the efficiency of determining the field angle is improved. BRIEF DESCRIPTION OF DRAWINGS

[0023] The accompanying drawings, which form a part of the present application, are intended to provide further understanding of the present application, and the illustrative embodiments of the present application and their description serve the purpose of explaining the present application. The accompanying drawings should not be regarded as a limitation of the present application. In the drawings:

[0024] Figure 1 is a flowchart of a recommended method of a field angle according to an embodiment of the present application;

[0025] Figure 2 is a schematic diagram of a target medical image according to an embodiment of the present application;

[0026] Figure 3 is a flowchart of an optional recommended method of a field angle according to an embodiment of the present application;

[0027] Figure 4 is a schematic diagram of a recommended device of a field angle according to an embodiment of the present application;

[0028] Figure 5is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] It should be noted that the embodiments and features of the embodiments in the present application can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0030] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0031] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0032] The present application will be described below in combination with preferred implementation steps, Figure 1 is a flowchart of a recommended method of field angle according to an embodiment of the present application, as Figure 1 shown, the method comprises the following steps:

[0033] Step S101, obtaining a multi-layer target medical image, wherein the multi-layer target medical image at least includes delineation information of a radiotherapy target area and delineation information of a radiotherapy organ at risk;

[0034] Step S102, performing feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain first target feature information;

[0035] Step S103, calculating the similarity values of the first target feature information and the second target feature information corresponding to a plurality of historical cases stored in the target database to obtain a plurality of similarity values;

[0036] Step S104, determining the target field angle of the multi-layer target medical image from the field angles corresponding to the plurality of historical cases according to the plurality of similarity values.

[0037] Specifically, a plurality of target medical images of a target object are acquired, and the medical images can be MR, CT, PET, or the like. It should be noted that each of the target medical images includes delineation information of a radiotherapy target region and delineation information of a radiotherapy organ at risk.

[0038] The feature values of the radiotherapy organ at risk are calculated according to the delineation information of the radiotherapy organ at risk image in the plurality of target medical images, to obtain first target feature information. A number of representative historical cases are selected by a physicist with rich experience, and then medical images corresponding to the historical cases are acquired, and the same feature extraction method as that of the target medical images is used to extract features from the medical images corresponding to each of the historical cases, to obtain the feature values of each of the historical cases, that is, the second target feature information.

[0039] Similarity calculation is performed on the first target feature information and the second target feature information. In an optional embodiment, the Euclidean distance can be used for similarity calculation. A plurality of similarity values are obtained by calculating the Euclidean distance between the first target feature information and the second target feature information. According to the plurality of similarity values, a field angle with the highest similarity is returned from the plurality of historical cases as a recommended field angle, that is, the target field angle.

[0040] In summary, in the present scheme, the delineation information of the radiotherapy organ at risk image in the plurality of target medical images is extracted to obtain the first target feature information of the radiotherapy organ at risk. The field angle most similar to the first target feature information is obtained from the field angles corresponding to the plurality of historical cases as a recommended field angle, which can effectively reduce the time and effort required by the physicist to try and error. Moreover, the historical field is a field that has been proven to be feasible in practice. Therefore, the efficiency of determining the field angle is improved, and the radiotherapy quality of the radiotherapy plan is also improved.

[0041] How to perform feature extraction is crucial. Therefore, in the method for recommending a field angle provided in the embodiments of the present application, the feature extraction of the delineation information of the radiotherapy organ at risk image in the plurality of target medical images is performed to obtain the first target feature information, including the following steps: reading a target center point in the plurality of target medical images, wherein the target center point is a center point of a historical field or a center point calculated according to the delineation information of a radiotherapy target region; dividing each of the target medical images according to the target center point and a preset interval angle to obtain a plurality of groups of target medical sub-images, wherein the plurality of groups of target medical sub-images are composed of the plurality of target medical sub-images; and calculating the relative position between the delineation information of the radiotherapy organ at risk image in each of the target medical sub-images and the target center point to obtain the first target feature value.

[0042] Specifically, a coordinate system is established for the multi-layer target medical image, with the top-left point of the picture as the origin, the x-axis increasing to the right, and the y-axis increasing downward. A corresponding coordinate point is established for each pixel point in the target medical image. Then, the target center point information is read from the target medical image, and the target center point is taken as an end point. The target medical image is equally divided at a preset interval angle (for example, 5°), as shown in the following Figure 2 After the multi-layer target medical image is equally divided, a plurality of groups of target medical sub-images are obtained. For example, if the image is equally divided at an interval of 5°, 72 groups of target medical sub-images are obtained. It should be noted that the target center point is the center point of the historical field irradiation or the center point calculated according to the delineation information of the radiotherapy target region, and the field of each historical data is different. Therefore, the center point of each historical data is also different. When the target medical image has historical field irradiation, the center point of the historical field irradiation is taken as the target center point. When the target medical image does not have historical field irradiation, the target center point is calculated through the delineation information of the radiotherapy target region in the target medical image.

[0043] When the field plan is formulated, in addition to ensuring that the target tumor receives sufficient dose of irradiation, it is also necessary to make the radiotherapy critical organ as small as possible. Therefore, the relative position of the delineation information of the radiotherapy critical organ image in each group of target medical sub-images and the target center point is calculated to obtain the corresponding first target feature value. Through the above feature extraction method, the feature information of the radiotherapy critical organ in the current medical image can be accurately and comprehensively extracted, and the accuracy of subsequent determination of the field angle is improved.

[0044] The following steps are adopted to obtain the first target feature value through the relative position of the delineation information of the radiotherapy critical organ image in each group of target medical sub-images and the target center point: according to the relative position of the delineation information of the radiotherapy critical organ image in each group of target medical sub-images and the target center point, the volume value of the radiotherapy critical organ image in each group of target medical sub-images is calculated; the minimum distance value between the pixel coordinates in the delineation information of the radiotherapy critical organ image in each group of target medical sub-images and the target center point and the volume value of the radiotherapy critical organ image in each group of target medical sub-images are taken as the first target feature value.

[0045] Specifically, the first target feature value includes the volume value of the radiotherapy critical organ and the minimum distance value between the pixel coordinates in the delineation information of the radiotherapy critical organ image in each group of target medical sub-images and the target center point. The two feature items sufficiently describe the radiotherapy critical organ in the current medical image.

[0046] How to calculate the volume value of the radiotherapy OAR image is crucial, therefore, in the field angle recommendation method provided in the embodiments of the present application, the volume value of the radiotherapy OAR image in each group of target medical sub-image is calculated according to the relative position of the delineation information of the radiotherapy OAR image in each group of target medical sub-image and the target center point, including: taking the target center point as the starting point, calculating the distance value between the pixel coordinates in the delineation information of the radiotherapy OAR image in each group of target medical sub-image and the target center point, to obtain a plurality of distance values; determining the maximum distance value between the pixel coordinates in the delineation information of the radiotherapy OAR image in each group of target medical sub-image and the target center point and the minimum distance value between the pixel coordinates in the delineation information of the radiotherapy OAR image in each group of target medical sub-image and the target center point from the plurality of distance values; performing sector area calculation according to the maximum distance value, the minimum distance value and the interval angle, to obtain the area value of the radiotherapy OAR image of each layer of target medical sub-image; and calculating the volume value of the radiotherapy OAR image in each group of target medical sub-image according to the area value of the radiotherapy OAR image of each layer of target medical sub-image.

[0047] Specifically, as shown in FIG. 5, the acquisition method of the pixel point coordinates on the segmentation line is: x increases by 1 pixel point, y value increases by tan(5°)*(x+1), x value is constantly increased, y value is calculated, the coordinates of each point on the segmentation line are obtained, the value of the corresponding pixel point is obtained according to the coordinates, if the value of the pixel point is greater than 0, it is the radiotherapy OAR, if it is 0, it is the background, and thus the traversal can obtain the coordinate points corresponding to the radiotherapy OAR image. Figure 2 The volume calculation of the radiotherapy OAR in each 5° target medical sub-image is to accumulate the pixel number of the radiotherapy OAR (OAR) in the same area range of each layer, and the pixel number of the OAR in the same layer is simplified to calculate the sector area. Taking the target center point as the starting point, the distance value between the pixel coordinates in the delineation information of the radiotherapy OAR image in each group of target medical sub-image and the target center point is calculated, and the maximum distance value and the minimum distance value between the radiotherapy OAR and the target center point are determined from the plurality of distance values. The sector area value of the radiotherapy OAR image in each layer of target medical sub-image is calculated through the maximum distance value, the minimum distance value and the interval angle; and finally, the volume value of the radiotherapy OAR image in each group of target medical sub-image is calculated according to the area value of the radiotherapy OAR image of each layer of target medical sub-image.

[0048] In an optional embodiment, the following formula can be used to calculate the volume value of the radiotherapy OAR image in each 5° target medical sub-image:

[0049]

[0050]

[0051] ​wherein, N is the total number of layers of the target medical image, r max is the distance of the farthest point to the target center point in the range to be calculated, in pixel as the basic unit; min is the distance of the nearest point to the target center point in the range to be calculated, in pixel as the basic unit.

[0052] In order to facilitate the calculation of the similarity value of the medical image in the historical case and the current target medical image, in the method for recommending the field angle provided in the embodiments of the present application, before obtaining the plurality of similarity values by calculating the similarity value of the first target feature information and the second target feature information corresponding to the plurality of historical cases stored in the target database, the method further comprises: obtaining the multi-layer medical image corresponding to each historical case, and performing feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer medical image corresponding to each historical case to obtain the second target feature information; and storing the second target feature information and the historical case corresponding to the second target feature information in the target database in the form of key-value pair.

[0053] Specifically, some representative historical cases are selected by experienced physicists, then the medical image corresponding to the historical case is obtained, and the feature extraction method described above is adopted to perform feature extraction on the medical image corresponding to each case to obtain the relevant feature value of each historical case, i.e. the second target feature information described above. After obtaining the second target feature information, the second target feature information and the historical case corresponding to the second target feature information are stored in the target database in the form of key-value pair. Through the above steps, the efficiency of calculating the similarity value of the medical image in the historical case and the current target medical image can be effectively improved.

[0054] In order to improve the accuracy of the similarity calculation, in the method for recommending the field angle provided in the embodiments of the present application, obtaining the plurality of similarity values by calculating the similarity value of the first target feature information and the second target feature information corresponding to the plurality of historical cases stored in the target database comprises: reading all the second target feature information from the target database; calculating the Euclidean distance between each feature value in the first target feature information and each feature value of the second target feature information to obtain the plurality of similarity values.

[0055] Determining the target field angle of the multi-layer target medical image from the field angles corresponding to the plurality of historical cases according to the plurality of similarity values comprises: determining the historical case corresponding to the maximum similarity value as the target historical case; obtaining the field angle corresponding to the target historical case, and taking the field angle corresponding to the target historical case as the target field angle of the multi-layer target medical image.

[0056] Specifically, the first target feature information is compared with the second target feature information of the historical cases in a 1:N manner. In each comparison, the second target feature information is loaded, and then the similarity is calculated in a 1:1 manner. The first target feature information is compared with the second target feature information of the historical cases in a loop, that is, the 1:N comparison is completed. The process can also be implemented by using the faiss tool library.

[0057] The similarity between the first target feature information and the second target feature information is calculated. In an optional embodiment, the Euclidean distance can be used for similarity calculation. The Euclidean distance formula is as follows:

[0058]

[0059] wherein K is the number of feature values, x 1,k is the kth feature value in the first target feature information, x 2,k is the kth feature value in the second target feature information.

[0060] After the 1:N comparison between the first target feature information and the second target feature information of the historical cases, the field angle corresponding to the second target feature information with the smallest Euclidean distance value is obtained, that is, the target field angle of the multi-layer target medical image.

[0061] In an optional embodiment, the flowchart as shown in Figure 3 can be used to recommend the field angle. Specifically, the feature extraction is performed according to the delineation information of the medical image of the patient to obtain the first target feature information. The similarity between the obtained first target feature information and the second target feature information corresponding to the historical cases in the target database is calculated, and the highest similar field angle is returned as the recommended field angle.

[0062] The method for recommending a field angle provided in the embodiments of the present application comprises the following steps: obtaining a multi-layer target medical image, wherein the multi-layer target medical image at least comprises delineation information of a radiotherapy target region and delineation information of a radiotherapy organ at risk; performing feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain first target feature information; calculating a similarity value of the first target feature information and second target feature information corresponding to a plurality of historical cases stored in a target database to obtain a plurality of similarity values; and determining a target field angle of the multi-layer target medical image from the field angles corresponding to the plurality of historical cases according to the plurality of similarity values. The method solves the problem that the field angle is determined by relying on artificial experience in the related art, and the efficiency of determining the field angle is relatively low. In the present scheme, the feature extraction is performed on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain the first target feature information corresponding to the radiotherapy organ at risk, and the field angle most similar to the first target feature information is obtained from the field angles corresponding to the plurality of historical cases as the recommended field angle, which can effectively reduce the large amount of time and energy consumed by the trial and error of a physicist, and the historical field angle is a feasible field angle proved by practice, and therefore the quality of the radiotherapy plan can be improved, and the efficiency of determining the field angle is improved.

[0063] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0064] The embodiments of the present application also provide a device for recommending a field angle. It should be noted that the device for recommending a field angle of the embodiments of the present application can be used to execute the method for recommending a field angle provided by the embodiments of the present application. The device for recommending a field angle provided by the embodiments of the present application is introduced as follows.

[0065] Figure 4 is a schematic diagram of the device for recommending a field angle according to the embodiments of the present application. As shown in Figure 4 the device comprises a first obtaining unit 401, an extraction unit 402, a calculation unit 403 and a determination unit 404.

[0066] The first obtaining unit 401 is configured to obtain a multi-layer target medical image, wherein the multi-layer target medical image at least comprises delineation information of a radiotherapy target region and delineation information of a radiotherapy organ at risk.

[0067] The extraction unit 402 is configured to perform feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain first target feature information.

[0068] The computing unit 403 is configured to calculate similarity values of the first target feature information and second target feature information corresponding to a plurality of historical cases stored in the target database, to obtain a plurality of similarity values.

[0069] The determining unit 404 is configured to determine a target field angle of the multi-layer target medical image from field angles corresponding to the plurality of historical cases according to the plurality of similarity values.

[0070] The field angle recommendation device provided by the embodiment of the present application obtains the multi-layer target medical image through the first obtaining unit 401, wherein the multi-layer target medical image at least includes delineation information of a radiotherapy target region and delineation information of a radiotherapy organ at risk; the extracting unit 402 extracts features of the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain first target feature information; the computing unit 403 calculates similarity values of the first target feature information and second target feature information corresponding to a plurality of historical cases stored in the target database, to obtain a plurality of similarity values; and the determining unit 404 determines a target field angle of the multi-layer target medical image from field angles corresponding to the plurality of historical cases according to the plurality of similarity values, thereby solving the problem that the field angle is determined by relying on artificial experience in the related art, which leads to a relatively low efficiency of determining the field angle. In the present solution, the features of the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image are extracted to obtain first target feature information corresponding to the radiotherapy organ at risk, and the field angle most similar to the first target feature information is obtained from the field angles corresponding to the plurality of historical cases as a recommended field angle, which can effectively reduce a large amount of time and energy consumed by the physicist for trial and error, and the historical field angle is a field angle that has been proven to be feasible through practice, so that the quality of the radiotherapy plan can also be improved, thereby achieving the effect of improving the efficiency of determining the field angle.

[0071] Optionally, in the field angle recommendation device provided by the embodiment of the present application, the extracting unit 402 includes: a reading subunit configured to read a target center point in the multi-layer target medical image, wherein the target center point is a center point of a historical field or a center point calculated according to the delineation information of the radiotherapy target region; a uniform division subunit configured to uniformly divide each layer of the target medical image according to the target center point and a preset interval angle to obtain a plurality of groups of target medical sub-images, wherein the plurality of groups of target medical sub-images are composed of the plurality of layers of target medical sub-images; and a first calculating subunit configured to calculate a relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point to obtain a first target feature value.

[0072] Optionally, in the field angle recommendation device provided by the embodiment of the present application, the first calculation subunit comprises: a calculation module, configured to calculate a volume value of the radiotherapy organ at risk image in each group of target medical sub-images according to the relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point; and a determination module, configured to take the minimum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point and the volume value of the radiotherapy organ at risk image in each group of target medical sub-images as the first target feature value.

[0073] Optionally, in the field angle recommendation device provided by the embodiment of the present application, the calculation module comprises: a first calculation sub-module, configured to take the target center point as a starting point to calculate distance values between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point, to obtain a plurality of distance values; a determination sub-module, configured to determine a maximum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point and a minimum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point from the plurality of distance values; a second calculation sub-module, configured to perform sector area calculation according to the maximum distance value, the minimum distance value and the interval angle to obtain an area value of the radiotherapy organ at risk image of each layer of target medical sub-images; and a third calculation sub-module, configured to calculate the volume value of the radiotherapy organ at risk image in each group of target medical sub-images according to the area value of the radiotherapy organ at risk image of each layer of target medical sub-images.

[0074] Optionally, in the field angle recommendation device provided by the embodiment of the present application, the device further comprises: a second acquisition unit, configured to, before obtaining a plurality of similarity values by calculating the first target feature information and the second target feature information corresponding to the plurality of historical cases stored in the target database, acquire the multi-layer medical images corresponding to each historical case, and perform feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer medical images corresponding to each historical case to obtain the second target feature information; and a storage unit, configured to store the second target feature information and the historical case corresponding to the second target feature information in the target database in the form of a key-value pair.

[0075] Optionally, in the field angle recommendation device provided by the embodiment of the present application, the calculation unit 403 comprises: a reading sub-unit, configured to read all the second target feature information from the target database; and a second calculation sub-unit, configured to calculate the Euclidean distance between each feature value in the first target feature information and each feature value of the second target feature information to obtain a plurality of similarity values.

[0076] Optionally, in the field angle recommendation device provided in the embodiments of this application, the determining unit 404 includes: a determining subunit, used to determine the historical case corresponding to the largest similarity value as the target historical case; and an obtaining subunit, used to obtain the field angle corresponding to the target historical case and use the field angle corresponding to the target historical case as the target field angle of the multi-layer target medical image.

[0077] The device for recommending the firing angle includes a processor and a memory. The first acquisition unit 401, extraction unit 402, calculation unit 403 and determination unit 404 mentioned above are all stored in the memory as program units. The processor executes the program units stored in the memory to realize the corresponding functions.

[0078] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and the recommended firing angle can be achieved by adjusting kernel parameters.

[0079] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0080] This invention provides a processor for running a program, wherein the program executes a method for recommending shooting field angles during runtime.

[0081] like Figure 5 As shown, this embodiment of the invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring multi-layer target medical images, wherein the multi-layer target medical images include at least the delineation information of the radiotherapy target area and the delineation information of radiotherapy-at-risk organs; extracting features from the delineation information of the radiotherapy-at-risk organs in the multi-layer target medical images to obtain first target feature information; calculating the similarity value between the first target feature information and second target feature information corresponding to multiple historical cases stored in the target database to obtain multiple similarity values; and determining the target radiation field angle of the multi-layer target medical images from the radiation field angles corresponding to the multiple historical cases based on the multiple similarity values.

[0082] Optionally, the feature extraction is performed on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain first target feature information, including: reading a target center point in the multi-layer target medical image, wherein the target center point is a center point of a historical field or a center point calculated according to the delineation information of the radiotherapy target volume; dividing each layer of the target medical image according to the target center point and a preset interval angle to obtain a plurality of groups of target medical sub-images, wherein the plurality of groups of target medical sub-images are composed of the plurality of layers of target medical sub-images; and calculating the relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point to obtain a first target feature value.

[0083] Optionally, the calculation of the relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point to obtain a first target feature value includes: calculating the volume value of the radiotherapy organ at risk image in each group of target medical sub-images according to the relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point; and taking the minimum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point and the volume value of the radiotherapy organ at risk image in each group of target medical sub-images as the first target feature value.

[0084] Optionally, the calculation of the volume value of the radiotherapy organ at risk image in each group of target medical sub-images according to the relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point includes: taking the target center point as a starting point, calculating the distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point to obtain a plurality of distance values; determining the maximum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point and the minimum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point from the plurality of distance values; performing sector area calculation according to the maximum distance value, the minimum distance value and the interval angle to obtain the area value of the radiotherapy organ at risk image in each layer of target medical image; and calculating the volume value of the radiotherapy organ at risk image in each group of target medical sub-images according to the area value of the radiotherapy organ at risk image in each layer of target medical image.

[0085] Optionally, before calculating the similarity values of the first target feature information and the second target feature information corresponding to a plurality of historical cases stored in the target database to obtain a plurality of similarity values, the method further includes: obtaining a plurality of layers of medical images corresponding to each historical case, and performing feature extraction on the delineation information of the radiotherapy organ at risk image in the plurality of layers of medical images corresponding to each historical case to obtain second target feature information; and storing the second target feature information and the historical case corresponding to the second target feature information in the target database in the form of key-value pairs.

[0086] Optionally, the calculating the similarity values between the first target feature information and the second target feature information corresponding to the plurality of historical cases stored in the target database comprises: reading all the second target feature information from the target database; and calculating the Euclidean distance between each feature value in the first target feature information and each feature value of the second target feature information to obtain the plurality of similarity values.

[0087] Optionally, the determining the target field angle of the multi-layer target medical image from the field angles corresponding to the plurality of historical cases according to the plurality of similarity values comprises: determining a historical case corresponding to the maximum similarity value as a target historical case; and obtaining the field angle corresponding to the target historical case and taking the field angle corresponding to the target historical case as the target field angle of the multi-layer target medical image.

[0088] The device herein can be a server, a PC, a PAD, a mobile phone, etc.

[0089] The application further provides a computer program product adapted to execute the program of the following method steps when executed on a data processing device: obtaining a multi-layer target medical image, wherein the multi-layer target medical image at least comprises delineation information of a radiotherapy target region and delineation information of a radiotherapy organ at risk; performing feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain first target feature information; calculating similarity values between the first target feature information and second target feature information corresponding to a plurality of historical cases stored in a target database to obtain a plurality of similarity values; and determining a target field angle of the multi-layer target medical image from field angles corresponding to the plurality of historical cases according to the plurality of similarity values.

[0090] Optionally, the performing feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain the first target feature information comprises: reading a target center point in the multi-layer target medical image, wherein the target center point is a center point of a historical field or a center point calculated according to the delineation information of the radiotherapy target region; dividing each layer of the target medical image according to the target center point and a preset interval angle to obtain a plurality of groups of target medical sub-images, wherein the plurality of groups of target medical sub-images are composed of the multi-layer target medical sub-images; and calculating the relative position between the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point to obtain the first target feature value.

[0091] Optionally, the calculating the relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point to obtain a first target feature value comprises: calculating a volume value of the radiotherapy organ at risk image in each group of target medical sub-images according to the relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point; and taking the minimum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point and the volume value of the radiotherapy organ at risk image in each group of target medical sub-images as the first target feature value.

[0092] Optionally, the calculating the volume value of the radiotherapy organ at risk image in each group of target medical sub-images according to the relative position of the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point comprises: taking the target center point as a starting point, calculating the distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point to obtain a plurality of distance values; determining the maximum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point and the minimum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point from the plurality of distance values; performing sector area calculation according to the maximum distance value, the minimum distance value and the interval angle to obtain an area value of the radiotherapy organ at risk image of each layer of target medical sub-images; and calculating the volume value of the radiotherapy organ at risk image in each group of target medical sub-images according to the area value of the radiotherapy organ at risk image of each layer of target medical sub-images.

[0093] Optionally, before the calculating the similarity value between the first target feature information and the second target feature information corresponding to a plurality of historical cases stored in the target database to obtain a plurality of similarity values, the method further comprises: obtaining a plurality of medical images corresponding to each historical case, and performing feature extraction on the delineation information of the radiotherapy organ at risk image in the plurality of medical images corresponding to each historical case to obtain the second target feature information; and storing the second target feature information and the historical case corresponding to the second target feature information in the target database in the form of a key-value pair.

[0094] Optionally, the calculating the similarity value between the first target feature information and the second target feature information corresponding to a plurality of historical cases stored in the target database to obtain a plurality of similarity values comprises: reading all the second target feature information from the target database; and calculating the Euclidean distance between each feature value in the first target feature information and each feature value of the second target feature information to obtain a plurality of similarity values.

[0095] Optionally, determining the target field angle of the multi-layer target medical image from the field angles corresponding to the historical cases according to the plurality of similarity values comprises: determining a historical case corresponding to a maximum similarity value as a target historical case; and obtaining a field angle corresponding to the target historical case, and taking the field angle corresponding to the target historical case as the target field angle of the multi-layer target medical image.

[0096] Those skilled in the art will understand that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer usable program code.

[0097] The present application is described with reference to the flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams.

[0098] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a process for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams.

[0100] In one typical arrangement, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0101] Memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable program read-only memory (EEPROM), flash memory, or other memory technologies. The memory is an example of computer readable media.

[0102] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0103] It should also be noted that the terms "comprising," "including," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements in the list, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0104] Those skilled in the art will appreciate that embodiments of the present application can be devised for a method, a system, or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer readable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0105] The above merely provides an example of the present application, and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall fall into the scope of claims of the present application.

Claims

1. A method of field angle recommendation, characterized by, The method comprises the following steps: acquiring a multi-layer target medical image, wherein the multi-layer target medical image comprises delineation information of a radiotherapy target region and delineation information of a radiotherapy organ at risk; extracting features of the delineation information of the radiotherapy organ at risk in the multi-layer target medical image to obtain first target feature information; calculating similarity values between the first target feature information and second target feature information corresponding to a plurality of historical cases stored in a target database to obtain a plurality of similarity values; determining a target field angle of the multi-layer target medical image from field angles corresponding to the plurality of historical cases according to the plurality of similarity values; wherein the step of extracting features of the delineation information of the radiotherapy organ at risk in the multi-layer target medical image to obtain first target feature information comprises the following steps: reading a target center point in the multi-layer target medical image, wherein the target center point is a center point of a historical field or a center point calculated according to the delineation information of the radiotherapy target region; dividing each layer of the target medical image according to the target center point and a preset interval angle to obtain a plurality of groups of target medical sub-images, wherein the plurality of groups of target medical sub-images are composed of a plurality of layers of target medical sub-images; calculating the relative position between the delineation information of the radiotherapy organ at risk in each group of target medical sub-images and the target center point to obtain the first target feature information.

2. The method of claim 1, wherein, The step of calculating the relative position between the delineation information of the radiotherapy organ at risk in each group of target medical sub-images and the target center point to obtain the first target feature information comprises the following steps: calculating the volume value of the radiotherapy organ at risk in each group of target medical sub-images according to the relative position between the delineation information of the radiotherapy organ at risk in each group of target medical sub-images and the target center point; taking the minimum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk in each group of target medical sub-images and the target center point and the volume value of the radiotherapy organ at risk in each group of target medical sub-images as the first target feature information.

3. The method of claim 2, wherein, The step of calculating the volume value of the radiotherapy organ at risk in each group of target medical sub-images according to the relative position between the delineation information of the radiotherapy organ at risk in each group of target medical sub-images and the target center point comprises the following steps: taking the target center point as a starting point, calculating the distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk in each group of target medical sub-images and the target center point to obtain a plurality of distance values; determining the maximum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk in each group of target medical sub-images and the target center point and the minimum distance value between the pixel coordinates in the delineation information of the radiotherapy organ at risk in each group of target medical sub-images and the target center point from the plurality of distance values; calculating the area value of the radiotherapy organ at risk in each layer of target medical sub-image according to the maximum distance value, the minimum distance value and the interval angle to obtain the area value of the radiotherapy organ at risk in each layer of target medical sub-image; calculating the volume value of the radiotherapy organ at risk in each group of target medical sub-images according to the area value of the radiotherapy organ at risk in each layer of target medical sub-image.

4. The method of claim 1, wherein, Before the calculating the similarity values between the first target feature information and the second target feature information corresponding to the plurality of historical cases stored in the target database, the method further comprises: obtaining the multi-layer medical image corresponding to each historical case, and performing feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer medical image corresponding to each historical case to obtain the second target feature information; storing the second target feature information and the historical case corresponding to the second target feature information in the target database in the form of key-value pairs.

5. The method of claim 4, wherein, The calculating the similarity values between the first target feature information and the second target feature information corresponding to the plurality of historical cases stored in the target database comprises: reading all the second target feature information from the target database; calculating the Euclidean distance between each feature value in the first target feature information and each feature value of the second target feature information to obtain the plurality of similarity values.

6. The method of claim 1, wherein, According to the plurality of similarity values, determining the target field angle of the multi-layer target medical image from the field angles corresponding to the plurality of historical cases comprises: determining the historical case corresponding to the maximum similarity value as the target historical case; obtaining the field angle corresponding to the target historical case, and taking the field angle corresponding to the target historical case as the target field angle of the multi-layer target medical image.

7. A field angle recommendation apparatus, characterized by comprising: comprises: a first obtaining unit configured to obtain a multi-layer target medical image, wherein the multi-layer target medical image at least includes delineation information of a radiotherapy target region and delineation information of a radiotherapy organ at risk; an extracting unit configured to perform feature extraction on the delineation information of the radiotherapy organ at risk image in the multi-layer target medical image to obtain first target feature information; a calculating unit configured to calculate similarity values between the first target feature information and second target feature information corresponding to a plurality of historical cases stored in a target database, to obtain a plurality of similarity values; a determining unit configured to determine a target field angle of the multi-layer target medical image from field angles corresponding to the plurality of historical cases according to the plurality of similarity values; wherein the extracting unit comprises: a reading subunit configured to read a target center point in the multi-layer target medical image, wherein the target center point is a center point of a historical field irradiation or a center point calculated according to the delineation information of the radiotherapy target region; a uniform division subunit configured to uniformly divide each layer of the target medical image according to the target center point and a preset interval angle to obtain a plurality of groups of target medical sub-images, wherein the plurality of groups of target medical sub-images are composed of a plurality of layers of target medical sub-images; and a first calculating subunit configured to calculate the relative position between the delineation information of the radiotherapy organ at risk image in each group of target medical sub-images and the target center point to obtain the first target feature information.

8. A processor, comprising: The processor is configured to run a program, wherein the program performs the method for recommending a field angle according to any one of claims 1 to 6 when the program is running.

9. An electronic device, comprising: The apparatus comprises one or more processors and memory storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-6 for recommending a field angle.

Images