Device, method, electronic device and storage medium for determining field angle

Abstract

The present application discloses a device, method, electronic device and storage medium for determining a field angle, and relates to the field of medical technology. The device includes: a ray setting unit, which is used to set M rays for each of the N field angles; a feature acquisition unit, which is used to acquire the target features corresponding to each ray, wherein the target features include the spatial position information between the target point and the source point on each ray, and the density information on the target organ position where the target point is located. The source point is a ray emission source set when performing radiotherapy on the target object, and the target organ position is the target area of ​​the target object or the position on the endangered organ; a determination unit, which is used to determine at least one target field angle from the N field angles according to the target features corresponding to each ray. The present application solves the technical problem of low efficiency in determining the field angle caused by setting the field angle based on artificial experience in the prior art.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a device, method, electronic device and storage medium for determining a radiation field angle. Background Art

[0002] IMRT (Intensity-Modulated Radiation Therapy) is a way to treat cancer that can achieve high dose consistency while minimizing the radiation dose to organs at risk. However, the selection of the field angle in the traditional IMRT planning process is based on the trial and error search of the physicist, for example, the physicist selects the patient's field angle based on his or her own planning experience and understanding on the TPS (treatment planning system).

[0003] However, for novice physicists, due to their lack of experience, it usually takes a long time to optimize the field angle in order to improve the quality of the radiotherapy plan.

[0004] It can be seen that manual adjustment of the field angle is often highly dependent on the personal experience and expertise of the physicist. Different physicists may come up with different field design plans based on the same clinical data, resulting in inconsistency in plan quality. This subjectivity may lead to fluctuations in the planning effect, making it difficult to ensure the optimal dose distribution and minimize normal tissue exposure. Moreover, manual adjustment of the field angle is a time-consuming process that requires repeated trials and optimization, especially when dealing with complex tumor geometries, multi-target irradiation, or involving multiple critical organ restrictions. This process may require multiple iterations, which increases the time cost of radiotherapy planning and affects the timeliness of patient treatment.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The present application provides a device, method, electronic device and storage medium for determining a field angle, so as to at least solve the technical problem of low efficiency in determining the field angle caused by setting the field angle based on manual experience in the prior art.

[0007] According to one aspect of the present application, a device for determining a field angle is provided, comprising: a ray setting unit, for setting M rays for each of N field angles, wherein N and M are both integers greater than 1; a feature acquisition unit, for acquiring target features corresponding to each ray, wherein the target features include spatial position information between a target point and a source point on each ray, and density information on a target organ position where the target point is located, wherein the source point is a ray emission source set when performing radiotherapy on a target object, and the target organ position is a target area of ​​the target object or a position on an endangered organ; a determination unit, for determining at least one target field angle from the N field angles according to the target features corresponding to each ray, wherein the target field angle is used to formulate a radiotherapy plan for the target object.

[0008] In the device for determining the field angle provided in the present application, the ray setting unit includes: a first acquisition subunit, used to acquire a target area delineation image and an organ at risk delineation image of the target object, wherein the target area delineation image is used to characterize the contour information of the target area of ​​the target object in the medical image, and the organ at risk delineation image is used to characterize the contour information of the organ at risk of the target object in the medical image; a first setting subunit, used to set M rays for each of the N field angles according to the target area delineation image.

[0009] In the device for determining the field angle provided in the present application, the first setting subunit includes: a first setting module, which is used to set an initial ray passing through the isocenter of the target area outline image for each field angle; a second setting module, which is used to use the initial ray of each field angle as the center line, expand the first preset distance, and evenly set X first rays for each field angle, where X is an integer greater than 1; a first processing module, which is used to expand the X first rays by a second preset distance to obtain X second rays for each field angle; and a second processing module, which is used to use the initial ray, X first rays, and X second rays of each field angle as M rays for each field angle.

[0010] The device for determining the field angle provided in the present application also includes: a target point setting unit, which is used to set multiple target points on the initial ray of each field angle, wherein a preset length is spaced between any two adjacent target points, and the preset length is determined by the distance between the source point and the isocenter point of the target area delineation image; a processing unit, which is used to determine the target point on the first ray and the target point on the second ray of each field angle in a symmetrical manner based on the target point on the initial ray of each field angle.

[0011] In the device for determining the field angle provided in the present application, the determination unit includes: a first determination subunit, used to determine target information based on the target feature corresponding to each of the M rays, wherein the target information includes at least the position information and density information of the area of ​​interest involved in the irradiation path from the source point to the isocenter of the target area of ​​the target object; a second determination subunit, used to determine at least one target field angle from N field angles based on the target information.

[0012] In the device for determining the field angle provided in the present application, the second determination subunit includes: a tensor determination module, which is used to determine the target tensor according to the target information, wherein the target tensor includes: batch information, channel information, height information and width information, wherein the batch information represents the number of data samples used to update the model weights in one training iteration, the channel information is used to represent the color channel information of the image, the height information is used to represent the product of the number of field angles, the number of rays and the number of regions of interest, and the width information is used to represent the number of target points on each ray; the field determination module is used to determine at least one target field angle from N field angles based on the target tensor.

[0013] In the device for determining the field angle provided in the present application, the field determination module includes: a third processing submodule, which is used to determine the irradiation volume percentage and the irradiation volume percentage of each of the N field angles according to the target tensor through the prior knowledge learned by the target neural network model in the model training stage, wherein the irradiation volume percentage and the irradiation volume percentage of each field angle represent the sum of the irradiation volume percentages of all endangered organs irradiated when each field angle is used for irradiation, and the irradiation volume percentage of each endangered organ refers to the ratio of the actual irradiation volume of the endangered organ to the total volume of the endangered organ; a sorting submodule, which is used to sort the N field angles according to the irradiation volume percentage and the irradiation volume percentage of each field angle to obtain a sorting result; a fourth processing submodule, which is used to determine at least one target field angle from the N field angles according to the sorting result.

[0014] The device for determining the field angle provided in the present application also includes: a first processing unit, which is used to obtain a reference feature corresponding to each of the M rays, wherein the reference feature includes the spatial position information between the reference point on each ray and the reference source point, and the density information on the reference organ position where the reference point is located, the reference source point is a ray emission source set when performing radiotherapy on the reference object, and the reference organ position is the target area or the position on the endangered organ of the reference object; a second processing unit, which is used to determine reference information according to the reference feature corresponding to each of the M rays, wherein the reference information at least includes the position information and density information of the region of interest involved in the irradiation path from the reference source point to the isocenter point of the target area of ​​the reference object; a third processing unit, which is used to generate a reference tensor according to the reference information; a fourth processing unit, which is used to determine the irradiation volume percentage and the irradiation volume percentage of each field angle used in the radiotherapy process of the reference object according to the actual radiotherapy plan of the reference object; a model training unit, which is used to iteratively train the neural network according to the reference tensor and the irradiation volume percentage and the irradiation volume percentage of each field angle used in the radiotherapy process of the reference object to obtain a target neural network model.

[0015] In the device for determining the field angle provided in the present application, the fourth processing submodule includes: a strategy calling submodule, used to obtain a target strategy, wherein the target strategy is used to ensure that the angle difference between any two adjacent target field angles selected is greater than or equal to a preset angle when selecting at least one target field angle according to a sorting result; and a field determination submodule, used to determine at least one target field angle from N field angles according to the target strategy and the sorting result.

[0016] According to another aspect of the present application, a method for determining a field angle is also provided, which includes: setting M rays for each of N field angles, wherein N and M are both integers greater than 1; collecting target features corresponding to each ray, wherein the target features include spatial position information between a target point and a source point on each ray, and density information on a target organ position where the target point is located, wherein the source point is a ray emission source set when performing radiotherapy on a target object, and the target organ position is a target area of ​​the target object or a position on an endangered organ; determining at least one target field angle from the N field angles based on the target features corresponding to each ray, wherein the target field angle is used to formulate a radiotherapy plan for the target object.

[0017] According to another aspect of the present application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program runs, the device where the computer-readable storage medium is located controls the operation of the device for determining the field angle of any of the above items.

[0018] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors control the operation of the device for determining the field angle of any of the above items.

[0019] In the present application, a device for determining a field angle is provided, comprising: a ray setting unit, used to set M rays for each of N field angles, wherein N and M are both integers greater than 1; a feature acquisition unit, used to acquire target features corresponding to each ray, wherein the target features include spatial position information between a target point and a source point on each ray, and density information on a target organ position where the target point is located, wherein the source point is a ray emission source set when performing radiotherapy on a target object, and the target organ position is a target area of ​​the target object or a position on an endangered organ; a determination unit, used to determine at least one target field angle from the N field angles according to the target features corresponding to each ray, wherein the target field angle is used to formulate a radiotherapy plan for the target object.

[0020] From the above content, it can be seen that according to the technical solution of the present application, multiple rays can be set based on each field angle, and each ray can be used to collect target features, wherein the target features include the spatial position information between the target point and the source point on each ray, and the density information (HU value) at the target organ position where the target point is located. Finally, according to the technical solution of the present application, the target field angle to be used can be automatically predicted and determined based on the collected target features. Compared with the prior art, the solution of the present application will not be limited by the influence of manual experience, so it can efficiently output a more objective and accurate target field angle, which can not only reduce labor costs, but also shorten the time for determining the target field angle, thereby solving the technical problem of low efficiency in determining the field angle caused by setting the field angle based on manual experience in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0022] Figure 1 is a schematic diagram of an optional device for determining a field angle according to an embodiment of the present application;

[0023] Figure 2 is a schematic diagram of an optional isocenter plane of a PTV according to an embodiment of the present application;

[0024] Figure 3It is a flowchart of an optional method for determining a field angle according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] It should also be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) collected by this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation portals are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0028] According to an embodiment of the present application, an embodiment of a device for determining a field angle is provided, wherein: Figure 1 is a schematic diagram of an optional device for determining a field angle according to an embodiment of the present application, such as Figure 1 As shown, the device for determining the field angle includes: a ray setting unit 101, a feature collection unit 102, and a determination unit 103.

[0029] Optionally, the device for determining the field angle can be a software system, an embedded system combining software and hardware, or a device. Those skilled in the art should be aware that the present application does not specifically limit the specific form of the device for determining the field angle.

[0030] In an optional embodiment, the ray setting unit 101 is used to set M rays for each of the N field angles, where N and M are both integers greater than 1.

[0031] Optionally, during radiotherapy, the field and the field angle are two important concepts, which play an important role in ensuring the treatment effect and reducing the damage to normal tissue. Among them, the field refers to a specific area in the patient's body where the radiation is irradiated during radiotherapy. In the radiotherapy plan, the doctor will determine the range of the field according to the location, size and shape of the tumor, as well as the sensitivity of the surrounding normal tissue. The determination of the field needs to take into account the three-dimensional structure of the tumor so that the tumor cells can be accurately irradiated while minimizing damage to normal tissue. The field angle refers to the angle between the radiation beam and the patient's body surface. During radiotherapy, the doctor will choose a suitable field angle to irradiate the tumor according to the location and shape of the tumor. Different field angles can change the incident direction of the radiation beam, thereby achieving multi-angle irradiation of the tumor. Multi-angle irradiation helps to improve the treatment effect while reducing damage to normal tissue.

[0032] Optionally, the ray setting unit 101 may set M rays for each field angle, for example, 25 rays are set for a field angle (30 degrees); and 25 rays are also set for a field angle (65 degrees).

[0033] It should be noted that by setting M rays for each field angle, the radiation rays generated when radiation is performed according to the field angle can be simulated.

[0034] In an optional embodiment, the device for determining the field angle also includes a feature acquisition unit 102, which is used to collect target features corresponding to each ray, wherein the target features include spatial position information between the target point and the source point on each ray, and density information on the target organ position where the target point is located, the source point is a ray emission source set when performing radiotherapy on the target object, and the target organ position is the target area of ​​the target object or the position on the endangered organ.

[0035] Optionally, each ray may include multiple target points, and the target features corresponding to each ray are collected, mainly to collect the spatial position information between each target point on each ray and the source point, as well as the density information of the target organ where the target point is located. For example, assuming that the target point falls on the A position of PTV (Patient Target Volume, which refers to the target area that needs to receive radiotherapy during tumor treatment), the HU value (Hounsfield Unit, density value, also known as CT value, is a value used to describe tissue density) of the A position of PTV is collected; assuming that the target point falls on the B position of OAR (Organ at Risk), the HU value of the B position of OAR is collected.

[0036] By collecting target features, the correlation between the target point on each ray and the source point and the organs at risk / target organs can be determined. Since this correlation can reflect the irradiation effect of the rays emitted from the source point on the organs at risk / target organs, it can be used to screen the field angle later.

[0037] In an optional embodiment, the determination unit 103 is used to determine at least one target field angle from N field angles according to the target feature corresponding to each ray, wherein the target field angle is used to formulate a radiotherapy plan for the target object.

[0038] Optionally, the determination unit 103 may use a pre-trained neural network model to determine at least one target field angle from N field angles based on the target features corresponding to each ray. Alternatively, the determination unit 103 may use the reference features corresponding to each ray in multiple historical radiotherapy plans, and by comparing the similarity between the target features corresponding to each ray and the reference features, determine a historical radiotherapy plan with the highest matching degree with the target object, and then determine the target field angle (which may be a reference angle, or a field angle obtained by adjusting the reference angle) from the N field angles by using the field angle selected by the historical radiotherapy plan as a reference angle.

[0039] From the above content, it can be seen that according to the technical solution of the present application, multiple rays can be set based on each field angle, and each ray can be used to collect target features, wherein the target features include the spatial position information between the target point and the source point on each ray, and the density information (HU value) at the target organ position where the target point is located. Finally, according to the technical solution of the present application, the target field angle to be used can be automatically predicted and determined based on the collected target features. Compared with the prior art, the solution of the present application will not be limited by the influence of manual experience, so it can efficiently output a more objective and accurate target field angle, which can not only reduce labor costs, but also shorten the time for determining the target field angle, thereby solving the technical problem of low efficiency in determining the field angle caused by setting the field angle based on manual experience in the prior art.

[0040] In an optional embodiment, the ray setting unit 101 includes: a first acquisition subunit and a first setting subunit.

[0041] Optionally, the first acquisition subunit is used to acquire a target area delineation image and an organ at risk delineation image of the target object, wherein the target area delineation image is used to characterize the contour information of the target area of ​​the target object in the medical image, and the organ at risk delineation image is used to characterize the contour information of the organ at risk of the target object in the medical image; the first setting subunit is used to set M rays for each of N field angles according to the target area delineation image.

[0042] Optionally, the target area delineation image and the organ at risk delineation image can be obtained by manual delineation or by automatic delineation using a neural network model. Alternatively, the target area delineation image can be obtained by manual delineation, and the organ at risk delineation image can be obtained by automatic delineation using a neural network model. Of course, the organ at risk delineation image can also be obtained by manual delineation, and the target area delineation image can be obtained by automatic delineation using a neural network model.

[0043] It should be noted that since the purpose of radiotherapy is mainly to kill cancer cells in the target area through radiation, the target penetration area of ​​all radiation is the target area, but it may inevitably irradiate endangered organs. On this basis, the present application outlines the image according to the target area and sets M rays for each of the N field angles, so as to restore the real radiotherapy scene as much as possible.

[0044] In an optional embodiment, the first setting subunit includes: a first setting module, a second setting module, a first processing module, and a second processing module.

[0045] Optionally, the first setting module is used to set an initial ray passing through the isocenter of the target area outline image for each field angle; the second setting module is used to use the initial ray of each field angle as the center line, expand the first preset distance, and evenly set X first rays for each field angle, where X is an integer greater than 1; the first processing module is used to expand the X first rays by the second preset distance to obtain X second rays for each field angle; the second processing module is used to use the initial ray, X first rays and X second rays of each field angle as M rays for each field angle.

[0046] Optionally, for each of the N field angles, first set a ray (which can be recorded as the initial ray) passing through the isocenter of the PTV (i.e., the above-mentioned target area delineation image), and then use the initial ray of each field angle as the center line, expand the first preset distance, and evenly set X first rays for each field angle. For example, assuming that X is 12, 12 rays (which can be recorded as first rays) are evenly set on the circumference outside the first preset distance outside the initial ray. Finally, expand the X first rays by the second preset distance to obtain X second rays for each field angle. For example, the above 12 first rays are expanded outward by a certain distance (such as the second preset distance) to obtain 12 second rays. Finally, the initial ray, X first rays, and X second rays of each field angle are used as M rays for each field angle.

[0047] Optionally, Figure 2 is a schematic diagram of an optional isocenter plane of a PTV according to an embodiment of the present application, such as Figure 2 As shown in the figure, the middle point is the isocenter of the PTV, and the plane passing through this point and perpendicular to the field angle is the isocenter plane. Figure 2 It is the isocenter plane obtained by taking the field angle direction as the viewing angle direction. Figure 2 The irregular curve in is used to characterize the edge of the plane cut from the PTV by the isocenter. With the isocenter as the center, two radius values ​​are selected to draw a circle. The outermost circle is roughly the largest inscribed circle of the PTV contour, and the radius of the inner circle is half of the outer circle. The intersection of the two circles divided into 12 equal parts is the position where the ray passes. Therefore, Figure 2 An initial ray is set at the center point, 12 first rays are set at the 12 middle points, and 12 second rays are set at the 12 outermost points.

[0048] It should be noted that each ray angle corresponds to M rays, which are used to simulate the rays emitted by the ray source from each ray angle, so as to simulate the real radiotherapy scenario as much as possible.

[0049] In an optional embodiment, the device for determining the field angle includes: a target point setting unit and a processing unit.

[0050] Optionally, a target point setting unit is used to set multiple target points on the initial ray of each field angle, wherein any two adjacent target points are separated by a preset length, and the preset length is determined by the distance between the source point and the isocenter of the target area delineation image; the processing unit is used to determine the target point on the first ray and the target point on the second ray of each field angle in a symmetrical manner based on the target point on the initial ray of each field angle.

[0051] Optionally, multiple target points are set on each ray. The following method can be used to determine the target points:

[0052] First, multiple target points are set on the initial ray. For example, since the initial ray is shot from the source point to the isocenter of the PTV, assuming that the distance from the source point to the isocenter of the PTV is 1000mm, the preset length can be set to 0.5mm, and a target point is determined every 0.5mm on the line segment from the source point to the isocenter of the PTV in the initial ray, and a total of 2000 target points are determined.

[0053] It should be noted that the above-mentioned preset length can be customized, and the above-mentioned preset length of 0.5 mm is only an example. In addition, the distance from the source point to the isocenter of the PTV may also be other values, which are determined according to actual conditions.

[0054] Optionally, after determining the target point on the initial ray, since the first ray and the second ray can be regarded as rays obtained by translation or symmetry of the initial ray, each target point on the initial ray can be mapped to the first ray and the second ray in a symmetrical manner, thereby obtaining the target point on the first ray and the target point on the second ray.

[0055] In an optional embodiment, a feature collector can be set on the target point on each of the M rays by software, and the feature collector is used to collect target features. That is, the feature collector on each target point is used to collect the spatial position information between the target point and the source point and the density information of the target organ where the target point is located.

[0056] From the above content, it can be seen that the M rays of each field angle extract the HU value of each target point and the spatial position information from the target point to the source point at the distance between the source point and the center point such as PTV. It can be understood that at this field angle, the target features extracted using M rays are used to re-establish the medical imaging data of the target object. Since the imaging data of different patients are different, for different patients, the medical imaging data reconstructed using the solution of the present application is also personalized data.

[0057] In an optional embodiment, the determining unit 103 includes: a first determining subunit and a second determining subunit.

[0058] Optionally, the first determination subunit is used to determine target information based on target features corresponding to each of the M rays, wherein the target information includes at least position information and density information of the area of ​​interest involved in the irradiation path from the source point to the isocenter of the target area of ​​the target object; the second determination subunit is used to determine at least one target field angle from N field angles based on the target information.

[0059] Optionally, after obtaining the target features of each ray, the target features of each ray can be reorganized, and the feature data corresponding to the same ROI area can be integrated together. For example, if the target object has 8 OARs and 1 PTV, then the target feature on one ray can be further divided into 9 sub-features, which represent the respective features of the 8 OARs and 1 PTV at the distance from the source point to the isocenter of the PTV. The 9 sub-features are combined into the above-mentioned target information, that is, the target information at least includes the position information and density information of the region of interest involved in the irradiation path from the source point to the isocenter of the target area of ​​the target object.

[0060] Finally, the second determination subunit determines at least one target field angle from the N field angles according to the target information.

[0061] From the above content, it can be seen that based on the re-established medical imaging data of the target object, the position information of each ROI (Region of Interest) and the HU value information of the position can also be determined. These two information are the information that need to be considered when setting the field angle. Therefore, by using the target features to screen the target field angle from N field angles, the radiation dose of healthy tissues and organs around the PTV can be minimized.

[0062] In an optional embodiment, the second determination subunit includes: a tensor determination module and a field determination module.

[0063] Optionally, a tensor determination module is used to determine a target tensor based on target information, wherein the target tensor includes: batch information, channel information, height information and width information, wherein the batch information represents the number of data samples used to update the model weights in one training iteration, the channel information is used to represent the color channel information of the image, the height information is used to represent the product of the number of field angles, the number of rays and the number of regions of interest, and the width information is used to represent the number of target points on each ray; the field determination module is used to determine at least one target field angle from N field angles based on the target tensor.

[0064] Optionally, after obtaining the target information, the tensor determination module may determine a four-dimensional target tensor according to the target information, wherein the target tensor includes: batch information, channel information, height information, and width information.

[0065] Optionally, the following is an example of a target tensor:

[0066] Batch: can be set to a power of 2, depending on the performance of the graphics card;

[0067] Channel: can be set to 1;

[0068] Height: can be set to , from 0 to 360 degrees, a field angle is set every 2 degrees, for a total of 180 field angles; each field angle has 25 rays, where Z represents the number of ROIs of the target object, which is set according to the specific situation, so ;

[0069] Width: Here it is set to 2000, indicating that the number of target points on each ray is 2000.

[0070] In an optional embodiment, the field determination module includes: a third processing submodule, a sorting submodule and a fourth processing submodule.

[0071] Optionally, a third processing submodule is used to determine the irradiation volume percentage of each of the N field angles according to the target tensor through the prior knowledge learned by the target neural network model in the model training stage, wherein the irradiation volume percentage of each field angle represents the sum of the irradiation volume percentages of all endangered organs irradiated when each field angle is used for irradiation, and the irradiation volume percentage of each endangered organ refers to the ratio of the actual irradiation volume of the endangered organ to the total volume of the endangered organ; a sorting submodule is used to sort the N field angles according to the irradiation volume percentage of each field angle to obtain a sorting result; a fourth processing submodule is used to determine at least one target field angle from the N field angles according to the sorting result.

[0072] Optionally, the target tensor can be input into the target neural network model, and then the target neural network model determines multiple alternative field angles from N field angles based on the prior knowledge learned in the model training phase, where G is an integer greater than 1, and the alternative field angles are the field angles that the target neural network model preliminarily believes can be applied to the target object's radiotherapy process.

[0073] In addition, the target neural network model can also calculate the sum of the irradiated volume percentages of each of the N field angles. For example, when the field angle is 30 degrees, 5% of the heart volume is irradiated and 8% of the liver volume is irradiated, so the sum of the irradiated volume percentages of the field angle (30 degrees) is 13%. The sum of the irradiated volume percentages of each field angle is calculated in this way.

[0074] Optionally, the N field angles may be sorted in ascending order according to the irradiated volume percentage of each field angle to obtain a sorting result, and then at least one target field angle may be determined from the multiple candidate field angles according to the sorting result. In addition, at least one target field angle may be determined from the N field angles according to the sorting result. Among them, the field angle with a smaller irradiated volume percentage is preferably selected as the target field angle.

[0075] It should be noted that by calculating the sum of the irradiation volume proportions of each field angle, it can be ensured that the selected target field angle has the least impact on the organs at risk, thereby avoiding excessive and unnecessary irradiation of the organs at risk.

[0076] In an optional embodiment, the fourth processing submodule includes: a strategy calling submodule and a field determination submodule.

[0077] Optionally, a strategy calling submodule is used to obtain a target strategy, wherein the target strategy is used to ensure that the angle difference between any two adjacent target field angles selected is greater than or equal to a preset angle when selecting at least one target field angle according to the sorting result; and a field determination submodule is used to determine at least one target field angle from N field angles according to the target strategy and the sorting result.

[0078] Optionally, whether determining at least one target field angle from a plurality of candidate field angles according to the sorting result, or determining at least one target field angle from N field angles according to the sorting result, the target field angle can be determined in combination with the target strategy. For example, a preset number of field angles are selected in sequence as target field angles according to the sorting result. If the angle difference between any two adjacent field angles during the selection is less than the preset angle, the two adjacent field angles with the larger irradiation volume ratio are skipped, and the next field angle is selected until a preset number of target field angles are selected.

[0079] In an optional embodiment, the device for determining the field angle further includes: a first processing unit, a second processing unit, a third processing unit, a fourth processing unit and a model training unit.

[0080] Optionally, the first processing unit is used to obtain a reference feature corresponding to each of the M rays, wherein the reference feature includes spatial position information between a reference point on each ray and a reference source point, and density information on a reference organ position where the reference point is located, the reference source point is a ray emission source set when performing radiotherapy on a reference object, and the reference organ position is a target area or a position on an endangered organ of the reference object.

[0081] The second processing unit is used to determine reference information based on the reference feature corresponding to each of the M rays, wherein the reference information at least includes position information and density information of the area of ​​interest involved in the irradiation path from the reference source point to the isocenter point of the target area of ​​the reference object.

[0082] The third processing unit is used to generate a reference tensor based on the reference information; the fourth processing unit is used to determine the irradiated volume percentage of each field angle used in the radiotherapy of the reference object according to the actual radiotherapy plan of the reference object; the model training unit is used to iteratively train the neural network based on the reference tensor and the irradiated volume percentage of each field angle used in the radiotherapy of the reference object to obtain a target neural network model.

[0083] Optionally, the neural network used in this application includes at least: a feature extractor and a predictor. Among them, the feature extractor can be configured with eight convolutional layers, which extract distinguishable features of geometric information through convolutional layers of various step sizes. The width and height of the first convolutional layer are 1×Z respectively (Z is the number of ROIs of the patient, which is set according to the specific situation). The convolutional layer operates with a step size of Z and the same padding options. The width and height of the second convolutional layer are 1×M respectively, and a step size of M can be used to process target features extracted from M rays. The rest of the feature extractor is designed with six convolutional layers (width: 3, height: 3, step size: 1) and a maximum pooling layer. The output of the feature extractor is flattened and then passed to the predictor. The predictor is designed with four fully connected (FC) layers to extract the target features from arrive Continuous prediction.

[0084] Optionally, during the training of the target neural network model, the training data is a reference tensor, and the training label is the sum of the irradiated volume percentages of each field angle used by the reference object during radiotherapy. If the reference object uses a certain field angle, a first label can be set for the field angle, and the sum of the irradiated volume percentages of the field angle can be filled in the first label; if the reference object does not use a certain field angle, a second label can be set for the field angle, and the sum of the irradiated volume percentages does not need to be filled in the second label.

[0085] In addition, it should be noted that the determination process of the above-mentioned reference features, reference information and reference tensors can refer to the specific calculation process of the above-mentioned target features, target information and target tensors, and this application will not repeat them here.

[0086] From the above content, it can be seen that according to the technical solution of the present application, multiple rays can be set based on each field angle, and each ray can be used to collect target features, wherein the target features include the spatial position information between the target point and the source point on each ray, and the density information (HU value) at the target organ position where the target point is located. Finally, according to the technical solution of the present application, the target field angle to be used can be automatically predicted and determined based on the collected target features. Compared with the prior art, the solution of the present application will not be limited by the influence of manual experience, so it can efficiently output a more objective and accurate target field angle, which can not only reduce labor costs, but also shorten the time for determining the target field angle, thereby solving the technical problem of low efficiency in determining the field angle caused by setting the field angle based on manual experience in the prior art.

[0087] According to another aspect of the present application, a method for determining a field angle is also provided, wherein: Figure 3 is a flow chart of an optional method for determining a field angle according to an embodiment of the present application, such as Figure 3 As shown, the following steps are included:

[0088] Step S301, setting M rays for each of the N field angles.

[0089] In step S301, N and M are both integers greater than 1.

[0090] Optionally, during radiotherapy, the field and the field angle are two important concepts, which play an important role in ensuring the treatment effect and reducing the damage to normal tissue. Among them, the field refers to a specific area in the patient's body where the radiation is irradiated during radiotherapy. In the radiotherapy plan, the doctor will determine the range of the field according to the location, size and shape of the tumor, as well as the sensitivity of the surrounding normal tissue. The determination of the field needs to take into account the three-dimensional structure of the tumor so that the tumor cells can be accurately irradiated while minimizing damage to normal tissue. The field angle refers to the angle between the radiation beam and the patient's body surface. During radiotherapy, the doctor will choose a suitable field angle to irradiate the tumor according to the location and shape of the tumor. Different field angles can change the incident direction of the radiation beam, thereby achieving multi-angle irradiation of the tumor. Multi-angle irradiation helps to improve the treatment effect while reducing damage to normal tissue.

[0091] Optionally, M rays may be set for each field angle, for example, 25 rays may be set for a field angle of (30 degrees); and 25 rays may also be set for a field angle of (65 degrees).

[0092] It should be noted that by setting M rays for each field angle, the radiation rays generated when radiation is performed according to the field angle can be simulated.

[0093] Step S302: collecting target features corresponding to each ray.

[0094] In step S302, the target features include the spatial position information between the target point and the source point on each ray, and the density information on the target organ position where the target point is located. The source point is the ray emission source set when performing radiotherapy on the target object, and the target organ position is the target area of ​​the target object or the position on the endangered organ.

[0095] Optionally, each ray may include multiple target points, and the target features corresponding to each ray are collected, mainly to collect the spatial position information between each target point on each ray and the source point, and the density information of the target organ where the target point is located. For example, assuming that the target point falls on the A position of the PTV, the HU value of the A position of the PTV is collected; assuming that the target point falls on the B position of the OAR, the HU value of the B position of the OAR is collected.

[0096] By collecting target features, the correlation between the target point on each ray and the source point and the organs at risk / target organs can be determined. Since this correlation can reflect the irradiation effect of the rays emitted from the source point on the organs at risk / target organs, it can be used to screen the field angle later.

[0097] Step S303: determining at least one target field angle from the N field angles according to the target feature corresponding to each ray.

[0098] In step S303, the target field angle is used to formulate a radiotherapy plan for the target object.

[0099] Optionally, a pre-trained neural network model can be used to determine at least one target field angle from N field angles based on the target features corresponding to each ray. Alternatively, the reference features corresponding to each ray in multiple historical radiotherapy plans can be used to compare the similarity between the target features corresponding to each ray and the reference features to determine a historical radiotherapy plan with the highest matching degree with the target object, and then the field angle selected by the historical radiotherapy plan is used as a reference angle to determine the target field angle from N field angles (which can be a reference angle, or a field angle adjusted based on the reference angle).

[0100] From the above content, it can be seen that according to the technical solution of the present application, multiple rays can be set based on each field angle, and each ray can be used to collect target features, wherein the target features include the spatial position information between the target point and the source point on each ray, and the density information (HU value) at the target organ position where the target point is located. Finally, according to the technical solution of the present application, the target field angle to be used can be automatically predicted and determined based on the collected target features. Compared with the prior art, the solution of the present application will not be limited by the influence of manual experience, so it can efficiently output a more objective and accurate target field angle, which can not only reduce labor costs, but also shorten the time for determining the target field angle, thereby solving the technical problem of low efficiency in determining the field angle caused by setting the field angle based on manual experience in the prior art.

[0101] According to another aspect of the present application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program runs, the device where the computer-readable storage medium is located controls the operation of the device for determining the field angle of any of the above items.

[0102] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors control the operation of the device for determining the field angle of any of the above items.

[0103] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0104] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0105] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0106] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0107] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0108] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc., which can store program code.

[0109] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A device for determining a field angle, characterized in that: include: A ray setting unit, used for setting M rays for each of the N field angles, wherein N and M are both integers greater than 1; A feature acquisition unit, used for acquiring target features corresponding to each ray, wherein the target features include spatial position information between a target point and a source point on each ray, and density information on a target organ position where the target point is located, the source point being a ray emission source set when performing radiotherapy on a target object, and the target organ position being a target area or a position on an organ at risk of the target object; a determination unit, configured to determine at least one target field angle from the N field angles according to a target feature corresponding to each ray, wherein the target field angle is used to formulate a radiotherapy plan for the target object; Wherein, the determination unit includes: a first determination subunit, used to determine target information according to the target feature corresponding to each of the M rays, wherein the target information at least includes the position information and density information of the area of ​​interest involved in the irradiation path from the source point to the isocenter point of the target area of ​​the target object; a second determination subunit, used to determine at least one target field angle from the N field angles according to the target information.

2. The device for determining the field angle according to claim 1, characterized in that: The ray setting unit comprises: A first acquisition subunit is used to acquire a target area delineation image and an organ at risk delineation image of the target object, wherein the target area delineation image is used to characterize contour information of the target area of ​​the target object in the medical image, and the organ at risk delineation image is used to characterize contour information of the organ at risk of the target object in the medical image; The first setting subunit is used to set M rays for each of the N field angles according to the target area outline image.

3. The device for determining the field angle according to claim 2, characterized in that: The first setting subunit includes: A first setting module is used to set an initial ray passing through the isocenter of the target area delineation image for each field angle; A second setting module is used to evenly set X first rays of each field angle by taking the initial ray of each field angle as the center line and expanding the first preset distance, where X is an integer greater than 1; A first processing module, configured to expand the X first rays outward by a second preset distance to obtain X second rays at each field angle; The second processing module is used to use the initial ray of each field angle, the X first rays and the X second rays as the M rays of each field angle.

4. The device for determining the field angle according to claim 3, characterized in that: The device for determining the field angle also includes: A target point setting unit, used for setting a plurality of target points on the initial ray of each field angle, wherein any two adjacent target points are spaced apart by a preset length, and the preset length is determined by the distance between the source point and the isocenter of the target area delineation image; The processing unit is used to determine the target point on the first ray and the target point on the second ray of each field angle in a symmetrical manner according to the target point on the initial ray of each field angle.

5. The device for determining the field angle according to claim 1, characterized in that: The second determining subunit includes: A tensor determination module is used to determine a target tensor according to the target information, wherein the target tensor includes: batch information, channel information, height information and width information, wherein the batch information represents the number of data samples used to update the model weights in one training iteration, the channel information is used to represent the color channel information of the image, the height information is used to represent the product of the number of the field angles, the number of the rays and the number of the regions of interest, and the width information is used to represent the number of target points on each ray; The field determination module is used to determine at least one target field angle from the N field angles according to the target tensor.

6. The device for determining the field angle according to claim 5, characterized in that: The radiation field determination module comprises: A third processing submodule is used to determine the irradiation volume percentage and the irradiation volume percentage of each of the N field angles according to the target tensor through the prior knowledge learned by the target neural network model in the model training stage, wherein the irradiation volume percentage and the irradiation volume percentage of each field angle represent the sum of the irradiation volume percentages of all organs at risk irradiated when irradiation is performed using each field angle, and the irradiation volume percentage of each organ at risk refers to the ratio of the actual irradiation volume of the organ at risk to the total volume of the organ at risk; A sorting submodule, used for sorting the N field angles according to the irradiation volume proportion of each field angle, to obtain a sorting result; The fourth processing submodule is used to determine at least one target field angle from the N field angles according to the sorting result.

7. The device for determining the field angle according to claim 6, characterized in that: The device for determining the field angle also includes: a first processing unit, configured to obtain a reference feature corresponding to each of the M rays, wherein the reference feature includes spatial position information between a reference point on each ray and a reference source point, and density information on a reference organ position where the reference point is located, the reference source point being a ray emission source set when performing radiotherapy on a reference object, and the reference organ position being a position on a target area or an organ at risk of the reference object; a second processing unit, configured to determine reference information according to a reference feature corresponding to each of the M rays, wherein the reference information at least includes position information and density information of a region of interest involved in an irradiation path from the reference source point to an isocenter of a target area of ​​the reference object; A third processing unit, configured to generate a reference tensor according to the reference information; a fourth processing unit, configured to determine, according to an actual radiotherapy plan of the reference object, a sum of irradiation volume proportions of each field angle used in the radiotherapy process of the reference object; The model training unit is used to iteratively train the neural network according to the reference tensor and the irradiation volume proportion of each field angle used in the radiotherapy process of the reference object to obtain the target neural network model.

8. The device for determining the field angle according to claim 6, characterized in that: The fourth processing submodule comprises: A strategy calling submodule, used for obtaining a target strategy, wherein the target strategy is used to ensure that the angle difference between any two adjacent target field angles selected is greater than or equal to a preset angle when selecting at least one target field angle according to the sorting result; The field determination submodule is used to determine at least one target field angle from the N field angles according to the target strategy and the sorting result.

9. A method for determining a field angle, characterized in that: include: For each of the N field angles, M rays are set, where N and M are both integers greater than 1; Collecting target features corresponding to each ray, wherein the target features include spatial position information between a target point and a source point on each ray, and density information on a target organ position where the target point is located, the source point being a ray emission source set when performing radiotherapy on a target object, and the target organ position being a target area or a position on an organ at risk of the target object; Determining at least one target field angle from the N field angles according to the target feature corresponding to each ray, wherein the target field angle is used to formulate a radiotherapy plan for the target object; Wherein, according to the target feature corresponding to each of the rays, at least one target field angle is determined from the N field angles, including: determining target information according to the target feature corresponding to each of the M rays, wherein the target information at least includes position information and density information of the area of ​​interest involved in the irradiation path from the source point to the isocenter of the target area of ​​the target object; according to the target information, determining at least one target field angle from the N field angles.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located controls the operation of the device for determining the field angle according to any one of claims 1 to 8.

11. An electronic device, characterized in that: It comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors control the operation of the device for determining the field angle as described in any one of claims 1 to 8.

Images