Field identification method, computer device and computer readable storage medium

Abstract

The application relates to a field recognition method, computer equipment and a computer readable storage medium, wherein the field recognition method comprises the following steps: acquiring a field image generated by a radiotherapy device; performing binaryzation processing on the field image by traversing all gray values to determine a to-be-recognized image; recognizing a light spot center and an effective light spot in the to-be-recognized image; and determining a field shape in the to-be-recognized image according to the light spot center and the effective light spot. By utilizing all gray values to perform binaryzation processing, the to-be-recognized image in which the light spot is most complete and clear is determined, the light spot center and the effective light spot in the to-be-recognized image are recognized, the effective recognition area of the to-be-recognized image is determined, the field shape can be accurately determined according to the light spot center and the effective light spot, and the time consumption of QA verification can be reduced and the precision can be improved through automatic recognition.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a method for identifying shooting fields, a computer device, and a computer-readable storage medium. Background Technology

[0002] Radiation therapy is a local treatment method that uses radiation to treat tumors. The radiation includes alpha, beta, and gamma rays from radioactive isotopes, as well as X-rays, electron beams, proton beams, and other particle beams produced by various X-ray therapy machines or accelerators. The equipment used to perform radiation therapy is called a radiation therapy device. During radiation therapy, the radiation source generates radiation, and a conformal assembly conforms the radiation to the shape of the tumor. The patient lies on the treatment bed of the radiation therapy device, which carries the patient into the treatment chamber and positions the tumor area at the isocenter of the device. The conformal radiation passes through the isocenter at different angles, treating the patient's tumor.

[0003] The higher the precision of the radiation irradiation position of a radiotherapy device, the higher the treatment accuracy and the better it can prevent damage to the patient's healthy tissues. Therefore, to ensure the accuracy of the radiation generated by radiotherapy devices, quality assurance (QA) verification is usually required before use. However, current technologies only analyze and identify film images corresponding to straight radiation fields. There is no complete field identification scheme for other shapes of radiation fields, which makes QA verification of radiotherapy devices too time-consuming and inaccurate.

[0004] Currently, there is no effective solution to the problem that there is no complete field identification scheme in related technologies. Summary of the Invention

[0005] This application provides a method for identifying firing fields, a computer device, and a computer-readable storage medium to at least address the problem that there is no complete firing field identification scheme in the related art.

[0006] In a first aspect, embodiments of this application provide a radiation field identification method, comprising: acquiring a radiation field image generated by a radiotherapy device; performing binarization processing on the radiation field image by traversing all gray values ​​to determine an image to be identified; identifying the light spot center and effective light spot in the image to be identified; and determining the shape of the radiation field in the image to be identified based on the light spot center and effective light spot.

[0007] In one embodiment, the process involves binarizing the field image by traversing all gray values ​​to determine the image to be identified; binarizing the field image by traversing all gray values ​​to obtain all binarized images; determining the optimal gray value based on all the binarized images; and binarizing the field image with the optimal gray value to obtain the image to be identified.

[0008] In one embodiment, determining the optimal grayscale value based on all the binarized images includes: identifying light spots in all the binarized images and determining the number of light spots in all the binarized images; determining the initial grayscale value range based on the binarized image with the largest number of light spots; calculating the area of ​​light spots in all the binarized images corresponding to the initial grayscale value range; and taking the grayscale value corresponding to the binarized image with the smallest light spot area as the optimal grayscale value.

[0009] In one embodiment, identifying light spots in all binarized images and determining the number of light spots in all binarized images includes: identifying light spots in all binarized images; calculating the area of ​​all light spots and determining the geometric center of the light spot with the largest area; constructing a bounding box with the geometric center as the center; and calculating the number of light spots intersecting with the bounding box.

[0010] In one embodiment, identifying the spot center and effective spots of the image to be identified includes: identifying all spots in the image to be identified; taking the geometric center of the spot with the largest area as the spot center of the image to be identified; determining a boundary based on the spot center and the size of the image to be identified; and taking the spots within the boundary as the effective spots.

[0011] In one embodiment, determining the field shape in the image to be identified based on the spot center and the effective spot includes: constructing multiple circles in the image to be identified with the spot center as the center and at preset radius intervals; intersecting the multiple circles with the effective spot to form a node corresponding to each circle; constructing a linked list tree based on the node corresponding to each circle; and determining the field shape in the image to be identified based on the linked list tree.

[0012] In one embodiment, constructing a linked list tree based on the nodes corresponding to each circle includes: obtaining all nodes corresponding to each circle; connecting each node in a circle to the node with the smallest distance in the adjacent circles towards the center, forming a doubly linked list; and constructing a linked list tree from multiple doubly linked lists.

[0013] In one embodiment, determining the field shape in the image to be identified based on the linked list tree includes: filtering out doubly linked lists with branches from all doubly linked lists constituting the linked list tree; deleting the trunk portion of the doubly linked list with branches and retaining the branch portion; and performing linear fitting based on the doubly linked list with the branch portion and the doubly linked list without branches to determine the field shape in the image to be identified.

[0014] In a second aspect, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the field identification method as described in the first aspect above.

[0015] Thirdly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the field identification method as described in the first aspect above.

[0016] Compared to related technologies, the radiation field recognition method provided in this application first acquires the radiation field image generated by the radiotherapy equipment, then performs binarization processing on the radiation field image by traversing all gray values ​​to determine the image to be recognized, identifies the spot center and effective spot in the image to be recognized, and finally determines the shape of the radiation field in the image to be recognized based on the spot center and effective spot. By using all gray values ​​for binarization processing, the image to be recognized with the most complete and clear display of the spot is determined. Then, the spot center and effective spot in the image to be recognized are identified, thus determining the effective recognition area of ​​the image to be recognized. Finally, the shape of the radiation field can be accurately determined based on the spot center and effective spot. Automated recognition can reduce the time consumption of QA verification and improve accuracy.

[0017] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 This is a flowchart of a shooting field identification method according to an embodiment of this application;

[0020] Figure 2 This is a flowchart of a method for determining an image to be identified according to an embodiment of this application;

[0021] Figure 3 It is a binarized image according to an embodiment of this application;

[0022] Figure 4 This is a flowchart of a method for identifying valid light spots according to an embodiment of this application;

[0023] Figure 5 This is a flowchart of a method for determining the shape of a firing field according to an embodiment of this application;

[0024] Figure 6 It is the image to be identified according to the embodiments of this application;

[0025] Figure 7 This is a structural block diagram of a field identification device according to an embodiment of this application;

[0026] Figure 8 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0028] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0029] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0030] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0031] When a patient requires radiotherapy, the first step is to have a localization CT scan performed in the positioning room. Based on the images, the doctor determines the location of the tumor and outlines its contours. The Radiotherapy Planning System (TPS) then develops a treatment plan for the patient based on this outlined image. The TPS transmits the treatment plan to the Radiotherapy Information Management System (OIS), which schedules the patient's treatment. Once a patient is scheduled, before using the radiotherapy equipment, a Quality Assurance (QA) verification of the radiation field is performed to ensure accurate radiation placement and dosage, achieving precise treatment results. After QA verification, the radiotherapy equipment delivers radiation to the patient according to the acquired treatment plan.

[0032] During QA verification, the radiation source of the radiotherapy equipment generates radiation. The radiation conformal component adjusts the shape of the radiation to make it appear as a long strip. A phantom is placed along the path of the radiation, with a film placed in the center of the phantom. The radiation forms a straight radiation field image on the film. By rotating the treatment head of the radiotherapy equipment, another straight line intersecting the previous line is formed on the film. By continuously rotating the treatment head multiple times, multiple intersecting straight line radiation field images are formed on the film. Because multiple radiation fields intersect, this is also called a stellate radiation field image.

[0033] This embodiment provides a method for identifying shooting fields. The subject executing this method can be a computer device, which can be a device with computing processing capabilities, such as a desktop computer, laptop computer, tablet computer, or mobile phone. Figure 1 This is a flowchart of the firing field identification method according to an embodiment of this application, such as... Figure 1 As shown, the process includes the following steps:

[0034] Step S101: Obtain the radiation field image generated by the radiotherapy device.

[0035] During QA verification of radiotherapy equipment, the treatment head generates a radiation field image on the film. For example, the computer device can directly acquire the radiation field image after scanning; alternatively, the computer device can store the radiation field image in memory after scanning, and retrieve it from memory when needed.

[0036] Step S102: Binarize the field image by traversing all gray values ​​to determine the image to be identified.

[0037] The field image is binarized using all grayscale values ​​to obtain multiple binarized images. Among these, the binarized image with the most complete and clearest number of light spots is selected as the image to be identified. Specifically, when binarizing the field image using a single grayscale value, the pixel value of each pixel in the field image is compared with this grayscale value. Pixels with values ​​greater than or equal to this grayscale value have their values ​​set to 1; pixels with values ​​less than this grayscale value have their values ​​set to 0, thus obtaining the corresponding binarized image. First, it is necessary to calculate the binarized images corresponding to all grayscale values, and then determine the image to be identified from them. The range of all grayscale values ​​can be [0, 255]. Since the image quality of the binarized images corresponding to the highest and lowest grayscale values ​​is not ideal, all grayscale values ​​can also be a range of grayscale values ​​set by the physician according to the actual situation. This reduces the computational load on the computer and improves efficiency. This grayscale value range can be set according to the actual situation; this embodiment does not impose a specific limitation. For example, we can first select the binarized images with the most light spots from all the binarized images, and then determine the clearest binarized image from these images as the image to be recognized. Selecting the image with the most light spots is to ensure the accuracy of image recognition, while selecting the clearest image is to better recognize the image.

[0038] Step S103: Identify the center of the light spot and the effective light spot in the image to be identified.

[0039] After determining the image to be identified, the first step is to identify the light spots within that image. In the radiation field image, the black areas represent the parts illuminated by radiation, while the white areas represent the parts not illuminated. The black areas are the light spots in the radiation field image, which are also the light spots in the image to be identified. First, all the black areas in the image to be identified need to be identified, that is, all the light spots. Then, based on the geometric relationship of all the light spots, the geometric center of the pattern formed by all the light spots is found and used as the center of the light spot. Due to ray attenuation and scattering, the edges of the image to be identified may have discontinuous light spots. To facilitate identification, light spots within a preset range centered on the center of the light spot can be considered as effective light spots. This preset range can be determined by the physician based on the actual situation; this embodiment does not impose a specific limitation. Furthermore, selecting effective light spots can reduce the computational load of radiation field identification, further accelerating the efficiency of radiation field identification.

[0040] Step S104: Determine the shape of the radiation field in the image to be identified based on the center of the light spot and the effective light spot.

[0041] After determining the spot center and the effective spot, the centerline of the effective spot is first determined. The centerline is the line located at the center of the effective spot along its direction. Then, based on the spot intensity and the centerline of the effective spot, the shape of the radiation field in the image to be identified is determined.

[0042] The radiation field recognition method provided in this application first acquires a radiation field image generated by a radiotherapy device, then binarizes the radiation field image by traversing all grayscale values ​​to determine the image to be recognized, identifies the spot center and effective spot in the image to be recognized, and finally determines the shape of the radiation field in the image to be recognized based on the spot center and effective spot. By using all grayscale values ​​for binarization, the image to be recognized that displays the most complete and clear spot is determined. Then, the spot center and effective spot in the image to be recognized are identified, thus determining the effective recognition area of ​​the image to be recognized. Finally, the shape of the radiation field can be accurately determined based on the spot center and effective spot. Automated recognition can reduce the time consumption of QA verification and improve accuracy.

[0043] This embodiment provides a method for determining an image to be identified. Figure 2 This is a flowchart of a method for determining an image to be identified according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0044] Step S201: Traverse all gray values ​​to perform binarization processing on the field image to obtain all binarized images.

[0045] After acquiring the field images, each field image is binarized using all grayscale values ​​to obtain all binarized images. All grayscale values ​​can also be a range set by the physician based on the actual situation. This range can be set according to the actual situation, and is not specifically limited in this embodiment.

[0046] Step S202: Determine the optimal grayscale value based on all binarized images.

[0047] After obtaining all binarized images, the first step is to identify the light spots in each image and determine their quantity. This means that for each binarized image, the black areas (i.e., light spots) are identified, and the number of light spots is determined based on these identifications. Taking the determination of the number of light spots in one binarized image as an example... Figure 3 As shown, Figure 3 This is a binarized image according to an embodiment of this application. Each label in 'ah' represents a light spot. Figure 3 The binarized image contains a total of 8 light spots, meaning the total number of light spots is 8. For example, among all the binarized images, some have 8 light spots, some have 7, and some have 9; meaning that all binarized images will identify multiple categories of light spot counts. Based on the binarized image with the largest number of light spots, the initial grayscale value range is determined. This means first finding the number of light spots in all binarized images, and then selecting the binarized image with the most light spots. For example, if the most light spots are 9, then all binarized images with 9 light spots need to be selected. Then, based on the grayscale values ​​corresponding to the binarized image with the most light spots, the initial grayscale value range is determined. This means selecting the grayscale values ​​corresponding to the binarized image with the most light spots; the set of these grayscale values ​​is the initial grayscale value range. Finally, the area of ​​the light spots in all binarized images corresponding to the initial grayscale value range is calculated. After determining the initial grayscale value range, it is necessary to calculate the area of ​​all light spots in each binarized image. Then, by comparing the light spot areas in each binarized image, the binarized image with the smallest light spot area is determined. The grayscale value corresponding to the binarized image with the smallest light spot area is taken as the optimal grayscale value. The binarized image corresponding to this optimal grayscale value ensures that the number of light spots displayed in the image is maximized, and, given the maximum number of light spots, the image with the smallest light spot area is selected as the one most easily recognizable for the radiation field shape.

[0048] When identifying light spots in a binarized image and determining the number of light spots in the binarized image, it is first necessary to identify all light spots in all binarized images. When calculating the area of ​​each binarized image, the area of ​​all light spots in that image is first calculated, then the areas of all light spots are compared, and the light spot with the largest area is selected. The geometric center of the largest area light spot is then calculated. A bounding box is constructed around this geometric center; for example, a rectangular selection box is constructed around this geometric center. The side length of this rectangular selection box is half the diameter of the largest inscribed circle in the binarized image. The above example is only for illustration; the side length of the rectangular selection box can be set according to actual needs, and this embodiment does not impose specific limitations. After the rectangular selection box is constructed, the number of light spots intersecting with the rectangular selection box is calculated. This number of light spots is the number of light spots in the binarized image.

[0049] Step S203: Binarize the field image with the optimal gray value to obtain the image to be identified.

[0050] After determining the optimal grayscale value, the field image is binarized using the optimal grayscale value. Specifically, the pixel values ​​of pixels in the field image that are greater than or equal to the optimal grayscale value are adjusted to 1, and the pixel values ​​of pixels that are less than the optimal grayscale value are adjusted to 0, thus obtaining the image to be recognized.

[0051] This embodiment adjusts the grayscale values ​​of the binarized image by selecting different grayscale values. When adjusting the grayscale values, the binarized image is first made to have the maximum number of light spots. Based on this, the identified field shape is the most realistic field shape. Then, the binarized image with the smallest light spot area is selected. In this way, the outline of the binarized image is more distinct, which can better identify the corresponding field shape.

[0052] This embodiment provides a method for identifying effective light spots. Figure 4 This is a flowchart of a method for identifying valid light spots according to an embodiment of this application, such as... Figure 4 As shown, the process includes the following steps:

[0053] Step S401: Identify all light spots in the image to be identified.

[0054] A light spot is a series of black strip-shaped areas in an image to be identified. Identifying light spots means identifying all the black strip-shaped areas.

[0055] Step S402: The geometric center of the largest spot area is taken as the spot center of the image to be identified.

[0056] Multiple black strip-shaped regions intersect in the image to be identified. Due to ray attenuation and scattering, there are discontinuous light spots. To avoid the influence of noise and discontinuous light spots, it is necessary to select the light spot with the largest area to determine the center of the radiation field shape. First, the area of ​​all light spots needs to be calculated, and then the light spot with the largest area is selected. The geometric center of the light spot with the largest area is taken as the light spot center of the image to be identified.

[0057] Step S403: Determine the boundary based on the center of the light spot and the size of the image to be identified.

[0058] Similarly, to avoid the influence of edge noise in the image to be identified, only a portion of the light spot needs to be selected to determine the shape of the radiation field, which also eliminates noise at the image edges. Selecting a portion of the image can also speed up subsequent image recognition. For example, with the center of the light spot as the center, the inscribed circle of the image can be determined according to the image size, and this inscribed circle serves as the boundary. Understandably, this boundary can also be set by the physician according to the actual situation; this embodiment does not specifically limit the shape and size of the boundary.

[0059] Step S404: The light spots within the boundary are taken as valid light spots.

[0060] After the boundary is determined, the light spots inside the boundary are retained as valid light spots, and the light spots outside the boundary are erased.

[0061] This embodiment improves the accuracy of subsequent field shape recognition by defining boundaries and erasing noise and independent light spots outside the boundaries in the image to be identified, thus avoiding noise interference.

[0062] This embodiment provides a method for determining the shape of the firing field. Figure 5 This is a flowchart of a method for determining the shape of a firing field according to an embodiment of this application, such as... Figure 5 As shown, the process includes the following steps:

[0063] Step S501: Construct multiple circles in the image to be recognized, with the center of the light spot as the center and at preset radius intervals.

[0064] In the image to be identified, the center of the light spot and the effective light spot have been determined. To determine the centerline of the effective light spot, it is first necessary to construct multiple circles with the center of the light spot as the center. For example... Figure 6 As shown, Figure 6 This is the image to be identified according to an embodiment of this application. In the figure, 2 and 3 represent the smallest and largest circles, respectively. Multiple circles can also be evenly spaced between 2 and 3, and the spacing between the circles does not have to be equal; it is sufficient to ensure that a sufficient number of circles are set to determine the centerline of each light spot. In the figure, 1 is the rectangular selection box for determining the number of light spots.

[0065] In step S502, multiple circles intersect with the effective light spot to form a node corresponding to each circle.

[0066] Each constructed circle intersects with all valid light spots. Taking a circle as an example, since each valid light spot has a certain width, the intersection of a circle and a valid light spot forms an arc segment. The midpoint of this arc segment is taken as the node of the circle at the corresponding valid light spot position. A circle will intersect with all valid light spots, meaning a circle will form a node with each valid light spot. This is the node of the corresponding circle.

[0067] Step S503: Construct a linked list tree based on the node corresponding to each circle.

[0068] Obtain all nodes corresponding to each circle. Connect each node in a circle to the node with the smallest distance in the adjacent circle towards the center, forming a doubly linked list. For example, five circles are set from the center outwards, with the first circle closest to the center, followed by the second, third, fourth, and fifth circles. First, filter out all nodes in the first and second circles. Then, obtain the first node in the second circle, calculate the distance between it and all nodes in the first circle, and connect it to the node with the smallest distance. Next, obtain the second node in the second circle, calculate the distance between it and all nodes in the first circle, and connect it to the node with the smallest distance. Repeat this process for each remaining node in the second circle, calculating the distance between it and all nodes in the first circle, and connecting it to the node with the smallest distance. This completes the connection between nodes in the first and second circles. Referring to the connection between each node in the first circle and the nodes in the second circle, connect each node in the third circle to the nodes in the second circle, each node in the fourth circle to the nodes in the third circle, and each node in the fifth circle to the nodes in the fourth circle. This forms multiple doubly linked lists. Figure 6 The center lines of the black light spot regions in the diagram are all doubly linked lists. Multiple doubly linked lists placed together form a linked list tree.

[0069] Step S504: Determine the shape of the field of view in the image to be identified based on the linked list tree.

[0070] The process involves filtering out doubly linked lists that form the linked list tree, specifically those with branches. When creating the radiation field image, the conformal component is adjusted into a long strip, and then the treatment head is rotated to form a stellar radiation field. During this process, if the angle of rotation of the treatment head is too small at any given moment, the angle between two radiation fields will be too small. Since straight radiation fields have a certain width, this will cause partial overlap between the two straight radiation fields. Therefore, when constructing the linked list tree, branches will appear in the corresponding doubly linked lists. For example... Figure 6The center lines of sections 4 and 5 form a branched doubly linked list; the center lines of the remaining individual straight lines form a non-branched doubly linked list. After identifying a branched doubly linked list, the trunk portion of the branched doubly linked list is deleted, that is... Figure 6 The center line of the four parts, retaining the branch parts, that is Figure 6 The centerline of the five parts is determined. The main branch can interfere with the subsequent line fitting, so it needs to be deleted, keeping only the branch parts. Finally, line fitting is performed based on the doubly linked list of the branch parts and the doubly linked list without branches to determine the shape of the field of view in the image to be identified.

[0071] In this embodiment, the node corresponding to each circle is determined by constructing multiple concentric circles. The structure connecting each circle forms a doubly linked list, and all the doubly linked lists form a linked list tree. Then, the trunk of the doubly linked list with branches in the linked list tree is deleted. Linear fitting is performed using the branched parts and the doubly linked lists without branches to obtain the final field shape. This enables the recognition of star-shaped lines at any angle, making image recognition more accurate.

[0072] This application provides a method for approximate stellar field of film and EPD images. This method is applicable to stellar lines where the field lines ideally intersect completely at the center, and also applicable to stellar lines where the field lines do not ideally intersect at the center point, that is, where some field lines deviate from the center or the angle between some adjacent field lines is very small.

[0073] First, the geometric center of the star-shaped light spot is initially identified. Taking the case of three lines on the star-shaped light spot as an example, the geometric center of the largest light spot in the binary image is automatically obtained by binarizing the image with different gray values. Using this geometric center as the center, a bounding box is constructed with a length of 50% of the largest circle radius that can be obtained on the image. When three lines are exactly identified on the bounding box, the geometric center of the corresponding light spot is determined as the geometric center of the star-shaped light spot.

[0074] The system automatically finds the optimal grayscale binarized image. Assuming the image has 12, 11, 10, 9… lines, it iterates through each line count, automatically identifying the star-shaped lines using different grayscale binarized images. Finally, it selects the optimal grayscale threshold, which maximizes the number of lines identified within a 50% radius while minimizing the area of ​​the illuminated spot in the binarized image. Using the geometric center of the largest illuminated spot in the optimal grayscale binarized image as the center, it reclaims the largest radius on the image, erasing all grayscale information outside this circle and revealing all independent illuminated spots.

[0075] After obtaining the binarized image with the optimal grayscale value, concentric circles with increasing radii are drawn around the geometric center of the light spot. The intersection of these circles with the stellar line is used to identify the midpoint of the light spot where the circle intersects the stellar line, which is then taken as a point on the stellar line. For each point, the nearest point on the stellar line within the circle of the previous radius is found, forming a doubly linked list. This process continues until the search for the stellar line light spot under the circle of the largest radius is completed. Multiple doubly linked lists form a linked list tree. All points in the longest leaf tree are then fitted to a straight line to obtain the stellar line. This method can accurately identify the position of each radiation field direction on the film in an approximate stellar shape, providing a useful tool for QA (Quality Assurance) in radiotherapy physicists.

[0076] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures 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 may be executed in a different order than that shown here.

[0077] This embodiment also provides a field identification device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the terms "module," "unit," "subunit," etc., can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0078] Figure 7 This is a structural block diagram of a field identification device according to an embodiment of this application, such as... Figure 7 As shown, the device includes: an acquisition module 100, a binarization processing module 200, an identification module 300, and a field shape determination module 400.

[0079] The acquisition module 100 is used to acquire radiation field images generated by the radiotherapy equipment.

[0080] The binarization processing module 200 is used to traverse all gray values ​​to perform binarization processing on the shooting field image and determine the image to be recognized.

[0081] The recognition module 300 is used to identify the center of the light spot and the effective light spot in the image to be recognized.

[0082] The field shape determination module 400 is used to determine the field shape in the image to be identified based on the center of the light spot and the effective light spot.

[0083] The binarization processing module 200 is also used to traverse all gray values ​​to perform binarization processing on the shooting field image to obtain all binarized images; determine the optimal gray value based on all binarized images; and perform binarization processing on the shooting field image with the optimal gray value to obtain the image to be recognized.

[0084] The binarization processing module 200 is also used to identify light spots in all binarized images and determine the number of light spots in all binarized images; determine the initial grayscale value range based on the binarized image with the largest number of light spots; calculate the area of ​​light spots in all binarized images corresponding to the initial grayscale value range; and take the grayscale value corresponding to the binarized image with the smallest light spot area as the optimal grayscale value.

[0085] The binarization processing module 200 is also used to identify light spots in all binarized images; calculate the area of ​​all light spots and determine the geometric center of the light spot with the largest area; construct a bounding box with the geometric center as the center; and calculate the number of light spots that intersect with the bounding box.

[0086] The recognition module 300 is also used to recognize all light spots in the image to be recognized; to take the geometric center of the largest light spot as the light spot center of the image to be recognized; to determine the boundary based on the light spot center and the size of the image to be recognized; and to take the light spots within the boundary as valid light spots.

[0087] The field shape determination module 400 is also used to construct multiple circles in the image to be recognized with the center of the light spot as the center and at preset radius intervals; the multiple circles intersect with the effective light spot to form a node corresponding to each circle; a linked list tree is constructed according to the node corresponding to each circle; and the field shape in the image to be recognized is determined according to the linked list tree.

[0088] The field shape determination module 400 is also used to obtain all nodes corresponding to each circle; each node in the circle is connected to the node with the smallest distance in the adjacent circle in the direction of the circle center to form a doubly linked list; multiple doubly linked lists form a linked list tree.

[0089] The field shape determination module 400 is also used to filter out the doubly linked lists with branches among all the doubly linked lists that constitute the linked list tree; delete the trunk part of the doubly linked list with branches and retain the branch part; and perform line fitting based on the doubly linked list with branch part and the doubly linked list without branches to determine the field shape in the image to be identified.

[0090] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0091] In addition, combined Figure 1 The field identification method described in this application can be implemented by a computer device. Figure 8 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of this application.

[0092] The computer device may include a processor 81 and a memory 82 storing computer program instructions.

[0093] Specifically, the processor 81 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0094] The memory 82 may include a mass storage device for data or instructions. For example, and not limitingly, the memory 82 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 82 may include removable or non-removable (or fixed) media. Where appropriate, the memory 82 may be internal or external to a data processing device. In a particular embodiment, the memory 82 is non-volatile memory. In a particular embodiment, the memory 82 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0095] The memory 82 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 81.

[0096] The processor 81 implements any of the shooting field identification methods in the above embodiments by reading and executing computer program instructions stored in the memory 82.

[0097] In some embodiments, the computer device may further include a communication interface 83 and a bus 80. For example, Figure 8 As shown, the processor 81, memory 82, and communication interface 83 are connected through bus 80 and complete communication with each other.

[0098] The communication interface 83 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of this application. The communication port 83 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0099] Bus 80 includes hardware, software, or both, that couples components of a computer device together. Bus 80 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 80 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 80 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0100] The computer device can execute the field identification method in the embodiments of this application based on the acquired computer instructions, thereby achieving a combination of Figure 1 The described method for identifying shooting fields.

[0101] Furthermore, in conjunction with the field identification methods in the above embodiments, this application embodiment can provide a computer-readable storage medium for implementation. This computer-readable storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the field identification methods in the above embodiments.

[0102] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0103] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for identifying shooting fields, characterized in that, include: Acquire images of the radiation field generated by the radiotherapy equipment; Binarize the field image by iterating through all gray values ​​to determine the image to be identified; Identify the center of the light spot and the effective light spot in the image to be identified; Multiple circles are constructed in the image to be identified, with the center of the light spot as the center and at preset radius intervals. Multiple circles intersect with the effective light spot to form nodes corresponding to each circle; Construct a linked list tree based on the nodes corresponding to each circle; The shape of the field of view in the image to be identified is determined based on the linked list tree; The step of constructing a linked list tree based on the node corresponding to each circle includes: Get all nodes corresponding to each circle; Each node in the circle is connected to the node in the adjacent circle with the smallest distance towards the center, forming a doubly linked list; Multiple doubly linked lists form a linked list tree; The step of determining the field shape in the image to be identified based on the linked list tree includes: performing line fitting based on the linked list tree to determine the field shape in the image to be identified.

2. The field identification method according to claim 1, characterized in that, The image of the shooting field is binarized by traversing all gray values ​​to determine the image to be identified. Binarize the field image by iterating through all gray values ​​to obtain all binarized images; Based on all the binarized images, determine the optimal grayscale value; The field image is binarized using the optimal grayscale value to obtain the image to be identified.

3. The field identification method according to claim 2, characterized in that, The step of determining the optimal grayscale value based on all the binarized images includes: Identify light spots in all binarized images and determine the number of light spots in all binarized images; The range of gray values ​​for the initial screening is determined based on the binarized image with the maximum number of light spots. Calculate the area of ​​the light spot in all binarized images corresponding to the initial grayscale value range; The gray value corresponding to the binarized image with the smallest spot area is taken as the optimal gray value.

4. The field identification method according to claim 3, characterized in that, The process of identifying light spots in all binarized images and determining the number of light spots in all binarized images includes: Identify light spots in all binarized images; Calculate the area of ​​all light spots and determine the geometric center of the light spot with the largest area; Construct a bounding box centered on the geometric center; Calculate the number of light spots that intersect with the bounding box.

5. The firing field identification method according to claim 1, characterized in that, The identification of the light spot center and effective light spot of the image to be identified includes: Identify all light spots in the image to be identified; The geometric center of the largest spot area is taken as the spot center of the image to be identified; The boundary is determined based on the center of the light spot and the size of the image to be identified; The light spot within the boundary is taken as the effective light spot.

6. The firing field identification method according to claim 1, characterized in that, The step of performing line fitting based on the linked list tree to determine the field shape in the image to be identified includes: Filter out all doubly linked lists that make up the linked list tree, and select those doubly linked lists with branches; Delete the trunk portion of the doubly linked list with branches, and retain the branch portions; The shape of the field of fire in the image to be identified is determined by performing linear fitting on the doubly linked list of the branch portion and the doubly linked list without branches.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the field identification method as described in any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the field identification method as described in any one of claims 1 to 6.

Images