CT image data-based radiation field accurate positioning system and method

Abstract

The embodiment of the invention provides a radiation field accurate positioning system and method based on CT image data, and belongs to the technical field of data processing. The system comprises a data processing module used for collecting target CT image data of a target object and performing data segmentation on the target CT image data to obtain a target segmentation result; the target recognition module is used for performing target recognition on each segmented region in the target segmentation result to obtain a target recognition result; the first reconstruction module is used for performing three-dimensional reconstruction according to the target recognition result and the segmented region to obtain an initial three-dimensional model; the second reconstruction module is used for determining a target three-dimensional model of the target object according to the target segmentation result and the initial three-dimensional model; the edge processing module is used for determining first edge information of the target tumor according to the target three-dimensional model and determining second edge information corresponding to the target organ according to the target three-dimensional model; and the result determination module is used for performing radiation field positioning analysis according to the first edge information and the second edge information to obtain a target positioning result.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a precise radiotherapy field positioning system and method based on CT image data. Background Art

[0002] The methods of radiotherapy vary according to different treatment purposes. For digestive tract tumors, there are significant differences in the number of radiotherapy days, dose, means, and measures between radical radiotherapy, adjuvant radiotherapy, and palliative radiotherapy. Among them, the dose of radical radiotherapy is relatively large, which can kill G-phase tumor cells simultaneously, thereby enhancing the effect of subsequent chemotherapy. However, since the location of digestive tract tumors is close to the heart and lung organs, lymph nodes, and lymph trunks, radiotherapy may cause damage to the patient's alveoli, myocardium, and lymph trunks. In addition, the autonomous and involuntary movements of the myocardium, diaphragm, and intercostal muscles in this area increase the difficulty of precise radiotherapy. At present, although image-guided radiotherapy technology is widely used, its accuracy and validity still have certain deficiencies.

[0003] Therefore, it is urgent to design a technical solution to solve at least one of the above technical problems. Summary of the Invention

[0004] The main purpose of the embodiments of the present invention is to provide a precise radiotherapy field positioning system and method based on CT image data, aiming to solve the problem that although image-guided radiotherapy technology is widely used in related technologies, its accuracy and validity still have certain deficiencies.

[0005] In a first aspect, the embodiments of the present invention provide a precise radiotherapy field positioning system based on CT image data, including:

[0006] A data processing module, configured to collect target CT image data corresponding to a target object, and perform data segmentation on the target CT image data to obtain a target segmentation result;

[0007] A target recognition module, configured to perform target recognition on each segmentation region in the target segmentation result to obtain a target recognition result;

[0008] A first reconstruction module, configured to perform three-dimensional reconstruction according to the target recognition result and the segmentation region to obtain an initial three-dimensional model corresponding to the segmentation region;

[0009] A second reconstruction module, configured to determine a target three-dimensional model corresponding to the target object according to the target segmentation result and the initial three-dimensional model;

[0010] An edge processing module, configured to determine first edge information corresponding to a target tumor according to the target three-dimensional model and determine second edge information corresponding to a target organ according to the target three-dimensional model;

[0011] A result determination module, configured to perform radiotherapy field positioning analysis based on the first edge information and the second edge information to obtain a target positioning result corresponding to the target object.

[0012] In a second aspect, an embodiment of the present invention provides a method for accurately positioning a radiotherapy field based on CT image data, including:

[0013] Collecting target CT image data corresponding to a target object, and performing data segmentation on the target CT image data to obtain a target segmentation result;

[0014] Performing target recognition on each segmentation region in the target segmentation result to obtain a target recognition result;

[0015] Performing three-dimensional reconstruction based on the target recognition result and the segmentation region to obtain an initial three-dimensional model corresponding to the segmentation region;

[0016] Determining a target three-dimensional model corresponding to the target object according to the target segmentation result and the initial three-dimensional model;

[0017] Determining first edge information corresponding to a target tumor according to the target three-dimensional model and determining second edge information corresponding to a target organ according to the target three-dimensional model;

[0018] Performing radiotherapy field positioning analysis based on the first edge information and the second edge information to obtain a target positioning result corresponding to the target object.

[0019] In a third aspect, an embodiment of the present invention further provides a terminal device, which includes a processor, a memory, a computer program stored on the memory and executable by the processor, and a data bus for realizing connection communication between the processor and the memory. When the computer program is executed by the processor, the steps of any radiotherapy field accurate positioning system based on CT image data provided in the specification of the present invention are implemented.

[0020] In a fourth aspect, an embodiment of the present invention further provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any radiotherapy field accurate positioning system based on CT image data provided in the specification of the present invention.

[0021] An embodiment of the present invention provides a radiotherapy field precise positioning system and method based on CT image data. The system uses a data processing module to collect target CT image data of a target object and perform data segmentation to obtain a target segmentation result, so as to accurately extract the image features of the target area, improve the accuracy of subsequent processing. Then, a target recognition module performs target recognition on each segmentation area in the target segmentation result, which can accurately distinguish different tissues and organs, provide a reliable basis for subsequent three-dimensional reconstruction, and ensure the accuracy of the reconstructed model. Then, a first reconstruction module performs three-dimensional reconstruction according to the target recognition result and the segmentation area to generate an initial three-dimensional model. Thus, a second reconstruction module combines the target segmentation result and the initial three-dimensional model to further optimize and combine the target three-dimensional model of the target object. Furthermore, an edge processing module determines the first edge information of the target tumor and the second edge information of the target organ through the target three-dimensional model, which can accurately delimit the boundaries of the tumor and the organ, provide key data support for radiotherapy planning. Finally, a result determination module performs radiotherapy field positioning analysis according to the first edge information and the second edge information to obtain the target positioning result of the target object, so as to ensure the accuracy and safety of radiotherapy, reduce the accidental injury to normal tissues, and improve the treatment effect. Through the collaborative work of the above modules, the accuracy and effect of radiotherapy can be significantly improved, the treatment risk can be reduced, and the treatment success rate and quality of life of patients can be improved. It also solves the problem that although image-guided radiotherapy technology is widely used in related technologies, its accuracy and validity still have certain deficiencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 It is a schematic block diagram of the module structure of a radiotherapy field precise positioning system based on CT image data provided by an embodiment of the present invention;

[0024] Figure 2 It is a schematic flowchart of a radiotherapy field precise positioning method based on CT image data provided by an embodiment of the present invention;

[0025] Figure 3 It is a schematic block diagram of the structure of a terminal device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0027] The flowchart shown in the accompanying drawings is only an example illustration, and does not necessarily include all the content and operations / steps, nor does it necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged, so the actual execution order may change according to the actual situation.

[0028] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0029] The embodiments of the present invention provide a radiotherapy field precise positioning system and method based on CT image data. Among them, the radiotherapy field precise positioning system based on CT image data can be applied to a terminal device, and the terminal device can be an electronic device such as a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0030] The following will describe in detail some embodiments of the present invention with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0031] Please refer to Figure 1 , Figure 1 which is a schematic diagram of the module structure of a radiotherapy field precise positioning system 200 provided by an embodiment of the present invention.

[0032] A radiotherapy field precise positioning system 200 based on CT image data provided by an embodiment of the present application. The radiotherapy field precise positioning system 200 based on CT image data includes a data processing module 201, a target recognition module 202, a first reconstruction module 203, a second reconstruction module 204, an edge processing module 205, and a result determination module 206. Among them, the data processing module 201 is configured to collect target CT image data corresponding to a target object, and perform data segmentation on the target CT image data to obtain a target segmentation result; the target recognition module 202 is configured to perform target recognition on each segmentation region in the target segmentation result to obtain a target recognition result; the first reconstruction module 203 is configured to perform three-dimensional reconstruction according to the target recognition result and the segmentation region to obtain an initial three-dimensional model corresponding to the segmentation region; the second reconstruction module 204 is configured to determine a target three-dimensional model corresponding to the target object according to the target segmentation result and the initial three-dimensional model; the edge processing module 205 is configured to determine first edge information corresponding to a target tumor according to the target three-dimensional model and determine second edge information corresponding to a target organ according to the target three-dimensional model; the result determination module 206 is configured to perform radiotherapy field positioning analysis according to the first edge information and the second edge information to obtain a target positioning result corresponding to the target object.

[0033] Exemplarily, the data processing module 201 uses a CT imaging device to collect CT image data of a target object, that is, a target patient, so as to obtain the target CT image data corresponding to the target object.

[0034] Exemplarily, the data processing module 201 uses image processing algorithms such as threshold segmentation, region growing, and edge detection to segment the target CT image data to obtain a target segmentation result.

[0035] Exemplarily, the target recognition module 202 classifies the type of each segmentation region in the target segmentation result according to a target recognition model such as a traditional machine learning model or a deep learning model, so as to obtain a target recognition result for each segmentation region. The target recognition result can be any one of a tumor or a certain organ.

[0036] Exemplarily, the first reconstruction module 203 extracts key feature points from the image of the segmentation region, such as corner points, edge points, or regions with rich texture, and uses feature extraction algorithms (such as SIFT, SURF, or ORB) to identify and describe these feature points, so as to associate the extracted feature points with the category information in the target recognition result, ensure that each feature point carries the category label of the target, and then estimate the depth information of the segmentation region through a monocular or binocular vision algorithm. Finally, according to the depth information and the image data of the segmentation region, a corresponding three-dimensional point cloud is generated, so as to convert the three-dimensional point cloud into an initial three-dimensional model corresponding to the segmentation region.

[0037] Exemplarily, the second reconstruction module 204 obtains the initial three-dimensional models corresponding to each segmented region, and then determines the relative positional relationship between the initial three-dimensional models according to the target segmentation result, so as to distribute the target organ and the target tumor based on the relative positional relationship and the initial three-dimensional models corresponding to each segmented region, thereby obtaining the target three-dimensional model corresponding to the target object. The target three-dimensional model includes the three-dimensional model of the organ and tumor distribution of the target object.

[0038] Exemplarily, the edge processing module 205 differentiates the regions of the target tumor and the target organ according to the target category annotation, and then extracts the surfaces of the target tumor and the target organ from the target three-dimensional model, so as to use a mesh segmentation algorithm (such as a segmentation method based on curvature or geometric features) to separate the surface regions of the target tumor and the target organ, and organize the extracted surface data into a set of vertices, edges and faces for facilitating the subsequent extraction of edge information. Then, an edge detection algorithm (such as normal change, curvature analysis or edge detection based on distance field) is used to identify the first edge information on the surface of the target tumor, and a similar edge detection process is performed on the surface of the target organ to identify the second edge information.

[0039] Exemplarily, the result determination module 206 receives the first edge information from the edge processing module, that is, the edge corresponding to the target tumor, and the second edge information, that is, the edge corresponding to the target organ, and then calculates the minimum distance, average distance and maximum distance between the first edge information and the second edge information, so as to analyze the relative positional relationship between the target tumor and the target organ, and judge whether the target tumor is close to or far from the target organ. Then, according to the three-dimensional coordinates of the first edge information and the second edge information, the spatial ranges of the target tumor and the target organ are calculated, so as to provide a reference for radiotherapy field positioning. Thus, according to the spatial range, the outer boundary of the radiotherapy field is determined to ensure that the radiotherapy field covers the tumor edge while avoiding the organ edge as much as possible, and the distance from the first edge information to the radiotherapy field boundary is calculated to evaluate the influence of the radiotherapy field on the organ, so as to ensure that the main part of the organ is located in the safe area of the radiotherapy field, reduce the risk of radiation damage. Then, according to the radiotherapy field boundary and the safe area analysis, the target positioning result of the target object is calculated. The target positioning result includes the central position, size, angle of the radiotherapy field and the relative relationship with the tumor and the organ.

[0040] In some embodiments, the data processing module includes: a data acquisition module for acquiring the initial CT image data corresponding to the target object; and a data correction module for correcting the contrast and brightness of the initial CT image data by using an adaptive gamma algorithm to obtain the target CT image data.

[0041] Exemplarily, the data acquisition module determines the target object for which CT image data needs to be acquired, and then uses a CT scanning device to perform data acquisition to obtain the initial CT image data of the target object.

[0042] Exemplarily, the data correction module calculates the histogram of the initial CT image data, analyzes the distribution of pixel values, and then determines the distribution characteristics of the bright and dark regions of the initial CT image data, providing a basis for gamma value adjustment. Then, according to the image histogram and the target distribution (such as linearized gray scale distribution or specific contrast requirements), it calculates the adaptive gamma value, and further uses an optimization algorithm (such as the least squares method or the gradient descent method) to automatically adjust the gamma value, and then applies adaptive gamma correction to the initial CT image data to adjust the distribution of pixel values, thereby obtaining the target CT image data.

[0043] In some embodiments, the data processing module includes: a data determination module, configured to determine the target segmentation quantity corresponding to the target CT image data, and determine a plurality of corresponding initial thresholds according to the target segmentation quantity; an initial segmentation module, configured to segment the target CT image data according to the plurality of initial thresholds to obtain an initial segmentation result corresponding to each initial threshold; an error determination module, configured to calculate a segmentation error according to the initial thresholds and the initial segmentation result to obtain an initial segmentation error; a data adjustment module, configured to adjust the initial thresholds according to the initial segmentation error to obtain a plurality of target thresholds that meet the error requirements; and a target segmentation module, configured to segment the target CT image data according to the target thresholds to obtain the target segmentation result.

[0044] Exemplarily, the data determination module determines the number of organs included according to the region of the photographed target object, and then determines an initial threshold for each type in the target segmentation data.

[0045] Exemplarily, the initial segmentation module uses a threshold segmentation algorithm in combination with the initial thresholds to segment the target CT image data to generate an initial segmentation result corresponding to each initial threshold.

[0046] Exemplarily, the error determination module uses segmentation error metrics (such as pixel error, region overlap, DICE coefficient, etc.) to calculate the segmentation error corresponding to each initial threshold.

[0047] Exemplarily, the data adjustment module uses optimization algorithms such as the gradient descent method and the genetic algorithm to adjust the initial thresholds according to the segmentation errors corresponding to the initial segmentation results, gradually reducing the segmentation error, and ensuring that there are no conflicts between the thresholds of the target types during the optimization process. Then, when the segmentation error meets the target error requirements, new target thresholds are generated.

[0048] Exemplarily, the target segmentation module uses each target threshold to separately segment the target CT image data, thereby generating a target segmentation result corresponding to the target CT image data.

[0049] Specifically, the data determination module determines the target segmentation quantity and multiple initial thresholds according to the target CT image data. The initial segmentation module performs segmentation based on these thresholds and obtains an initial segmentation result. The error determination module calculates the segmentation error. The data adjustment module adjusts the thresholds according to the error to obtain target thresholds that meet the requirements. Finally, the target segmentation module segments the target CT image according to the target thresholds to obtain a target segmentation result. This process combines multiple links such as threshold generation, segmentation execution, error calculation, and optimization adjustment to ensure the accuracy and reliability of the segmentation result.

[0050] In some implementation methods, the error determination module includes: a pixel analysis module for performing pixel analysis on the target CT image data to obtain a pixel histogram corresponding to the target CT image data; a range determination module for determining a relevant pixel range corresponding to the initial segmentation result according to the initial thresholds, where the relevant pixel range is between a first pixel value and a second pixel value; an error calculation module for calculating the initial segmentation error corresponding to the initial threshold according to the first pixel and the second pixel using the pixel histogram; where the initial segmentation error is obtained according to the following formula:

[0051]

[0052] where err represents the initial segmentation error, k represents the target segmentation quantity, value 1in represents the first pixel value corresponding to the i-th initial threshold in the n-th pixel channel, value 2i represents the second pixel value corresponding to the i-th initial threshold in the n-th pixel channel, and p(j) represents the distribution probability corresponding to the pixel value j in the pixel histogram.

[0053] Exemplarily, the pixel analysis module counts the number of occurrences of each pixel value in the target CT image data to obtain a corresponding pixel histogram, and the pixel histogram reflects the distribution of different pixel values in the target CT image data.

[0054] Exemplarily, the range determination module obtains multiple initial thresholds from the data determination module, and then analyzes the pixel value range corresponding to each initial threshold. For each initial threshold, determine the pixel value range in its corresponding segmentation result, including a first pixel value and a second pixel value. For example, the first pixel value and the second pixel value respectively represent the minimum pixel value and the maximum pixel value in the segmentation result.

[0055] Exemplarily, the error calculation module calculates the initial segmentation error corresponding to the initial threshold according to the first pixel and the second pixel by using the pixel histogram in combination with the following formula:

[0056]

[0057] where err represents the initial segmentation error, k represents the number of target segments, value 1in represents the first pixel value corresponding to the i-th initial threshold in the n-th pixel channel, value 2i represents the second pixel value corresponding to the i-th initial threshold in the n-th pixel channel, and p(j) represents the distribution probability corresponding to the pixel value j in the pixel histogram.

[0058] Exemplarily, through this formula, the segmentation error can be quantified into specific numerical values, thereby providing an objective and comparable evaluation index. This helps to intuitively understand the performance differences between different initial thresholds or different segmentation methods. Calculating the error by using the pixel histogram in combination with the formula can take into account the distribution of pixel values in the target CT image data. This makes the error calculation more accurate and can reflect the segmentation accuracy and precision of the segmentation result.

[0059] In some embodiments, the target recognition module includes: an image segmentation module for locally segmenting the segmentation region by using the image segmentation layer of the target classification model with a plurality of preset boxes of different scales and ratios to obtain a plurality of local regions corresponding to the segmentation region; a feature extraction module for respectively extracting features from the plurality of local regions by using the feature extraction layer of the target classification model to obtain multi-scale feature maps corresponding to each of the local regions; an out-class calculation module for calculating a first correlation value between the multi-scale feature maps and a preset feature map corresponding to a preset type by using the out-class local interaction layer of the target classification model; an in-class calculation module for calculating a second correlation value between any two of the multi-scale feature maps by using the in-class local interaction layer of the target classification model; an initial classification module for determining an initial classification result corresponding to the local region according to the first correlation value, the second correlation value, and the multi-scale feature maps by using the type classification layer of the target classification model; and a classification fusion module for determining the target recognition result corresponding to the segmentation region by using the classification fusion layer of the target classification model according to the initial classification result by using a voting mechanism.

[0060] Exemplarily, the target recognition module includes an image segmentation module, a feature extraction module, an out-class calculation module, an in-class calculation module, an initial classification module, and a classification fusion module.

[0061] Exemplarily, the image segmentation module generates a plurality of preset boxes with different scales and ratios according to the image segmentation layer of the target classification model. These preset boxes are used to cover different parts of the segmentation region, and then the preset boxes are used to perform local image segmentation on the segmentation region to generate a plurality of local regions. Each local region corresponds to a preset box and contains a part of the target CT image data covered by the preset box.

[0062] Exemplarily, the feature extraction module respectively extracts features from a plurality of local regions according to the feature extraction layer of the target classification model to generate multi-scale feature maps corresponding to each local region. The feature extraction layer can be a convolutional layer, a pooling layer, etc. in a convolutional neural network (CNN).

[0063] Exemplarily, the out-class calculation module calculates the similarity between each multi-scale feature map and a preset feature map corresponding to a preset type such as a target organ type or a target tumor type learned in advance according to the out-class local interaction layer of the target classification model to obtain a first correlation value. These preset feature maps represent the typical features of different classes.

[0064] Exemplarily, the in-class calculation module uses the in-class local interaction layer of the target classification model to perform feature classification on each multi-scale feature map to obtain classification information corresponding to each multi-scale feature map, and then calculates a second correlation value between any two multi-scale feature maps according to the classification information. The closer the classification information is, the more it indicates that the multi-scale feature maps have the same classification type, and thus have a stronger correlation compared to other multi-scale feature maps with dissimilar classification information.

[0065] Exemplarily, the initial classification module determines the initial classification result of each local region according to the type classification layer of the target classification model by using the first correlation value, the second correlation value, and the multi-scale feature map. The type classification layer can be a fully connected layer or a softmax layer for outputting the class probability of each local region.

[0066] Exemplarily, the classification fusion module determines the target recognition result of the segmentation region according to the classification fusion layer of the target classification model by using the initial classification results of a plurality of local regions through a voting mechanism. The voting mechanism can be simple majority voting, weighted voting, etc.

[0067] In some embodiments, the first reconstruction module includes: a vertex determination module, configured to determine the three-dimensional vertex distribution positions corresponding to the segmentation region according to the target recognition result and the segmentation region by using a convolutional neural network; a coordinate supplement module, configured to perform coordinate point insertion according to the three-dimensional vertex distribution positions and the segmentation region to determine a first three-dimensional model corresponding to the segmentation region; a surface reconstruction module, configured to reconstruct a three-dimensional surface of the first three-dimensional model by using the least squares method to obtain a second three-dimensional model; and a matching adjustment module, configured to perform matching adjustment on the second three-dimensional model by using the target features corresponding to the segmentation region to obtain an initial three-dimensional model.

[0068] Exemplarily, the vertex determination module obtains the target recognition result and the segmentation region, and then selects the convolutional neural network corresponding to the segmentation region according to the target recognition result, so as to input the image data corresponding to the segmentation region into the trained convolutional neural network. Then, the network will output the prediction of the three-dimensional vertex distribution positions of each part within the segmentation region, and obtain the three-dimensional vertex distribution positions corresponding to the segmentation region.

[0069] Exemplarily, in the regions where the vertices are sparse or missing, the coordinate supplement module reasonably inserts new coordinate points according to the positions and distribution rules of the surrounding vertices. Ensure that the inserted coordinate points are consistent with the surrounding vertices in terms of spatial and geometric relationships. Then, use the three-dimensional vertex distribution positions and the inserted coordinate points to jointly construct the first three-dimensional model of the segmentation region.

[0070] Exemplarily, the surface reconstruction module uses the least squares method to fit the surface of the first three-dimensional model, and then finds the best fitting surface by minimizing the sum of squared errors. Thus, according to the result of the least squares method, reconstruct the three-dimensional surface of the segmentation region to generate a second three-dimensional model.

[0071] Exemplarily, the matching adjustment module first extracts the key features of the region from the segmentation region. These key features may include various detailed information such as shape, texture, color, etc., and are used to accurately describe the characteristics of the target. Next, match the extracted target features with the second three-dimensional model. Through comparative analysis, identify the regions in the model that do not match or deviate from the target features. Adjust the second three-dimensional model according to the matching result, such as shape correction, texture mapping, etc., to ensure that the geometric features and surface details of the model are more in line with the true features of the target. Through this series of adjustments, finally generate an initial three-dimensional model, making it highly consistent with the key features of the target region, thereby improving the accuracy and consistency of the model.

[0072] In some embodiments, the result determination module includes: a surface determination module configured to obtain first surface information corresponding to the first edge information and second surface information corresponding to the second edge information; an information determination module configured to determine a radiation range corresponding to the radiotherapy field and an initial positioning result corresponding to the target object; a first calculation module configured to calculate a first radiation value corresponding to the target tumor under the first surface information for the radiotherapy field according to the radiation range and the initial positioning result; a second calculation module configured to calculate a second radiation value corresponding to the target organ under the second surface information for the radiotherapy field according to the radiation range and the initial positioning result; a radiation calculation module configured to determine a target radiation value corresponding to the initial positioning result according to the first radiation value and the second radiation value; and a positioning determination module configured to adjust the initial positioning result according to the radiation value to obtain the target positioning result corresponding to the target object.

[0073] Exemplarily, the surface determination module determines the first surface information and the second surface information for the first edge information and the second edge information respectively by a surface fitting or reconstruction method. The first surface information describes the surface morphology of the target tumor, and the second surface information describes the surface morphology of the target organ.

[0074] Exemplarily, the information determination module determines the radiation range corresponding to the radiotherapy field according to expert experience or historical records. The radiation range includes information such as the intensity, direction, and coverage area of the radiation. And the initial positioning result of the target object is obtained according to expert experience.

[0075] Exemplarily, the first calculation module first calculates first distance information between the initial positioning result and the first surface information. Next, according to the first distance information and the radiation range of the radiotherapy field, a first radiation value corresponding to the target tumor under the first surface information for the radiotherapy field is calculated using the mapping relationship between distance and radiation. The magnitude of the first radiation value directly affects the treatment effect, and the larger the value, the better, because a higher radiation value can ensure sufficient irradiation dose to the tumor, thereby effectively killing tumor cells and improving the success rate of treatment. Through this process, it is ensured that the treatment of the tumor can fully play its role and achieve the best treatment effect.

[0076] Exemplarily, the second calculation module first calculates the second distance information between the initial positioning result and the second surface information. Based on this, in combination with the radiation range of radiotherapy and the second distance information, the module calculates the second radiation value corresponding to the target organ under the second surface information by using the mapping relationship between distance and radiation. To ensure the safety of treatment, the smaller the second radiation value, the better, because a lower radiation value can effectively reduce the radiation dose to the target organ, thereby avoiding unnecessary radiation damage and reducing the possible side effects during treatment. By accurately calculating and controlling the second radiation value, the safety of the target organ in radiotherapy is ensured, further improving the reliability of treatment and the comfort of the patient.

[0077] Exemplarily, the radiation calculation module first calculates the reciprocal of the second radiation value, and then determines the target radiation value corresponding to the initial positioning result by summing the reciprocal of the second radiation value and the first radiation value. The target radiation value is a comprehensive radiation dose assessment of the target tumor and organs, which protects normal tissues while maximizing the treatment effect.

[0078] Exemplarily, the positioning determination module adjusts the initial positioning result according to the target radiation value to optimize the positioning accuracy of radiotherapy. The goal of the adjustment is to make the radiation value of the target tumor reach the best treatment effect while minimizing the radiation dose to the target organ as much as possible. Thus, through multiple iterations and adjustments, the target positioning result corresponding to the target object is finally determined. Ensure that the final positioning result can meet the requirements of the treatment plan and provide the most optimized treatment plan. Thus, by adjusting the initial positioning result, it is ensured that the final positioning result can maximize the treatment effect, minimize side effects, and improve the safety and effectiveness of treatment.

[0079] As Figure 2 shown, the method for precise radiotherapy field positioning based on CT image data includes steps S101 to S106.

[0080] Step S101: Collect the target CT image data corresponding to the target object, and perform data segmentation on the target CT image data to obtain a target segmentation result.

[0081] Step S102: Perform target recognition on each segmentation region in the target segmentation result to obtain a target recognition result.

[0082] Step S103: Perform three-dimensional reconstruction according to the target recognition result and the segmentation region to obtain an initial three-dimensional model corresponding to the segmentation region.

[0083] Step S104: Determine the target three-dimensional model corresponding to the target object according to the target segmentation result and the initial three-dimensional model.

[0084] Step S105: Determine the first edge information corresponding to the target tumor based on the target three-dimensional model and determine the second edge information corresponding to the target organ based on the target three-dimensional model.

[0085] Step S106: Perform radiotherapy field positioning analysis based on the first edge information and the second edge information to obtain the target positioning result corresponding to the target object.

[0086] In some embodiments, the acquisition of the target CT image data corresponding to the target object includes:

[0087] Acquire the initial CT image data corresponding to the target object;

[0088] Use the adaptive gamma algorithm to perform contrast and brightness correction on the initial CT image data to obtain the target CT image data.

[0089] In some embodiments, the data segmentation of the target CT image data to obtain the target segmentation result includes:

[0090] Determine the target segmentation number corresponding to the target CT image data, and determine a corresponding plurality of initial thresholds according to the target segmentation number;

[0091] Segment the target CT image data according to the plurality of initial thresholds to obtain an initial segmentation result corresponding to each initial threshold;

[0092] Calculate the segmentation error according to the initial threshold and the initial segmentation result to obtain the initial segmentation error;

[0093] Adjust the initial threshold according to the initial segmentation error to obtain a plurality of target thresholds that meet the error requirements;

[0094] Segment the target CT image data according to the target threshold to obtain the target segmentation result.

[0095] In some embodiments, the calculating the segmentation error according to the initial threshold and the initial segmentation result to obtain the initial segmentation error includes:

[0096] Perform pixel analysis on the target CT image data to obtain a pixel histogram corresponding to the target CT image data;

[0097] Determine the relevant pixel range corresponding to the initial segmentation result according to the initial threshold, and the relevant pixel range is between a first pixel value and a second pixel value;

[0098] Calculate the initial segmentation error corresponding to the initial threshold according to the first pixel and the second pixel using the pixel histogram;

[0099] Among them, the initial segmentation error is obtained according to the following formula:

[0100]

[0101] Among them, err represents the initial segmentation error, k represents the target segmentation number, and value 1in represents the first pixel value corresponding to the i-th initial threshold in the n-th pixel channel, and value 2i represents the second pixel value corresponding to the i-th initial threshold in the n-th pixel channel, and p(j) represents the corresponding distribution probability in the pixel histogram when the pixel value is j.

[0102] In some embodiments, the obtaining the target recognition result by performing target recognition on each segmentation region in the target segmentation result includes:

[0103] Using the image segmentation layer of the target classification model to perform local image segmentation on the segmentation region using a plurality of preset boxes with different scales and ratios to obtain a plurality of local regions corresponding to the segmentation region;

[0104] Using the feature extraction layer of the target classification model to perform feature extraction on the plurality of local regions respectively to obtain a multi-scale feature map corresponding to each local region;

[0105] Using the out-of-class local interaction layer of the target classification model to calculate a first correlation value between the multi-scale feature map and a preset feature map corresponding to a preset type;

[0106] Using the in-class local interaction layer of the target classification model to calculate a second correlation value between any two of the multi-scale feature maps;

[0107] Using the type classification layer of the target classification model to determine an initial classification result corresponding to the local region according to the first correlation value, the second correlation value, and the multi-scale feature map;

[0108] Using the classification fusion layer of the target classification model to determine the target recognition result corresponding to the segmentation region according to the initial classification result using a voting mechanism.

[0109] In some embodiments, the obtaining the initial 3D model corresponding to the segmentation region by performing 3D reconstruction according to the target recognition result and the segmentation region includes:

[0110] Determining the 3D vertex distribution position corresponding to the segmentation region according to the target recognition result and the segmentation region using a convolutional neural network;

[0111] Determine the first three-dimensional model corresponding to the segmentation region by inserting coordinate points according to the three-dimensional vertex distribution positions and the segmentation region;

[0112] Reconstruct a three-dimensional surface for the first three-dimensional model using the least squares method to obtain a second three-dimensional model;

[0113] Match and adjust the second three-dimensional model using the target features corresponding to the segmentation region to obtain an initial three-dimensional model.

[0114] In some embodiments, the obtaining the target positioning result corresponding to the target object by performing radiotherapy field positioning analysis according to the first edge information and the second edge information includes:

[0115] Obtain the first surface information corresponding to the first edge information and the second surface information corresponding to the second edge information;

[0116] Determine the radiation range corresponding to radiotherapy field treatment and the initial positioning result corresponding to the target object;

[0117] Calculate the first radiation value corresponding to the target tumor under the first surface information for the radiotherapy field treatment according to the radiation range and the initial positioning result;

[0118] Calculate the second radiation value corresponding to the target organ under the second surface information for the radiotherapy field treatment according to the radiation range and the initial positioning result;

[0119] Determine the target radiation value corresponding to the initial positioning result according to the first radiation value and the second radiation value;

[0120] Adjust the initial positioning result according to the radiation value to obtain the target positioning result corresponding to the target object.

[0121] In some embodiments, the radiotherapy field precise positioning method based on CT image data can be applied to a terminal device.

[0122] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described radiotherapy field precise positioning method based on CT image data can refer to the corresponding process in the foregoing embodiment of the radiotherapy field precise positioning system based on CT image data, and will not be elaborated herein.

[0123] Please refer to Figure 3 , Figure 3 which is a schematic block diagram of the structure of a terminal device provided by an embodiment of the present invention.

[0124] As Figure 3As shown in the figure, the terminal device 300 includes a processor 301 and a memory 302. The processor 301 and the memory 302 are connected through a bus 303, which is, for example, an I2C (Inter - integrated Circuit) bus.

[0125] Specifically, the processor 301 is used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 301 can be a Central Processing Unit (CPU), or it can also be other general - purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field - Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general - purpose processor can be a microprocessor or any conventional processor, etc.

[0126] Specifically, the memory 302 can be a Flash chip, a Read - Only Memory (ROM), a magnetic disk, an optical disc, a USB flash drive, or a mobile hard disk, etc.

[0127] Those skilled in the art can understand that Figure 3 the structure shown in the figure is only a block diagram of some parts of the structure related to the solution of the embodiment of the present invention, and does not constitute a limitation on the terminal device to which the solution of the embodiment of the present invention is applied. A specific server may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0128] Among them, the processor is used to run a computer program stored in the memory and, when executing the computer program, implement any one of the radiation field precise positioning systems based on CT image data provided by the embodiments of the present invention.

[0129] In one embodiment, the processor is used to run a computer program stored in the memory and, when executing the computer program, implement the following steps:

[0130] A data processing module, configured to collect target CT image data corresponding to a target object and perform data segmentation on the target CT image data to obtain a target segmentation result;

[0131] A target recognition module, configured to perform target recognition on each segmentation region in the target segmentation result to obtain a target recognition result;

[0132] The first reconstruction module is used to perform 3D reconstruction based on the target recognition result and the segmentation region to obtain an initial 3D model corresponding to the segmentation region;

[0133] The second reconstruction module is used to determine a target 3D model corresponding to the target object according to the target segmentation result and the initial 3D model;

[0134] The edge processing module is used to determine first edge information corresponding to the target tumor according to the target 3D model and second edge information corresponding to the target organ according to the target 3D model;

[0135] The result determination module is used to perform radiotherapy field positioning analysis according to the first edge information and the second edge information to obtain a target positioning result corresponding to the target object.

[0136] In some embodiments, during the data processing module, the processor 301 executes:

[0137] The data acquisition module is used to acquire initial CT image data corresponding to the target object;

[0138] The data correction module is used to correct the contrast and brightness of the initial CT image data by using an adaptive gamma algorithm to obtain the target CT image data.

[0139] In some embodiments, during the data processing module, the processor 301 executes:

[0140] The data determination module is used to determine the target segmentation quantity corresponding to the target CT image data, and determine corresponding multiple initial thresholds according to the target segmentation quantity;

[0141] The initial segmentation module is used to segment the target CT image data according to the multiple initial thresholds to obtain an initial segmentation result corresponding to each initial threshold;

[0142] The error determination module is used to calculate a segmentation error according to the initial threshold and the initial segmentation result to obtain an initial segmentation error;

[0143] The data adjustment module is used to adjust the initial threshold according to the initial segmentation error to obtain multiple target thresholds that meet the error requirement;

[0144] The target segmentation module is used to segment the target CT image data according to the target threshold to obtain the target segmentation result.

[0145] In some embodiments, during the error determination module, the processor 301 executes:

[0146] A pixel analysis module for performing pixel analysis on the target CT image data to obtain a pixel histogram corresponding to the target CT image data;

[0147] A range determination module for determining a relevant pixel range corresponding to the initial segmentation result according to the initial threshold, where the relevant pixel range is between a first pixel value and a second pixel value;

[0148] An error calculation module for calculating the initial segmentation error corresponding to the initial threshold according to the first pixel and the second pixel using the pixel histogram;

[0149] Wherein, the initial segmentation error is obtained according to the following formula:

[0150]

[0151] Wherein, err represents the initial segmentation error, k represents the target segmentation number, and value 1in represents the first pixel value corresponding to the i-th initial threshold in the n-th pixel channel, and value 2i represents the second pixel value corresponding to the i-th initial threshold in the n-th pixel channel, and p(j) represents the distribution probability corresponding to the pixel value j in the pixel histogram.

[0152] In some embodiments, during the target recognition module process, the processor 301 executes:

[0153] An image segmentation module for performing local image segmentation on the segmentation area using the image segmentation layer of the target classification model with a plurality of preset boxes of different scales and ratios to obtain a plurality of local areas corresponding to the segmentation area;

[0154] A feature extraction module for respectively extracting features from a plurality of the local areas using the feature extraction layer of the target classification model to obtain a multi-scale feature map corresponding to each local area;

[0155] An out-of-class calculation module for calculating a first correlation value between the multi-scale feature map and a preset feature map corresponding to a preset type using the out-of-class local interaction layer of the target classification model;

[0156] An in-class calculation module for calculating a second correlation value between any two of the multi-scale feature maps using the in-class local interaction layer of the target classification model;

[0157] An initial classification module for determining an initial classification result corresponding to the local area according to the first correlation value, the second correlation value, and the multi-scale feature map using the type classification layer of the target classification model;

[0158] A classification fusion module, configured to use the classification fusion layer of the target classification model to determine the target recognition result corresponding to the segmentation region according to the initial classification result by using a voting mechanism.

[0159] In some embodiments, during the process of the first reconstruction module, the processor 301 performs:

[0160] A vertex determination module, configured to use a convolutional neural network to determine the three-dimensional vertex distribution position corresponding to the segmentation region according to the target recognition result and the segmentation region;

[0161] A coordinate supplement module, configured to insert coordinate points according to the three-dimensional vertex distribution position and the segmentation region to determine a first three-dimensional model corresponding to the segmentation region;

[0162] A surface reconstruction module, configured to reconstruct a three-dimensional surface of the first three-dimensional model by using the least squares method to obtain a second three-dimensional model;

[0163] A matching adjustment module, configured to perform matching adjustment on the second three-dimensional model by using the target features corresponding to the segmentation region to obtain an initial three-dimensional model.

[0164] In some embodiments, during the process of the result determination module, the processor 301 performs:

[0165] A surface determination module, configured to obtain first surface information corresponding to the first edge information and second surface information corresponding to the second edge information;

[0166] An information determination module, configured to determine the radiation range corresponding to the radiotherapy field and the initial positioning result corresponding to the target object;

[0167] A first calculation module, configured to calculate a first radiation value corresponding to the target tumor under the first surface information of the radiotherapy field according to the radiation range and the initial positioning result;

[0168] A second calculation module, configured to calculate a second radiation value corresponding to the target organ under the second surface information of the radiotherapy field according to the radiation range and the initial positioning result;

[0169] A radiation calculation module, configured to determine a target radiation value corresponding to the initial positioning result according to the first radiation value and the second radiation value;

[0170] A positioning determination module, configured to adjust the initial positioning result according to the radiation value to obtain the target positioning result corresponding to the target object.

[0171] It should be noted that those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process of the above-described terminal device can refer to the corresponding process in the foregoing embodiment of the radiation field precise positioning system based on CT image data, and will not be elaborated herein.

[0172] The embodiment of the present invention further provides a storage medium for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any one of the radiation field precise positioning systems based on CT image data provided in the specification of the embodiment of the present invention.

[0173] Among them, the storage medium can be an internal storage unit of the terminal device in the foregoing embodiment, such as the hard disk or memory of the terminal device. The storage medium can also be an external storage device of the terminal device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the terminal device.

[0174] Those of ordinary skill in the art will understand that all or some of the steps in the methods disclosed above, and the functional modules / units in systems and devices, can be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division of the functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be executed by several physical components working together. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, a communication medium typically contains computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

[0175] It should be understood that the term "and / or" used in the specification and appended claims of the present invention refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations. It should be noted that in this text, the term "comprises", "comprising", or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements that are inherent to such process, method, article, or system. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article, or system comprising that element.

[0176] The serial numbers of the embodiments of the present invention above are only for description and do not represent the advantages or disadvantages of the embodiments. The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A radiation field precise positioning system based on CT image data, characterized in that: The system comprises: A data processing module is used to collect target CT image data corresponding to the target object, and perform data segmentation on the target CT image data to obtain a target segmentation result; A target recognition module, used for performing target recognition on each segmented area in the target segmentation result to obtain a target recognition result; A first reconstruction module, used for performing three-dimensional reconstruction according to the target recognition result and the segmented area to obtain an initial three-dimensional model corresponding to the segmented area; A second reconstruction module, used for determining a target three-dimensional model corresponding to the target object according to the target segmentation result and the initial three-dimensional model; An edge processing module, used to determine first edge information corresponding to a target tumor according to the target three-dimensional model and to determine second edge information corresponding to a target organ according to the target three-dimensional model; A result determination module is used to perform radiation field positioning analysis according to the first edge information and the second edge information to obtain a target positioning result corresponding to the target object.

2. The system according to claim 1, characterized in that The data processing module comprises: A data acquisition module, used for acquiring initial CT image data corresponding to the target object; The data correction module is used to perform contrast and brightness correction on the initial CT image data using an adaptive gamma algorithm to obtain the target CT image data.

3. The system according to claim 1, characterized in that The data processing module comprises: A data determination module, used to determine the number of target segmentations corresponding to the target CT image data, and determine a plurality of corresponding initial thresholds according to the number of target segmentations; An initial segmentation module, used to segment the target CT image data according to the multiple initial thresholds to obtain an initial segmentation result corresponding to each initial threshold; An error determination module, used to calculate the segmentation error according to the initial threshold and the initial segmentation result to obtain an initial segmentation error; A data adjustment module, used for adjusting the initial threshold according to the initial segmentation error to obtain multiple target thresholds that meet the error requirements; The target segmentation module is used to perform data segmentation on the target CT image data according to the target threshold to obtain the target segmentation result.

4. The system according to claim 3, characterized in that The error determination module comprises: A pixel analysis module, used for performing pixel analysis on the target CT image data to obtain a pixel histogram corresponding to the target CT image data; A range determination module, configured to determine a relevant pixel range corresponding to the initial segmentation result according to the initial threshold, wherein the relevant pixel range is between a first pixel value and a second pixel value; an error calculation module, configured to calculate the initial segmentation error corresponding to the initial threshold value using the pixel histogram according to the first pixel and the second pixel; The initial segmentation error is obtained according to the following formula: Among them, err represents the initial segmentation error, k represents the number of target segmentations, and value 1in represents the first pixel value corresponding to the i-th initial threshold value under the n-th pixel channel, value 2i represents the second pixel value corresponding to the ith initial threshold under the nth pixel channel, and p(j) represents the corresponding distribution probability in the pixel histogram when the pixel value is j.

5. The system according to claim 1, characterized in that The target recognition module comprises: An image segmentation module is used to perform local image segmentation on the segmented area using a plurality of preset frames of different scales and proportions by using an image segmentation layer of a target classification model to obtain a plurality of local areas corresponding to the segmented area; A feature extraction module, used to use the feature extraction layer of the target classification model to extract features from the plurality of local regions respectively to obtain a multi-scale feature map corresponding to each local region; an out-of-class calculation module, used to calculate a first correlation value between the multi-scale feature map and a preset feature map corresponding to a preset type by using an out-of-class local interaction layer of the target classification model; An intra-class calculation module, used to calculate a second correlation value between any two of the multi-scale feature maps using an intra-class local interaction layer of the target classification model; An initial classification module, configured to determine an initial classification result corresponding to the local area according to the first association value, the second association value and the multi-scale feature map by using a type classification layer of the target classification model; A classification fusion module is used to use the classification fusion layer of the target classification model to determine the target recognition result corresponding to the segmented area according to the initial classification result using a voting mechanism.

6. The system according to claim 1, characterized in that The first reconstruction module comprises: A vertex determination module, used to determine the three-dimensional vertex distribution position corresponding to the segmented area using a convolutional neural network according to the target recognition result and the segmented area; A coordinate supplement module, used for inserting coordinate points according to the three-dimensional vertex distribution positions and the segmented area to determine a first three-dimensional model corresponding to the segmented area; A surface reconstruction module, used for reconstructing a three-dimensional surface of the first three-dimensional model using a least square method to obtain a second three-dimensional model; The matching and adjustment module is used to match and adjust the second three-dimensional model using the target features corresponding to the segmented area to obtain an initial three-dimensional model.

7. The system according to claim 1, characterized in that The result determination module comprises: A curved surface determination module, used to obtain first curved surface information corresponding to the first edge information and second curved surface information corresponding to the second edge information; An information determination module, used to determine a radiation range corresponding to the radiation field treatment and an initial positioning result corresponding to the target object; A first calculation module is used to calculate a first radiation value corresponding to the target tumor under the first curved surface information by the radiation field treatment according to the radiation range and the initial positioning result; A second calculation module is used to calculate a second radiation value corresponding to the target organ under the second curved surface information by the radiation field treatment according to the radiation range and the initial positioning result; a radiation calculation module, configured to determine a target radiation value corresponding to the initial positioning result according to the first radiation value and the second radiation value; The positioning determination module is used to adjust the initial positioning result according to the radiation value to obtain the target positioning result corresponding to the target object.

8. A method for accurately positioning a radiation field based on CT image data, characterized in that: The method comprises: Acquiring target CT image data corresponding to the target object, and performing data segmentation on the target CT image data to obtain a target segmentation result; Performing target recognition on each segmented area in the target segmentation result to obtain a target recognition result; Performing three-dimensional reconstruction according to the target recognition result and the segmented area to obtain an initial three-dimensional model corresponding to the segmented area; Determine a target three-dimensional model corresponding to the target object according to the target segmentation result and the initial three-dimensional model; Determine first edge information corresponding to a target tumor according to the target three-dimensional model and determine second edge information corresponding to a target organ according to the target three-dimensional model; A radiation field positioning analysis is performed according to the first edge information and the second edge information to obtain a target positioning result corresponding to the target object.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program and implement the radiation field precise positioning system based on CT image data as described in any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium for computer storage, characterized in that: The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the radiation field precise positioning system based on CT image data as described in any one of claims 1 to 7.

Images