Exposure parameter updating method and apparatus, electronic device, and storage medium

Abstract

The application provides an exposure parameter updating method and device, electronic equipment and a storage medium. The method is applied to the field of exposure parameter updating. The method comprises the following steps: obtaining thickness information of a to-be-detected part of a target object, determining a target exposure parameter of a ray generator based on the thickness information; determining density information of the to-be-detected part based on the thickness information and the target exposure parameter, adjusting a beam limiter to a target pose based on the density information; controlling the ray generator to perform ray scanning on the to-be-detected part based on the target exposure parameter, and obtaining an initial detection image of the to-be-detected part; updating the thickness information of the to-be-detected part based on an image brightness parameter of the initial detection image and an image exposure parameter of the initial detection image; and performing parameter updating on the target exposure parameter based on the updated thickness information, thereby improving the imaging accuracy of the medical equipment.

Description

Technical Field

[0001] This application relates to the field of medical devices, and more particularly to a method, apparatus, electronic device, and storage medium for updating exposure parameters. Background Technology

[0002] In real-life scenarios, medical devices are widely used as aids in the diagnosis of diseases. However, the use of these devices requires manual setting of exposure parameters by the operator. This manual operation is limited by operator experience and patient size variations, easily leading to settings that deviate significantly from actual requirements. Consequently, the resulting diagnostic images lack accuracy, thus affecting the diagnosis of the patient's condition. Summary of the Invention

[0003] This application provides an exposure parameter updating method, apparatus, electronic device, and storage medium, aiming to reduce the hardware resource requirements of vascular imaging and improve the applicability and recognition accuracy of vascular imaging methods. The technical solution is as follows: In a first aspect, embodiments of this application provide an exposure parameter update method, including: Obtain the thickness information of the part of the target object to be inspected, and determine the target exposure parameters of the X-ray generator based on the thickness information; The density information of the area to be detected is determined based on the thickness information and the target exposure parameters, and the beam limiter is adjusted to the target pose based on the density information. The control X-ray generator performs X-ray scanning on the area to be detected based on the target exposure parameters to obtain an initial detection image of the area to be detected; The thickness information of the area to be detected is updated based on the image brightness parameters and image exposure parameters of the initial detection image; The target exposure parameters are updated based on the updated thickness information.

[0004] Secondly, embodiments of this application provide an exposure parameter updating device. The medical device includes a radiation generator and a beam limiter. The device includes: The parameter calculation unit is used to obtain the thickness information of the part of the target object to be detected, and to determine the target exposure parameters of the X-ray generator based on the thickness information; The pose calculation unit is used to determine the density information of the part to be detected based on the thickness information and the target exposure parameters, and to adjust the chamfer to the target pose based on the density information. The image generation unit controls the X-ray generator to perform X-ray scanning on the area to be detected based on the target exposure parameters, thereby obtaining an initial detection image of the area to be detected. The data update unit is used to update the thickness information of the area to be detected based on the image brightness parameters and image exposure parameters of the initial detection image, and to update the target exposure parameters based on the updated thickness information.

[0005] Thirdly, embodiments of this application provide an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the exposure parameter update method as described above.

[0006] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed, implements the exposure parameter update method as described above.

[0007] In the above technical solution, by acquiring the thickness information of the area to be detected of the target object and determining the target exposure parameters of the X-ray generator based on the thickness information, the initial imaging conditions are made more closely aligned with actual needs. Subsequently, the density information of the area to be detected is determined based on the thickness information and the target exposure parameters, and the collimator is adjusted to the target pose according to the density information, thereby optimizing the collimation and coverage of the X-ray beam. After controlling the X-ray generator to perform X-ray scanning based on the target exposure parameters to obtain the initial detection image, the thickness information is updated based on the image brightness parameters and image exposure parameters of the initial detection image to correct parameter deviations. Finally, the target exposure parameters are updated based on the updated thickness information to further refine the scanning settings. By introducing image feedback and parameter correction mechanisms, the above solution effectively reduces errors in the imaging process, thereby improving the imaging accuracy of medical equipment. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a schematic diagram of a scenario for an exposure parameter update method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating an exposure parameter update method provided in an embodiment of this application; Figure 3 This is a schematic diagram of a scenario for an exposure parameter update method provided in an embodiment of this application; Figure 4 This is a schematic diagram of a scenario for an exposure parameter update method provided in an embodiment of this application; Figure 5 This is a flowchart illustrating an exposure parameter update method provided in an embodiment of this application; Figure 6 This is a flowchart illustrating an exposure parameter update method provided in an embodiment of this application; Figure 7 This is a flowchart illustrating an exposure parameter update method provided in an embodiment of this application; Figure 8 This is a flowchart illustrating an exposure parameter update method provided in an embodiment of this application; Figure 9 This is a schematic diagram of a scenario for an exposure parameter update method provided in an embodiment of this application; Figure 10 This is a schematic diagram of the structure of an exposure parameter updating device provided in an embodiment of this application; Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0010] To make the features and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0011] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0012] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0013] This application provides an exposure parameter update method, which is executed by an exposure parameter update device or an electronic device equipped with an exposure parameter update device. The following is a detailed description; it should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments. Please refer to... Figure 1 , Figure 1 This is a schematic diagram illustrating a scenario of an exposure parameter update method provided in an embodiment of this application. The specific process of the exposure parameter update method can be as follows: Please see Figure 1 , Figure 1 This is a schematic diagram illustrating a scenario of an exposure parameter update method provided in an embodiment of this application. For example... Figure 1 As shown, the medical equipment includes a gantry, operating table, X-ray generator, and detector.

[0014] It should be noted that the frame is equipped with a lifting axis control assembly for controlling the movement of the detector. The operating table is used to hold the target object, which can be the patient to be examined. The detector is equipped with a range sensor, a structured light sensor, and a pressure sensor. Specifically, the detector is used to generate an exposure image of the area to be examined on the target object. The range sensor in the detector is used to monitor the relative distance between the detector and the target object; the pressure sensor is used to monitor the pressure data of the medical equipment; and the structured light sensor is used to acquire the point cloud data of the target object's body surface. The X-ray generator is used to generate and emit X-rays. The X-ray generator is also equipped with a laser sensor 4, which is used to acquire the point cloud data of the target object's body surface.

[0015] The area where the medical equipment is located includes laser sensor 1, laser sensor 2 fixed to the ceiling of the operating room, and laser sensor 3 fixed in the shadowless lamp. Laser sensor 1, laser sensor 2, and laser sensor 3 fixed in the shadowless lamp are used to generate regional point cloud data of the area where the medical equipment is located.

[0016] Specifically, laser sensor 1, laser sensor 2 and laser sensor 3 acquire regional point cloud data of the area where the medical device is located, while the structured light sensor and laser sensor 4 collect surface point cloud data of the target object. Based on the regional point cloud data and the surface point cloud, a three-dimensional data model of the area where the medical device is located is generated.

[0017] The pre-trained neural network is invoked to analyze the geometric and semantic features of each entity in the 3D data model. The neural network can be implemented based on any of the U-Net, YOLO, or PSPNet models; no specific limitation is made here. Based on the geometric and semantic features, the target object is distinguished and located from medical equipment, surrounding environmental objects, and medical personnel. Feature parsing is performed on the 3D point cloud data of the target object. Specifically, the encoder abstracts local and global 3D features at different levels, and the decoder segments and classifies the point cloud of the target object part by part based on the 3D features. Finally, the semantic label of each point cloud is output, thereby determining the corresponding region of each part of the target object.

[0018] After the deep neural network completes the segmentation and identification of the target object in the 3D data model, the area to be detected is selected based on the segmentation results, and the operator of the medical device can manually modify the area to be detected. Based on the 3D feature data of the area to be detected, the thickness information of the area to be detected is determined, and the target exposure parameters associated with the thickness information are determined.

[0019] It should be noted that the target exposure parameters are the station parameters of the X-ray generator. These parameters include pulse width, voltage, current, additional filter selection parameters, and focal spot size selection parameters. The pulse width controls the duration of each X-ray emission from the generator, determining the time-integrated energy of a single exposure. The voltage parameter sets the accelerating potential difference across the X-ray generator, determining the maximum energy and penetrating power of the X-ray. The current parameter defines the flux of the cathode electron beam in the X-ray generator, determining the radiation dose per unit time. The additional filter selection parameters filter low-energy X-rays using specific materials to optimize the X-ray energy spectrum and reduce scattering. The focal spot size selection parameters adjust the physical size of the bombardment area on the anode target surface of the X-ray generator.

[0020] Based on the target exposure parameters and the thickness information of the area to be detected, a ray transmission physical model is invoked to simulate the characteristics of the ray beam generated by the ray generator under the target exposure parameters. The simulated ray intensity distribution data after the area to be detected is output as the simulated exposure result. The simulated exposure result is input into a grayscale conversion model to obtain the predicted exposure image corresponding to the area to be detected. The predicted exposure image is segmented into independent detection regions, and full-pixel sampling is performed in each region to calculate the grayscale statistical mean. The grayscale density conversion function is called to convert the grayscale mean into a density value in real time. For high grayscale gradient transition regions, an edge compensation algorithm is used to eliminate some volumetric effect interference, and the density information of the area to be detected is output. Based on the density information, the ray attenuation gradient of the ray penetrating different thickness areas is calculated. Based on the dose homogenization objective function, the target pose required by the collimator is solved inversely based on the ray attenuation gradient, and the collimator is moved to the target pose to prevent image overexposure.

[0021] The X-ray generator scans the area to be inspected based on target exposure parameters. The detector receives the X-rays emitted by the generator, converts them into analog electrical signals, and samples them through an analog-to-digital converter to generate raw digital projection data. This raw digital projection data is then input into an image processor, where a reconstruction algorithm is executed to generate an initial image of the area to be inspected. Based on the image brightness and exposure parameters of the initial image, and combined with a X-ray attenuation physical model, the actual and theoretical deviations of the tissue attenuation coefficient are calculated. The thickness correction amount is determined based on this deviation, and the original thickness information of the area to be inspected is corrected to obtain updated thickness information. Based on the updated thickness information, the corresponding target exposure parameters are looked up in a preset parameter relationship mapping table and applied to the X-ray generator to complete the exposure parameter update.

[0022] In this embodiment, by acquiring the thickness information of the target area to be detected and determining the target exposure parameters of the X-ray generator based on the thickness information, the initial imaging conditions are made more closely aligned with actual needs. Subsequently, the density information of the target area to be detected is determined based on the thickness information and the target exposure parameters, and the collimator is adjusted to the target pose according to the density information, thereby optimizing the collimation and coverage of the X-ray beam. After controlling the X-ray generator to perform X-ray scanning based on the target exposure parameters to obtain the initial detection image, the thickness information is updated based on the image brightness parameters and image exposure parameters of the initial detection image to correct parameter deviations. Finally, the target exposure parameters are updated based on the updated thickness information to further refine the scanning settings. The above scheme effectively reduces errors in the imaging process by introducing image feedback and parameter correction mechanisms, thereby improving the imaging accuracy of medical equipment.

[0023] based on Figure 1 The scene diagram shown below will be combined with... Figures 2-9 This application provides a detailed description of an exposure parameter update method based on an embodiment.

[0024] Please see Figure 2 , Figure 2 This is a flowchart illustrating an exposure parameter update method provided in an embodiment of this application. Figure 2 As shown, the method in this application embodiment may include the following steps S101-S105.

[0025] S101, Obtain the thickness information of the part of the target object to be inspected, and determine the target exposure parameters of the X-ray generator based on the thickness information.

[0026] In this embodiment, the target exposure parameters are the operating parameters of the X-ray generator. These parameters include pulse width, voltage, current, additional filter selection parameters, and focal spot size selection parameters. The pulse width controls the duration of each X-ray emission from the generator. The voltage parameter sets the accelerating potential difference across the X-ray generator, determining the maximum energy and penetrating power of the X-ray. The current parameter defines the flux of the cathode electron beam in the X-ray generator, determining the radiation amount per unit time. The additional filter selection parameters filter low-energy X-rays using specific materials to optimize the X-ray energy spectrum and reduce scattering. The focal spot size selection parameters adjust the physical size of the bombardment area on the anode target surface of the X-ray generator.

[0027] Specifically, the system acquires regional point cloud data of the area where the medical device is located using pre-defined laser sensors 1, 2, and 3. Then, it acquires surface point cloud data of the target object using a structured light sensor and laser sensor 4. Based on the geometric centroid positions of the regional and surface point cloud data, a spatial translation reference is calculated. Furthermore, the spatial distribution characteristics of the regional and surface point cloud data are analyzed using the covariance matrix, and singular value decomposition is employed to obtain the optimal rotation matrix and translation vector. Confidence weights are assigned to the transformation parameters of the optimal rotation matrix, and iterative optimization is performed using a spatial distance error function until convergence to a preset accuracy. Finally, the regional and surface point cloud data in a unified coordinate system are input into a pre-defined surface reconstruction algorithm corresponding to the 3D data model of the area where the medical device is located.

[0028] A pre-trained deep neural network is invoked to perform semantic segmentation on each entity in the 3D data model, thereby identifying all entities in the area where the medical device is located and labeling each entity with its corresponding semantic label.

[0029] Select entities whose semantic labels indicate human body parts, and select one entity as the target object to be detected. The selection of entities can be done manually by the medical device operator or automatically by a preset detection program. For example, if the preset detection program is for the chest, then the entity with the semantic label "chest" will be determined as the target object to be detected.

[0030] The three-dimensional feature data of the part to be detected is obtained from the three-dimensional data model, and a multi-layer surface model is constructed based on the three-dimensional feature data of the part to be detected. The shortest vertical distance from the internal structure of the part to be detected to the surface is calculated by the spatial distance field algorithm to generate a thickness distribution field. The distribution field is projected and integrated along the preset projection direction to extract the cumulative equivalent thickness value of the penetrating ray path. After Gaussian smoothing filtering, the thickness information corresponding to the part to be detected is obtained.

[0031] In this embodiment, a parameter relationship mapping table of different thickness information and exposure parameters is pre-established. The parameter relationship mapping table records multiple exposure parameter combinations corresponding to multiple parts with different thicknesses. After obtaining the thickness information of the part to be detected, the thickness information is used as the query condition to perform a matching search in the parameter relationship mapping table to determine the target exposure parameter associated with the thickness information from the correspondence recorded in the parameter relationship mapping table.

[0032] S102 determines the density information of the area to be detected based on the thickness information and the target exposure parameters, and adjusts the beam limiter to the target pose based on the density information.

[0033] Based on the target exposure parameters and the thickness information of the area to be inspected, the ray transmission physical model is invoked to simulate the characteristics of the ray beam generated by the ray generator under the target exposure parameters. Among them, the ray transmission physical model calculates the attenuation law of the ray in the tissue equivalent medium of the area to be inspected in combination with the thickness information, and dynamically corrects the attenuation coefficient of the penetrating ray. Finally, the ray intensity distribution data of the area to be inspected after simulated penetration is output, which is determined as the simulated exposure result.

[0034] The simulated exposure results are input into the grayscale conversion model. The ray intensity values ​​at each spatial location point are mapped to bit grayscale values ​​within a preset range through a pre-calibrated nonlinear mapping function in the grayscale conversion model, generating a corresponding two-dimensional pixel matrix. After image spatial domain filtering and adjustment of the two-dimensional pixel matrix by window width / window level, the predicted exposure image of the area to be detected is output.

[0035] The predicted exposure image is divided into several independent detection regions. Full pixel sampling is performed in each region and the gray-level statistical mean is calculated. The gray-level mean is converted into a density value in real time by calling a preset gray-level density conversion function. For high gray-level gradient transition regions, an edge compensation algorithm is used to eliminate some volume effect interference. Finally, the density information of the detection area is output.

[0036] Based on the target exposure parameters and density information, the attenuation gradient of the rays emitted by the ray generator penetrating different areas to be detected is simulated and calculated. Based on the dose homogenization objective function, the displacement and tilt angle parameters required by the beam limiter are solved in reverse. By driving the beam limiter to synchronously adjust the lateral position and spatial tilt angle, the intensity distribution of the ray beam emitted by the ray generator is matched to areas with different densities.

[0037] Please refer to the following: Figure 3 , Figure 3 This is a schematic diagram illustrating a scenario of an exposure parameter update method provided in an embodiment of this application. For example... Figure 3 As shown, when the X-ray generator is moved into the beam limiter, the beam limiter is adjusted to the target pose, thereby adjusting the intensity of the X-ray emitted by the X-ray generator in the area with weak density when passing through the part to be detected, thus avoiding overexposure in the area.

[0038] S103 controls the X-ray generator to perform X-ray scanning on the area to be detected based on the target exposure parameters, thereby obtaining an initial detection image of the area to be detected.

[0039] Specifically, the target exposure parameters are applied to the X-ray generator. Based on these parameters, the generator emits scanning rays to scan and detect the area to be inspected. Upon receiving the scanning rays passing through the area, the detector converts them into visible light signals. These signals are then converted into analog electrical signals by an integrated photoelectric conversion unit. These analog electrical signals undergo current-to-voltage conversion via a transimpedance amplifier and are sampled by a high-speed analog-to-digital converter to generate raw digital projection data. This raw digital projection data is then transmitted to an image processor, where the core reconstruction algorithm is executed based on the electrical signals to generate an initial detection image corresponding to the area to be inspected.

[0040] S104, update the thickness information of the area to be detected based on the image brightness parameters and image exposure parameters of the initial detection image.

[0041] Specifically, the image brightness parameters of the initial detection image are extracted, and combined with the voltage, current and exposure time values ​​contained in the image exposure parameters of the initial detection image, and then the deviation between the actual measured value and the theoretical expected value of the tissue attenuation coefficient of the detection site is calculated in reverse using the X-ray attenuation physical model. Based on the deviation, the correction amount that needs to be calibrated for the thickness information of the detection site is determined, and the original thickness information of the detection site is corrected based on the correction amount to obtain the updated thickness information.

[0042] S105, update the target exposure parameters based on the updated thickness information.

[0043] Specifically, the target exposure parameters corresponding to the updated thickness information are determined in the preset parameter relationship mapping table, and the target exposure parameters corresponding to the updated thickness information are applied to the X-ray generator.

[0044] Please refer to the following: Figure 4 , Figure 4 This is a schematic diagram illustrating a scenario of an exposure parameter update method provided in an embodiment of this application. For example... Figure 4As shown, a 3D data model is obtained by reconstructing 3D data based on point cloud data acquired by sensors. After semantic segmentation of the 3D data model, the target area to be detected is determined, along with its thickness and density information. The target exposure parameters of the ray generator are determined based on the thickness information, as are the target detection position of the detector. The target pose of the beam limiter is determined based on the density information of the target area. After the detector moves to the target detection position and the beam limiter adjusts to the target pose, the ray generator is controlled based on the target exposure parameters, and the target exposure parameters are updated based on the initial detection image generated by the detector.

[0045] In this embodiment, by acquiring the thickness information of the target area to be detected and determining the target exposure parameters of the X-ray generator based on the thickness information, the initial imaging conditions are made more closely aligned with actual needs. Subsequently, the density information of the target area to be detected is determined based on the thickness information and the target exposure parameters, and the collimator is adjusted to the target pose according to the density information, thereby optimizing the collimation and coverage of the X-ray beam. After controlling the X-ray generator to perform X-ray scanning based on the target exposure parameters to obtain the initial detection image, the thickness information is updated based on the image brightness parameters and image exposure parameters of the initial detection image to correct parameter deviations. Finally, the target exposure parameters are updated based on the updated thickness information to further refine the scanning settings. The above scheme effectively reduces errors in the imaging process by introducing image feedback and parameter correction mechanisms, thereby improving the imaging accuracy of medical equipment.

[0046] Because medical devices often struggle to recognize complex environments in real-world scenarios, it's necessary to eliminate interference from mixed environmental information. Please refer to [link / reference needed]. Figure 5 , Figure 5 This is a flowchart illustrating an exposure parameter update method provided in an embodiment of this application. Figure 5 As shown, the method in this application embodiment may include the following steps S201-S203.

[0047] S201, acquire the regional point cloud data of the area where the medical device is located and the surface point cloud data of the target object.

[0048] In this embodiment, the regional point cloud data of the area where the medical device is located is acquired by laser sensor 1, laser sensor 2 and laser sensor 3; the surface point cloud data of the target object is acquired by structured light sensor and laser sensor 4.

[0049] Specifically, laser sensor 1 and laser sensor 2 installed on the ceiling of the operating room, and laser sensor 3 of the lamp, simultaneously emit pulsed laser beams based on a preset time synchronization protocol. By measuring the reflection time difference of the pulsed laser beams on the surfaces of various entities in the operating room, regional point cloud data of the area where the medical equipment is located is generated. At the same time, the structured light sensor and laser sensor 4 integrated in the detector emit pulsed laser beams to the surface of the target object. By acquiring and measuring the reflection time difference of the pulsed laser beams on the surface of the target object, surface point cloud data of the target object is generated.

[0050] S202, based on regional point cloud data and body surface point cloud data, obtains a three-dimensional data model corresponding to the area where the medical device is located.

[0051] Specifically, the spatial translation reference is calculated based on the geometric centroid positions of regional point cloud data and body surface point cloud data. Further, the spatial distribution characteristics of the regional and body surface point cloud data are analyzed based on the covariance matrix, and the optimal rotation matrix and translation vector are obtained using singular value decomposition. Then, based on the accuracy indicators of different sensors, such as the positioning error of lidar, confidence weights are assigned to the transformation parameters of the optimal rotation matrix, and iterative optimization is performed using a spatial distance error function until convergence to the preset accuracy. Finally, the regional and body surface point cloud data in a unified coordinate system are input into a preset surface reconstruction algorithm to generate a three-dimensional data model containing the operating room facilities, operating table, and the surface of the target object.

[0052] It should be noted that surface reconstruction algorithms are computational methods that transform discrete 3D point cloud data into continuous, computable surface models. Surface reconstruction algorithms are classified into two types: explicit and implicit. Explicit methods directly connect adjacent point clouds to generate triangular meshes. Explicit methods are highly efficient but sensitive to noise. Implicit methods, such as Poisson reconstruction, construct implicit functions by fitting the normal vector field of the point cloud data, and then extract closed and topologically correct watertight surfaces through isosurfaces to generate high-fidelity spatial anatomical models. In this embodiment, the specific surface reconstruction algorithm used can be set according to the actual application scenario, and no specific limitation is made here.

[0053] S203 performs semantic segmentation on the 3D data model to determine the parts of the target object to be detected.

[0054] In this embodiment, a pre-trained deep neural network is invoked to perform semantic segmentation on the 3D data model. The deep neural network can be implemented based on any of the U-Net, YOLO, and PSPNet models, without specific limitations. It should be noted that the U-Net model achieves high-precision pixel-level segmentation through a symmetric encoder-decoder structure and skip connections, making it suitable for handling complex organ boundaries in medical images. The YOLO model, based on a single-stage detection framework combined with an instance segmentation head, achieves real-time target recognition and contour segmentation, suitable for rapid localization in dynamic intraoperative scenes. The PSPNet model utilizes pyramid pooling modules to capture multi-scale contextual information and improves the semantic segmentation consistency of large-scale anatomical structures by fusing global features.

[0055] Specifically, the generated 3D data model is converted into voxel format and input into a pre-trained deep neural network. The deep neural network analyzes the geometric structure and spatial topological features of the 3D data model through multi-scale feature extraction and skip connection feature fusion mechanisms. Furthermore, the deep neural network performs segmentation while simultaneously identifying multiple entities contained in the 3D data model and assigning semantic labels to these entities. These entities include at least multiple parts of the target object, medical devices, and personnel in the area. For example, the target object's parts include the head, chest, and buttocks; medical devices include the operating table and shadowless lamp; and personnel in the area include patients and medical staff.

[0056] After obtaining the semantic tags of multiple entities, the operator of the medical device will manually select one entity as the target object to be detected, or the preset detection program will automatically select the target object. The specific selection method can be set according to the actual use scenario, and no specific limitation is made here.

[0057] In this embodiment, by acquiring the regional point cloud data of the area where the medical device is located and the surface point cloud data of the target object, and fusing and reconstructing them into a unified three-dimensional data model, the surgical space structure and the anatomical morphology of the patient can be reproduced. Subsequently, based on semantic segmentation technology, the target object to be detected in the three-dimensional data model is accurately segmented into independent anatomical units, and the semantic recognition and spatial annotation of key entities in the surgical environment are completed simultaneously. This provides a quantifiable spatial benchmark with clear physical environmental constraints and clear anatomical boundaries for detector positioning, avoiding collision risks and positioning deviations of the medical device during subsequent use.

[0058] In one feasible implementation, the specific steps performed when obtaining the thickness information of the part to be detected of the target object are as follows: obtaining the three-dimensional feature data of the part to be detected, performing feature analysis on the three-dimensional feature data, and obtaining the thickness information of the part to be detected.

[0059] Specifically, a multi-layered surface model is constructed based on the point cloud distribution and surface normal vectors of the 3D feature data of the area to be detected. The shortest vertical distance from each vertex of the internal anatomical structure to the corresponding surface model is calculated using a spatial distance field algorithm, simultaneously generating a global thickness distribution field. Subsequently, the thickness distribution field is integrated along a predefined projection direction to extract the cumulative equivalent thickness value along the penetration ray path. Finally, Gaussian smoothing filtering is used to eliminate physiological fluctuation noise, and the thickness information of the area to be detected is output. For example, if the area to be detected is the abdomen, the thickness information of the abdomen is 25.3 cm.

[0060] In this embodiment, by analyzing the three-dimensional feature data of the area to be detected, millimeter-level precision thickness information that strictly corresponds to the anatomical structure is obtained. This information is generated based on spatial geometric characteristics through physically interpretable transformation, providing an objective quantitative benchmark for exposure parameters and detector positioning, thereby effectively ensuring the geometric accuracy and density resolution of the imaging.

[0061] Please see Figure 6 , Figure 6 This is a flowchart illustrating an exposure parameter update method provided in an embodiment of this application. Figure 6 As shown, the method in this application embodiment may include the following steps S301-S303.

[0062] S301, based on the target exposure parameters and the thickness information of the area to be inspected, obtains the simulated exposure result for the area to be inspected.

[0063] In this embodiment, the simulated X-ray generator is used to monitor the area to be detected based on the target exposure parameters, and the simulated exposure result of the area to be detected is determined by combining the thickness information of the area to be detected.

[0064] Specifically, based on the obtained target exposure parameters, the ray transmission physical model is invoked to simulate the characteristics of the ray beam generated by the ray generator under the target exposure parameters. The ray transmission physical model is used to calculate the attenuation law of the ray in the tissue equivalent medium of the area to be detected based on the thickness information of the area to be detected; the attenuation coefficient of the penetrating ray is dynamically corrected in combination with the thickness information; and finally, the ray intensity distribution data of the area to be detected after simulated penetration is output, which is determined as the simulated exposure result for the area to be detected.

[0065] S302, generates a predicted exposure image of the area to be detected based on the simulated exposure results.

[0066] In this embodiment, the simulated exposure result is input into a grayscale conversion model to obtain a predicted exposure image of the area to be detected. The grayscale conversion model converts the simulated exposure result into a visually resolvable image grayscale distribution. The grayscale conversion maps the ray intensity value to 8- to 16-bit grayscale values ​​using a pre-calibrated nonlinear mapping function, while dynamically adjusting the grayscale gradient distribution based on a window function to generate the predicted exposure image.

[0067] Specifically, by inputting the simulated exposure results into the grayscale conversion model, the grayscale conversion model will perform grayscale quantization on the ray intensity values ​​of each spatial location point in the simulated exposure results to generate the corresponding two-dimensional pixel matrix; after the two-dimensional pixel matrix is ​​filtered in the image spatial domain and pre-adjusted for window width / window level, the predicted exposure image corresponding to the area to be detected is output.

[0068] S303 determines the density information of the area to be detected based on the gray values ​​of each region in the predicted exposed image.

[0069] Specifically, the predicted exposure image is segmented into several independent detection regions based on the preloaded anatomical structure template. Full-pixel sampling is performed on each independent detection region, and the gray-level statistical mean is calculated. A preset gray-level density conversion function is called. The gray-level density conversion function is established by fitting standard density phantom scan data using the least squares method. The gray-level mean of each independent detection region is input into the function operation unit for real-time conversion calculation. For high gray-level gradient transition regions, the edge compensation algorithm is automatically activated to eliminate some volume effect interference. Finally, the density information of the detected part is output.

[0070] In this embodiment, a high-fidelity simulated exposure result is generated by simulating the physical model of the target exposure parameters and thickness information, and the ray attenuation characteristics under the real imaging environment are predicted in advance. The predicted exposure image generated based on this result accurately maps the theoretical penetration effect with gray-scale gradient, so that the density information can be quantitatively extracted through noiseless gray-scale analysis, thereby eliminating the dose waste and image quality fluctuation in traditional trial and error exposure, providing a quantifiable density benchmark and exposure calibration basis for actual scanning, thereby ensuring the geometric consistency and material resolution reliability of the image.

[0071] Please see Figure 7 , Figure 7 This is a flowchart illustrating an exposure parameter update method provided in an embodiment of this application. Figure 7 As shown, the method in this application embodiment may include the following steps S401-S403.

[0072] S401, based on the density information of the area to be detected, obtain the ray gradient attenuation value.

[0073] In this embodiment, based on the density information of the area to be detected, the change in linear energy attenuation rate of the ray along different penetration paths is calculated by the ray attenuation physical model and recorded as the ray gradient attenuation value; wherein, the ray gradient attenuation value is used to represent the vector parameter of the attenuation intensity change gradient per unit length when the ray penetrates a high or low density tissue area.

[0074] S402 determines the target position and target angle of the beam limiter based on the ray gradient attenuation value.

[0075] S403, determine the target pose of the clamp limiter based on the target position and target angle, and adjust the clamp limiter to the target pose.

[0076] Specifically, in S402-S403, the ray gradient attenuation value is used as an input parameter, and the required spatial position offset and planar tilt angle of the collimator are inversely solved by combining the dose homogenization objective function. The collimator's lateral displacement and rotation mechanisms are synchronously driven by the collimator's built-in lifting axis control component, dynamically adjusting the collimator to the target pose defined by the target position and target angle. It should be noted that the target position controls the ray flux cross-sectional coverage area to compensate for the risk of overexposure in low-density areas, while the target angle modulates the ray incident direction through spatial tilt to offset excessive attenuation in high-density areas.

[0077] In this embodiment, the spatial quantitative analysis of tissue absorption characteristics is achieved by accurately solving the ray gradient attenuation value based on the density information of the area to be detected. Then, the target position and target angle of the beam limiter are dynamically determined based on the attenuation value. By synchronously adjusting the lateral displacement and spatial tilt of the filter, the ray beam intensity distribution is matched with the density gradient difference in real time. Finally, the uniformity of the energy deposition of penetrating rays is ensured, and the defects of local overexposure or underexposure of the image caused by density change are eliminated, thereby improving the grayscale consistency of the image.

[0078] To address the distortion of the original projected data caused by signal conversion lag and noise interference, please refer to [link to relevant documentation]. Figure 8 , Figure 8 This is a flowchart illustrating an exposure parameter update method provided in an embodiment of this application. Figure 8 As shown, the method in this application embodiment may include the following steps S501-S502.

[0079] S501 is based on the detector receiving scanning rays emitted by the ray generator.

[0080] Specifically, the detector uses an integrated X-ray sensing unit, which is typically composed of a scintillator crystal layer and a photoelectric conversion array, to receive scanning X-rays emitted by the X-ray generator in real time. When the X-rays emitted by the X-ray generator pass through the part of the target object to be detected, their attenuated energy will be captured by the X-ray sensing unit on the surface of the detector.

[0081] S502 converts the scanning rays into electrical signals and generates an initial detection image of the area to be detected based on the electrical signals.

[0082] Specifically, the detector converts the received scanning rays into visible light signals through an internal crystal layer. Then, the integrated photoelectric conversion unit converts the visible light signals into analog electrical signals. These analog electrical signals are converted from current to voltage by a transimpedance amplifier, and then the dynamic range is adjusted by a programmable gain amplifier. After being input into an anti-aliasing filter to suppress high-frequency noise, the signals are finally sampled by a high-speed analog-to-digital converter to generate raw digital projection data. The raw digital projection data is then transmitted to an image processor, where the core operation of the reconstruction algorithm is performed based on the electrical signals to generate an initial detection image of the area to be detected that meets the spatial resolution and grayscale depth requirements.

[0083] In this embodiment, the detector accurately receives the scanning rays emitted by the X-ray generator through a high-sensitivity sensing unit and directly converts the ray energy into a quantifiable electrical signal. This process preserves the integrity of the original attenuation information to the maximum extent. Based on the electrical signal, an initial detection image is generated through a high-fidelity signal chain and digital reconstruction. This ensures that the details of the anatomical structure are physically mapped without hysteresis or insertion noise through pixel grayscale values. This provides a high-quality underlying data foundation with excellent geometric accuracy and density resolution for subsequent diagnostic analysis, fundamentally guaranteeing the traceability and clinical credibility of the images.

[0084] In one possible implementation, the following steps may be performed before executing a scanning beam emitted by a detector-based beam generator.

[0085] The target detection position of the detector is determined based on the thickness information of the part to be detected; the detector is then moved to the target detection position.

[0086] In this embodiment, a mapping table is pre-established between the detector's detection position and thickness information, and the target detection position corresponding to different thickness information is marked in the mapping table.

[0087] Specifically, after determining the thickness information of the part to be detected of the target object based on the above embodiments, a matching query is performed based on the pre-established mapping relationship table between the thickness information and the detector's detection position. The target detection position to be moved by the detector is determined according to the target detection position corresponding to different thickness information marked in the mapping relationship table. Then, the distance between the detector and the surface of the target object is fed back in real time by the ranging sensor, and the detector is precisely moved to the target detection position by the frame motion mechanism, so that the detector and the part to be detected of the target object maintain the optimal working distance.

[0088] For example, if the area to be detected is the chest and the thickness of the area is 20 cm, the mapping table shows that the target detection position corresponding to the thickness of 20 cm is 15 cm away from the surface of the area to be detected. Assuming that the detector is initially 23 cm away from the area to be detected, the control frame will then drive the detector to move to a position 15 cm away from the area to be detected.

[0089] Please refer to the following: Figure 9 , Figure 9 This is a schematic diagram illustrating a scenario of an exposure parameter update method provided in an embodiment of this application. For example... Figure 9 As shown in the diagram on the left, the detector is in its initial detection position. After moving downwards a certain distance, the detector reaches... Figure 9 The target detection location is shown in the diagram on the right.

[0090] In this embodiment, the target detection position is determined based on the thickness information of the part to be detected and the detector is driven to move precisely to that position. The pre-calibrated thickness-position mapping relationship ensures that the detector is always at the optimal working distance for the corresponding thickness, which can eliminate geometric projection distortion and ray scattering interference caused by distance inaccuracy, while maximizing the detector signal reception efficiency, thereby improving the overall accuracy of medical imaging.

[0091] In one feasible implementation, the following steps are specifically performed when moving the detector to the target detection location.

[0092] When the detector is in motion, the relative distance between the detector and the target object is obtained.

[0093] In this embodiment, the detector being in a moving state indicates that the detector is moving towards the target detection position. The relative distance between the detector and the target object is monitored in real time by a preset ranging sensor in the detector.

[0094] Specifically, the ranging sensor emits a detection signal directionally toward the surface of the target object, such as emitting non-contact signals like ultrasonic waves or infrared rays. This emitted detection signal is reflected back to the ranging sensor after being reflected from the surface of the target object. The ranging sensor internally uses a timing circuit to measure the time difference between the transmission and reception of the detection signal, and combines this with the speed of the detection signal in the air to calculate the linear relative distance between the detector and the target object in real time.

[0095] The detector stops moving when the relative distance meets a preset distance threshold.

[0096] Specifically, when the detector is in motion, the relative distance between the detector and the target object is acquired in real time; once the relative distance reaches or exceeds a preset distance threshold, a control command is immediately issued to stop the detector from moving, thereby preventing the detector from causing crushing injury to the patient.

[0097] For example, if the preset distance threshold is 200 mm, and the detector detects that the relative distance between the detector and the target object is 198 mm when the detector is in motion, which is greater than the preset distance threshold, the detector will be immediately controlled to stop moving, thereby preventing the detector from continuing to move and causing crush damage to the patient.

[0098] In this embodiment, by using the relative distance between the detector and the target object in real time and stopping the detector movement immediately when the relative distance reaches a threshold, it is possible to effectively prevent the detector from causing crushing injury to the patient due to excessive pressure during movement, thus significantly improving the safety of using medical equipment.

[0099] In one feasible implementation, the following steps are specifically performed when moving the detector to the target detection location.

[0100] The pressure detection data of the medical device is acquired while the detector is in motion.

[0101] In this embodiment, the pressure detection data of the medical device is acquired in real time based on the pressure sensor preset in the detector. Under pressure, the electrode spacing or coverage area of ​​the pressure sensor changes due to the deformation of the dielectric layer, causing a change in capacitance. The capacitance change is converted into an electrical signal by a measurement circuit, such as a capacitance-to-digital converter. The electrical signal is then amplified, filtered, and converted from analog to digital to output a digital signal, thereby mapping the electrical signal into pressure detection data.

[0102] The detector stops moving when the pressure detection data meets the preset pressure threshold.

[0103] Specifically, when the detector is in motion, it acquires pressure detection data of the medical device in real time; once the pressure detection data reaches or exceeds the preset pressure threshold, it immediately issues a control command to stop the detector from moving, thereby preventing the detector from causing crushing injury to the patient.

[0104] For example, if the preset pressure threshold is 15 kPa, and the pressure data detected by the detector when it is in motion is 15.1 kPa, which is greater than the preset pressure threshold, the detector will be immediately controlled to stop moving, thereby preventing the detector from continuing to move and causing crush injury to the patient.

[0105] In this embodiment, by monitoring pressure data in real time and immediately stopping the detector movement when a threshold is reached, it is possible to effectively prevent the detector from causing crushing injury to the patient due to excessive pressure during movement, thus significantly improving the safety of using medical equipment.

[0106] based on Figure 1 The following is a scene illustration, which will be combined with... Figure 10This application provides a detailed description of the exposure parameter updating device provided in its embodiments. It should be noted that... Figure 10 The exposure parameter update device in the present application is used to perform the following operations. Figures 1-9 The methods shown in the embodiments are for illustrative purposes only, illustrating the parts relevant to the embodiments of this application. For specific technical details not disclosed, please refer to this application. Figures 1-9 In the embodiment shown, the exposure parameter update device 600 may include a parameter calculation unit 601, a pose calculation unit 602, an image generation unit 603, and a data update unit 604, as detailed below: The parameter calculation unit 601 is used to obtain the thickness information of the part to be detected of the target object and determine the target exposure parameters of the X-ray generator based on the thickness information. The pose calculation unit 602 is used to determine the density information of the part to be detected based on the thickness information and the target exposure parameters, and to adjust the chamfer to the target pose based on the density information. The image generation unit 603 is used to control the X-ray generator to perform X-ray scanning on the area to be detected based on the target exposure parameters, so as to obtain an initial detection image of the area to be detected. The data update unit 604 is used to update the thickness information of the area to be detected based on the image brightness parameters and image exposure parameters of the initial detection image, and to update the target exposure parameters based on the updated thickness information.

[0107] Optionally, in some embodiments, the parameter calculation unit 601 can be used for: Acquire regional point cloud data of the area where the medical device is located and surface point cloud data of the target object; Based on regional point cloud data and body surface point cloud data, a three-dimensional data model corresponding to the area where the medical device is located is obtained. Semantic segmentation is performed on the 3D data model to determine the parts of the target object to be detected.

[0108] Optionally, in some embodiments, the parameter calculation unit 601 can be used for: The three-dimensional feature data of the area to be detected is acquired, and feature analysis is performed on the three-dimensional feature data to obtain the thickness information of the area to be detected.

[0109] Optionally, in some embodiments, the pose calculation unit 602 can be used for: Based on the target exposure parameters and the thickness information of the area to be detected, simulated exposure results are obtained for the area to be detected. A predicted exposure image of the area to be detected is generated based on the simulated exposure results; Based on the grayscale values ​​of each region in the predicted exposure image, the density information of the area to be detected is determined.

[0110] Optionally, in some embodiments, the pose calculation unit 602 can be used for: Based on the density information of the area to be detected, the ray gradient attenuation value is obtained; The target position and target angle of the beam limiter are determined based on the ray gradient attenuation value. The target pose of the beam limiter is determined based on the target position and target angle, and the beam limiter is adjusted to the target pose.

[0111] Optionally, in some embodiments, the image generation unit 603 can be used to: Based on the detector receiving scanning rays emitted by the ray generator; The scanning rays are converted into electrical signals, and an initial detection image of the area to be detected is generated based on the electrical signals.

[0112] Optionally, in some embodiments, the image generation unit 603 can be used to: The target detection position of the detector is determined based on the thickness information of the part to be detected; Move the detector to the target detection location.

[0113] Optionally, in some embodiments, the image generation unit 603 can be used to: When the detector is in motion, the relative distance between the detector and the target object is obtained; The detector stops moving when the relative distance meets a preset distance threshold.

[0114] Optionally, in some embodiments, the image generation unit 603 can be used to: Acquire pressure detection data from the medical device while the detector is in motion; The detector stops moving when the pressure detection data meets the preset pressure threshold.

[0115] In this embodiment, by acquiring the thickness information of the target area to be detected and determining the target exposure parameters of the X-ray generator based on the thickness information, the initial imaging conditions are made more closely aligned with actual needs. Subsequently, the density information of the target area to be detected is determined based on the thickness information and the target exposure parameters, and the collimator is adjusted to the target pose according to the density information, thereby optimizing the collimation and coverage of the X-ray beam. After controlling the X-ray generator to perform X-ray scanning based on the target exposure parameters to obtain the initial detection image, the thickness information is updated based on the image brightness parameters and image exposure parameters of the initial detection image to correct parameter deviations. Finally, the target exposure parameters are updated based on the updated thickness information to further refine the scanning settings. The above scheme effectively reduces errors in the imaging process by introducing image feedback and parameter correction mechanisms, thereby improving the imaging accuracy of medical equipment.

[0116] Furthermore, the exposure parameter updating device provided in the above embodiments and the exposure parameter updating method embodiments belong to the same concept, and their implementation process can be found in the method embodiments, which will not be repeated here.

[0117] The sequence numbers of the embodiments described above are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0118] Please see Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 11 As shown, the electronic device 700 includes a processor 701 and a memory 702. The processor 701 and the memory 702 are electrically connected.

[0119] The processor 701 is the control center of the electronic device 700 and may include one or more processing cores. The processor 701 connects to various parts of the electronic device using various interfaces and lines. By running or calling computer programs stored in the memory 702, and by calling data stored in the memory 702, it executes various functions and processes data of the electronic device, thereby providing overall control over the electronic device. Optionally, the processor 701 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 701 may integrate one or more of the following: CPU, Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user page, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 701 and may be implemented separately using a communication chip.

[0120] The memory 702 can be used to store software programs and modules. The processor 701 executes various functional applications and data processing by running the computer programs and modules stored in the memory 702. The memory 702 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, computer programs required for at least one function, etc.; the data storage area may store data created according to the use of the electronic device, etc.

[0121] Furthermore, memory 702 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory 702 may also include a memory controller to provide processor 701 with access to memory 702.

[0122] In this embodiment, the processor 701 in the electronic device 700 loads the instructions corresponding to the processes of one or more computer programs into the memory 702 according to the following steps, and the processor 701 runs the computer programs stored in the memory 702 to realize various functions, as follows: Obtain the thickness information of the part of the target object to be inspected, and determine the target exposure parameters of the X-ray generator based on the thickness information; The density information of the area to be detected is determined based on the thickness information and the target exposure parameters, and the beam limiter is adjusted to the target pose based on the density information. The control X-ray generator performs X-ray scanning on the area to be detected based on the target exposure parameters to obtain an initial detection image of the area to be detected; The thickness information of the area to be detected is updated based on the image brightness parameters and image exposure parameters of the initial detection image; The target exposure parameters are updated based on the updated thickness information.

[0123] Optionally, before acquiring the thickness information of the target object's detection area, the processor 701 specifically performs the following: acquiring regional point cloud data of the area where the medical device is located and surface point cloud data of the target object; obtaining a three-dimensional data model corresponding to the area where the medical device is located based on the regional point cloud data and surface point cloud data; and performing semantic segmentation on the three-dimensional data model to determine the target object's detection area.

[0124] Optionally, the processor 701, when executing the process of obtaining the thickness information of the part to be detected of the target object, specifically performs the following: obtaining the three-dimensional feature data of the part to be detected, performing feature analysis on the three-dimensional feature data, and obtaining the thickness information of the part to be detected.

[0125] Optionally, the processor 701, when determining the density information of the area to be detected based on the thickness information and the target exposure parameters, specifically performs the following: obtaining a simulated exposure result for the area to be detected based on the target exposure parameters and the thickness information of the area to be detected; generating a predicted exposure image of the area to be detected based on the simulated exposure result; and determining the density information of the area to be detected based on the grayscale values ​​of each region in the predicted exposure image.

[0126] Optionally, the processor 701 performs the following steps when adjusting the bundle limiter to the target pose based on density information: obtaining the ray gradient attenuation value based on the density information of the part to be detected; determining the target position and target angle of the bundle limiter based on the ray gradient attenuation value; determining the target pose of the bundle limiter based on the target position and target angle, and adjusting the bundle limiter to the target pose.

[0127] Optionally, the processor 701, when executing the initial detection image of the area to be detected, specifically performs the following: receiving scanning rays emitted by the X-ray generator based on the detector; converting the scanning rays into electrical signals; and generating the initial detection image of the area to be detected based on the electrical signals.

[0128] Optionally, before executing the scanning ray emitted by the ray generator based on the detector receiving the ray, the processor 701 specifically performs the following: determining the target detection position of the detector based on the thickness information of the part to be detected; and moving the detector to the target detection position.

[0129] Optionally, when the processor 701 moves the detector to the target detection position, it specifically performs the following: while the detector is in a moving state, it acquires the relative distance between the detector and the target object; and when the relative distance meets a preset distance threshold, it controls the detector to stop moving.

[0130] Optionally, when the processor 701 moves the detector to the target detection position, it specifically performs the following: while the detector is in a moving state, it acquires the pressure detection data of the medical device; and when the pressure detection data meets a preset pressure threshold, it controls the detector to stop moving.

[0131] In this embodiment, by acquiring the thickness information of the target area to be detected and determining the target exposure parameters of the X-ray generator based on the thickness information, the initial imaging conditions are made more closely aligned with actual needs. Subsequently, the density information of the target area to be detected is determined based on the thickness information and the target exposure parameters, and the collimator is adjusted to the target pose according to the density information, thereby optimizing the collimation and coverage of the X-ray beam. After controlling the X-ray generator to perform X-ray scanning based on the target exposure parameters to obtain the initial detection image, the thickness information is updated based on the image brightness parameters and image exposure parameters of the initial detection image to correct parameter deviations. Finally, the target exposure parameters are updated based on the updated thickness information to further refine the scanning settings. The above scheme effectively reduces errors in the imaging process by introducing image feedback and parameter correction mechanisms, thereby improving the imaging accuracy of medical equipment.

[0132] In addition, the device provided in this application embodiment may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute an exposure parameter update method provided in the above embodiment.

[0133] This application also provides a computer-readable storage medium storing a computer program. When the computer program is run on a computer, it causes the computer to execute the above-described related method steps to implement the exposure parameter update method provided in the above embodiments.

[0134] This application also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement the exposure parameter update method provided in the above embodiments.

[0135] In this application, the apparatus, computer-readable storage medium, computer program product or chip provided in the embodiments are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0136] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0137] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the related couplings or direct couplings or communication connections shown or discussed may be through some interfaces; indirect couplings or communication connections between apparatuses or units may be electrical, mechanical, or other forms.

[0138] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for updating exposure parameters, characterized in that, Applied to a medical device, the medical device including a radiation generator and a beam constrictor, the method includes: Obtain the thickness information of the part of the target object to be inspected, and determine the target exposure parameters of the X-ray generator based on the thickness information; The density information of the region to be detected is determined based on the thickness information and the target exposure parameters, and the beam limiter is adjusted to the target pose based on the density information. The X-ray generator is controlled to perform X-ray scanning on the area to be detected based on the target exposure parameters to obtain an initial detection image of the area to be detected; The thickness information of the region to be detected is updated based on the image brightness parameters and the image exposure parameters of the initial detection image; The target exposure parameters are updated based on the updated thickness information; The step of determining the density information of the region to be detected based on the thickness information and the target exposure parameters includes: Based on the target exposure parameters and the thickness information of the area to be detected, a simulated exposure result for the area to be detected is obtained; A predicted exposure image of the area to be detected is generated based on the simulated exposure results; Based on the gray values ​​of each region in the predicted exposure image, the density information of the part to be detected is determined; The step of adjusting the beam limiter to the target pose based on the density information includes: Based on the density information of the region to be detected, the ray gradient attenuation value is obtained; The target position and target angle of the beam limiter are determined based on the ray gradient attenuation value. The target pose of the beam limiter is determined based on the target position and the target angle, and the beam limiter is adjusted to the target pose.

2. The method according to claim 1, characterized in that, Before obtaining the thickness information of the part to be detected of the target object, the method includes: Acquire the regional point cloud data of the area where the medical device is located and the surface point cloud data of the target object; Based on the regional point cloud data and the body surface point cloud data, a three-dimensional data model corresponding to the area where the medical device is located is obtained. Semantic segmentation is performed on the three-dimensional data model to determine the detection area of ​​the target object.

3. The method according to claim 1, characterized in that, The process of obtaining the thickness information of the part of the target object to be detected includes: The three-dimensional feature data of the area to be detected is acquired, and feature analysis is performed on the three-dimensional feature data to obtain the thickness information of the area to be detected.

4. The method according to claim 1, characterized in that, The medical device also includes a detector. Before controlling the X-ray generator to perform X-ray scanning on the area to be detected based on the target exposure parameters, the method includes: The target detection position of the detector is determined based on the thickness information of the part to be detected; Move the detector to the target detection position.

5. The method according to claim 4, characterized in that, Moving the detector to the target detection position includes: When the detector is in a moving state, the relative distance between the detector and the target object is obtained; When the relative distance meets a preset distance threshold, the detector is controlled to stop moving.

6. The method according to claim 4, characterized in that, Moving the detector to the target detection position includes: When the detector is in a moving state, the pressure detection data of the medical device is acquired; When the pressure detection data meets a preset pressure threshold, the detector is controlled to stop moving.

7. An exposure parameter updating device, characterized in that, Applied to medical devices, the medical devices including a radiation generator and a beam limiter, the device includes: The parameter calculation unit is used to obtain the thickness information of the part to be detected of the target object, and to determine the target exposure parameters of the X-ray generator based on the thickness information; The pose calculation unit is used to determine the density information of the part to be detected based on the thickness information and the target exposure parameters, and to adjust the chamfer to the target pose based on the density information. An image generation unit is used to control the ray generator to perform ray scanning on the area to be detected based on the target exposure parameters, so as to obtain an initial detection image of the area to be detected. The data update unit is used to update the thickness information of the part to be detected based on the image brightness parameters and the image exposure parameters of the initial detection image, and to update the target exposure parameters based on the updated thickness information. The pose calculation unit is used for: Based on the target exposure parameters and the thickness information of the area to be detected, simulated exposure results are obtained for the area to be detected. A predicted exposure image of the area to be detected is generated based on the simulated exposure results; Based on the gray values ​​of each region in the predicted exposure image, the density information of the area to be detected is determined; The pose calculation unit is used for; Based on the density information of the area to be detected, the ray gradient attenuation value is obtained; The target position and target angle of the beam limiter are determined based on the ray gradient attenuation value. The target pose of the beam limiter is determined based on the target position and target angle, and the beam limiter is adjusted to the target pose.

8. An electronic device, characterized in that, The electronic device includes: Memory, used to store executable program code; A processor is configured to call and run the executable program code from the memory, causing the electronic device to perform the exposure parameter update method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the exposure parameter update method as described in any one of claims 1 to 6.

Images