Method for automatically adjusting height of vertical position detector assembly, shooting method and equipment

Abstract

The invention provides a method for automatically adjusting the height of a vertical position detector assembly, a method for shooting a chest radiograph, equipment, a medium and a product. The method for automatically adjusting the height of the vertical position detector assembly comprises the steps that the first height between the lower jaw of a detected person and the ground is obtained; acquiring a second height between the vertical position detector assembly and the ground; calculating the height difference between the first height and the second height; a signal is sent to the vertical position detector assembly adjusting mechanism according to the height difference, and the vertical position detector assembly adjusting mechanism adjusts the height of the vertical position detector assembly according to the height difference. The technical problems that in the prior art, due to the fact that height adjustment of a traditional vertical position detector assembly depends on manual operation of medical staff according to experience, the adjustment process is time-consuming, the manual adjustment precision is not high, the image quality is inconsistent, and the workload of the medical staff is increased are solved. According to the method for automatically adjusting the height of the standing position detector assembly, automatic adjustment can be carried out according to the face image of the patient and the image of the standing position detector assembly.

Description

Technical Field

[0001] The present invention relates to the field of software, and in particular to a method for automatically adjusting the height of a standing detector assembly, a method for taking a chest X-ray, a device, a medium and a product. Background Art

[0002] Digital radiography (DR) is a widely used medical imaging modality in clinical practice, with chest X-rays being one of the most common examination items. To obtain high-quality DR chest radiographs, the height of the upright detector assembly must be adjusted appropriately based on the patient's height and body shape, ensuring that the flat-panel receiver is positioned appropriately.

[0003] The height adjustment of traditional standing detector components mainly relies on manual operation based on the experience of medical staff. However, manual operation has the following problems: First, the adjustment process is time-consuming, and medical staff need to adjust repeatedly to achieve the ideal position; second, the manual adjustment accuracy is not high, which can easily affect the quality of chest X-rays due to inaccurate positioning; third, different medical staff have different operating habits, resulting in inconsistent image quality; fourth, it increases the workload of medical staff, especially in high-workload work environments. Summary of the Invention

[0004] Based on the above problems, the present invention proposes a method for automatically adjusting the height of a standing detector assembly, a method, equipment, medium and product for taking chest X-rays. The present invention solves the technical problems in the prior art that the traditional height adjustment of a standing detector assembly depends on manual operation by medical staff based on experience, which results in a time-consuming adjustment process, low manual adjustment accuracy, inconsistent image quality and increased workload for medical staff. The present invention solves the technical problems in the prior art that the traditional height adjustment of a standing detector assembly depends on manual operation by medical staff based on experience, which results in a time-consuming adjustment process, low manual adjustment accuracy, inconsistent image quality and increased workload for medical staff. The method for automatically adjusting the height of a standing detector assembly provided by the present invention can automatically adjust according to the patient's facial image and the image of the standing detector assembly without manual intervention, thereby greatly improving the shooting accuracy and efficiency. In addition, it only requires adding RGB cameras and depth point cloud camera equipment to the existing equipment, which is low cost and effective.

[0005] The present invention provides a method for automatically adjusting the height of a standing position detector assembly, comprising:

[0006] Obtaining a first height between the subject's lower jaw and the ground;

[0007] Obtain a second height between the standing detector assembly and the ground;

[0008] Calculate the height difference between the first height and the second height;

[0009] A signal is sent to the standing detector assembly adjustment mechanism according to the height difference, and the standing detector assembly adjustment mechanism adjusts the height of the standing detector assembly according to the height difference.

[0010] Furthermore, obtaining a first height between the subject's lower jaw and the ground includes:

[0011] Obtaining a face image of the subject and extracting a face bounding box, and extracting two-dimensional coordinate points of the mandibular feature points from the face bounding box;

[0012] Obtain a face area point cloud subset based on the face point cloud image;

[0013] Constructing a spatial ray equation based on the two-dimensional coordinates of the mandibular feature points and the internal parameters of the camera device that captures the facial image;

[0014] Find the point closest to the ray represented by the spatial ray equation from the face area point cloud subset as the three-dimensional coordinate point of the mandibular feature point;

[0015] Obtaining three-dimensional coordinate points of at least three mandibular feature points and fitting them to a first ground plane equation;

[0016] The three-dimensional coordinate point of the mandibular feature point is converted from the camera coordinate system to the world coordinate system with the first ground plane equation as a reference. The z-axis coordinate in the world coordinate system is the first height.

[0017] Furthermore, obtaining a second height between the standing position detector assembly and the ground includes:

[0018] Acquire an RGB image of the standing detector assembly and extract an edge region of the standing detector assembly;

[0019] Acquire a point cloud image of the standing detector assembly, and construct a point cloud subset of the edge area according to the edge area of ​​the standing detector assembly;

[0020] Performing image processing on the point cloud subset to obtain a high-precision three-dimensionally reconstructed point cloud subset image of the standing detector assembly;

[0021] Calculate the three-dimensional coordinate points of the standing detector component according to the point cloud subset image;

[0022] Obtaining three-dimensional coordinate points of at least three standing detector assemblies and fitting them to a second ground plane equation;

[0023] The three-dimensional coordinate point of the standing detector assembly is converted from the camera coordinate system to the world coordinate system with the second ground plane equation as a reference, and the z-axis coordinate in the world coordinate system is the second height.

[0024] Furthermore, the performing image processing on the point cloud subset includes:

[0025] Multi-resolution stereo matching is performed on point cloud subsets and then optimized for sub-pixel accuracy.

[0026] In addition, image processing also includes: applying Kalman filtering to smooth the trajectory of the point cloud subset optimized for sub-pixel accuracy for image processing.

[0027] The present invention further provides a method for taking a chest X-ray using any of the above methods for automatically adjusting the height of a standing detector assembly, comprising:

[0028] After the height adjustment of the standing detector assembly is completed, the respiratory data of the subject monitored by the radar is obtained;

[0029] Determine the timing of chest X-ray based on respiratory data.

[0030] In addition, the timing for initiating chest X-ray shooting based on respiratory data includes:

[0031] When respiratory data showing deep breathing followed by breath holding is detected, the chest X-ray image corresponding to the respiratory data at this moment is taken as the final diagnostic image, or the chest X-ray is started at this moment and the image taken is taken as the final diagnostic image.

[0032] The present invention further provides an electronic device, comprising:

[0033] at least one processor; and,

[0034] a memory communicatively connected to at least one of the processors; wherein,

[0035] The memory stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors to enable at least one of the processors to perform the method for automatically adjusting the height of the standing detector assembly as described in any one of the above items.

[0036] The present invention also provides a storage medium storing computer instructions. When a computer executes the computer instructions, the storage medium is used to execute all steps of the method for automatically adjusting the height of a standing detector assembly as described in any one of the above items.

[0037] The present invention also proposes a computer program product, including a computer program / instruction, characterized in that when the computer program / instruction is executed by a processor, it implements the method for automatically adjusting the height of the standing detector assembly as described in any of the above items.

[0038] The present invention solves the technical problems in the prior art that the traditional height adjustment of the standing detector assembly relies on manual operation by medical staff based on experience, which results in a time-consuming adjustment process, low manual adjustment accuracy, inconsistent image quality, and increased workload for medical staff. The method for automatically adjusting the height of the standing detector assembly provided by the present invention can automatically adjust according to the patient's facial image and the image of the standing detector assembly without manual intervention, greatly improving the shooting accuracy and efficiency. In addition, it only requires adding RGB cameras and depth point cloud camera equipment to the existing equipment, which is low-cost and effective. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flow chart of a method for automatically adjusting the height of a standing detector assembly provided by one embodiment of the present invention;

[0040] Figure 2 A method for taking chest X-rays using a method for automatically adjusting the height of a standing detector assembly provided in one embodiment of the present invention;

[0041] Figure 3 A schematic diagram of an electronic device provided by one embodiment of the present invention;

[0042] Figure 4 A flowchart of image processing and positioning provided by one embodiment of the present invention;

[0043] Figure 5 A flow chart of a method for automatically adjusting the height of a standing detector assembly provided by one embodiment of the present invention;

[0044] Figure 6 A schematic diagram of an interface for automatically adjusting the height of a standing detector assembly provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The present invention is further described in detail below with reference to specific embodiments and accompanying drawings, which are intended only to elaborate on the specific embodiments of the present invention and do not impose any limitation on the present invention. The scope of protection of the present invention shall be subject to the claims.

[0046] Reference Figure 1 The present invention provides a method for automatically adjusting the height of a standing detector assembly, comprising:

[0047] Step S001, obtaining a first height between the subject's lower jaw and the ground;

[0048] Step S002, obtaining a second height between the standing detector assembly and the ground;

[0049] Step S003, calculating the height difference between the first height and the second height;

[0050] Step S004: sending a signal to the standing detector assembly adjustment mechanism according to the height difference, and the standing detector assembly adjustment mechanism adjusts the height of the standing detector assembly according to the height difference.

[0051] In step S001, a first height between the subject's lower jaw and the ground is obtained;

[0052] In order to calculate the height difference between the subject's mandible and the standing detector assembly and adjust the height of the standing detector assembly, the ground is used as a reference plane to obtain the first height between the subject's mandible and the ground. The specific steps are as follows:

[0053] Obtaining a face image of the subject and extracting a face bounding box, and extracting two-dimensional coordinate points of the mandibular feature points from the face bounding box;

[0054] Obtain a face area point cloud subset based on the face point cloud image;

[0055] Constructing a spatial ray equation based on the two-dimensional coordinates of the mandibular feature points and the internal parameters of the camera device that captures the facial image;

[0056] Find the point closest to the ray represented by the spatial ray equation from the face area point cloud subset as the three-dimensional coordinate point of the mandibular feature point;

[0057] Obtaining three-dimensional coordinate points of at least three mandibular feature points and fitting them to a first ground plane equation;

[0058] The three-dimensional coordinate point of the mandibular feature point is converted from the camera coordinate system to the world coordinate system with the first ground plane equation as a reference. The z-axis coordinate in the world coordinate system is the first height.

[0059] Specifically:

[0060] Obtain a face image and extract a face bounding box, and extract the two-dimensional coordinate points of the mandibular feature points from the face bounding box;

[0061] The process of obtaining a face image and extracting the face bounding box is as follows:

[0062] There are many methods for image edge detection, such as extracting the face contour through Canny operator edge detection and then generating a bounding box. Usually a set of numerical values ​​is used to represent the position and range of the face in the image.

[0063] For example, the upper left corner + lower right corner coordinate representation (xmin, ymin, xmax, ymax), for example: (100, 150, 300, 400) means the left boundary is in the 100th column, the upper boundary is in the 150th row, the right boundary is in the 300th column, and the lower boundary is in the 400th row.

[0064] The representation of center point + width and height (x_center, y_center, width, height) is as follows:

[0065] The rectangle is represented by the center coordinates (x_center, y_center) plus the width and height. For example, (200,275,200,250) means the center is at (200,275), the width is 200 pixels, and the height is 250 pixels.

[0066] Normalization can be performed later.

[0067] The two-dimensional coordinate points of the mandibular feature points extracted from the face bounding box are as follows:

[0068] Extracting mandibular key points involves filtering out mandibular-related points (such as the mandibular apex and mandibular line points) from the key point list. For example, in a 68-point model, the mandibular key points are located at points 17-26 (a total of 10 points, arranged clockwise from left to right along the mandibular line). Point 17 is the starting point of the left mandible (the leftmost end of the mandibular line), point 26 is the starting point of the right mandible (the rightmost end of the mandibular line), and point 24 is the mandibular apex (the lowest point on the mandibular line and the point with the largest y coordinate). Each point is represented by pixel coordinates (x, y). For example, point 24 has coordinates (x24, y24).

[0069] You can also choose a lightweight model to output 5 points, 10 points, or only the mandibular tip (or mandibular midpoint). For example, the 5th point is the midpoint of the mandibular bottom (x_center, y_bottom).

[0070] The process of extracting mandibular key points can be quickly implemented by directly calling mature image processing libraries (such as Dlib and OpenCV) without manually calculating coordinates.

[0071] Face images can be acquired through RGB cameras.

[0072] Obtain a face area point cloud subset based on the face point cloud image;

[0073] The facial point cloud image can be acquired by a depth point cloud camera. A 3D search space is constructed based on the center of the face bounding box, and points that meet the screening criteria constitute the face area point cloud subset.

[0074] The specific method is to traverse each point (x, y, z) in the original point cloud (face bounding box), retaining the points that meet the preset conditions to form the face area point cloud subset. The process from raw data to point cloud subset is the process of filtering out useful points, retaining only the necessary points. Therefore, the input data is the original image data, and the output data is the filtered image data.

[0075] Constructing a spatial ray equation based on the two-dimensional coordinates of the mandibular feature points and the internal parameters of the camera device that captures the facial image;

[0076] Input the two-dimensional coordinates of the mandibular feature points and normalize them using the internal parameters of the camera device;

[0077] Determine the ray direction vector;

[0078] The space ray equation is constructed based on the normalized two-dimensional coordinate points and the ray direction vector. The ray direction vector is

[0079]

[0080] Among them, K is the internal parameter of the camera device, x c ,y c is a two-dimensional coordinate point;

[0081] The space ray equation is

[0082]

[0083] Where t represents the distance the ray extends from the optical center along the direction of the ray direction vector.

[0084] The spatial ray equation represents a three-dimensional ray starting from the optical center of the camera and passing through a point on the image plane. The ray direction vector points from the optical center to the unit vector of the target point on the image plane.

[0085] The two-dimensional coordinate point is converted into the normalized coordinate in the camera coordinate system through the camera intrinsic parameter matrix K.

[0086] In the camera coordinate system, the ray starts from the optical center (0,0,0) and passes through the normalized coordinate point (x,y,1), so the direction vector is:

[0087]

[0088] Substituting the starting point (0,0,0) and the direction vector, we get the spatial ray equation:

[0089]

[0090] Find the point closest to the ray represented by the spatial ray equation from the face area point cloud subset as the three-dimensional coordinate point of the mandibular feature point;

[0091] The calculation formula is:

[0092]

[0093] Among them, o is the origin of the camera coordinate system, is the three-dimensional coordinate point of the mandibular feature point, and P is the nearest point.

[0094] Obtain three-dimensional coordinate points of at least three mandibular feature points and fit them to the ground plane equation;

[0095] The least square method is used to fit the ground plane equation Ax+By+CZ+D=0;

[0096] Among them, A, B, C, D are the plane parameters to be determined;

[0097] Input the three-dimensional coordinates of the mandibular feature points into the ground plane equation to solve the optimal plane parameters.

[0098] When solving for the optimal plane parameters, the singular value decomposition (SVD) method and the normal equation formula solving method can be used to solve for the optimal plane parameters.

[0099] For example, the process of solving the normal equation formula is as follows:

[0100]

[0101] Solution:

[0102] In this case, C is the inverse of the coefficient of Z.

[0103] M is the design matrix, Z is the observation vector, M T is the transpose of M, (M T M) -1 is the matrix M T The inverse of M.

[0104] The SVD solution is to decompose the original matrix M and use its pseudo-inverse M + To directly calculate the solution. The two methods are mature algorithms and will not be described in detail here.

[0105] The coordinate conversion formula for converting the three-dimensional coordinate point of the mandibular feature point from the camera coordinate system to the world coordinate system with the ground plane equation as the reference is:

[0106]

[0107] in, is the three-dimensional coordinate point in the world coordinate system, is the three-dimensional coordinate point in the camera coordinate system, R is the rotation matrix, and T is the translation vector. R and T are determined by the ground plane equation;

[0108] The shooting device in the present invention is an integration of an RGB camera and a point cloud depth camera.

[0109] In one embodiment, obtaining a face region point cloud subset based on a face point cloud image includes:

[0110] A three-dimensional search space is constructed according to the center of the face bounding box, and the points that meet the screening conditions constitute the face area point cloud subset.

[0111] By establishing a subset of the face area point cloud, the processed data is reduced and the subsequent processing speed is increased.

[0112] In one embodiment, constructing a spatial ray equation based on the two-dimensional coordinates of the mandibular feature point and the internal parameters of the camera device that captures the facial image includes:

[0113] Input the two-dimensional coordinates of the mandibular feature points and normalize them using the internal parameters of the camera device;

[0114] Determine the ray direction vector;

[0115] The space ray equation is constructed based on the normalized two-dimensional coordinate points and the ray direction vector. The ray direction vector is

[0116]

[0117] Among them, K is the internal parameter of the camera device, x c ,y c is a two-dimensional coordinate point;

[0118] The space ray equation is

[0119]

[0120] Where t represents the distance the ray extends from the optical center along the direction of the ray direction vector.

[0121] By constructing the spatial ray equation, we prepare for the subsequent finding of the three-dimensional coordinate points of the mandibular feature points.

[0122] In one embodiment, a reference measurement value H is introduced. ref Make the fitted ground plane equation consistent with the actual ground, H ref The actual measured distance from the mandibular point to the ground. The plane parameters must meet the following conditions:

[0123]

[0124] Among them, X ref ,Y ref ,Z ref is the three-dimensional coordinate point of the measured mandible.

[0125] In order to accurately determine the ground position, it is necessary to input a reference measurement value obtained by conventional measurement means (such as a handheld laser rangefinder, etc.), that is, the actual measured distance H from the tester's jaw point to the ground in a level view state. ref , through H ref The introduction of makes the fitted ground plane equation consistent with the actual ground.

[0126] In step S002, the second height between the standing detector assembly and the ground is obtained, specifically:

[0127] Acquire an RGB image of the standing detector assembly and extract an edge region of the standing detector assembly;

[0128] Acquire a point cloud image of the standing detector assembly, and construct a point cloud subset of the edge area according to the edge area of ​​the standing detector assembly;

[0129] Performing image processing on the point cloud subset to obtain a high-precision three-dimensionally reconstructed point cloud subset image of the standing detector assembly;

[0130] Calculate the three-dimensional coordinate points of the standing detector component according to the point cloud subset image;

[0131] Obtaining three-dimensional coordinate points of at least three standing detector assemblies and fitting them to a second ground plane equation;

[0132] The three-dimensional coordinate point of the standing detector assembly is converted from the camera coordinate system to the world coordinate system with the second ground plane equation as a reference, and the z-axis coordinate in the world coordinate system is the second height.

[0133] The entire processing process for the standing detector assembly is similar to that for facial images. First, the edge region of the two-dimensional image is extracted. Then, based on the edge region and the point cloud image, a three-dimensional point cloud subset corresponding to the edge region is constructed. To obtain a high-precision three-dimensional reconstructed point cloud subset image of the standing detector assembly, image processing is performed. The three-dimensional coordinate points of the standing detector assembly are calculated. Based on the fitted second ground plane equation, the three-dimensional coordinate points of the standing detector assembly are converted from the camera coordinate system to the world coordinate system with the second ground plane equation as a reference. The z-axis coordinate in the world coordinate system is the second height. Here, the second height can be taken as the distance from the center point of the standing detector assembly to the ground. Of course, depending on the calculation needs, the upper edge of the standing detector assembly can also be used.

[0134] In step S003, the height difference between the first height and the second height is calculated;

[0135] When actually taking a chest X-ray of a patient, the optimal distance between the patient's lower jaw and the center of the standing detector assembly is about 20 cm, so the height difference between the first height and the second height is calculated. If the height difference is greater than or less than 20 cm, a signal is sent to the standing detector assembly adjustment mechanism according to the height difference to adjust the height of the standing detector assembly.

[0136] In step S004, a signal is sent to the standing detector assembly adjustment mechanism according to the height difference, and the standing detector assembly adjustment mechanism adjusts the height of the standing detector assembly according to the height difference.

[0137] The present invention solves the technical problems in the prior art that the traditional height adjustment of the standing detector assembly relies on manual operation by medical staff based on experience, which results in a time-consuming adjustment process, low manual adjustment accuracy, inconsistent image quality, and increased workload for medical staff. The method for automatically adjusting the height of the standing detector assembly provided by the present invention can automatically adjust according to the patient's facial image and the image of the standing detector assembly without manual intervention, greatly improving the shooting accuracy and efficiency. In addition, it only requires adding RGB cameras and depth point cloud camera equipment to the existing equipment, which is low-cost and effective.

[0138] In one embodiment, obtaining a first height between the subject's lower jaw and the ground includes:

[0139] Obtaining a face image of the subject and extracting a face bounding box, and extracting two-dimensional coordinate points of the mandibular feature points from the face bounding box;

[0140] Obtain a face area point cloud subset based on the face point cloud image;

[0141] Constructing a spatial ray equation based on the two-dimensional coordinates of the mandibular feature points and the internal parameters of the camera device that captures the facial image;

[0142] Find the point closest to the ray represented by the spatial ray equation from the face area point cloud subset as the three-dimensional coordinate point of the mandibular feature point;

[0143] Obtaining three-dimensional coordinate points of at least three mandibular feature points and fitting them to a first ground plane equation;

[0144] The three-dimensional coordinate point of the mandibular feature point is converted from the camera coordinate system to the world coordinate system with the first ground plane equation as a reference. The z-axis coordinate in the world coordinate system is the first height.

[0145] By obtaining the first height between the subject's lower jaw and the ground, a basis is provided for subsequent height difference calculation.

[0146] In one embodiment, obtaining a second height between the standing detector assembly and the ground includes:

[0147] Acquire an RGB image of the standing detector assembly and extract an edge region of the standing detector assembly;

[0148] Acquire a point cloud image of the standing detector assembly, and construct a point cloud subset of the edge area according to the edge area of ​​the standing detector assembly;

[0149] Performing image processing on the point cloud subset to obtain a high-precision three-dimensionally reconstructed point cloud subset image of the standing detector assembly;

[0150] Calculate the three-dimensional coordinate points of the standing detector component according to the point cloud subset image;

[0151] Obtaining three-dimensional coordinate points of at least three standing detector assemblies and fitting them to a second ground plane equation;

[0152] The three-dimensional coordinate point of the standing detector assembly is converted from the camera coordinate system to the world coordinate system with the second ground plane equation as a reference, and the z-axis coordinate in the world coordinate system is the second height.

[0153] By obtaining the second height between the standing detector assembly and the ground, a basis is provided for subsequent height difference calculation.

[0154] In one embodiment, performing image processing on the point cloud subset includes:

[0155] Multi-resolution stereo matching is performed on point cloud subsets and then optimized for sub-pixel accuracy.

[0156] The role of multi-resolution stereo matching: By performing stereo matching at different resolutions, we can improve matching efficiency and robustness while maintaining matching accuracy. This allows us to find the exact correspondence between corresponding points on the standing detector assembly at different viewing angles, thereby obtaining more accurate 3D information. For example, this can be achieved by constructing a pyramid, moving from low resolution to high resolution.

[0157] Sub-pixel precision optimization further improves the accuracy of matching points, making the 3D reconstruction more precise, capturing finer details and features on the surface of the plate, and reducing errors. This includes using B-spline surface fitting, precise edge extraction, and corner point calculation.

[0158] In one embodiment, the image processing further comprises: performing image processing on the point cloud subset optimized for sub-pixel accuracy by applying a Kalman filter to smooth the trajectory.

[0159] The purpose of applying Kalman filtering to smooth the trajectory is to smooth the trajectory of the acquired point cloud data, removing the influence of noise and instability, making the motion trajectory of the standing detector assembly more stable and continuous, improving the reliability and accuracy of the entire system, and providing high-quality data for subsequent analysis and applications. After image processing, a high-precision 3D reconstruction and trajectory-smoothed point cloud image of the standing detector assembly is obtained.

[0160] The following is a specific pseudo code in one embodiment:

[0161] Visual data acquisition: RGB-D cameras simultaneously acquire color images and depth point cloud data. The RGB camera is used to capture high-definition color images with a resolution of 1920×1080 pixels and a frame rate of 30 fps. The depth point cloud camera (D camera) is used to capture scene depth information with a resolution of 640×480 pixels and a depth accuracy better than ±1mm (at a test distance of 1 meter). The captured point cloud data is expressed in three-dimensional xyz coordinates.

[0162] The core pseudo code for image data acquisition is as follows:

[0163]

[0164]

[0165] The core pseudo code for face detection and mandibular feature point recognition is as follows:

[0166] The core pseudo code for three-dimensional space feature point positioning is as follows:

[0167]

[0168]

[0169] The core pseudo code for multi-point acquisition and fitting the ground plane equation is as follows:

[0170]

[0171]

[0172] The core pseudo code of coordinate system conversion is as follows:

[0173]

[0174] like Figure 4 and Figure 5 As shown, the core pseudo code for DR standing detector assembly positioning is as follows:

[0175]

[0176]

[0177] The core pseudo code of linkage control and automatic adjustment is as follows:

[0178]

[0179]

[0180] Human-computer interaction interface Figure 6 The core pseudo code for status display and visualization is as follows:

[0181]

[0182] The core pseudo code for user interaction and control is as follows:

[0183]

[0184]

[0185] Operation process: It includes three main parts: initialization phase, calibration phase and operation phase. The core pseudo code of the initialization phase is as follows:

[0186]

[0187] The core pseudo code of the calibration phase is as follows:

[0188]

[0189]

[0190] The core pseudo code of the running phase is as follows:

[0191]

[0192]

[0193] Compared with the prior art, this embodiment has the following significant advantages and beneficial effects:

[0194] High-precision three-dimensional positioning: This embodiment combines RGB images and depth point cloud images to achieve high-precision three-dimensional positioning of facial mandibular feature points, with positioning accuracy reaching millimeter level, which is significantly higher than traditional two-dimensional image recognition methods.

[0195] No specific posture required: The face detection and feature point recognition algorithm of this embodiment has strong adaptability to the patient's posture, and accurate mandibular position information can be obtained without the patient having to cooperate with a specific posture, thereby improving the user-friendliness of the system and the flexibility of application scenarios.

[0196] Innovative construction of ground plane equation (reference plane): This embodiment uses multi-point acquisition and plane fitting methods to construct a unified coordinate reference system without precise calibration, which simplifies the system deployment and usage process and improves the applicability and reliability of the system.

[0197] Simultaneously acquiring the patient and device positions: This embodiment uses the same visual acquisition device to simultaneously acquire the patient's facial features and the position of the DR standing detector assembly, ensuring the consistency and relative accuracy of position measurement and providing a reliable basis for precise adjustment.

[0198] Closed-loop automatic control: This embodiment realizes complete closed-loop control from feature point positioning to equipment adjustment, with a high degree of automation, reducing manual intervention and improving work efficiency and consistency.

[0199] Easy hardware deployment: This embodiment only requires one set of RGB-D camera equipment to achieve full functionality, without the need for additional sensors or markers, reducing system complexity and cost, and facilitating its promotion and application in various medical institutions.

[0200] Intuitive user interface: This embodiment provides a user interface with high visualization and easy operation. Medical staff can intuitively understand the system status and perform manual intervention when necessary, which enhances the controllability and safety of the system.

[0201] Significantly improve medical efficiency: Actual application tests show that this embodiment can shorten the manual height adjustment time of traditional standing detector components from an average of 50 seconds to less than 5 seconds, saving about 45 seconds per examination. For medical institutions with a daily examination volume of more than 100 people, more than 75 minutes can be saved per day, thereby improving work efficiency to a certain extent.

[0202] Improving image quality consistency: This embodiment ensures consistency in image acquisition position under different patient and operator conditions by precisely controlling the relative position relationship between the height of the standing detector assembly and the patient's mandible, thereby helping to improve image quality and diagnostic accuracy.

[0203] Improve patient experience: This embodiment reduces the time and frequency of patient cooperation and adjustment, reduces discomfort during the examination process, and optimizes the patient's examination experience.

[0204] The method of this embodiment is not only applicable to DR chest X-ray examinations, but can also be expanded through appropriate adjustments to other medical imaging examination scenarios that require automatic adjustment of equipment position according to human body characteristics, such as automatic adjustment of bed height of CT (Computed Tomography) and MRI (Magnetic Resonance Imaging). It has broad application prospects and significant socioeconomic value.

[0205] Reference Figure 2 The present invention further provides a method for taking a chest X-ray using any of the above-mentioned methods for automatically adjusting the height of a standing detector assembly, comprising:

[0206] Step S005, after the height adjustment of the standing position detector assembly is completed, obtaining the respiratory data of the subject monitored by radar;

[0207] Step S006: Determine the timing of taking a chest X-ray based on the respiratory data.

[0208] When the subject takes a chest X-ray, he or she will be asked to take a deep breath and the radar will be used to monitor the subject. When the radar detects a curve of taking a deep breath and then holding the breath in the subject's breathing curve, the camera will be taken immediately.

[0209] The breathing curve can be observed manually or automatically by the device. When the breathing displacement is detected to be significantly higher than the previous average value and a nearly flat curve appears afterwards, it means that the subject is taking a deep breath, and the shooting is automatically started at this time.

[0210] In one embodiment, the timing of initiating chest X-ray taking based on respiratory data includes:

[0211] When respiratory data showing deep breathing followed by breath holding is detected, the chest X-ray image corresponding to the respiratory data at this moment is taken as the final diagnostic image, or the chest X-ray is started at this moment and the image taken is taken as the final diagnostic image.

[0212] Millimeter-wave radar can monitor the breathing status and chest micro-movements of the person being monitored in real time. Millimeter-wave radar operates by transmitting electromagnetic wave signals and receiving signals reflected from a target. By analyzing these signals, it can detect tiny displacements of the human chest caused by breathing. Millimeter-wave radar technology can provide millimeter-level accuracy, making it an ideal sensing technology for monitoring human biosignals and supporting non-contact monitoring. In this embodiment, a 77GHz FMCW (frequency modulated continuous wave) millimeter-wave radar is used to effectively capture micro-movements caused by breathing in the human chest. Millimeter-wave radar has the ability to "perceive minute details," accurately detecting subtle vital signs such as breathing and body movements (heartbeat) at a long distance.

[0213] The processing flow is as follows:

[0214] 1. Signal acquisition: Collect the echo signal received by the radar.

[0215] 2. Distance and speed estimation: Extract distance and speed information through algorithms such as FFT.

[0216] 3. Chest micro-motion extraction: Isolate the tiny displacement signals representing breathing.

[0217] 4. Respiratory cycle analysis: Extract respiratory frequency and depth through time-frequency analysis.

[0218] 5. Respiratory status assessment: Determine whether the current respiratory status of the person being tested is suitable for X-ray exposure.

[0219] Respiratory states can be categorized into three types: deep inhalation, deep exhalation, and intermediate states. According to chest X-ray specifications, chest X-rays are typically taken during deep inhalation for optimal results. The system analyzes the breathing curve in real time, identifies the respiratory phase, and recommends the optimal exposure timing. Specifically, if the subject's breathing curve shows a deep breath followed by breath-holding, the system immediately captures the image.

[0220] In addition, to overcome the limitations of traditional radar single-point monitoring, this system adopts an improved spatial layout strategy, placing the radar at a high altitude and utilizing the high-resolution characteristics of millimeter-wave radar to distinguish targets from the distance dimension, ensuring monitoring accuracy and reliability.

[0221] Reference Figure 3 The present invention also provides a hardware structure diagram of an electronic device, including:

[0222] at least one processor 301; and,

[0223] A memory 302 in communication with at least one of the processors 301; wherein,

[0224] The memory 302 stores instructions that can be executed by at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the above-mentioned method for automatically adjusting the height of the standing detector assembly.

[0225] Figure 3 A processor 301 is taken as an example.

[0226] The electronic device is preferably a controller of the vehicle. The electronic device may further include: an input device 303 and a display device 304 .

[0227] The processor 301 , the memory 302 , the input device 303 and the display device 304 may be connected via a bus or other means, with the bus connection being used as an example in the figure.

[0228] The memory 302 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs, and modules, such as the program instructions / modules corresponding to the method for automatically adjusting the height of the standing position detector assembly in the embodiment of the present application, for example, Figure 2The processor 301 executes various functional applications and data processing by running the non-volatile software programs, instructions and modules stored in the memory 302, that is, implementing the method for automatically adjusting the height of the standing position detector assembly in the above embodiment.

[0229] The memory 302 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the method for automatically adjusting the height of the standing detector assembly, etc. In addition, the memory 302 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 302 may optionally include a memory remotely located relative to the processor 301, and these remote memories may be connected to a device that executes the method for automatically adjusting the height of the standing detector assembly via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0230] The input device 303 can receive user clicks and generate signal inputs related to user settings and function controls of the method for automatically adjusting the height of the standing position detector assembly. The display device 304 can include a display device such as a display screen.

[0231] One or more modules are stored in the memory 302 and, when executed by one or more processors 301 , perform the method for automatically adjusting the height of the standing detector assembly in any of the above method embodiments.

[0232] An embodiment of the present invention provides a storage medium storing computer instructions. When a computer executes the computer instructions, the storage medium is used to execute all steps of the method for automatically adjusting the height of a standing detector assembly as described above.

[0233] In the context of the present disclosure, a storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. The storage medium may be a machine-readable signal medium or a machine-readable storage medium. Alternatively, the storage medium may be a non-transitory computer-readable storage medium, for example, a non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device.

Claims

1. A method for automatically adjusting the height of a standing detector assembly, characterized in that: include: Obtaining a first height between the subject's lower jaw and the ground; Obtain a second height between the standing detector assembly and the ground; Calculate the height difference between the first height and the second height; A signal is sent to the standing detector assembly adjustment mechanism according to the height difference, and the standing detector assembly adjustment mechanism adjusts the height of the standing detector assembly according to the height difference.

2. The method for automatically adjusting the height of a standing position detector assembly according to claim 1, characterized in that: The obtaining of a first height between the subject's lower jaw and the ground comprises: Obtaining a face image of the subject and extracting a face bounding box, and extracting two-dimensional coordinate points of the mandibular feature points from the face bounding box; Obtain a face area point cloud subset based on the face point cloud image; Constructing a spatial ray equation based on the two-dimensional coordinates of the mandibular feature points and the internal parameters of the camera device that captures the facial image; Find the point closest to the ray represented by the spatial ray equation from the face area point cloud subset as the three-dimensional coordinate point of the mandibular feature point; Obtaining three-dimensional coordinate points of at least three mandibular feature points and fitting them to a first ground plane equation; The three-dimensional coordinate point of the mandibular feature point is converted from the camera coordinate system to the world coordinate system with the first ground plane equation as a reference. The z-axis coordinate in the world coordinate system is the first height.

3. The method for automatically adjusting the height of a standing position detector assembly according to claim 1, characterized in that: The obtaining of a second height between the standing position detector assembly and the ground comprises: Acquire an RGB image of the standing detector assembly and extract an edge region of the standing detector assembly; Acquire a point cloud image of the standing detector assembly, and construct a point cloud subset of the edge area according to the edge area of ​​the standing detector assembly; Performing image processing on the point cloud subset to obtain a high-precision three-dimensionally reconstructed point cloud subset image of the standing detector assembly; Calculate the three-dimensional coordinate points of the standing detector component according to the point cloud subset image; Obtaining three-dimensional coordinate points of at least three standing detector assemblies and fitting them to a second ground plane equation; The three-dimensional coordinate point of the standing detector assembly is converted from the camera coordinate system to the world coordinate system with the second ground plane equation as a reference, and the z-axis coordinate in the world coordinate system is the second height.

4. The method for automatically adjusting the height of a standing position detector assembly according to claim 3, wherein: The image processing of the point cloud subset includes: Multi-resolution stereo matching is performed on point cloud subsets and then optimized for sub-pixel accuracy.

5. The method for automatically adjusting the height of a standing position detector assembly according to claim 4, characterized in that: Image processing also includes: applying Kalman filtering to smooth the trajectory of the point cloud subset optimized for sub-pixel accuracy for image processing.

6. A method for taking a chest X-ray using the method for automatically adjusting the height of a standing detector assembly according to any one of claims 1 to 5, characterized in that: include: After the height adjustment of the standing detector assembly is completed, the respiratory data of the subject monitored by the radar is obtained; Determine the timing of chest X-ray based on respiratory data.

7. The method for taking a chest X-ray according to claim 6, characterized in that: The timing for starting to take a chest X-ray based on respiratory data includes: When respiratory data showing deep breathing followed by breath holding is detected, the chest X-ray image corresponding to the respiratory data at this moment is taken as the final diagnostic image, or the chest X-ray is started at this moment and the image taken is taken as the final diagnostic image.

8. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors to enable at least one of the processors to execute the method for automatically adjusting the height of a standing detector assembly as described in any one of claims 1 to 5.

9. A storage medium, characterized in that: The storage medium stores computer instructions, and when a computer executes the computer instructions, it is used to execute all steps of the method for automatically adjusting the height of a standing position detector assembly as described in any one of claims 1 to 5.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the method for automatically adjusting the height of a standing detector assembly as described in any one of claims 1 to 5 is implemented.

Images