Imaging method and device based on dual-energy X-ray absorption

Abstract

The invention discloses an imaging method and device based on dual-energy X-ray absorption, and the method comprises the steps: obtaining two groups of image data of a to-be-imaged object on an imaging platform through two cameras disposed above the imaging platform; based on the image data, obtaining pose data of the to-be-imaged object, the pose data including key point coordinate data and thickness data; determining an imaging area of the to-be-imaged object in the image data; generating a scanning area corresponding to the imaging area on the imaging platform; and moving a dual-energy X-ray emission source and a detector to the scanning area to obtain an image of the to-be-imaged object in the scanning area. Through the two cameras arranged above the imaging platform, the scanning area can be remotely positioned, and the whole body thickness map of the to-be-imaged object can be obtained, so that the accuracy of determining the scanning area is improved, and the time required for completing detection is shortened.

Description

Technical Field

[0001] This application relates to the field of medical imaging and analysis technology, and in particular to an imaging method and apparatus based on dual-energy X-ray absorption. Background Technology

[0002] Dual-energy X-ray absorptiometry (DEXA) is a routine diagnostic method for osteoporosis. It involves irradiating a target area of ​​the patient's body with two energy levels (high-energy and low-energy) of X-rays and measuring the absorption rate of each. By analyzing the difference in absorption rates between low-energy and high-energy X-rays, the bone resorption can be determined, thereby determining the patient's bone density and enabling rapid diagnosis.

[0003] In existing dual-energy X-ray absorption-based detection devices, to ensure the accuracy of the dual-energy X-ray irradiation area, doctors typically need to manually locate the scanning area and analyze the images. This manual locating of the scanning area is prone to errors in positioning the same area, or errors due to patient movement, requiring multiple rescans of the same area. This situation is exacerbated when multiple areas need to be scanned, often requiring doctors to repeatedly locate and determine the dual-energy X-ray scanning area. This significantly increases the exposure risk to both patients and doctors under X-rays, negatively impacting the user experience.

[0004] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0005] To address the aforementioned deficiencies in the prior art, this application provides an imaging method and apparatus based on dual-energy X-ray absorption, thereby solving the problem that existing dual-energy X-ray absorption-based detection devices require manual positioning by doctors, leading to errors, repeated operations, increased user exposure risks, and negatively impacting user experience.

[0006] The first aspect of this application provides an imaging method based on dual-energy X-ray absorption, comprising: Two sets of image data of the object to be imaged on the imaging platform are acquired by two cameras set above the imaging platform. Based on the image data, the pose data of the object to be imaged is obtained, and the pose data includes key point coordinate data and thickness data; Determine the imaging region of the object to be imaged in the image data; Generate a scanning area on the imaging platform corresponding to the imaging region; The dual-energy X-ray emission source and detector are moved to the scanning area to obtain an image of the object to be imaged in the scanning area.

[0007] In one embodiment, before acquiring two sets of image data of the object to be imaged on the imaging platform using two cameras positioned above the imaging platform, the method further includes: Four positioning marks are set on the imaging platform to form a rectangular scanning range; Obtain the movement coordinates of the dual-energy X-ray emission source and the detector within the scanning range; The movement coordinates are mapped to the planar coordinates of the image data to obtain the bijective correspondence between the movement coordinates and the planar coordinates.

[0008] In one embodiment, the positioning mark is a QR code. The scanning range is defined by the vertices of the diagonal positioning graphic of the QR code as the vertices of the scanning range, forming a rectangle. The diagonal positioning graphic is the positioning graphic on the QR code located at the corner diagonal position where no positioning graphic is set. The movement coordinates and the planar coordinates of the image data are mapped using the following formula to obtain the bijective correspondence between the movement coordinates and the planar coordinates:

[0009]

[0010]

[0011]

[0012] The origin is defined as one vertex of the scan range. Let x be the x-coordinate of the origin in the plane coordinate system. The ordinate of the origin in the plane coordinate system is given by [reference to the origin]. The x-coordinate of the diagonal point opposite the origin in the plane coordinate system is given. The ordinate of the diagonal point opposite the origin in the plane coordinate system is given by the given coordinate system. x Let x be the x-coordinate of any point within the plane coordinate system. y Let be the ordinate of any point within the plane coordinate system. Let x be the x-coordinate of any point within the moving coordinate system. Let be the ordinate of any point within the moving coordinate system. The x-coordinate of the origin within the moving coordinate system is given. The ordinate of the origin within the moving coordinate system is given by [reference to the origin]. The x-coordinate of the diagonal point within the moving coordinate system is given. The ordinate of the diagonal point within the moving coordinate system is given.

[0013] In one implementation, obtaining the pose data of the object to be imaged based on the image data specifically includes: Based on the image data, key points of the object to be imaged are determined, including shoulder joint points, elbow joint points, wrist joint points, finger joint points, hip joint points, knee joint points, and ankle joint points. Obtain the key point coordinate data within the planar coordinates of the image data; Based on the physical data from the two cameras and the differences between the two sets of image data, the thickness data of the object to be imaged is obtained.

[0014] In one implementation, determining the imaging region of the object to be imaged in the image data specifically includes: Based on the key points, an imaging region with a preset size is generated, and the imaging region surrounds the key points; The imaging region coordinates within the planar coordinates of the image data are obtained, along with the imaging region thickness data of the object to be imaged within the imaging region, to determine the imaging region of the object to be imaged in the image data.

[0015] In one embodiment, generating a scanning region on the imaging platform corresponding to the imaging region specifically includes: Based on the imaging area coordinate data, the imaging area thickness data, the preset size, and the physical data of the camera, the projection area of ​​the imaging area on the imaging platform is obtained; Based on the bijective correspondence between the moving coordinates and the planar coordinates, the scanning area corresponding to the projection area under the moving coordinates is obtained.

[0016] In one embodiment, moving a dual-energy X-ray emission source and a detector to the scanning area to obtain an image of the object to be imaged in the scanning area specifically includes: Two line laser emitters are arranged on both sides of the detector. The line laser emitters move synchronously with the dual-energy X-ray emission source and the detector. The line laser emitted by the line laser emitters is perpendicular to the imaging platform. The projections of the line lasers emitted by the two line laser emitters on the imaging platform are perpendicular to each other. The intersection of the projections on the imaging platform, the focal point of the dual-energy X-ray emission source, and the center point of the detector form a straight line. Move the dual-energy X-ray emission source and the detector until the intersection of the projections coincides with a vertex of the scanning area; The dual-energy X-ray emission source and the detector are moved back and forth in parallel within the scanning area to obtain an image of the object to be imaged in the scanning area.

[0017] In one implementation, after obtaining the pose data of the object to be imaged based on the image data, the method further includes: Acquire historical pose data, which includes standard pose data of standard pose and past pose data of the object to be imaged in previous imaging poses; The pose data is compared with the historical pose data; Correction information is generated based on the comparison results to ensure that the pose of the object to be imaged is consistent with the standard pose and the previous imaging pose, and the pose data is stored as the historical pose data.

[0018] In one embodiment, after obtaining an image of the object to be imaged in the scanning area, image post-processing is further included, specifically including: Identify key anatomical features within the image, including the femur, femoral head, greater trochanter of the femur, lumbar vertebrae, and lumbar vertebrae. Based on the key anatomical features, a recognition box corresponding to the key anatomical features is generated on the image; Based on the recognition box, the human body structure boundary corresponding to the key anatomical features is determined, and the processed image is obtained.

[0019] A second aspect of this application also provides an imaging device based on dual-energy X-ray absorption, comprising: Imaging platform; A C-arm, which surrounds the imaging platform and is movable along the length of the imaging platform; Two cameras, which are fixed above the imaging platform; A dual-energy X-ray emission source is provided, which is mounted on the C-arm and located below the imaging platform. The dual-energy X-ray emission source moves synchronously with the C-arm. A detector is mounted on the C-arm and positioned above the imaging platform, corresponding to the dual-energy X-ray emission source. The detector moves synchronously with the C-arm and remains relatively stationary with the dual-energy X-ray emission source. A processor is communicatively connected to the C-arm, the camera, the dual-energy X-ray emission source, and the detector, and the processor stores an imaging program based on dual-energy X-ray absorption to perform the following steps: Two sets of image data of the object to be imaged on the imaging platform are acquired by the two cameras set above the imaging platform. Based on the image data, the pose data of the object to be imaged is obtained, and the pose data includes key point coordinate data and thickness data; Determine the imaging region of the object to be imaged in the image data; Generate a scanning area on the imaging platform corresponding to the imaging region; The dual-energy X-ray emission source and the detector are moved to the scanning area to obtain an image of the object to be imaged in the scanning area.

[0020] This application discloses an imaging method and apparatus based on dual-energy X-ray absorption. The method includes acquiring two sets of image data of an object to be imaged on the imaging platform using two cameras positioned above the platform; acquiring pose data of the object to be imaged based on the image data, the pose data including key point coordinate data and thickness data; determining the imaging region of the object to be imaged in the image data; generating a scanning region on the imaging platform corresponding to the imaging region; and moving a dual-energy X-ray emission source and detector to the scanning region to obtain an image of the object to be imaged in the scanning region. By using two cameras positioned above the imaging platform, this application can remotely locate the scanning region and acquire a full-body thickness map of the object to be imaged, thereby improving the accuracy of determining the scanning region and reducing the time required to complete the detection. Attached Figure Description

[0021] Figure 1 This is a flowchart of the dual-energy X-ray absorption-based imaging method described in this application.

[0022] Figure 2 This is a schematic diagram of image data acquired by a camera in one embodiment of the dual-energy X-ray absorption imaging method described in this application.

[0023] Figure 3 This is a three-dimensional schematic diagram of the dual-energy X-ray absorption imaging device described in this application.

[0024] Figure 4 This is a three-dimensional schematic diagram of the dual-energy X-ray absorption imaging device described in this application after the front panel has been removed.

[0025] Figure 5 yes Figure 4 An enlarged schematic diagram of part A in the middle.

[0026] Figure 6 This is a schematic diagram of the dual-energy X-ray absorption imaging device described in this application from another angle.

[0027] Figure 7 This is one embodiment of an image of the lumbar spine obtained by the dual-energy X-ray absorption imaging method described in this application.

[0028] Figure 8This is one embodiment of an image of the left hip obtained by the dual-energy X-ray absorption imaging method described in this application. Detailed Implementation

[0029] To make the objectives, technical solutions, and effects of this application clearer and more explicit, the following detailed description of this application is provided with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining this application and are not intended to limit this application.

[0030] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0031] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0032] In existing technologies, doctors often need to operate next to a dual-energy X-ray absorption detector to specify the scanning area and analyze the images. When multiple areas need to be scanned, manually modifying the scanning area can easily lead to misalignment, affecting the accuracy of the scan. This results in both doctors and patients needing to be exposed to X-rays for a longer period, impacting the user experience. To address this issue, this application discloses an imaging method and apparatus based on dual-energy X-ray absorption. It acquires a thickness-based image of the patient's body using two cameras, and then utilizes an artificial intelligence system to assist in locating the patient's area to be scanned. This allows doctors to remotely operate the positioning and imaging, and the machine-based positioning achieves higher accuracy, effectively reducing detection time, minimizing the exposure time of doctors and patients to radiation, and optimizing the user experience.

[0033] Specifically, such as Figure 1 As shown, the imaging method based on dual-energy X-ray absorption described in this application includes the following steps: S100. Two sets of image data of the object to be imaged on the imaging platform are acquired by two cameras set above the imaging platform.

[0034] The cameras are configured to remain relatively fixed to the imaging platform. Two cameras can be fixed above the imaging platform using a mounting bracket, or they can be fixed to the ceiling. By acquiring image data of the object to be imaged on the imaging platform through two cameras with a distance difference, two sets of image data with positional differences can be obtained. With the height difference between the cameras and the imaging platform remaining constant, the depth information of each entity in the image can be obtained by combining the two sets of image data, thereby determining the body thickness of the object lying on the imaging platform. In this way, doctors can remotely control the positioning of the scanning area using the image data acquired by the cameras, thereby improving the accuracy of the scanning area and reducing misalignments caused by improper positioning. Furthermore, the depth information in the image data can be used to determine the relationship between the surface area of ​​the object to be imaged and the imaging platform, thereby improving the accuracy of positioning the scanning area.

[0035] Furthermore, the dual-energy X-ray absorption-based imaging method described in this application, prior to step S100, further includes: S10. Set four positioning marks on the imaging platform to form a rectangular scanning range; S20. Obtain the movement coordinates of the dual-energy X-ray emission source and the detector within the scanning range; and S30. Map the movement coordinates to the planar coordinates of the image data to obtain the bijective correspondence between the movement coordinates and the planar coordinates.

[0036] The positioning marks are used to enclose a rectangular scanning range, thereby defining the movement range of the dual-energy X-ray emission source and detector within the image data from the camera. Specifically, the coordinate data in the movement coordinates represents the number of steps the dual-energy X-ray emission source and the detector move relative to the imaging platform in the length and width directions following the stepper motor. The coordinate data in the planar coordinates represents the coordinate data of each point in the image data within the coordinate system formed by the scanning range. Therefore, mapping the movement coordinates of the dual-energy X-ray emission source and the detector within the scanning range to the planar coordinates of the image data acquired by the camera determines a one-to-one correspondence between the positions of the dual-energy X-ray emission source and the detector in physical space and the position of a point in the image data. This ensures that after selecting a point in the image data, moving the dual-energy X-ray emission source and the detector to the corresponding position in physical space allows scanning of the selected point in the image data, ensuring scanning accuracy.

[0037] Optionally, the positioning mark is a QR code. The vertices of the diagonal positioning graphics of the QR code are used as the vertices of the scanning range, forming a rectangular scanning range. The diagonal positioning graphics are the positioning graphics on the QR code located diagonally opposite the corner where no positioning graphics are set. By rotating four QR codes by 90° sequentially, a rectangular scanning range is formed between four points on the imaging platform surface, and each point corresponds to a different label in the image data, thereby defining the horizontal and vertical coordinates in the scanning range. Further, the movement coordinates and the planar coordinates of the image data are mapped using the following formula to obtain the bijective correspondence between the movement coordinates and the planar coordinates:

[0038]

[0039]

[0040]

[0041] The origin is defined as one vertex of the scan range. Let x be the x-coordinate of the origin in the plane coordinate system. The ordinate of the origin in the plane coordinate system is given by [reference to the origin]. The x-coordinate of the diagonal point opposite the origin in the plane coordinate system is given. The ordinate of the diagonal point opposite the origin in the plane coordinate system is given by the given coordinate system. x Let x be the x-coordinate of any point within the plane coordinate system. y Let be the ordinate of any point within the plane coordinate system. Let x be the x-coordinate of any point within the moving coordinate system. Let be the ordinate of any point within the moving coordinate system. The x-coordinate of the origin within the moving coordinate system is given. The ordinate of the origin within the moving coordinate system is given by [reference to the origin]. The x-coordinate of the diagonal point within the moving coordinate system is given. The ordinate of the diagonal point within the moving coordinate system is given.

[0042] Specifically, such as Figure 2 and Figure 3As shown, taking the imaging platform 100 in a horizontal position as an example, four positioning marks 110 are respectively set at the four corners of the imaging platform 100. In this embodiment, the positioning marks 110 are QR codes. Using the QR codes and the vertices of the diagonals without positioning patterns as the four vertices of the scanning range, a rectangular scanning range is formed. The four QR codes correspond to the upper left, upper right, lower left, and lower right corners of the imaging platform 100, respectively. The four QR codes form a scanning range 101, and an imaging area 102 is generated within the scanning range 101. Taking the vertex of the upper left corner of the scanning range as the origin, the horizontal axis in the figure represents the length direction of the imaging platform 100, and the vertical axis represents the width direction of the imaging platform 100. Then ( , () represents the coordinates of the upper left corner vertex of the scan range in the planar coordinates of the image data; , () represents the coordinates of the lower right corner vertex of the scan range in the planar coordinates of the image data; , () represents the coordinates of any point in the image data, where the horizontal coordinate is the coordinate along the length direction of the imaging platform 100, and the vertical coordinate is the coordinate along the width direction of the imaging platform 100; , () represents the coordinates of the upper left corner vertex of the scan range within the movement coordinates; , The coordinates of the lower right corner vertex of the scan range within the movement coordinates are... This represents the total number of motor steps required to move vertically from the leftmost to the rightmost edge of the scanning range. The total number of motor steps required to move vertically from the top to the bottom of the scanning range; , ) is to move from the top left corner vertex of the scan range to the corresponding point ( , When the imaging platform 100 is moved, the number of motor steps required to move along its length and width, i.e., the number of motor steps required to move along its width, is the point ( , The coordinates of the corresponding point within the moving coordinate system are given. Through this mapping relationship, each point in the moving coordinate system corresponds one-to-one with each point in the planar coordinate system. Therefore, the position in the moving coordinate system can be quickly and accurately converted to the position in the planar coordinate system, ensuring that the situation observed by the doctor through the camera matches the actual situation. This also ensures that the doctor's operation and positioning of the dual-energy X-ray emission source and the detector are accurate and verifiable, improving the stability and accuracy of the detection.

[0043] Furthermore, such as Figure 1 As shown, the imaging method based on dual-energy X-ray absorption described in this application further includes, after step S100: S200. Based on the image data, obtain the pose data of the object to be imaged, wherein the pose data includes key point coordinate data and thickness data.

[0044] By inputting any set of image data into a pre-trained human pose recognition model, the positions of each joint of the object to be imaged in the image data can be determined, thereby assisting in the rapid determination of the key point coordinates and corresponding thickness data in the pose data of the object to be imaged. The human pose recognition model can be a pre-trained convolutional neural network that, combined with the characteristics of the human skeleton, locates key points of the human body in the image data, thereby determining the pose of the object to be imaged and acquiring the corresponding pose data.

[0045] Specifically, step S200 includes: S210. Based on the image data, determine the key points of the object to be imaged, including the shoulder joint point, elbow joint point, wrist joint point, finger joint point, hip joint point, knee joint point, and ankle joint point. S220, Obtain the key point coordinate data within the planar coordinates of the image data; and S230. Based on the physical data of the two cameras and the difference between the two sets of image data, obtain the thickness data of the object to be imaged.

[0046] This application utilizes an AI-based human pose recognition model to determine the pose of the object to be imaged from the image data and locate key points corresponding to each joint, thereby obtaining the key point coordinate data of the key points on the planar coordinate plane of the image data. Simultaneously, by utilizing the differences between the same location in two sets of image data, combined with the height difference between the two cameras and the imaging platform, the focal length of the cameras, and the distance between the two cameras, the thickness data of various points on the surface of the object to be imaged can be obtained, facilitating the subsequent determination of the correspondence between the surface area of ​​the object to be imaged and the surface area of ​​the imaging platform.

[0047] Specifically, after determining the corresponding points of the key points in the image data, the coordinates of each key point in the planar coordinates of the image data can be generated, thus obtaining the coordinates of each point on the surface of the object to be imaged, as well as the key point coordinate data. Further, the thickness data at any point within the scanning range is calculated using the following formula:

[0048] in, The average height difference between the two cameras relative to the imaging platform. The focal length of the camera is... The baseline distance between the two cameras. The final result is the difference in position of a point in two sets of image data. This refers to the thickness data at that point.

[0049] Furthermore, after obtaining the pose data of the object to be imaged based on the image data in step S200, the method further includes: S240. Obtain historical pose data, which includes standard pose data of standard pose and past pose data of the object to be imaged in previous imaging poses. S250, compare the pose data with the historical pose data; and S260. Generate correction information based on the comparison results to make the pose of the object to be imaged consistent with the standard pose and the previous imaging pose, and store the pose data as the historical pose data.

[0050] Due to the requirements of dual-energy X-ray absorptiometry (DXA), the subject needs to lie in a standard posture on the imaging platform to ensure the accuracy of the imaging results. Therefore, for the first imaging of a subject, the posture of the subject needs to be matched and compared with the standard posture to ensure that the similarity is within a certain range to ensure imaging accuracy. For subjects that have already been imaged, the posture formed during the previous imaging is stored in the system. When the subject needs to be imaged again, the current posture is matched and compared with the historical posture from previous imaging to ensure that the similarity is within a certain range to ensure imaging accuracy. If the current posture data does not match the historical posture data, an alarm can be triggered to remind the doctor and the subject to adjust the posture until a match is achieved. This setting ensures that the posture remains consistent across multiple imaging sessions, taking into account both the standard posture and posture variations due to individual differences. This ensures that the results of each imaging session are consistent for a specific subject, which is more conducive to subsequent treatment and diagnosis.

[0051] Furthermore, such as Figure 1 As shown, the imaging method based on dual-energy X-ray absorption described in this application further includes, after step S200: S300, Determine the imaging area of ​​the object to be imaged in the image data.

[0052] Specifically, the imaging area can be selected in the image data by manually selecting a box, or the imaging area can be determined for a specific joint position by identifying key points.

[0053] Specifically, step S300 includes: S310. Based on the key points, generate an imaging region of a preset size, the imaging region surrounding the key points; and S320. Obtain the imaging region coordinate data of the imaging region within the planar coordinates of the image data, and the imaging region thickness data of the object to be imaged within the imaging region, so as to determine the imaging region of the object to be imaged in the image data.

[0054] Specifically, for the specific location of the object to be imaged, corresponding key points are determined, and then the imaging region is generated based on the key points. Optionally, the preset size is set according to the specific location of the object to be imaged. For example, different sizes of imaging regions are preset for different locations such as the shoulder, elbow, wrist, fingers, femur, knee, and ankle, and the imaging region is rectangular to ensure that the joint corresponding to the specific location to be imaged is surrounded within the imaging region. In one embodiment, such as... Figure 2 As shown, the object to be imaged lies supine on the imaging platform 100. Within the scanning range 101 enclosed by four positioning marks 110, the black dots represent identified key points. When scanning the right hip bone of the object, an imaging region 102 is formed around the key points of the right hip bone for subsequent processing. Combining the key point coordinate data and thickness data obtained in step S200, the imaging region data and imaging region thickness data of each point in the imaging region within the planar coordinates of the image data can be obtained.

[0055] Specifically, after determining the corresponding key points, the imaging region is determined with the key points as the center, and the coordinates of a vertex of the imaging region are used as the imaging region coordinate data. This vertex is the starting point for the scanning imaging of the dual-energy X-ray emission source and the detector. For a coordinate system with the length direction of the imaging platform as the horizontal axis and the width direction of the imaging platform as the vertical axis, the upper left corner vertex of the imaging region is the scanning starting point. The coordinates of the scanning starting point of the imaging region are used as the imaging region coordinate data. In this case, the imaging region coordinate data is calculated using the following formula:

[0056]

[0057] in,( , The coordinates of the scanning starting point of the imaging region (the upper left corner vertex in this embodiment) in the planar coordinates of the image data are the imaging region coordinate data. The length of the imaging region along the length direction of the imaging platform within the preset size; The length of the imaging region along the width direction of the imaging platform within the preset size; , ) represents the coordinates of the key points corresponding to the imaging area in the planar coordinates of the image data.

[0058] Specifically, for a larger imaging area, multiple key points need to be combined to generate the corresponding imaging region. Taking the lumbar spine as an example, in a coordinate system with the length direction of the imaging platform as the horizontal axis and the width direction of the imaging platform as the vertical axis, the coordinates of the key points corresponding to the imaging region covering the lumbar spine in the planar coordinates of the image data are calculated using the following formula:

[0059]

[0060]

[0061]

[0062] in,( , () represents the coordinates of the left hip joint in the planar coordinates of the image data; , () represents the coordinates of the right hip joint in the planar coordinates of the image data; , () represents the coordinates of the left shoulder joint in the planar coordinates of the image data; , () represents the coordinates of the right shoulder joint in the planar coordinates of the image data; , The coordinates of the key points corresponding to the imaging area covering the lumbar spine in the planar coordinates of the image data are given. The preset size of the imaging area allows the imaging area to cover the four lumbar vertebrae L1, L2, L3 and L4, so as to scan and image the complete lumbar spine.

[0063] Furthermore, such as Figure 1 As shown, the imaging method based on dual-energy X-ray absorption described in this application further includes, after step S300: S400: Generate a scanning area on the imaging platform corresponding to the imaging area.

[0064] During scanning imaging, the focal point corresponding to the actual positions of the dual-energy X-ray emission source and the detector is the corresponding point on the upper surface of the imaging platform. However, due to the variation in the thickness of the object being imaged while lying on the imaging platform, without introducing thickness data, there is a deviation between the imaging area in the planar coordinates of the image data and the scanning area that needs to be scanned in the actual physical space. It is necessary to combine the thickness data at the imaging area to convert the imaging area coordinate data into the projection area coordinate data of the imaging platform surface, and then convert the projection area from planar coordinates to moving coordinates to obtain the scanning area under the moving coordinates, that is, the area coordinate data of the area that the dual-energy X-ray emission source and the detector need to move and start scanning imaging. This ensures that the area scanned by the dual-energy X-ray emission source and the detector is the actual selected imaging area in the image data, ensuring the accuracy of the detection process.

[0065] Specifically, step S400 includes: S410. Based on the imaging area coordinate data, the imaging area thickness data, the preset size, and the physical data of the camera, obtain the projection area of ​​the imaging area on the imaging platform; and S420. Based on the bijective correspondence between the moving coordinates and the planar coordinates, obtain the scanning area corresponding to the projection area under the moving coordinates.

[0066] Specifically, as Figure 3 and Figure 4 Taking the placement of the imaging platform as an example, the coordinate data of the projection area corresponding to the imaging area are calculated using the following formula:

[0067]

[0068]

[0069]

[0070]

[0071] in, Corresponding to the imaging area, The length of the imaging area along the length direction of the imaging platform is part of the preset size of the imaging area. The length of the imaging area along the width direction of the imaging platform within the preset size of the imaging region, ( , ) represents the coordinate data of the imaging region, that is, the coordinates of the scanning starting point of the imaging region (the upper left corner vertex in this embodiment) in the planar coordinates of the image data; Corresponding to the projection area The length of the projection area along the length direction of the imaging platform. The length of the projection area along the width direction of the imaging platform, ( , () represents the coordinates of the upper left corner vertex of the projection area in the planar coordinates of the image data; , The coordinates of the camera's center point in the planar coordinates of the image data are given. These coordinates can be derived from the camera's specific physical data; for example, if the camera's resolution is 1280×720, then... For 640 For 360; The average thickness of the imaging region, i.e., the thickness data for all points in the imaging region. Take the average; The average height difference between the two cameras relative to the imaging platform.

[0072] After obtaining the coordinate data of the projection area, the coordinate data of the projection area is converted into coordinate data under the moving coordinates by using the bi-radiation correspondence obtained in step S30, so as to obtain the coordinate data of the scanning area under the moving coordinates, so as to ensure that the scanning imaging position when the dual-energy X-ray emission source and the detector move to the scanning area coincides with the imaging area selected in the image data, thereby ensuring the accuracy of the detection process.

[0073] Furthermore, such as Figure 1 As shown, the imaging method based on dual-energy X-ray absorption described in this application further includes, after step S400: S500: Move the dual-energy X-ray emission source and detector to the scanning area to obtain an image of the object to be imaged in the scanning area.

[0074] Specifically, the coordinate data of the scanning area in the moving coordinate system is obtained, and then converted into the number of steps required for the dual-energy X-ray emission source and the detector to move relative to the length and width directions of the imaging platform. This allows the dual-energy X-ray emission source and the detector to be moved to one vertex of the scanning area as the scanning starting point. Then, through parallel reciprocating motion, the scanning image is scanned from the scanning starting point to the diagonal vertex opposite this vertex, thus completing the scanning image of the scanning area and obtaining an accurate image.

[0075] Specifically, step S500 includes: S510. Two line laser emitters are arranged on both sides of the detector. The line laser emitters move synchronously with the dual-energy X-ray emission source and the detector. The line laser emitted by the line laser emitters is perpendicular to the imaging platform. The projections of the line lasers emitted by the two line laser emitters on the imaging platform are perpendicular to each other. The intersection of the projections on the imaging platform, the focal point of the dual-energy X-ray emission source, and the center point of the detector form a straight line. S520. Move the dual-energy X-ray emission source and the detector until the intersection of the projections coincides with a vertex of the scanning area; S530. The dual-energy X-ray emission source and the detector are moved parallel to each other within the scanning area to obtain an image of the object to be imaged in the scanning area. like Figure 4 and Figure 6 As shown, two line laser emitters 600 are arranged next to the detector 500, and line lasers are emitted towards the imaging platform 100 through the line laser emitters 600. Figure 5 As shown, the line lasers emitted by the two line laser emitters are perpendicular to each other on the surface of the imaging platform 100, and their intersection point, the focal point of the dual-energy X-ray emission source, and the center point of the detector form a straight line. Furthermore, for all parallel planes from the upper surface of the imaging platform to the detector, the intersection point of the line lasers emitted by the two line laser emitters lies on this straight line. Thus, when the object to be imaged lies on the imaging platform, regardless of the thickness of the area to be scanned, the intersection point of the two line lasers always marks the irradiation point of the dual-energy X-ray emission source on the surface of the object, facilitating the doctor's positioning of the dual-energy X-ray emission source and the detector, as well as the scanning imaging position. Simultaneously, during setup or maintenance, two line lasers can be emitted perpendicularly to the surface of the imaging platform, intersecting perpendicularly on the platform. The focal point of the dual-energy X-ray emission source and the center point of the detector can then be aligned with the focal point of the two line lasers on the imaging platform surface, thereby aligning the dual-energy X-ray emission source and the detector.

[0076] After moving the dual-energy X-ray emission source and the detector to positions corresponding to the scanning area, a fan-shaped dual-energy X-ray beam is emitted through the dual-energy X-ray emission source and emitted within the scanning area in the manner described above. Figure 4The dashed "bow"-shaped line shown in the image sweeps across the entire scanning area in parallel reciprocating motion. The detector is an array that moves with the dual-energy X-ray emission source, synchronously receiving the dual-energy X-ray beam after absorption and scattering by the human body, thereby acquiring a dual-energy X-ray image of the object to be imaged in the scanning area, which facilitates subsequent analysis and diagnosis of bone density or other parameters of the object to be imaged.

[0077] Furthermore, the dual-energy X-ray absorption-based imaging method described in this application, after acquiring the image in step S500, also includes a post-processing analysis step of the image, specifically including: S600. Identify key anatomical features within the image, including the femur, femoral head, greater trochanter of the femur, lumbar vertebrae, and lumbar vertebrae. S700: Based on the key anatomical features, generate a bounding box corresponding to the key anatomical features on the image; and S800. Based on the recognition box, determine the human body structure boundary corresponding to the key anatomical features to obtain the processed image.

[0078] Specifically, the image is processed using a trained object detection model. Based on the characteristics of dual-energy X-ray imaging, key anatomical features are identified by observing the brightness changes of pixels in the image. These features include human joint structures such as the femur, femoral head, greater trochanter of the femur, lumbar vertebrae, and lumbar segments. Then, based on the specific shapes of the key anatomical features, a bounding box is generated on the image to mark the key anatomical features. Next, key shapes on the key anatomical features are identified within the bounding box. Finally, lines of different colors are used to delineate the human structural boundaries corresponding to the key anatomical features on the image to facilitate subsequent analysis and diagnosis of the image.

[0079] This application first generates a smaller, more specific recognition box, and then determines the boundaries of human structures within the recognition box. This requires processing less data, making the entire process more accurate and reliable. Specifically, this application can identify and analyze structures such as the lumbar vertebrae, individual vertebrae within the lumbar vertebrae, the left or right femur, the femoral head, the greater trochanter of the femur, the ulna or radius, as well as the phalanges, metacarpals, and carpal bones, thereby assisting in subsequent diagnostic analysis processes.

[0080] like Figure 7 The image shown is obtained from imaging analysis of the lumbar spine. First, a first recognition box 141 is generated for the complete lumbar spine, and corresponding recognition boxes are generated for the L1, L2, L3 and L4 lumbar vertebrae. Then, the human body structure boundary 142 of the lumbar spine is outlined with blue lines within the first recognition box 141 to facilitate subsequent analysis and diagnosis.

[0081] In one embodiment, this application can also utilize key shapes identified on the key anatomical features to determine a smaller identification range. For example... Figure 8 The image shown is obtained from imaging analysis of the left hip. A bounding box (red) is formed at the junction of the femur and hip bone. Then, different colored lines are used to form the boundaries of the hip bone (yellow) and femur (blue) within the bounding box. At the same time, bounding boxes (red) are generated for the femoral head and greater trochanter of the femur. Finally, the bounding box (red) for the femoral neck is generated using the coordinate data of the femoral head and greater trochanter of the femur. The specific calculation is performed by the following formula:

[0082]

[0083]

[0084]

[0085]

[0086] in,( , () represents the coordinates of the center point of the femoral head recognition box in the planar coordinates of the image; , () represents the coordinates of the center point of the recognition box of the greater trochanter of the femur in the planar coordinates of the image; , The coordinates of the center point of the final generated femoral neck bounding box in the plane coordinates of the image are: The rotation angle of the recognition box of the femoral neck relative to the recognition boxes of the femoral head and the greater trochanter of the femoral head; The width of the recognition box for the femoral neck after rotation; The height of the identification frame for the femoral neck after rotation is given. By utilizing the easily identifiable femoral head and greater trochanter, this application can further locate and identify human structures such as the femoral neck, broadening its application scope and facilitating its use in subsequent diagnostic analysis.

[0087] Furthermore, the dual-energy X-ray absorption-based imaging method described in this application can also be applied to human body fat. First, two sets of image data are acquired using two cameras. Combined with the physical parameters of the cameras, the body thickness data of the object to be imaged, i.e., the thickness data at various points on the human body surface, is obtained. Then, by combining the different absorption rates of high-energy and low-energy X-rays at corresponding locations during the scanning process, the compositional percentages of bones, fat, and other tissues at those locations are obtained, thus yielding the body fat percentage at those locations. Furthermore, the overall body fat percentage of the object to be imaged is obtained, providing a reference for subsequent diagnostic analysis and treatment plan development.

[0088] Therefore, the imaging method based on dual-energy X-ray absorption disclosed in this application firstly uses two cameras to ensure that doctors can remotely monitor the condition of the object to be imaged in real time and remotely control the positioning of the scanning area; then, the two sets of image data acquired by the two cameras provide depth data for the obtained image, thereby assisting in the accurate positioning of the scanning area in the image and the scanning area in the actual physical space; finally, combined with an artificial intelligence neural network model with corresponding functions, the specific human body structure in the image data is located, realizing intelligent analysis of the image and providing more accurate and efficient data assistance for subsequent diagnosis and treatment.

[0089] Those skilled in the art will understand that implementing all or part of the process steps in the above methods can be accomplished by a computer program instructing related hardware. The computer program executing the dual-energy X-ray absorption-based imaging method can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can implement the process including the method steps described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAM bus, direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0090] This application also provides an imaging device based on dual-energy X-ray absorption to achieve the dual-energy X-ray absorption-based imaging method described above, providing doctors and patients with a fast and accurate dual-energy X-ray absorption detection experience. Figure 4 and Figure 6 As shown, in one embodiment, the imaging device includes an imaging platform 100, a C-arm 200, two cameras 300, a dual-energy X-ray emission source 400, a detector 500, a line laser emitter 600, and a processor 700.

[0091] In this embodiment, the imaging platform 100 includes a rectangular top surface for the object to be imaged to lie on for scanning and imaging. The opening of the C-arm 200 surrounds the imaging platform 100, and the C-arm 200 can move along the length of the imaging platform 100 under the drive of a stepper motor. Two cameras 300 are fixed above the imaging platform 100 and are located in a plane parallel to the top surface of the imaging platform 100. Optionally, the cameras 300 are optical cameras, and the cameras 300 are fixed directly above the center of the top surface of the imaging platform 100 to ensure that the cameras 300 can clearly capture images of the object to be imaged lying on the surface of the imaging platform 100. Furthermore, the dual-energy X-ray emission source 400 is disposed on the lower arm of the C-arm 200, located below the imaging platform 100. The dual-energy X-ray emission source 400 moves along the length of the imaging platform 100 following the C-arm 200, and the dual-energy X-ray emission source 400 can move along the lower arm of the C-arm 200 under the drive of a stepper motor, so as to move relative to the width of the imaging platform 100. The detector 500 is disposed on the upper arm of the C-arm 200, located above the imaging platform 100. The detector 500 is located directly above the dual-energy X-ray emission source 400 and maintains a fixed relative position, that is, the line connecting the detector 500 and the dual-energy X-ray emission source 400 is always perpendicular to the top surface of the imaging platform 100.

[0092] Furthermore, two line laser emitters 600 are positioned adjacent to the detector 500, and the line laser emitters 600 move synchronously with the dual-energy X-ray source 400 and the detector 500. Specifically, the line lasers emitted by the two line laser emitters 600 form two mutually perpendicular line lasers on the top surface of the imaging platform 100, and the two line lasers are parallel to the length and width directions of the imaging platform 100, respectively. Further, the intersection point of the line lasers on the top surface of the imaging platform 100, the focal point of the dual-energy X-ray source 400, and the center point of the detector 500 form a straight line, thereby ensuring that the scanning point of the dual-energy X-ray is always accurately marked on the object to be imaged lying on the imaging platform 100. This facilitates accurate positioning and imaging by the doctor, and also facilitates the calibration of the relative positions of the dual-energy X-ray source 400 and the detector 500 during initial setup or subsequent maintenance.

[0093] Furthermore, the processor 700 is communicatively connected to the C-arm 200, the camera 300, the dual-energy X-ray source 400, and the detector 500, and is located away from the imaging platform 100, for example, in a separate room isolated from the imaging platform 100. Therefore, doctors can remotely control the movement of the C-arm 200, the dual-energy X-ray source 400, and the detector 500 through the processor 700; they can also acquire image data from the camera 300 to monitor the object to be imaged in real time and accurately locate the position to be scanned; and they can process the scanned images using an artificial intelligence model on the processor 700, facilitating subsequent treatment and diagnosis. Specifically, the processor 700 stores an imaging program based on dual-energy X-ray absorption to implement the dual-energy X-ray absorption-based imaging method described above; the specific method steps are not detailed here.

[0094] In summary, this application discloses an imaging method and apparatus based on dual-energy X-ray absorption. The method includes acquiring two sets of image data of an object to be imaged on the imaging platform using two cameras positioned above the platform; acquiring pose data of the object to be imaged based on the image data, the pose data including key point coordinate data and thickness data; determining the imaging region of the object to be imaged in the image data; generating a scanning region on the imaging platform corresponding to the imaging region; and moving a dual-energy X-ray emission source and detector to the scanning region to obtain an image of the object to be imaged in the scanning region. By using two cameras positioned above the imaging platform, this application can remotely locate the scanning region and acquire a full-body thickness map of the object to be imaged, thereby improving the accuracy of determining the scanning region and reducing the time required to complete the detection.

[0095] It should be understood that the application of this application is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. An imaging method based on dual-energy X-ray absorption, characterized in that, include: Two sets of image data of the object to be imaged on the imaging platform are acquired by two cameras set above the imaging platform. Based on the image data, the pose data of the object to be imaged is obtained, and the pose data includes key point coordinate data and thickness data; Determine the imaging region of the object to be imaged in the image data; Generate a scanning area on the imaging platform corresponding to the imaging region; The dual-energy X-ray emission source and detector are moved to the scanning area to obtain an image of the object to be imaged in the scanning area.

2. The imaging method based on dual-energy X-ray absorption according to claim 1, characterized in that, Before acquiring two sets of image data of the object to be imaged on the imaging platform using two cameras positioned above the imaging platform, the process further includes: Four positioning marks are set on the imaging platform to form a rectangular scanning range; Obtain the movement coordinates of the dual-energy X-ray emission source and the detector within the scanning range; The movement coordinates are mapped to the planar coordinates of the image data to obtain the bijective correspondence between the movement coordinates and the planar coordinates.

3. The imaging method based on dual-energy X-ray absorption according to claim 2, characterized in that, The positioning marker is a QR code. The scanning range is defined by the vertices of the diagonal positioning graphic of the QR code, forming a rectangular scanning range. The diagonal positioning graphic is the positioning graphic located on the corner diagonal of the QR code where no positioning graphic is set. The movement coordinates and the planar coordinates of the image data are mapped using the following formula to obtain a bijective correspondence between the movement coordinates and the planar coordinates: The origin is defined as one vertex of the scan range. Let x be the x-coordinate of the origin in the plane coordinate system. The ordinate of the origin in the plane coordinate system is given by [reference to the origin]. The x-coordinate of the diagonal point opposite the origin in the plane coordinate system is given. The ordinate of the diagonal point opposite the origin in the plane coordinate system is given by the given coordinate system. x Let x be the x-coordinate of any point within the plane coordinate system. y Let be the ordinate of any point within the plane coordinate system. Let x be the x-coordinate of any point within the moving coordinate system. Let be the ordinate of any point within the moving coordinate system. The x-coordinate of the origin within the moving coordinate system is given. The ordinate of the origin within the moving coordinate system is given by [reference to the origin]. The x-coordinate of the diagonal point within the moving coordinate system is given. The ordinate of the diagonal point within the moving coordinate system is given.

4. The imaging method based on dual-energy X-ray absorption according to claim 2, characterized in that, Based on the image data, the pose data of the object to be imaged is obtained, specifically including: Based on the image data, key points of the object to be imaged are determined, including shoulder joint points, elbow joint points, wrist joint points, finger joint points, hip joint points, knee joint points, and ankle joint points. Obtain the key point coordinate data within the planar coordinates of the image data; Based on the physical data from the two cameras and the differences between the two sets of image data, the thickness data of the object to be imaged is obtained.

5. The imaging method based on dual-energy X-ray absorption according to claim 4, characterized in that, Determining the imaging region of the object to be imaged in the image data specifically includes: Based on the key points, an imaging region with a preset size is generated, and the imaging region surrounds the key points; The imaging region coordinates within the planar coordinates of the image data are obtained, along with the imaging region thickness data of the object to be imaged within the imaging region, to determine the imaging region of the object to be imaged in the image data.

6. The imaging method based on dual-energy X-ray absorption according to claim 5, characterized in that, Generating a scanning area on the imaging platform corresponding to the imaging area specifically includes: Based on the imaging area coordinate data, the imaging area thickness data, the preset size, and the physical data of the camera, the projection area of ​​the imaging area on the imaging platform is obtained; Based on the bijective correspondence between the moving coordinates and the planar coordinates, the scanning area corresponding to the projection area under the moving coordinates is obtained.

7. The imaging method based on dual-energy X-ray absorption according to claim 2, characterized in that, Moving a dual-energy X-ray emission source and detector to the scanning area to obtain an image of the object to be imaged in the scanning area specifically includes: Two line laser emitters are arranged on both sides of the detector. The line laser emitters move synchronously with the dual-energy X-ray emission source and the detector. The line laser emitted by the line laser emitters is perpendicular to the imaging platform. The projections of the line lasers emitted by the two line laser emitters on the imaging platform are perpendicular to each other. The intersection of the projections on the imaging platform, the focal point of the dual-energy X-ray emission source, and the center point of the detector form a straight line. Move the dual-energy X-ray emission source and the detector until the intersection of the projections coincides with a vertex of the scanning area; The dual-energy X-ray emission source and the detector are moved back and forth in parallel within the scanning area to obtain an image of the object to be imaged in the scanning area.

8. The imaging method based on dual-energy X-ray absorption according to claim 1, characterized in that, After obtaining the pose data of the object to be imaged based on the image data, the method further includes: Acquire historical pose data, which includes standard pose data of standard pose and past pose data of the object to be imaged in previous imaging poses; The pose data is compared with the historical pose data; Correction information is generated based on the comparison results to ensure that the pose of the object to be imaged is consistent with the standard pose and the previous imaging pose, and the pose data is stored as the historical pose data.

9. The imaging method based on dual-energy X-ray absorption according to claim 1, characterized in that, After obtaining the image of the object to be imaged in the scanning area, image post-processing is also included, specifically including: Identify key anatomical features within the image, including the femur, femoral head, greater trochanter of the femur, lumbar vertebrae, and lumbar vertebrae. Based on the key anatomical features, a recognition box corresponding to the key anatomical features is generated on the image; Based on the recognition box, the human body structure boundary corresponding to the key anatomical features is determined, and the processed image is obtained.

10. An imaging device based on dual-energy X-ray absorption, characterized in that, include: Imaging platform; A C-arm, which surrounds the imaging platform and is movable along the length of the imaging platform; Two cameras, which are fixed above the imaging platform; A dual-energy X-ray emission source is provided, which is mounted on the C-arm and located below the imaging platform. The dual-energy X-ray emission source moves synchronously with the C-arm. A detector is mounted on the C-arm and positioned above the imaging platform, corresponding to the dual-energy X-ray emission source. The detector moves synchronously with the C-arm and remains relatively stationary with the dual-energy X-ray emission source. A processor is communicatively connected to the C-arm, the camera, the dual-energy X-ray emission source, and the detector, and the processor stores an imaging program based on dual-energy X-ray absorption to perform the following steps: Two sets of image data of the object to be imaged on the imaging platform are acquired by the two cameras set above the imaging platform. Based on the image data, the pose data of the object to be imaged is obtained, and the pose data includes key point coordinate data and thickness data; Determine the imaging region of the object to be imaged in the image data; Generate a scanning area on the imaging platform corresponding to the imaging region; The dual-energy X-ray emission source and the detector are moved to the scanning area to obtain an image of the object to be imaged in the scanning area.

Images