Movement control method of medical equipment, electronic equipment and computer program product

By generating a three-dimensional model of the patient and controlling the moving state of the medical equipment based on the model, the problem of misregulation caused by the inability to accurately identify the patient's contour in the prior art is solved, efficient collision detection and scanning field adjustment are achieved, and safety and efficiency are ensured. .

CN118919046APending Publication Date: 2024-11-08SHANGHAI UNITED IMAGING HEALTHCARE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410962763.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Existing medical equipment cannot accurately identify patient profiles, resulting in misregistration of automated controls, and existing hardware sensors are costly and inefficient, making it impossible to achieve effective collision detection.

Method used

By obtaining initial depth maps of different shooting angles, performing downsampling and synthesis operations, a three-dimensional model of the target object is generated, and the moving state of the medical device is controlled based on the three-dimensional model, ensuring that the tablet maintains a safe distance from the patient and has an appropriate scanning field of view.

Benefits of technology

Improve computing efficiency, reduce data volume, and realize accurate collision distance detection and scanning field adjustment, ensuring the image field of view while avoiding collision between the device and the patient, reducing radiation dose.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118919046A_ABST
    Figure CN118919046A_ABST
Patent Text Reader

Abstract

The invention provides a movement control method of medical equipment, electronic equipment and a computer program product. The movement control method comprises the following steps: acquiring a plurality of initial depth maps of a target object obtained from different shooting angles; performing downsampling operation and synthesis operation on each initial depth map to obtain a target depth map; generating a three-dimensional model of the target object based on the target depth map; and controlling the target state of the medical equipment based on the relative position of the medical equipment and the three-dimensional model. According to the method, the initial depth map of the target object is obtained through vision, the synthesis operation and the downsampling operation are carried out to construct the three-dimensional model of the target object, the calculation efficiency is improved, the to-be-processed data volume is reduced, collision distance detection and scanning view adjustment of the medical equipment are carried out according to the three-dimensional model, and the accuracy of collision distance detection is improved. The present invention ensures no collision while ensuring the field of view of an image.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of medical device control, and in particular to a mobile control method for medical equipment, an electronic device, and a computer program product. Background Art

[0002] In clinical surgery, when the C-arm (a medical instrument) is angled or translated, it is expected that the system will automatically adjust the SID (Source Image Distance) according to the patient's position, so as to ensure the image field of view and avoid collision, while keeping the distance between the flat panel and the human body consistent when the gantry moves, reducing the radiation dose.

[0003] Existing equipment cannot accurately identify human body models and usually uses theoretical patient models for collision distance detection. This method cannot truly perceive the patient's body shape and is prone to misadjustment. There is also a method of adding hardware sensors to the tablet to detect the distance between the tablet and the patient, but this method has the problem of distance detection failure under specific postures, and the cost is high. At the same time, it cannot realize collision detection of the model.

[0004] To achieve the above clinical needs, it is necessary to accurately identify the patient's outline and dynamically adjust the SID according to the actual distance between the tablet and the patient to keep the tablet and the patient at a safe distance. Summary of the invention

[0005] The technical problem to be solved by the present disclosure is to overcome the defect in the prior art that the automatic control of medical equipment is prone to misadjustment due to the inability to accurately identify the patient's contour, and to provide a mobile control method for medical equipment, an electronic device and a computer program product.

[0006] The present invention solves the above technical problems through the following technical solutions:

[0007] According to a first aspect of the present disclosure, a movement control method of a medical device is provided, the movement control method comprising:

[0008] Obtain several initial depth maps of the target object obtained from different shooting angles;

[0009] Performing downsampling and synthesis operations on each of the initial depth maps to obtain a target depth map;

[0010] generating a three-dimensional model of the target object based on the target depth map;

[0011] Based on the relative position of the medical device and the three-dimensional model, a target state of the medical device is controlled.

[0012] Preferably, the step of performing downsampling and synthesis operations on each of the initial depth maps to obtain a target depth map comprises:

[0013] Obtaining first coordinates of a plurality of first pixel points in each of the initial depth maps in the same coordinate system, and performing synthesis processing on the initial depth maps to obtain a synthesized depth map;

[0014] Dividing the synthesized depth map into a plurality of first sub-units, and performing downsampling processing on a plurality of second pixel points located in the first sub-units to obtain third pixel points corresponding to the synthesized depth map;

[0015] Based on the plurality of third pixel points, obtaining the target depth map;

[0016] or,

[0017] The step of performing downsampling and synthesis operations on each of the initial depth maps to obtain a target depth map comprises:

[0018] Dividing the initial depth map into a plurality of second sub-units, and performing downsampling processing on a plurality of the first pixel points located in the second sub-units to obtain the downsampled initial depth map;

[0019] The second coordinates of a plurality of fourth pixel points in the downsampled initial depth map in the same coordinate system are obtained, and a plurality of the downsampled initial depth maps are synthesized to obtain the target depth map.

[0020] Preferably, the step of generating the three-dimensional model of the target object based on the target depth map comprises:

[0021] Obtain target depth information corresponding to a target pixel point in the target depth map;

[0022] The target pixel points are converted into three-dimensional model coordinate points based on the target depth information to generate a three-dimensional model of the target object.

[0023] Preferably, the medical device comprises a moving component or a moving scanning component;

[0024] The step of controlling the target state of the medical device based on the relative position of the medical device and the three-dimensional model comprises:

[0025] Acquire a plurality of target three-dimensional model coordinate points located in a target area corresponding to the moving component or the moving scanning component;

[0026] Acquire the relative distance between the target three-dimensional model coordinate point and the moving component or the moving scanning component;

[0027] controlling the target state of the moving component or the moving scanning component according to the relative distance;

[0028] Wherein, when the medical device is the moving component, the target state includes a moving speed;

[0029] When the medical device is the mobile scanning component, the target state includes a moving speed and / or a scanning parameter, and the scanning parameter is used to adjust a scanning field of view.

[0030] Preferably, the step of obtaining the relative distance between the target three-dimensional model coordinate point and the moving component or the moving scanning component comprises:

[0031] Based on the target three-dimensional model coordinate point, dividing a preset range in the moving component or the moving scanning component corresponding to the target three-dimensional model coordinate point to obtain a plurality of blocks;

[0032] Acquire the relative distance between the block and the corresponding coordinate point of the target three-dimensional model;

[0033] and / or,

[0034] The step of controlling the target state of the moving component or the moving scanning component according to the relative distance comprises:

[0035] Determining a relative distance between the moving component or the moving scanning component and a target of the three-dimensional model according to a plurality of the relative distances;

[0036] The target state of the moving component or the moving scanning component is controlled based on the target relative distance.

[0037] Preferably, the step of controlling the target state of the moving component or the moving scanning component according to the relative distance comprises:

[0038] In response to the relative distance being greater than a first preset distance, increasing the moving speed of the mobile scanning component, and / or adjusting the scanning parameters to expand the scanning field of view;

[0039] In response to the relative distance being less than a second preset distance, the moving speed of the mobile scanning component is reduced or the moving of the mobile scanning component is stopped, and / or the scanning parameters are adjusted to narrow the scanning field of view.

[0040] Preferably, the step of obtaining target depth information corresponding to the target pixel point in the target depth map includes:

[0041] Acquire first depth information of the target pixel and second depth information corresponding to the position of the target pixel;

[0042] The first depth information is obtained from the target depth map, and the second depth information is preset background depth information;

[0043] The first depth information and the second depth information are calculated to obtain the target depth information corresponding to the target pixel.

[0044] Preferably, the step of dividing the synthesized depth map into a plurality of first sub-units comprises:

[0045] Identifying a first target area in the synthesized depth map corresponding to a preset area;

[0046] dividing the first target area into a plurality of the first sub-units;

[0047] or,

[0048] The step of dividing the initial depth map into a plurality of second sub-units comprises:

[0049] Identify a second target area in the initial depth map corresponding to the preset area;

[0050] dividing the second target area into a plurality of the second sub-units;

[0051] or,

[0052] The step of obtaining first coordinates of a plurality of first pixel points in each of the initial depth maps in the same coordinate system and synthesizing the initial depth maps to obtain a synthesized depth map comprises:

[0053] Identifying the second target area corresponding to the preset area in each of the initial depth maps;

[0054] Acquire the first coordinates of a plurality of the first pixel points in the second target area in the initial depth map in the same coordinate system, and perform synthesis processing on the second target area in the initial depth map to obtain the synthesized depth map;

[0055] or,

[0056] The movement control method further includes:

[0057] Obtaining the local coordinate system corresponding to each of the initial depth maps;

[0058] Obtaining a transformation relationship between the local coordinate system and the reference coordinate system;

[0059] The step of obtaining first coordinates of a plurality of first pixel points in each of the initial depth maps in the same coordinate system comprises:

[0060] Based on the conversion relationship, each of the first pixel points is converted from the local coordinate system to the reference coordinate system to obtain the first coordinate of each of the first pixel points in the reference coordinate system;

[0061] or,

[0062] The step of obtaining second coordinates of a plurality of fourth pixel points in the initial depth map after downsampling in the same coordinate system comprises:

[0063] Based on the conversion relationship, each of the fourth pixel points is converted from the local coordinate system to the reference coordinate system to obtain the second coordinate of each of the fourth pixel points in the reference coordinate system.

[0064] According to a second aspect of the present disclosure, an electronic device is provided, comprising a plurality of depth map acquisition devices disposed at different positions, a memory, a processor, and a computer program stored in the memory and used to run on the processor, wherein the plurality of depth map acquisition devices are used to acquire initial depth maps of a target object from different shooting angles;

[0065] When the processor executes the computer program, the movement control method described in the first aspect of the present disclosure is implemented.

[0066] According to a third aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the movement control method described in the first aspect of the present disclosure is implemented.

[0067] The positive progressive effect of the present disclosure is that the initial depth map of the target object is obtained through vision, and the initial depth map is synthesized and downsampled, which not only improves the computing efficiency but also reduces the amount of data to be processed. Then, a three-dimensional model of the target object is constructed according to the target depth map, and the constructed three-dimensional model is placed in a reference coordinate system to realize collision distance detection and scanning field of view adjustment during the movement of the medical device, ensuring the field of view of the image while ensuring that no collision occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 This is a flow chart of a method for controlling movement of a medical device according to Embodiment 1 of the present disclosure;

[0069] Figure 2 Schematic diagram of the reference coordinate system of Embodiment 1 of the present disclosure;

[0070] Figure 3 This is a schematic diagram of dividing the first target area in Embodiment 1 of the present disclosure;

[0071] Figure 4 This is a schematic diagram of a C-arm according to Embodiment 1 of the present disclosure;

[0072] Figure 5 This is a schematic diagram of a mobile control system module of a medical device according to Embodiment 2 of the present disclosure;

[0073] Figure 6 This is a schematic diagram of the structure of an electronic device according to Embodiment 3 of the present disclosure. DETAILED DESCRIPTION

[0074] The present disclosure is further described below by way of examples, but the present disclosure is not limited to the scope of the examples.

[0075] Prefixes such as "first" and "second" are used in the embodiments of the present disclosure only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present disclosure does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and no unnecessary limitation should be constituted due to the use of such prefixes. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0076] In the embodiments of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0077] Example 1

[0078] In a specific embodiment of the present disclosure, a method for controlling movement of a medical device is provided, such as Figure 1 As shown, the mobile control method includes:

[0079] S1. Obtain several initial depth maps of the target object obtained from different shooting angles;

[0080] S2, performing downsampling and synthesis operations on each initial depth map to obtain a target depth map;

[0081] S3, generating a three-dimensional model of the target object based on the target depth map;

[0082] S4. Control the target state of the medical device based on the relative position of the medical device and the three-dimensional model.

[0083] Specifically, depth map acquisition devices (e.g., depth cameras) can be set at different positions in a specific area. In step S1, a target object (e.g., a patient) in the specific area is photographed by the depth map acquisition device, thereby obtaining several initial depth maps of the target object obtained from different shooting angles.

[0084] For example, taking the bed as a specific area, one or more depth cameras can be set at multiple different positions such as the head of the bed, both sides of the bed, and the foot of the bed. When the patient lies on the bed, the depth cameras set at different positions can be used to obtain the initial depth map corresponding to the patient at different shooting angles. In order to realize the construction of the three-dimensional model of the human body, it is preferred to set three depth cameras for initial depth map acquisition. The three depth cameras can be set at the head of the bed and both sides of the bed.

[0085] After obtaining several initial depth maps of the target object under different shooting angles, each initial depth map is downsampled and synthesized to obtain a depth map that can fully reflect the position of the target object. Therefore, a reference coordinate system can be established in advance, such as Figure 2 As shown, with the bed head reference point (for example, the midpoint of the width of the bed board at the bed head) as the origin, horizontal movement toward the bed base (bed foot) is the positive direction of the X axis, movement toward the left side of the bed (bed board inward) is the positive direction of the Y axis, and movement above the bed board (away from the ground) is the positive direction of the Z axis to establish a reference coordinate system. Through step S2, each initial depth map at different shooting angles is converted to the reference coordinate system for synthesis operation. In order to improve the calculation efficiency and reduce the amount of data to be processed, a downsampling operation can also be performed to obtain a target depth map.

[0086] Since the target depth map includes the depth information of each position of the target object, and the depth information of each position can reflect the outline of the target object, the depth information can be converted into three-dimensional model data in step S3 to generate a three-dimensional model of the target object.

[0087] After generating the three-dimensional model of the target object, the relative position between the medical device and the three-dimensional model is calculated through step S4, and the target state of the medical device is controlled according to the relative position, for example, the moving state and scanning field of view of the medical device are controlled, so that during the movement of the medical device, the field of view of the image is ensured and no collision occurs, and a certain distance is maintained from the target object when the medical device moves, thereby reducing the radiation dose.

[0088] This specific implementation method obtains the initial depth map of the target object through vision, and performs synthesis and downsampling operations on the depth map, which not only improves the computing efficiency but also reduces the amount of data to be processed. A three-dimensional model of the target object is then constructed based on the target depth map, and the constructed three-dimensional model is placed in a reference coordinate system to realize collision distance detection and scanning field of view adjustment during the movement of the medical device, thereby ensuring the field of view of the image while ensuring that no collision occurs.

[0089] In a specific implementation, step S2 includes:

[0090] S211, obtaining first coordinates of multiple first pixel points in each initial depth map in the same coordinate system, and performing synthesis processing on the initial depth maps to obtain a synthesized depth map;

[0091] S212, dividing the synthesized depth map into a plurality of first sub-units, and performing downsampling processing on a plurality of second pixel points located in the first sub-units to obtain third pixel points corresponding to the synthesized depth map;

[0092] S213, obtaining a target depth map based on the plurality of third pixel points;

[0093] Specifically, after the setting position of the depth map acquisition device is fixed, its shooting angle for the target object is also fixed. In order to facilitate the positioning of the pixel points in the initial depth map, a local coordinate system can be established according to the setting position of the depth map acquisition device. Each first pixel point in the initial depth map captured by the depth map acquisition device corresponds to a coordinate point in the local coordinate system.

[0094] Therefore, in the process of synthesizing the initial depth maps under different shooting angles, the local coordinate system corresponding to the initial depth map can be obtained to obtain the first local coordinates of the first pixel point in the initial depth map in the local coordinate system, and then the conversion relationship between the local coordinate system and the reference coordinate system is obtained, and the first local coordinates of each first pixel point are converted to the reference coordinate system to obtain the first coordinates of each first pixel point in the reference coordinate system.

[0095] After obtaining the first coordinate of each first pixel point in the initial depth map under different shooting angles in the reference coordinate system, the initial depth map may be synthesized to obtain a synthesized depth map.

[0096] In order to improve computational efficiency and reduce the amount of data to be processed, the synthesized depth map may be downsampled. By dividing the synthesized depth map into multiple sub-units, and downsampling multiple second pixels in each sub-unit to obtain third pixels, a target depth map composed of multiple third pixels may be obtained.

[0097] In a specific practicable manner, step S212 includes:

[0098] S2121, identifying a first target area in the synthesized depth map corresponding to a preset area;

[0099] S2122. Divide the first target area into a plurality of the first sub-units.

[0100] Specifically, the area where the target object in the specific area is located can be used as a preset area, and only the first target area corresponding to the preset area in the synthetic depth map can be downsampled to further improve the calculation efficiency and reduce the amount of data to be processed. For example, starting from the origin of the reference coordinate system, the area composed of the (0~2500mm) segment on the X-axis and the (-500mm~500mm) segment on the Y-axis is used as the preset area, and then the first target area corresponding to the preset area in the synthetic depth map is identified, and then the first target area is divided into multiple sub-units, and the multiple second pixel points in each sub-unit are downsampled to obtain third pixel points, so as to obtain a target depth map composed of multiple third pixel points.

[0101] For example, Figure 3 As shown, the spatial range of the first target area is 2500mm*1000mm, and the spatial size of the subunit is 5cm*5cm. Then the first target area can be divided into 1000 subunits, and then the multiple second pixel points in each subunit are merged into one pixel point to obtain a third pixel point, and the multiple third pixel points constitute the target depth map. Among them, the spatial size of the subunit can be adjusted according to the actual accuracy requirements, and this specific implementation is not limited to this.

[0102] In another specific practicable manner, step S211 includes:

[0103] S2111, identifying a second target area corresponding to a preset area in each initial depth map;

[0104] S2112: Obtain first coordinates of a plurality of first pixel points in the second target region in the initial depth map in the same coordinate system, and perform synthesis processing on the second target region in the initial depth map to obtain a synthesized depth map.

[0105] Specifically, before synthesizing the initial depth map, the second target area corresponding to the preset area where the target object is located in each initial depth map can be identified, and only the second target area in each initial depth map is synthesized to further improve the computing efficiency and reduce the amount of data to be processed. This specific implementation method first synthesizes the initial depth maps at different shooting angles to obtain a synthesized depth map, and then downsamples the synthesized depth map, which can not only improve the computing efficiency and reduce the amount of data to be processed, but also ensure the image quality of the target depth map.

[0106] In another specific implementation, step S2 includes:

[0107] S221, dividing the second target area into a plurality of second sub-units, and performing downsampling processing on a plurality of first pixel points located in the second sub-units to obtain an initial depth map after downsampling;

[0108] S222: Obtain second coordinates of multiple fourth pixel points in the downsampled initial depth map in the same coordinate system, and perform synthesis processing on the multiple downsampled initial depth maps to obtain a target depth map.

[0109] Specifically, before synthesizing the initial depth maps at different shooting angles, each initial depth map may be downsampled to obtain a downsampled initial depth map, and then, according to the local coordinate system corresponding to the initial depth map, the second local coordinate of the fourth pixel in the downsampled initial depth map in the local coordinate system is obtained, and each second local coordinate is converted to the reference coordinate system to obtain the second coordinate of each fourth pixel in the reference coordinate system, and the fourth pixel in the different downsampled initial depth maps is synthesized to obtain a target depth map. The implementation principles of the downsampling process and the synthesis process can refer to the above description and will not be repeated here.

[0110] In a specific practicable manner, step S221 includes:

[0111] S2211, identifying a second target area in the initial depth map corresponding to the preset area;

[0112] S2212. Divide the second target area into a plurality of second sub-units.

[0113] Specifically, the second target area corresponding to the preset area where the target object is located in each initial depth map can be identified first, and only the second target area in each initial depth map is downsampled and then synthesized to further improve the computing efficiency and reduce the amount of data to be processed. This specific implementation reduces the amount of data for synthesis processing by first downsampling the initial depth map to improve the computing efficiency and reduce the amount of data to be processed.

[0114] In a specific implementation, step S3 includes:

[0115] S31, obtaining target depth information corresponding to a target pixel in a target depth map;

[0116] Wherein, step S31 includes:

[0117] S311, obtaining first depth information of a target pixel and second depth information corresponding to a position of the target pixel; the first depth information is obtained from a target depth map, and the second depth information is pre-set background depth information;

[0118] S312: Calculate the first depth information and the second depth information to obtain target depth information corresponding to the target pixel.

[0119] S32: Convert the target pixel points into three-dimensional model coordinate points based on the target depth information to generate a three-dimensional model of the target object.

[0120] Specifically, since the depth information in the target depth map not only includes the depth information of the target object, but also includes the depth information of the preset area itself, for example, the area where the hospital bed is located is taken as the preset area, and the patient lies on the hospital bed, when the depth camera obtains the initial depth map of the patient, the depth information in the initial depth map also includes the depth information of the hospital bed itself (bed board thickness), and the target depth map obtained based on the initial depth map also includes the depth information of the hospital bed.

[0121] Therefore, in order to improve the accuracy of the three-dimensional model of the target object, it is also necessary to remove the depth information of the preset area itself and only retain the depth information of the target object. Among them, the depth map of the preset area that does not include the target object can be collected in advance to obtain the second depth information of the preset area itself, and then the first depth information of the target pixel point in the target depth map is deducted from the second depth information corresponding to the position of the target pixel point to obtain the target depth information depth of the target object.

[0122] After obtaining the target depth information depth, the target depth information depth can be converted into a three-dimensional model coordinate point by the following formula:

[0123]

[0124] Among them, model.x, model.y, and model.z represent the three coordinates of the three-dimensional model coordinate points. x Indicates the length of the subunit on the X axis, sacle y represents the length of the subunit on the Y axis, u represents the X axis coordinate of the target pixel, v represents the Y axis coordinate of the target pixel, depth represents the target depth information of the target pixel, and scale_z is a predefined scale factor.

[0125] It should be noted that the size of the scale factor can be set according to actual needs. For example, the maximum height of the defined area of ​​interest (Z axis) is 500mm. At this time, the depth information needs to be transmitted through two bytes. If it is reduced by 1 times through the scale factor, the maximum is 255, so it can be transmitted through one byte, thereby reducing the amount of transmitted data. However, when converting the depth information into a three-dimensional model, it is necessary to set the value of the scale factor sacle_z to 2 to obtain the actual three-dimensional model height.

[0126] After obtaining the three-dimensional model coordinate points at various positions of the target object, the three-dimensional model of the target object can be generated.

[0127] In one embodiment, the medical device includes a moving component or a moving scanning component;

[0128] Step S4 includes:

[0129] S41, obtaining a plurality of target three-dimensional model coordinate points located in a target area corresponding to a moving component or a moving scanning component;

[0130] S42, obtaining the relative distance between the target three-dimensional model coordinate point and the moving component or the moving scanning component;

[0131] S43, controlling the target state of the moving component or the moving scanning component according to the relative distance;

[0132] Wherein, when the medical device is a moving part, the target state includes the moving speed;

[0133] When the medical device is a mobile scanning component, the target state includes a moving speed and / or a scanning parameter, and the scanning parameter is used to adjust the scanning field of view.

[0134] Specifically, the moving parts in medical equipment include moving scanning parts (e.g., C-arms, G-arms, etc.) and interventional treatment parts (e.g., display screens, robotic surgical arms with puncture functions, etc.). In actual operations, the moving parts usually need to be moved to the corresponding target parts, and during the movement, collisions with patients need to be avoided. For moving scanning parts with scanning functions, the scanning field of view also needs to be adjusted according to the distance between the parts and the target parts to ensure the clarity and effectiveness of the scanned images. Taking the C-arm as an example, if Figure 4 As shown, the C-arm is pushed into the bed through the opening, and the angle value of the C-arm CAU (the angle formed by the enhancer located at the patient's foot and the anterior-posterior diameter of the horizontal plane of the thorax) is adjusted (such as CAU35°, CAU 50°, which is only used as an example) so that the image receptor on the C-arm is located at the part to be scanned. The scanning field of view is adjusted by adjusting the opening of the C-arm, that is, adjusting the distance SID (source-image distance) from the lower edge of the housing of the image receptor (image enhancer or flat panel) to the upper edge of the housing of the X-ray generator (tube).

[0135] In the process of moving, in order to avoid collision between the moving part and the patient, the target area on the three-dimensional model corresponding to the moving part can be obtained according to the position of the moving part, and the relative distance between the three-dimensional model and the moving part can be calculated through the target three-dimensional model coordinate points located in the target area. For example, the vertical distance from each target three-dimensional model coordinate point to the moving part is calculated.

[0136] After obtaining the relative distance between the three-dimensional model and the moving part, the moving speed of the moving part can be controlled according to the relative distance to avoid collision. For the moving scanning part, the scanning parameters need to be adjusted according to the relative distance to ensure the field of view of the image. For example, the moving speed of the moving part, the moving speed of the moving scanning part and the scanning parameters can be controlled according to the minimum value of multiple relative distances or the average value of multiple relative distances.

[0137] In a specific implementation, step S42 includes:

[0138] Based on the target three-dimensional model coordinate point, a preset range corresponding to the target three-dimensional model coordinate point in the moving component or the moving scanning component is divided into a plurality of blocks;

[0139] Get the relative distance between the block and the corresponding target 3D model coordinate point.

[0140] In a specific implementation, step S43 includes:

[0141] Determine the relative distance between the moving component or the moving scanning component and the target of the three-dimensional model according to a plurality of relative distances;

[0142] The target state of the moving component or the moving scanning component is controlled based on the target relative distance.

[0143] Specifically, since the moving part is usually a plane with a certain range, for example, the image receptor of the C-arm is a flat plate, and the three-dimensional model area corresponding to the moving part is usually not flat. Therefore, in order to better calculate the relative distance from the moving part to the three-dimensional model, the plane of the moving part can be divided according to the preset range corresponding to each coordinate point in the three-dimensional model to obtain a number of blocks. Among them, the divided blocks can correspond to each target three-dimensional model coordinate point one by one, or one block can correspond to multiple target three-dimensional model coordinate points, or multiple blocks can correspond to one target three-dimensional model coordinate point, which is not limited in this specific embodiment.

[0144] It is understandable that during the generation of the three-dimensional model, pixel points with a certain spatial size can be obtained through downsampling. When performing three-dimensional model coordinate transformation, the obtained three-dimensional model coordinate points correspond to the spatial size.

[0145] After obtaining a number of blocks, the relative distance between the block and the corresponding target three-dimensional model coordinate point can be calculated. Among them, the target relative distance between the moving component and the three-dimensional model can be determined from the calculated multiple relative distances. For example, the minimum value of the multiple relative distances is used as the target relative distance to control the moving speed of the moving component, the moving speed of the mobile scanning component and the scanning parameters according to the target relative distance.

[0146] In a specific implementation, step S43 includes:

[0147] In response to the relative distance being greater than a first preset distance, increasing the moving speed of the mobile scanning component, and / or adjusting the scanning parameters to expand the scanning field of view;

[0148] In response to the relative distance being less than the second preset distance, the moving speed of the mobile scanning component is reduced or the moving scanning component is stopped, and / or the scanning parameters are adjusted to narrow the scanning field of view.

[0149] Specifically, when the relative distance is greater than the first preset distance, the mobile scanning component is far away from the three-dimensional model, there is enough space, and collision is not likely to occur. In this case, the moving speed of the mobile scanning component can be increased to improve the movement efficiency, and / or the scanning parameters can be adjusted to expand the scanning field of view to ensure the quality of the scanned image.

[0150] Similarly, when the relative distance is less than the second preset distance, the distance between the mobile scanning component and the three-dimensional model is relatively close. If the position of the mobile scanning component is adjusted significantly, a collision is more likely to occur. Therefore, the moving speed of the mobile scanning component can be reduced to avoid the collision, and / or the scanning parameters can be adjusted to narrow the scanning field of view to ensure the quality of the scanned image.

[0151] The first preset distance and the second preset distance may be the same or different.

[0152] For example, continuing to take the C-arm as an example, when the relative distance between the flat panel and the three-dimensional model is greater than the first preset distance, that is, the relative distance between the image receptor and the three-dimensional model is in an increasing state, the movement speed of the flat panel can be reduced, and / or the SID can be controlled to dynamically decrease to expand the scanning field of view, and maintain the relative distance between the flat panel and the three-dimensional model to reduce the radiation dose; when the relative distance between the image receptor and the three-dimensional model is less than the second preset distance, that is, the relative distance between the image receptor and the three-dimensional model is in a decreasing state, the movement speed of the flat panel can be increased, and / or the SID can be controlled to dynamically increase to move away from the three-dimensional model, narrow the scanning field of view to ensure the scanning field of view range, and avoid collision. The specific adjustment method can be set according to actual needs.

[0153] This embodiment obtains an initial depth map of the target object through vision, and performs synthesis and downsampling operations on the depth map, which not only improves the computing efficiency but also reduces the amount of data to be processed. A three-dimensional model of the target object is then constructed based on the target depth map, and the constructed three-dimensional model is placed in a reference coordinate system to realize collision distance detection and scanning field of view adjustment during the movement of the medical device, thereby ensuring the field of view of the image while ensuring that no collision occurs.

[0154] Example 2

[0155] In a specific embodiment of the present disclosure, a mobile control system for a medical device is provided, such as Figure 5 As shown, the mobile control system includes an acquisition module 100, a processing module 200, a generation module 300 and a control module 400;

[0156] The acquisition module 100 is used to acquire a plurality of initial depth maps of the target object obtained from different shooting angles;

[0157] The processing module 200 is used to perform downsampling operations and synthesis operations on each initial depth map to obtain a target depth map;

[0158] The generating module 300 is used to generate a three-dimensional model of a target object based on the target depth map;

[0159] The control module 400 is used to control the target state of the medical device based on the relative position between the medical device and the three-dimensional model.

[0160] In a specific implementation, the processing module 200 includes a synthesis processing unit and a downsampling processing unit;

[0161] The synthesis processing unit is used to obtain first coordinates of multiple first pixel points in each initial depth map in the same coordinate system, and perform synthesis processing on the initial depth map to obtain a synthesized depth map;

[0162] The downsampling processing unit is used to divide the synthesized depth map into a plurality of first sub-units, perform downsampling processing on a plurality of second pixel points located in the first sub-units, and obtain third pixel points corresponding to the synthesized depth map; based on the plurality of third pixel points, obtain a target depth map.

[0163] In a specific implementable manner, the synthesis processing unit is further used to identify a first target area corresponding to a preset area in the synthesized depth map, and divide the first target area into a plurality of first sub-units.

[0164] In another specific implementable method, the synthesis processing unit is also used to identify a second target area corresponding to a preset area in each initial depth map, obtain the first coordinates of multiple first pixel points in the second target area in the initial depth map in the same coordinate system, and perform synthesis processing on the second target area in the initial depth map to obtain a synthesized depth map.

[0165] In another specific implementation, the downsampling processing unit is used to divide the initial depth map into a plurality of second sub-units, and perform downsampling processing on a plurality of first pixel points located in the second sub-units to obtain a downsampled initial depth map;

[0166] The synthesis processing unit is used to obtain second coordinates of multiple fourth pixel points in the downsampled initial depth map in the same coordinate system, and perform synthesis processing on the multiple downsampled initial depth maps to obtain a target depth map.

[0167] In a specific implementable manner, the downsampling processing unit is further used to identify a second target area corresponding to the preset area in the initial depth map, and divide the second target area into a plurality of second sub-units.

[0168] In a specific implementation, the generation module 300 is used to obtain target depth information corresponding to target pixels in the target depth map; convert the target pixels into three-dimensional model coordinate points based on the target depth information, and generate a three-dimensional model of the target object.

[0169] In one embodiment, the medical device includes a moving component or a moving scanning component;

[0170] The control module 400 is used to obtain a plurality of target three-dimensional model coordinate points located in a target area corresponding to the moving component or the moving scanning component; obtain a relative distance between the target three-dimensional model coordinate points and the moving component or the moving scanning component; and control a target state of the moving component or the moving scanning component according to the relative distance;

[0171] Wherein, when the medical device is a moving part, the target state includes the moving speed;

[0172] When the medical device is a mobile scanning component, the target state includes a moving speed and / or a scanning parameter, and the scanning parameter is used to adjust the scanning field of view.

[0173] In a specific implementation, the control module 400 is further used to divide the preset range corresponding to the target three-dimensional model coordinate point in the moving component or the mobile scanning component based on the target three-dimensional model coordinate point to obtain a plurality of blocks; obtain the relative distance between the block and the corresponding target three-dimensional model coordinate point;

[0174] In a specific implementation, the control module 400 is further configured to determine a target relative distance between the moving component or the moving scanning component and the three-dimensional model according to a plurality of relative distances; and to control a target state of the moving component or the moving scanning component based on the target relative distance.

[0175] In a specific embodiment, the control module 400 is further configured to increase the moving speed of the mobile scanning component and / or adjust the scanning parameters to expand the scanning field of view in response to the relative distance being greater than the first preset distance;

[0176] The control module 400 is further configured to reduce the moving speed of the mobile scanning component or stop moving the mobile scanning component in response to the relative distance being less than a second preset distance, and / or adjust the scanning parameters to narrow the scanning field of view.

[0177] In a specific embodiment, the generation module 300 is also used to obtain first depth information of the target pixel and second depth information corresponding to the position of the target pixel; the first depth information is obtained from the target depth map, and the second depth information is the pre-set background depth information; the first depth information and the second depth information are calculated to obtain the target depth information corresponding to the target pixel.

[0178] In a specific implementation, the acquisition module 100 is further used to acquire the local coordinate system corresponding to each initial depth map; acquire the conversion relationship between the local coordinate system and the reference coordinate system;

[0179] The synthesis processing unit is further used to transform each first pixel point from the local coordinate system to the reference coordinate system based on the transformation relationship, so as to obtain the first coordinate of each first pixel point in the reference coordinate system.

[0180] In a specific implementation, the synthesis processing unit is further configured to transform each fourth pixel point from the local coordinate system to the reference coordinate system based on a transformation relationship, so as to obtain a second coordinate of each fourth pixel point in the reference coordinate system.

[0181] As for the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only illustrative, wherein the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution.

[0182] This embodiment obtains an initial depth map of the target object through vision, and performs synthesis and downsampling operations on the depth map, which not only improves the computing efficiency but also reduces the amount of data to be processed. A three-dimensional model of the target object is then constructed based on the target depth map, and the constructed three-dimensional model is placed in a reference coordinate system to realize collision distance detection and scanning field of view adjustment during the movement of the medical device, thereby ensuring the field of view of the image while ensuring that no collision occurs.

[0183] Example 3

[0184] Figure 6This is a schematic diagram of the structure of an electronic device shown in an example embodiment of the present disclosure, the electronic device includes a plurality of depth map acquisition devices (not shown in the figure) arranged at different positions, a memory, a processor and a computer program stored in the memory and used to run on the processor, the plurality of depth map acquisition devices are used to acquire initial depth maps of a target object from different shooting angles, and the processor implements the mobile control method of the medical device described in any of the above embodiments when executing the computer program. Figure 6 The electronic device 30 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0185] like Figure 6 As shown, the electronic device 30 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0186] The bus 33 includes a data bus, an address bus, and a control bus.

[0187] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read-only memory (ROM) 323 .

[0188] The memory 32 may also include a program tool 325 (or utility) having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0189] The processor 31 executes various functional applications and data processing by running the computer program stored in the memory 32, such as the movement control method of the medical device provided in any of the above embodiments.

[0190] The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 35. Furthermore, the electronic device 30 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 36. As shown, the network adapter 36 communicates with other modules of the electronic device 30 via a bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0191] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0192] Example 4

[0193] The embodiments of the present disclosure further provide a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the method for controlling the movement of a medical device provided in any of the above embodiments is implemented.

[0194] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0195] Example 5

[0196] The embodiment of the present disclosure further provides a computer program product, including a computer program, which implements any of the above-mentioned methods for controlling movement of a medical device when executed by a processor.

[0197] Among them, the program code for executing the computer program product of the present disclosure can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0198] Although the specific embodiments of the present disclosure are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present disclosure is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present disclosure, but these changes and modifications all fall within the protection scope of the present disclosure.

Claims

1. A mobile control method for medical equipment, characterized in that: The movement control method comprises: Obtain several initial depth maps of the target object obtained from different shooting angles; Performing downsampling and synthesis operations on each of the initial depth maps to obtain a target depth map; generating a three-dimensional model of the target object based on the target depth map; Based on the relative position of the medical device and the three-dimensional model, a target state of the medical device is controlled.

2. The mobile control method according to claim 1, characterized in that: The step of performing downsampling and synthesis operations on each of the initial depth maps to obtain a target depth map comprises: Obtaining first coordinates of a plurality of first pixel points in each of the initial depth maps in the same coordinate system, and performing synthesis processing on the initial depth maps to obtain a synthesized depth map; Dividing the synthesized depth map into a plurality of first sub-units, and performing downsampling processing on a plurality of second pixel points located in the first sub-units to obtain third pixel points corresponding to the synthesized depth map; Based on the plurality of third pixel points, obtaining the target depth map; or, The step of performing downsampling and synthesis operations on each of the initial depth maps to obtain a target depth map comprises: Dividing the initial depth map into a plurality of second sub-units, and performing downsampling processing on a plurality of the first pixel points located in the second sub-units to obtain the downsampled initial depth map; The second coordinates of a plurality of fourth pixel points in the downsampled initial depth map in the same coordinate system are obtained, and a plurality of the downsampled initial depth maps are synthesized to obtain the target depth map.

3. The mobile control method according to claim 2, characterized in that: The step of generating a three-dimensional model of the target object based on the target depth map comprises: Obtain target depth information corresponding to a target pixel point in the target depth map; The target pixel points are converted into three-dimensional model coordinate points based on the target depth information to generate a three-dimensional model of the target object.

4. The mobile control method according to claim 3, characterized in that: The medical device comprises a moving part or a moving scanning part; The step of controlling the target state of the medical device based on the relative position of the medical device and the three-dimensional model comprises: Acquire a plurality of target three-dimensional model coordinate points located in a target area corresponding to the moving component or the moving scanning component; Acquire the relative distance between the target three-dimensional model coordinate point and the moving component or the moving scanning component; controlling the target state of the moving component or the moving scanning component according to the relative distance; Wherein, when the medical device is the moving component, the target state includes a moving speed; When the medical device is the mobile scanning component, the target state includes a moving speed and / or a scanning parameter, and the scanning parameter is used to adjust a scanning field of view.

5. The mobile control method according to claim 4, characterized in that: The step of obtaining the relative distance between the target three-dimensional model coordinate point and the moving component or the moving scanning component comprises: Based on the target three-dimensional model coordinate point, dividing a preset range in the moving component or the moving scanning component corresponding to the target three-dimensional model coordinate point to obtain a plurality of blocks; Acquire the relative distance between the block and the corresponding coordinate point of the target three-dimensional model; and / or, The step of controlling the target state of the moving component or the moving scanning component according to the relative distance comprises: Determining a relative distance between the moving component or the moving scanning component and a target of the three-dimensional model according to a plurality of the relative distances; The target state of the moving component or the moving scanning component is controlled based on the target relative distance.

6. The mobile control method according to claim 4, characterized in that: The step of controlling the target state of the moving component or the moving scanning component according to the relative distance comprises: In response to the relative distance being greater than a first preset distance, increasing the moving speed of the mobile scanning component, and / or adjusting the scanning parameters to expand the scanning field of view; In response to the relative distance being less than a second preset distance, the moving speed of the mobile scanning component is reduced or the moving of the mobile scanning component is stopped, and / or the scanning parameters are adjusted to narrow the scanning field of view.

7. The mobile control method according to claim 3, characterized in that: The step of obtaining target depth information corresponding to the target pixel point in the target depth map comprises: Acquire first depth information of the target pixel and second depth information corresponding to the position of the target pixel; The first depth information is obtained from the target depth map, and the second depth information is preset background depth information; The first depth information and the second depth information are calculated to obtain the target depth information corresponding to the target pixel.

8. The mobile control method according to claim 2, characterized in that: The step of dividing the synthesized depth map into a plurality of first sub-units comprises: Identifying a first target area in the synthesized depth map corresponding to a preset area; dividing the first target area into a plurality of the first sub-units; or, The step of dividing the initial depth map into a plurality of second sub-units comprises: Identify a second target area in the initial depth map corresponding to the preset area; dividing the second target area into a plurality of the second sub-units; or, The step of obtaining first coordinates of a plurality of first pixel points in each of the initial depth maps in the same coordinate system and synthesizing the initial depth maps to obtain a synthesized depth map comprises: Identifying the second target area corresponding to the preset area in each of the initial depth maps; Acquire the first coordinates of a plurality of the first pixel points in the second target area in the initial depth map in the same coordinate system, and perform synthesis processing on the second target area in the initial depth map to obtain the synthesized depth map; or, The movement control method further includes: Obtaining the local coordinate system corresponding to each of the initial depth maps; Obtaining a transformation relationship between the local coordinate system and the reference coordinate system; The step of obtaining first coordinates of a plurality of first pixel points in each of the initial depth maps in the same coordinate system comprises: Based on the conversion relationship, each of the first pixel points is converted from the local coordinate system to the reference coordinate system to obtain the first coordinate of each of the first pixel points in the reference coordinate system; or, The step of obtaining second coordinates of a plurality of fourth pixel points in the initial depth map after downsampling in the same coordinate system comprises: Based on the conversion relationship, each of the fourth pixel points is converted from the local coordinate system to the reference coordinate system to obtain the second coordinate of each of the fourth pixel points in the reference coordinate system.

9. An electronic device comprising a plurality of depth map acquisition devices arranged at different positions, a memory, a processor, and a computer program stored in the memory and used to run on the processor, characterized in that: The plurality of depth map acquisition devices are used to acquire initial depth maps of the target object from different shooting angles; When the processor executes the computer program, the movement control method according to any one of claims 1 to 8 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the movement control method according to any one of claims 1 to 8 is implemented.