Vascular intervention surgery image adjustment method and device, equipment and storage medium

Abstract

The application belongs to the field of vascular interventional surgery and relates to a vascular interventional surgery image adjusting method, device, equipment and storage medium.The method comprises the following steps: inputting a vascular interventional surgery perspective image into a pre-trained target detection model to identify an instrument position area in the vascular interventional surgery perspective image; acquiring a preset instrument limited area and calculating a center point deviation value of a first center point corresponding to the instrument position area and a second center point corresponding to the instrument limited area; judging whether the center point deviation value is greater than or equal to a preset movement threshold value; if yes, generating a corresponding movement control instruction according to the center point deviation value and sending the movement control instruction to a camera equipment for control, so that the center point deviation value is less than or equal to a preset standard threshold value, and an adjusted vascular interventional surgery perspective image is obtained.The application can automatically, effectively and accurately adjust the position of the camera equipment, so that the display position of the interventional instrument in the interventional surgery image is more convenient to observe.

Description

Technical Field

[0001] This application relates to the field of vascular interventional surgery technology, and in particular to a method, apparatus, computer equipment and storage medium for adjusting images in vascular interventional surgery. Background Technology

[0002] Interventional vascular surgery is a treatment method that uses surgical instruments to treat lesions within a patient's blood vessels. During the procedure, the operator remotely controls the surgical instruments to insert them into the blood vessel and treat the lesion.

[0003] When performing remote control, the operator needs to view the fluoroscopic images of the vascular interventional surgery in real time to obtain the position of the surgical instruments in the blood vessel, so as to control the surgical instruments in real time according to the position and safely reach the lesion site in the blood vessel.

[0004] However, in fluoroscopic images of vascular interventional surgery, due to the limited image capture range, the tip of the surgical instrument may appear near the edge of the vascular imaging image. Moving the instrument in this situation would cause the tip to move out of the effective image capture range, making it impossible for the operator to accurately determine the instrument's position within the blood vessel based on the vascular imaging image. Therefore, when the tip of the surgical instrument appears near the edge of the vascular imaging image, the operator needs to move the gantry equipped with the camera or the patient's bed to adjust the image capture area of ​​the fluoroscopic image of the vascular interventional surgery, placing the tip of the surgical instrument in the effective display position of the fluoroscopic image to facilitate subsequent operations. However, since adjusting the image requires manual movement of the camera, the operation is cumbersome and difficult to control in terms of precision, resulting in poor adjustment effect and efficiency of the image capture area of ​​the fluoroscopic image of the vascular interventional surgery, affecting the normal progress of the surgery. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, computer equipment and storage medium for adjusting images in vascular interventional surgery, so as to solve the problem of difficulty in effectively and accurately positioning the camera equipment during the operation, and to make the display position of interventional instruments in the interventional surgery images easier to observe.

[0006] To address the aforementioned technical problems, this application provides a method for adjusting vascular interventional surgical images, employing the following technical solution:

[0007] Acquire real-time fluoroscopic images of vascular interventional surgery captured by a camera device, input the fluoroscopic images of vascular interventional surgery into a pre-trained target detection model, and identify the instrument location region in the fluoroscopic images of vascular interventional surgery;

[0008] Obtain a preset instrument definition area, and calculate the center point deviation value between the first center point corresponding to the instrument position area and the second center point corresponding to the instrument definition area;

[0009] Determine whether the center point deviation value is greater than or equal to a preset movement threshold;

[0010] If the center point deviation value is greater than or equal to the preset movement threshold, a corresponding movement control command is generated based on the center point deviation value and sent to the camera device for movement control to adjust the center point deviation value so that the center point deviation value is less than or equal to the preset standard threshold, thereby obtaining an adjusted vascular interventional surgery fluoroscopy image, and the adjusted vascular interventional surgery fluoroscopy image is sent to the display interface for display.

[0011] Furthermore, before the steps of acquiring real-time fluoroscopic images of vascular interventional surgery captured by the camera device, inputting the fluoroscopic images of vascular interventional surgery into a pre-trained target detection model, and identifying the instrument location region in the fluoroscopic images of vascular interventional surgery, the following steps are also included:

[0012] Acquire fluoroscopic images of sample vascular interventional surgery, and determine the instrument sample target and instrument sample target region in the sample vascular interventional surgery fluoroscopic images according to a preset target detection algorithm;

[0013] The instrument sample target and the instrument sample target region in the fluoroscopic image of the sample vascular interventional surgery are marked to obtain a marked sample vascular interventional surgery fluoroscopic image;

[0014] Based on the spatial coordinate system of the fluoroscopic image of the labeled vascular interventional surgery, key regional information of the target region of the instrument sample is obtained;

[0015] The optical flow field of the region is obtained by calculating the image of the target area of ​​the instrument sample according to the preset motion prediction algorithm;

[0016] The labeled sample vascular interventional surgery fluoroscopic image, the key information of the region, and the optical flow field of the region are input into the machine learning model for model training to obtain the target detection model.

[0017] Furthermore, the step of obtaining key regional information of the target region of the instrument sample based on the spatial coordinate system of the fluoroscopic image of the labeled vascular interventional surgery specifically includes:

[0018] Determine the center point of the target region of the instrument sample;

[0019] Based on the spatial coordinate system of the fluoroscopic image of the labeled vascular interventional surgery, the coordinates of the center point and edge points of the target region of the instrument sample are obtained;

[0020] Calculate the length and width of the region based on the coordinates of its edge points.

[0021] The length of the region, the width of the region, and the coordinates of the center point of the region are used as the key information of the region.

[0022] Furthermore, the step of acquiring real-time fluoroscopic images of vascular interventional surgery captured by the camera device specifically includes:

[0023] Obtain the current time information, and search for the corresponding real-time image data in the image storage database of the camera device based on the current time information;

[0024] The real-time image data is extracted as the fluoroscopic image of the vascular interventional surgery.

[0025] Furthermore, the step of obtaining a preset instrument definition area and calculating the center point deviation between the first center point corresponding to the instrument position area and the second center point corresponding to the instrument definition area specifically includes:

[0026] Extract the preset instrument definition area from the database;

[0027] Determine the center point of a first region of the instrument location area and the center point of a second region of the instrument defined area, so as to obtain the first coordinate information of the center point of the first region and the second coordinate information of the center point of the second region.

[0028] The difference between the first coordinate information and the second coordinate information is calculated as the center point deviation value.

[0029] Furthermore, the step of generating a corresponding motion control command based on the center point deviation value and sending it to the camera device for motion control specifically includes:

[0030] Obtain a preset distance conversion coefficient, and calculate the movement distance information based on the distance conversion coefficient and the center point deviation value;

[0031] Generate corresponding movement control commands based on the movement distance information;

[0032] The motion control command is sent to the camera device, and the camera device moves according to the motion control command.

[0033] Furthermore, the distance conversion coefficients include X-axis distance conversion coefficients and Y-axis distance conversion coefficients. The step of calculating the movement distance information based on the distance conversion coefficients and the center point deviation value specifically includes:

[0034] Obtain the coordinate object corresponding to the center point deviation value;

[0035] Obtain the corresponding first movement distance calculation formula and second movement distance calculation formula based on the coordinate object;

[0036] The first moving distance information and the second moving distance information are calculated according to the first moving distance calculation formula and the second moving distance calculation formula, wherein the first moving distance calculation formula is: first moving distance = center point deviation value * X-axis distance conversion coefficient, and the second moving distance calculation formula is: second moving distance = center point deviation value * Y-axis distance conversion coefficient;

[0037] The first movement distance information and the second movement distance information are used as the movement distance information.

[0038] To address the aforementioned technical problems, this application also provides an image adjustment device for vascular interventional surgery, comprising:

[0039] The region recognition module is used to acquire real-time fluoroscopic images of vascular interventional surgery captured by the camera device, input the fluoroscopic images of vascular interventional surgery into a pre-trained target detection model, and identify the instrument location region in the fluoroscopic images of vascular interventional surgery.

[0040] The deviation calculation module is used to obtain a preset instrument limitation area and calculate the center point deviation value between the first center point corresponding to the instrument position area and the second center point corresponding to the instrument limitation area.

[0041] The judgment module is used to determine whether the center point deviation value is greater than or equal to a preset movement threshold.

[0042] The image adjustment module is used to generate a corresponding motion control command based on the center point deviation value and send it to the camera device for motion control if the center point deviation value is greater than or equal to the preset motion threshold, so as to adjust the center point deviation value to be less than or equal to the preset standard threshold, thereby obtaining an adjusted vascular interventional surgery fluoroscopic image, and sending the adjusted vascular interventional surgery fluoroscopic image to the display interface for display.

[0043] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution:

[0044] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described vascular interventional surgery image adjustment method.

[0045] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below:

[0046] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described vascular interventional surgery image adjustment method.

[0047] Compared with the prior art, the embodiments of this application have the following main advantages:

[0048] This application acquires real-time fluoroscopic images of vascular interventional surgery captured by a camera device, inputs these images into a pre-trained target detection model, and thus accurately identifies the instrument location region in the fluoroscopic image. By acquiring a preset instrument-defined region and calculating the center point deviation between the first center point and the second center point corresponding to the instrument location region, the degree of offset between the first and second center points can be effectively obtained. By determining whether the center point deviation value is greater than or equal to a preset movement threshold, it is determined whether the current conditions meet the requirements for controlling the control mechanism. If the center point deviation value is greater than or equal to the preset movement threshold, a corresponding movement control command is generated based on the center point deviation value and sent to the camera device for movement control to adjust the center point deviation value so that it is less than or equal to a preset standard threshold, resulting in an adjusted fluoroscopic image of the vascular interventional surgery. This adjusted fluoroscopic image is then sent to the display interface for display. This application can effectively and accurately adjust the position of the camera device, making the display position of interventional instruments in the interventional surgery image easier to observe. Attached Figure Description

[0049] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0050] Figure 1 A flowchart of an embodiment of the vascular interventional surgery image adjustment method according to this application;

[0051] Figure 2 yes Figure 1A flowchart of a specific implementation of step S10;

[0052] Figure 3 yes Figure 1 A flowchart of a specific implementation of step S20;

[0053] Figure 4 yes Figure 1 A flowchart of a specific implementation of step S40;

[0054] Figure 5 yes Figure 4 A flowchart of a specific implementation of step S401;

[0055] Figure 6 This is a schematic diagram of one embodiment of the vascular interventional surgery image adjustment device according to this application;

[0056] Figure 7 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0058] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0059] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0060] refer to Figure 1 A flowchart of an embodiment of the vascular interventional surgery image adjustment method according to this application is shown. The vascular interventional surgery image adjustment method includes the following steps:

[0061] Step S10: Obtain fluoroscopic images of vascular interventional surgery captured in real time by the camera device, and input the fluoroscopic images of vascular interventional surgery into a pre-trained target detection model to identify the instrument location area in the fluoroscopic images of vascular interventional surgery.

[0062] In this embodiment, the imaging equipment includes an angiography device for capturing images of the patient's blood vessels and a hospital bed for adjusting the patient's position. The fluoroscopic image of the vascular interventional surgery refers to the X-ray image captured in real time by the angiography device. The instrument location area refers to the image area containing the tip of the surgical interventional instrument, mainly used to show the specific location of the surgical interventional instrument in the image. The surgical interventional instrument includes a catheter and a guidewire. A pre-trained target detection model is used to identify the instrument location area in the fluoroscopic image of the vascular interventional surgery. By inputting the real-time acquired fluoroscopic image of the vascular interventional surgery into the pre-trained target detection model, the instrument location area where the instrument is located in the fluoroscopic image of the vascular interventional surgery is identified. In this embodiment, the instrument location area is marked and displayed with a rectangle of predetermined length and width.

[0063] Step S20: Obtain a preset instrument definition area, and calculate the center point deviation value between the first center point corresponding to the instrument position area and the second center point corresponding to the instrument definition area;

[0064] In this embodiment, the instrument-defined area refers to the area where surgical instruments are safely displayed in the fluoroscopic image of the interventional procedure. When the surgical instrument is within the instrument-defined area, it indicates that the surgical instrument is displayed in a safe position in the fluoroscopic image of the interventional procedure, and no adjustment of the camera equipment is required. When the surgical instrument is outside the instrument-defined area, it indicates that the surgical instrument is currently in a dangerous position in the fluoroscopic image of the interventional procedure, and the camera equipment needs to be adjusted to place the surgical instrument within the instrument-defined area. The center point deviation value is calculated based on the coordinate information of the first center point and the coordinate information of the second center point in the fluoroscopic image of the interventional procedure. The coordinate system corresponding to the above coordinate information is a preset coordinate system in the fluoroscopic image of the interventional procedure, which is used to calibrate the coordinates of each point in the fluoroscopic image of the interventional procedure.

[0065] Step S30: Determine whether the center point deviation value is greater than or equal to a preset movement threshold;

[0066] In this embodiment, since the preset movement threshold corresponds to the bounding box of a certain area in the fluoroscopic image of vascular interventional surgery, the preset movement threshold includes multiple values. After obtaining the center point deviation value, it is also necessary to determine the preset movement threshold corresponding to the center point deviation value based on the coordinate information corresponding to the center point deviation value, and use the preset movement threshold to compare and judge with the center point deviation value.

[0067] Step S40: If the center point deviation value is greater than or equal to the preset movement threshold, a corresponding movement control command is generated based on the center point deviation value and sent to the camera device for movement control to adjust the center point deviation value so that the center point deviation value is less than or equal to the preset standard threshold, thereby obtaining an adjusted vascular interventional surgery fluoroscopy image, and sending the adjusted vascular interventional surgery fluoroscopy image to the display interface for display.

[0068] In this embodiment, the imaging equipment includes an angiography device for capturing images of the patient's blood vessels and a hospital bed for adjusting the patient's position. The angiography device and the hospital bed can move according to movement control commands sent by the system to adjust the angle and position of image capture. By controlling the movement of the imaging equipment, the capturing range of the fluoroscopic image for the vascular interventional surgery is adjusted, thus forming an adjusted fluoroscopic image for the vascular interventional surgery. In this embodiment, the display interface can be a main control display screen for controlling surgical instruments. The adjusted fluoroscopic image for the vascular interventional surgery is displayed in real time within the display area of ​​the main control display screen.

[0069] This application acquires real-time fluoroscopic images of vascular interventional surgery captured by a camera device, inputs these images into a pre-trained target detection model, and thus accurately identifies the instrument location region in the fluoroscopic image. By acquiring a preset instrument-defined region and calculating the center point deviation between the first center point and the second center point corresponding to the instrument location region, the degree of offset between the first and second center points can be effectively obtained. By determining whether the center point deviation value is greater than or equal to a preset movement threshold, it is determined whether the current conditions meet the requirements for controlling the control mechanism. If the center point deviation value is greater than or equal to the preset movement threshold, a corresponding movement control command is generated based on the center point deviation value and sent to the camera device for movement control to adjust the center point deviation value so that it is less than or equal to a preset standard threshold, resulting in an adjusted fluoroscopic image of the vascular interventional surgery. This adjusted fluoroscopic image is then sent to the display interface for display. This application can effectively and accurately adjust the position of the camera device, making the display position of the interventional instruments in the interventional surgery image easier to observe.

[0070] In an optional embodiment of this example, the following steps are included before step S10:

[0071] Acquire fluoroscopic images of sample vascular interventional surgery, and determine the instrument sample target and instrument sample target region in the sample vascular interventional surgery fluoroscopic images according to a preset target detection algorithm;

[0072] In this embodiment, the preset target detection algorithm is a YOLO-based target detection algorithm. This algorithm can effectively identify target objects in an image and their corresponding target regions, thus facilitating the effective labeling of target objects in the image. Specifically, the YOLO target detection algorithm uses a convolutional neural network for target detection. It divides the image into multiple convolutional mesh images, then performs feature recognition on the convolutional mesh images, and uses the images containing the features as the images of detected targets. After recognizing all the images of detected targets, the target objects are determined based on these images, and then bounding boxes representing the edges of the target regions are generated based on the target objects.

[0073] The instrument sample target and the instrument sample target region in the fluoroscopic image of the sample vascular interventional surgery are marked to obtain a marked sample vascular interventional surgery fluoroscopic image;

[0074] In this embodiment, marking refers to displaying the instrument sample target and the instrument sample target area in the fluoroscopic image of vascular interventional surgery in the form of solid lines or dashed lines. By marking the instrument sample target and the instrument sample target area, it is convenient for the operator to view them.

[0075] Based on the spatial coordinate system of the fluoroscopic image of the labeled vascular interventional surgery, key regional information of the target region of the instrument sample is obtained;

[0076] In this embodiment, the key information of the region includes the coordinates of the center point of the target region of the instrument sample, as well as the height and width of the target region of the instrument sample. In this embodiment, the above-mentioned region is displayed as a rectangular frame in the image.

[0077] The optical flow field of the region is obtained by calculating the image of the target area of ​​the instrument sample according to the preset motion prediction algorithm;

[0078] In this embodiment, the preset motion prediction algorithm adopts the robust local optical flow algorithm. The robust local optical flow algorithm can effectively predict the motion direction of objects in an image, forming a regional optical flow field that displays the motion direction of the object. In this embodiment, the motion direction of the object refers to the motion direction of the surgical instrument, specifically the motion direction of the tip of the surgical instrument and the part near the tip. The robust local optical flow algorithm calculates and analyzes the pixel intensity of the same object in two consecutive frames of images based on an illumination model. The illumination model is I(x, y, t) + m*I(x, y, t) + c = I(x + u, y + v, t + 1), where x and y are pixel coordinates, t is the image frame number, I(x, y, t) defines the pixel intensity of the object at frame t, and m and c are illumination model parameters. By calculating and analyzing the pixel intensity changes of objects in the image using the robust local optical flow algorithm, robust object optical flow motion information is obtained to effectively determine the motion direction of objects in the image.

[0079] The labeled sample vascular interventional surgery fluoroscopic image, the key information of the region, and the optical flow field of the region are input into the machine learning model for model training to obtain the target detection model.

[0080] In this embodiment, after model training, in order to detect whether the model's prediction effect has met expectations, the trained model also needs to be evaluated. This is done by inputting multiple sets of test data into the trained model, outputting the prediction results, and then comparing the results with the corresponding test data to determine whether the trained model's prediction is accurate. When the error between the model's prediction results and the corresponding test data exceeds a preset standard threshold, the parameter weights in the labeled sample vascular interventional surgery fluoroscopy image, regional key information, and regional optical flow field need to be adjusted to retrain the model until the error between the model's prediction results and the corresponding test data is less than the preset standard threshold, thereby obtaining the target detection model.

[0081] In an optional embodiment of this example, the step of obtaining the key regional information of the target region of the instrument sample based on the spatial coordinate system of the fluoroscopic image of the labeled vascular interventional surgery specifically includes:

[0082] Determine the center point of the target region of the instrument sample;

[0083] In this embodiment, the target area of ​​the instrument sample is displayed as a rectangular bounding box in the image. The center point of the target area of ​​the instrument sample is determined by obtaining the edge points of the four corners of the rectangular bounding box and the length and width of the bounding box.

[0084] Based on the spatial coordinate system of the fluoroscopic image of the labeled vascular interventional surgery, the coordinates of the center point and edge points of the target region of the instrument sample are obtained;

[0085] In this embodiment, the coordinates of the region center point and the region edge point are calibrated by using a pre-established spatial coordinate system in the fluoroscopic image of the sample vascular intervention surgery, thereby obtaining the coordinates of the region center point and the region edge point.

[0086] Calculate the length and width of the region based on the coordinates of its edge points.

[0087] In this embodiment, the edge points of the region refer to the four corner points of the region. When calculating the length and width of the region, the region width is calculated using the edge point coordinates with the same value on the x-axis, and the region length is calculated using the edge point coordinates with the same value on the y-axis. The region length refers to the length of the longer side of the target region of the instrument sample, and the region width refers to the length of the shorter side of the target region of the instrument sample.

[0088] The length of the region, the width of the region, and the coordinates of the center point of the region are used as the key information of the region.

[0089] Continue to refer to Figure 2 The flowchart illustrates a specific embodiment of step S10, which includes the following steps:

[0090] Step S101: Obtain the current time information, and search for the corresponding real-time image data in the image storage database of the camera device according to the current time information;

[0091] In this embodiment, the current time information refers to the time currently displayed by the system. The image data includes the vascular fluoroscopy image captured by the camera device and the capture time information. The system searches for data in the image storage database of the camera device based on the current time information to find the image whose capture time information is closest to the current time information.

[0092] Step S102: Extract the real-time image data as the fluoroscopic image of the vascular interventional surgery.

[0093] In this embodiment, the extracted fluoroscopic images of vascular interventional surgery always correspond to the current moment required to ensure the real-time image adjustment of the system. Therefore, when real-time image data is stored in the database, it can be sorted according to time order to generate an image order sorting table. When an image is acquired each time, the image ranked last in the image order sorting table can be directly extracted as the fluoroscopic image of vascular interventional surgery.

[0094] Continue to refer to Figure 3 The flowchart of a specific embodiment of step S20 is shown, which includes the following steps:

[0095] Step S201: Extract the preset instrument definition area from the database;

[0096] In this embodiment, the instrument definition area is pre-stored in the database. The instrument definition area corresponds to the image display definition range set by the system. This definition range can be customized by the operator according to the actual situation, or it can be set by default by the system.

[0097] Step S202: Determine the center point of the first region of the instrument location area and the center point of the second region of the instrument defined area, so as to obtain the first coordinate information of the center point of the first region and the second coordinate information of the center point of the second region;

[0098] In this embodiment, the first region center point and the second region center point refer to the region center point of the instrument location area and the region center point of the instrument defined area, respectively. After selecting the first region center point and the second region center point, the first coordinate information and the second coordinate information are obtained by acquiring the coordinate information of the first region center point and the second region center point.

[0099] Step S203: Calculate the difference between the first coordinate information and the second coordinate information as the center point deviation value.

[0100] In this embodiment, the first coordinate information includes the x-axis and y-axis coordinates of the center point of the first region, and the second coordinate information includes the x-axis and y-axis coordinates of the center point of the second region. When calculating the center point deviation value, the first coordinate information should be used as the minuend, and the second coordinate information should be used as the subtrahend to obtain the center point deviation value. In this embodiment, the preset movement threshold corresponds to the center point deviation value and is set according to the region edge from the center point of the second region to the instrument's defined region. Therefore, it includes multiple values. When comparing the center point deviation value with the preset movement threshold, the preset movement threshold corresponding to the x-axis coordinate value of the center point deviation value can be determined first, that is, the preset movement threshold with the same x-axis coordinate value. Then, the absolute value of the y-axis coordinate of the preset movement threshold is compared with the absolute value of the y-axis coordinate of the center point deviation value. If the absolute value of the y-axis coordinate of the center point deviation value is greater than or equal to the absolute value of the y-axis coordinate of the preset movement threshold, it indicates that the center point of the instrument position region has deviated from the defined range of the instrument's defined region. If the absolute value of the y-axis coordinate of the center point deviation value is less than the absolute value of the y-axis coordinate of the preset movement threshold, it indicates that the center point of the instrument position region has not deviated from the defined range of the instrument's defined region. For example, if the center point deviation is (10, 15) and the preset movement thresholds are (10, 20) and (10, -20), then the absolute value of the y-axis coordinate of the center point deviation is 15, and the absolute value of the y-axis coordinate of the preset movement threshold is 20. The absolute value of the y-axis coordinate of the center point deviation is less than the absolute value of the y-axis coordinate of the preset movement threshold, indicating that the center point of the instrument position area has not deviated from the defined range of the instrument's defined area. If the center point deviation is (10, 25) and the preset movement thresholds are (10, 20) and (10, -20), then the absolute value of the y-axis coordinate of the center point deviation is 25, and the absolute value of the y-axis coordinate of the preset movement threshold is 20. The absolute value of the y-axis coordinate of the center point deviation is greater than or equal to the absolute value of the y-axis coordinate of the preset movement threshold, indicating that the center point of the instrument position area has deviated from the defined range of the instrument's defined area.

[0101] Simultaneously, during the above comparison, if no corresponding preset movement threshold is found among all preset movement thresholds for the x-axis coordinate value of the center point deviation, it indicates that the center point of the instrument position area deviates from the defined range of the instrument's restricted area. This allows for a quick comparison between the center point deviation value and the preset movement threshold. Alternatively, the comparison process can begin by determining the preset movement threshold corresponding to the y-axis coordinate value of the center point deviation value, and then comparing the absolute value of the x-axis coordinate of the preset movement threshold with the absolute value of the x-axis coordinate of the center point deviation value. The preset movement threshold can be set based on the distance relationship between the center point and the edge of the instrument's restricted range, or it can be customized according to actual conditions to obtain a more precise instrument restricted range.

[0102] Continue to refer to Figure 4The flowchart of a specific embodiment of step S40 is shown, which includes the following steps:

[0103] Step S401: Obtain a preset distance conversion coefficient, and calculate the movement distance information based on the distance conversion coefficient and the center point deviation value;

[0104] In this embodiment, the distance conversion coefficient refers to the proportionality coefficient used to convert the change in image spatial pixel coordinates corresponding to the center point deviation value to the distance the surgical device moves in physical space. The actual distance the surgical device moves in physical space is calculated using this proportionality coefficient and the center point deviation value to obtain the movement distance information.

[0105] Step S402: Generate corresponding movement control commands based on the movement distance information;

[0106] In this embodiment, the movement distance information includes x-axis movement information and y-axis movement information. Both x-axis movement information and y-axis movement information include movement position, movement distance, movement direction, and movement speed. Corresponding movement control commands are generated based on the x-axis movement information and y-axis movement information.

[0107] Step S403: The motion control command is sent to the camera device, and the camera device moves according to the motion control command.

[0108] In this embodiment, the movement control command includes a first control command to control the camera device to move in the left-right direction and a second control command to control the camera device to move in the front-back direction. The first control command corresponds to the x-axis movement information, and the second control command corresponds to the y-axis control information. The left-right and front-back directions correspond to the four spatial directions in the horizontal plane. After receiving the first and second control commands, the camera device controls the camera device to move according to the corresponding movement position, movement distance, movement direction, and movement speed.

[0109] Continue to refer to Figure 5 The flowchart of a specific embodiment of step S401 is shown, which includes the following steps:

[0110] Step S4011: Obtain the coordinate object corresponding to the center point deviation value;

[0111] In this embodiment, the coordinate objects corresponding to the center point deviation value include x-axis coordinate objects and y-axis coordinate objects. The coordinate objects are determined by querying whether the x-axis coordinate value and y-axis coordinate value in the center point deviation value are empty.

[0112] Step S4012: Obtain the corresponding first movement distance calculation formula and second movement distance calculation formula based on the coordinate object;

[0113] In this embodiment, the first and second movement distance calculation formulas are pre-stored in the database, and can be called according to the coordinate object.

[0114] Step S4013: Calculate the first moving distance information and the second moving distance information according to the first moving distance calculation formula and the second moving distance calculation formula, wherein the first moving distance calculation formula is: first moving distance = center point deviation value * X-axis distance conversion coefficient, and the second moving distance calculation formula is: second moving distance = center point deviation value * Y-axis distance conversion coefficient;

[0115] In this embodiment, the formula for calculating the first moving distance is M. x =P x *S x , of which M x For the first movement information, P x S is the deviation value of the x-axis center point. x The x-axis distance conversion factor is used; the formula for calculating the second movement distance is M. y =P y *S y , of which M y For the second movement information, P y S is the deviation value of the y-axis center point. y This is the y-axis distance conversion factor.

[0116] Step S4014: Use the first movement distance information and the second movement distance information as the movement distance information.

[0117] In this embodiment, the movement distance information always includes first movement distance information and second movement distance information. After obtaining the movement distance information, it is possible to check whether the values ​​of the first and second movement distance information are empty to determine whether the first and second movement distance information are present. If the first and / or second movement distance information are missing, it is necessary to recalculate according to the above calculation formula to obtain the corresponding first and / or second movement distance information. By setting the above detection steps, it is possible to effectively ensure that the content of the movement distance information is correct and avoid affecting the subsequent generation of movement control commands based on the movement distance information.

[0118] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0119] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0120] Further reference Figure 6 As a response to the above Figure 1 The implementation of the method shown in this application provides an embodiment of a vascular interventional surgery image adjustment device, which is similar to... Figure 1 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0121] like Figure 6 As shown, the vascular interventional surgery image adjustment device 6 described in this embodiment includes: a region recognition module 501, a deviation calculation module 502, a judgment module 503, and an image adjustment module 504. Wherein:

[0122] The region recognition module 501 is used to acquire real-time fluoroscopic images of vascular interventional surgery captured by the camera device, input the fluoroscopic images of vascular interventional surgery into a pre-trained target detection model, and identify the instrument location region in the fluoroscopic images of vascular interventional surgery.

[0123] The deviation calculation module 502 is used to obtain a preset instrument limitation area and calculate the center point deviation value between the first center point corresponding to the instrument position area and the second center point corresponding to the instrument limitation area.

[0124] The judgment module 503 is used to determine whether the center point deviation value is greater than or equal to a preset movement threshold.

[0125] The image adjustment module 504 is used to generate a corresponding motion control command based on the center point deviation value and send it to the camera device for motion control if the center point deviation value is greater than or equal to the preset motion threshold, so as to adjust the center point deviation value so that the center point deviation value is less than or equal to the preset standard threshold, thereby obtaining an adjusted vascular interventional surgery fluoroscopy image, and sending the adjusted vascular interventional surgery fluoroscopy image to the display interface for display.

[0126] This embodiment, by setting up a device module corresponding to the vascular interventional surgery image adjustment method, can acquire vascular interventional surgery fluoroscopic images through the region recognition module 501, input the vascular interventional surgery fluoroscopic images into a pre-trained target detection model, thereby accurately identifying the instrument position region in the vascular interventional surgery fluoroscopic images; obtain a preset instrument limitation region through the deviation calculation module 502, and calculate the center point deviation value between the first center point corresponding to the instrument position region and the second center point corresponding to the instrument limitation region, thereby effectively obtaining the offset degree of the first center point and the second center point; determine whether the center point deviation value is greater than or equal to a preset movement threshold through the judgment module 503, thereby determining whether the current conditions meet the conditions for controlling the control mechanism; if the center point deviation value is greater than or equal to the preset movement threshold, the image adjustment module 504 generates a corresponding movement control command based on the center point deviation value and sends it to the camera device for movement control to adjust the center point deviation value so that the center point deviation value is less than or equal to the preset standard threshold, thereby obtaining an adjusted vascular interventional surgery fluoroscopic image, and sending the adjusted vascular interventional surgery fluoroscopic image to the display interface for display. This embodiment can effectively and accurately adjust the position of the camera device, making it easier to observe the display position of interventional instruments in interventional surgical images.

[0127] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 7 , Figure 7 This is a basic structural block diagram of the computer device in this embodiment.

[0128] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected via a system bus. It should be noted that only the computer device 6 with components 61-63 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0129] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0130] The memory 61 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 61 may be an internal storage unit of the computer device 6, such as the hard disk or memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 6. Of course, the memory 61 may also include both the internal storage unit and its external storage device of the computer device 6. In this embodiment, the memory 61 is typically used to store the operating system and various application software installed on the computer device 6, such as the program code of the vascular interventional surgery image adjustment method. In addition, the memory 61 can also be used to temporarily store various types of data that have been output or will be output.

[0131] In some embodiments, the processor 62 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 62 is typically used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run program code stored in the memory 61 or process data, for example, to run program code for the vascular interventional surgery image adjustment method.

[0132] The network interface 63 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 6 and other electronic devices.

[0133] This embodiment, by setting up computer equipment corresponding to the vascular interventional surgery image adjustment method, can effectively and accurately adjust the position of the camera equipment, making the display position of interventional instruments in the interventional surgery image easier to observe.

[0134] This application also provides another embodiment, namely, a computer-readable storage medium storing a vascular interventional surgery image adjustment program, which can be executed by at least one processor to perform the steps of the vascular interventional surgery image adjustment method as described above.

[0135] This embodiment, by setting a computer-readable storage medium corresponding to the vascular interventional surgery image adjustment method, can effectively and accurately adjust the position of the camera device, making the display position of the interventional instruments in the interventional surgery image easier to observe.

[0136] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0137] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A method for adjusting images in vascular interventional surgery, characterized in that, Includes the following steps: Acquire real-time fluoroscopic images of vascular interventional surgery captured by a camera device, input the fluoroscopic images of vascular interventional surgery into a pre-trained target detection model, and identify the instrument location region in the fluoroscopic images of vascular interventional surgery; Obtain a preset instrument definition area, and calculate the center point deviation value between the first center point corresponding to the instrument position area and the second center point corresponding to the instrument definition area; Determine whether the center point deviation value is greater than or equal to a preset movement threshold; If the center point deviation value is greater than or equal to the preset movement threshold, a corresponding movement control command is generated based on the center point deviation value and sent to the camera device for movement control to adjust the center point deviation value so that the center point deviation value is less than or equal to the preset standard threshold, thereby obtaining an adjusted vascular interventional surgery fluoroscopy image, and sending the adjusted vascular interventional surgery fluoroscopy image to the display interface for display. Before the steps of acquiring real-time fluoroscopic images of vascular interventional surgery captured by the camera device, inputting the fluoroscopic images of vascular interventional surgery into a pre-trained target detection model, and identifying the instrument location region in the fluoroscopic images of vascular interventional surgery, the following steps are also included: Acquire fluoroscopic images of sample vascular interventional surgery, and determine the instrument sample target and instrument sample target region in the sample vascular interventional surgery fluoroscopic images according to a preset target detection algorithm; The instrument sample target and the instrument sample target region in the fluoroscopic image of the sample vascular interventional surgery are marked to obtain a marked sample vascular interventional surgery fluoroscopic image; Based on the spatial coordinate system of the fluoroscopic image of the labeled vascular interventional surgery, key regional information of the target region of the instrument sample is obtained; The optical flow field of the region is obtained by calculating the image of the target area of ​​the instrument sample according to the preset motion prediction algorithm; The labeled sample vascular interventional surgery fluoroscopic image, the key information of the region, and the optical flow field of the region are input into the machine learning model for model training to obtain the target detection model.

2. The method for adjusting vascular interventional surgical images according to claim 1, characterized in that, The step of obtaining key regional information of the target region of the instrument sample based on the spatial coordinate system of the fluoroscopic image of the labeled vascular interventional surgery specifically includes: Determine the center point of the target region of the instrument sample; Based on the spatial coordinate system of the fluoroscopic image of the labeled vascular interventional surgery, the coordinates of the center point and edge points of the target region of the instrument sample are obtained; Calculate the length and width of the region based on the coordinates of the edge points of the region; The length of the region, the width of the region, and the coordinates of the center point of the region are used as key information of the region.

3. The blood vessel intervention procedure image adjustment method of claim 1, wherein, The step of acquiring real-time fluoroscopic images of vascular interventional surgery captured by the camera device specifically includes: Obtain the current time information, and search for the corresponding real-time image data in the image storage database of the camera device based on the current time information; The real-time image data is extracted as the fluoroscopic image of the vascular interventional surgery.

4. The blood vessel intervention procedure image adjustment method of claim 1, wherein, The step of obtaining a preset instrument definition area and calculating the center point deviation between the first center point corresponding to the instrument position area and the second center point corresponding to the instrument definition area specifically includes: Extract the preset instrument definition area from the database; Determine the center point of a first region of the instrument location area and the center point of a second region of the instrument defined area, so as to obtain the first coordinate information of the center point of the first region and the second coordinate information of the center point of the second region. The difference between the first coordinate information and the second coordinate information is calculated as the center point deviation value.

5. The method of claim 1, wherein, The step of generating a corresponding motion control command based on the center point deviation value and sending it to the camera device for motion control specifically includes: Obtain a preset distance conversion coefficient, and calculate the movement distance information based on the distance conversion coefficient and the center point deviation value; Generate corresponding movement control commands based on the movement distance information; The motion control command is sent to the camera device, and the camera device moves according to the motion control command.

6. The blood vessel intervention procedure image adjustment method of claim 5, wherein, The distance conversion coefficients include X-axis distance conversion coefficients and Y-axis distance conversion coefficients. The step of calculating the movement distance information based on the distance conversion coefficients and the center point deviation value specifically includes: Obtain the coordinate object corresponding to the center point deviation value; Obtain the corresponding first movement distance calculation formula and second movement distance calculation formula based on the coordinate object; The first moving distance information and the second moving distance information are calculated according to the first moving distance calculation formula and the second moving distance calculation formula, wherein the first moving distance calculation formula is: first moving distance = center point deviation value * X-axis distance conversion coefficient, and the second moving distance calculation formula is: second moving distance = center point deviation value * Y-axis distance conversion coefficient; The first movement distance information and the second movement distance information are used as the movement distance information.

7. A blood vessel intervention operation image adjustment apparatus characterized by comprising: include: The region recognition module is used to acquire real-time fluoroscopic images of vascular interventional surgery captured by the camera device, input the fluoroscopic images of vascular interventional surgery into a pre-trained target detection model, and identify the instrument location region in the fluoroscopic images of vascular interventional surgery. The deviation calculation module is used to obtain a preset instrument limitation area and calculate the center point deviation value between the first center point corresponding to the instrument position area and the second center point corresponding to the instrument limitation area. The judgment module is used to determine whether the center point deviation value is greater than or equal to a preset movement threshold; The image adjustment module is used to generate a corresponding motion control command based on the center point deviation value and send it to the camera device for motion control if the center point deviation value is greater than or equal to the preset motion threshold, so as to adjust the center point deviation value so that the center point deviation value is less than or equal to the preset standard threshold, thereby obtaining an adjusted vascular interventional surgery fluoroscopic image, and sending the adjusted vascular interventional surgery fluoroscopic image to the display interface for display. The vascular interventional surgery image adjustment device also includes: The target recognition module is used to acquire fluoroscopic images of sample vascular interventional surgery and determine the instrument sample target and instrument sample target region in the sample vascular interventional surgery fluoroscopic images according to a preset target detection algorithm. The target marking module is used to mark the instrument sample target and the instrument sample target region in the fluoroscopic image of the sample vascular interventional surgery to obtain the marked sample vascular interventional surgery fluoroscopic image; The key information acquisition module is used to acquire regional key information of the target area of ​​the instrument sample based on the spatial coordinate system of the fluoroscopic image of the vascular interventional surgery of the marked sample; The optical flow field calculation module is used to calculate the regional optical flow field by analyzing the image of the target area of ​​the instrument sample according to a preset motion prediction algorithm. The model training module is used to input the fluoroscopic image of the labeled sample vascular interventional surgery, the key information of the region, and the optical flow field of the region into the machine learning model for model training, so as to obtain the target detection model.

8. A computer device, comprising: The method includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the vascular interventional surgery image adjustment method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions that, when executed by a processor, implement the steps of the vascular interventional surgery image adjustment method as described in any one of claims 1 to 6.

Images