A carotid artery missegmentation processing method and device for robotic autonomous scanning

Abstract

The application discloses a carotid artery mis-segmentation processing method and device for robot autonomous scanning, and the method comprises the following steps: calculating an average height; controlling the ultrasonic probe to start moving from the starting point of longitudinal scanning, and acquiring a current ultrasonic image in real time; calculating the height mean value and the height standard deviation of the longitudinal profile of the blood vessel; judging whether the longitudinal profile of the blood vessel is a jugular vein; if yes, calculating the moving distance along the X-axis direction of the tool coordinate system at the next moment and the exertion strength at the next moment; otherwise, taking the preset step length and the preset strength as the moving distance and the exertion strength at the next moment respectively, determining the moving direction at the next moment based on the trend of the longitudinal profile of the blood vessel; controlling the ultrasonic probe to move to the position at the next moment, and re-executing the above process until the ultrasonic probe moves to the end point of the longitudinal scanning. The method effectively reduces the adverse effect of carotid artery mis-segmentation on scanning, and ensures that the carotid artery can be continuously and stably tracked.

Description

Technical Field

[0001] This invention relates to the field of ultrasound robotics, and in particular to a method and apparatus for handling missegmentation of the carotid artery during autonomous robotic scanning. Background Technology

[0002] During autonomous ultrasound robotic scanning, image detection models are needed to segment organ contours in ultrasound images to guide the robot in completing the scanning task. However, due to artifacts, low tissue contrast, and high similarity between adjacent organs in ultrasound imaging, image detection models inevitably suffer from missegmentation, thus affecting the efficiency and stability of autonomous scanning. In autonomous carotid artery scanning, veins and arteries have significant similarities in morphology and echogenicity (especially in longitudinal sections), making it difficult for image detection models to distinguish them correctly. This often leads to the robot following the wrong blood vessel, impacting overall scanning efficiency and imaging quality.

[0003] In the research and application of autonomous ultrasound robot scanning systems, the image detection model undertakes the core visual perception task. It identifies and segments organ contours in real-time ultrasound images, providing crucial guidance for the robot's motion planning and control. However, due to artifact interference, low tissue contrast, and high similarity between adjacent organs in ultrasound imaging, the image detection model inevitably suffers from missegmentation, thus affecting the efficiency and stability of the robot's autonomous scanning.

[0004] In autonomous carotid artery scanning, the carotid artery and the adjacent jugular vein exhibit high morphological similarity in longitudinal section, both appearing as elongated, anechoic or hypoechoic tubular structures with remarkably similar linear echo characteristics of their walls. This anatomical and imaging similarity makes it difficult for even well-trained image detection models to avoid confusion and missegmentation in consecutive frame sequences. If the model incorrectly identifies the jugular vein as the carotid artery, the autonomous scanning robot will plan and control its path based on this erroneous information, leading it to follow the wrong vessel. This fundamental error triggers a series of adverse reactions: the robot may perform ineffective scanning along the jugular vein path, wasting scanning time and reducing efficiency; more seriously, it may miss complete imaging of the carotid artery, resulting in incomplete or completely erroneous diagnostic image sequences. Furthermore, during error tracking, in order to maintain the current "incorrect" vascular centerline, the robot may perform abnormal motion posture adjustments and force control. These non-optimized control commands further affect the stability of the coupling between the probe and the skin, thereby degrading the imaging quality and ultimately seriously questioning the reliability and clinical applicability of the entire autonomous scanning process.

[0005] Therefore, overcoming the inherent limitations of image detection models and improving their ability to distinguish between the carotid artery and jugular vein in complex real-world scenarios has become a key technological bottleneck in promoting the clinical application of ultrasound scanning robots. Summary of the Invention

[0006] To effectively reduce the adverse effects of carotid artery missegmentation on scanning and ensure continuous and stable tracking of the carotid artery during autonomous scanning, this invention provides a carotid artery missegmentation processing method and device for robotic autonomous scanning, which can effectively improve the overall scanning efficiency.

[0007] In a first aspect, embodiments of the present invention provide a method for handling missegmentation of the carotid artery during autonomous robotic scanning, comprising:

[0008] The ultrasound probe is controlled to move from the starting point of the transverse scan. The image detection model is used to identify the transverse contour of the carotid artery in each frame of ultrasound image acquired in real time, and the height of the transverse contour of the carotid artery is calculated until the ultrasound probe moves to the end point of the transverse scan. The average height is calculated based on the height of the transverse contour of each carotid artery.

[0009] The ultrasound probe is controlled to move from the starting point of the longitudinal scan and to acquire the current ultrasound image in real time.

[0010] The image detection model is used to identify the longitudinal profile of blood vessels in the current ultrasound image, and the mean height and standard deviation of the longitudinal profile of the blood vessels are calculated.

[0011] Based on the mean height, the standard deviation of height, the average height, and the first threshold set, determine whether the longitudinal profile of the blood vessel is the jugular vein;

[0012] If so, the moving distance along the X-axis of the tool coordinate system at the next moment is calculated based on the mean height, the standard deviation of the height, the average height, and the second threshold set; and the applied force at the next moment is calculated based on the mean height, the standard deviation of the height, the average height, the first threshold set, and the third threshold set.

[0013] Otherwise, the preset step length and preset force are used as the moving distance and applied force at the next moment, respectively, and the moving direction at the next moment is determined based on the direction of the longitudinal profile of the blood vessel.

[0014] Based on the moving distance, applied force, and moving direction at the next moment, the ultrasound probe is controlled to move to the position at the next moment. Based on the acquired new ultrasound image, the above judgment and the calculation process of moving distance, applied force, and moving direction are repeated until the ultrasound probe moves to the end point of the longitudinal scan.

[0015] Optionally, the controlled ultrasound probe moves from the starting point of the transverse scan, uses an image detection model to identify the transverse contour of the carotid artery in each frame of the real-time acquired ultrasound image, and calculates the height of the transverse contour of the carotid artery, until the ultrasound probe moves to the end point of the transverse scan. Based on the height of the transverse contour of each carotid artery, the average height is calculated, including:

[0016] The ultrasound probe is controlled to move from the starting point of the transverse scan. Based on the real-time acquired ultrasound images, the transverse contour of the blood vessels is identified using a preset image detection model.

[0017] If the cross-sectional profile of a blood vessel is identified, the cross-sectional profile of the blood vessel is determined to be the cross-sectional profile of the carotid artery, and the height of the cross-sectional profile of the carotid artery is obtained.

[0018] If the cross-sectional contours of two blood vessels are identified, the cross-sectional contour of the carotid artery and its height are determined based on the center point, width, and height corresponding to the cross-sectional contours of the two blood vessels.

[0019] During the control of the ultrasound probe movement, based on the new ultrasound images acquired in real time, the process of calculating the height of the transverse profile of the carotid artery is repeated until the ultrasound probe moves to the end of the transverse scan, and the average height is calculated based on the height of the transverse profile of each carotid artery.

[0020] Optionally, determining the cross-sectional profile of the carotid artery and its height based on the center point, width, and height corresponding to the cross-sectional profiles of the two determined blood vessels includes:

[0021] Based on the width and height corresponding to the cross-sectional contours of the two blood vessels, the arithmetic mean of the sum of the width values ​​and the sum of the height values ​​of the cross-sectional contours of the two blood vessels is calculated.

[0022] The corresponding contour area is calculated based on the width and height of the cross-sectional contour of each blood vessel;

[0023] For the cross-sectional contours of two blood vessels located on the left side of the human body, if the difference between the x-coordinate of the center point of the cross-sectional contour of the blood vessel with the larger contour area and the x-coordinate of the center point of the cross-sectional contour of the blood vessel with the smaller contour area is greater than the arithmetic mean, then the cross-sectional contour of the blood vessel with the smaller contour area is the cross-sectional contour of the carotid artery; otherwise, the cross-sectional contour of the blood vessel with the larger contour area is the cross-sectional contour of the carotid artery.

[0024] For the cross-sectional contours of two blood vessels located on the right side of the human body, if the difference between the x-coordinate of the center point of the cross-sectional contour of the blood vessel with smaller contour area and the x-coordinate of the center point of the cross-sectional contour of the blood vessel with larger contour area is greater than the arithmetic mean, then the cross-sectional contour of the blood vessel with smaller contour area is the cross-sectional contour of the carotid artery; otherwise, the cross-sectional contour of the blood vessel with larger contour area is the cross-sectional contour of the carotid artery.

[0025] Optionally, the step of using the image detection model to identify the longitudinal profile of blood vessels in the current ultrasound image and calculating the mean height and standard deviation of the longitudinal profile of blood vessels includes:

[0026] Based on the current ultrasound image, the image detection model is used to identify the longitudinal contour of the blood vessel, and the height and width data of the longitudinal contour of the blood vessel are obtained.

[0027] Based on the height and width data, the average height is calculated using the following formula:

[0028]

[0029] in, Indicates the average height; Indicates position Height data at the location; This represents the width data;

[0030] Based on the mean height, the height data, and the width data, the standard deviation of height is calculated using the following formula:

[0031]

[0032] in, Indicates the standard deviation of height.

[0033] Optionally, the first threshold set includes a first standard deviation threshold, a maximum coefficient value, and a minimum coefficient value;

[0034] The step of determining whether the longitudinal profile of the blood vessel is a jugular vein based on the mean height, the standard deviation of the height, the average height, and a first threshold set includes:

[0035] If the height standard deviation is greater than the first standard deviation threshold, and / or if the height mean is greater than the product of the maximum coefficient value and the average height, and / or if the height mean is less than the product of the minimum coefficient value and the average height, then the longitudinal profile of the blood vessel is the jugular vein.

[0036] Optionally, the second threshold set includes the base step size value, the scaling factor of the height difference, the scaling factor of the standard deviation, the step size increment, and the second standard deviation threshold.

[0037] The calculation of the movement distance along the X-axis at the next moment, based on the mean height, the standard deviation of height, the average height, and the second threshold set, includes:

[0038] Based on the base step size, the height difference scaling factor, the standard deviation scaling factor, the second standard deviation threshold, the mean height, the standard deviation of height, the step size increment, and the average height, the moving step size is calculated according to the following formula:

[0039]

[0040] in, Indicates the step size; This represents the basic step size value; The scaling factor represents the height difference; The proportionality coefficient representing the standard deviation; This represents the step size increment; This represents the second standard deviation threshold; This represents the average height;

[0041] Based on the stated step size, the moving distance is calculated using the following formula:

[0042]

[0043] in, Indicates the distance traveled; This indicates the direction of motion along the X-axis of the tool coordinate system.

[0044] Optionally, the third threshold set includes the scaling factor of the minimum average height, the scaling factor of the maximum average height, the scaling factor of the height standard deviation, the expected force of the base, and the maximum force offset;

[0045] The calculation of the applied force at the next moment based on the mean height, the standard deviation of height, the average height, the first threshold set, and the third threshold set includes:

[0046] Based on the average height, the height mean, the scaling factor of the minimum average height, the scaling factor of the maximum average height, the minimum scaling factor, and the maximum scaling factor, the first force offset is calculated according to the following formula:

[0047]

[0048] in, Indicates the first force bias; The scaling factor representing the minimum average height; The scaling factor represents the maximum average height; Indicates the minimum coefficient value; Indicates the maximum coefficient value;

[0049] Based on the height standard deviation, the scaling factor of the height standard deviation, and the first standard deviation threshold, the second force bias is calculated according to the following formula:

[0050]

[0051] in, Indicates the second force bias; The proportionality coefficient representing the standard deviation of height; Indicates the first standard deviation threshold;

[0052] Based on the first force offset, the second force offset, the expected force of the foundation, and the maximum force offset, the applied force at the next moment is calculated according to the following formula:

[0053]

[0054] in, Indicates the application of force; It represents the basic expectation force; This indicates the maximum force offset.

[0055] Secondly, embodiments of the present invention provide a carotid artery missegmentation processing device for autonomous robotic scanning, comprising:

[0056] The transverse scanning movement module is used to control the robot to move from the starting point of the transverse scanning. It uses an image detection model to identify the transverse contour of the carotid artery in each frame of ultrasound image acquired in real time, and calculates the height of the transverse contour of the carotid artery until the ultrasound probe moves to the end point of the transverse scanning. The average height is calculated based on the height of the transverse contour of each carotid artery.

[0057] The image acquisition module is used to control the ultrasound probe to move from the starting point of the longitudinal scan and to acquire the current ultrasound image in real time.

[0058] The first calculation module is used to identify the longitudinal profile of blood vessels in the current ultrasound image using the image detection model, and to calculate the mean height and standard deviation of the longitudinal profile of blood vessels.

[0059] The judgment module is used to determine whether the longitudinal profile of the blood vessel is the jugular vein based on the mean height, the standard deviation of the height, the average height and the first threshold set; if yes, the second calculation module calculates the moving distance and applied force at the next moment; if no, the data acquisition module obtains the moving distance and applied force at the next moment.

[0060] The second calculation module is used to calculate the moving distance along the X-axis of the tool coordinate system at the next moment based on the mean height, the standard deviation of the height, the average height, and the second threshold set; and to calculate the applied force at the next moment based on the mean height, the standard deviation of the height, the average height, the first threshold set, and the third threshold set.

[0061] The data acquisition module is used to determine the movement distance and applied force at the next moment based on the acquired preset step length and preset force, respectively, and to determine the movement direction at the next moment based on the direction of the longitudinal profile of the blood vessel.

[0062] The transverse scanning movement module is used to control the ultrasound probe to move to the position of the next moment based on the moving distance, applied force and moving direction at the next moment, and based on the acquired new ultrasound image, the first calculation module, the judgment module, the second calculation module and the data acquisition module re-execute the corresponding process until the ultrasound probe moves to the end point of the longitudinal scanning.

[0063] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the carotid artery missegmentation processing method for autonomous robot scanning as described in the first aspect.

[0064] Fourthly, embodiments of the present invention provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the carotid artery missegmentation processing method for autonomous robot scanning as described in the first aspect.

[0065] Fifthly, embodiments of the present invention provide a computer program product containing instructions that, when the computer program product is run on a computer device, cause the computer device to perform the carotid artery missegmentation processing method for autonomous robot scanning as described in the first aspect.

[0066] The beneficial effects of the above-mentioned technical solutions provided in the embodiments of the present invention include at least the following:

[0067] This invention provides a method for handling carotid artery missegmentation during robotic autonomous scanning. By calculating the mean and standard deviation of the vessel height and comparing it with the average height established through transverse scanning, the method determines the type of the longitudinal profile of the currently identified vessel. This method does not rely entirely on the recognition accuracy of the image detection model, thus effectively reducing the misidentification rate of the carotid artery. When the vessel is identified as a jugular vein, the applied force is dynamically adjusted. Increasing the applied force flattens the jugular vein to eliminate interference, further improving the recognition ability of the carotid artery. Once the currently identified vessel is confirmed to be a carotid artery, scanning is performed using a preset step size and preset force to obtain a true and clear carotid artery image, providing a reliable basis for clinical diagnosis. Simultaneously, during longitudinal scanning, the type of the vessel's longitudinal profile is continuously determined to ensure continuous and stable tracking of the carotid artery, avoiding the problem of robots tracking the wrong vessel in existing technologies, thereby effectively improving the overall scanning efficiency.

[0068] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0069] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0070] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0071] Figure 1 This is an example diagram of an ultrasonic robot device provided in this embodiment of the invention, which can be applied to a method for handling missegmentation of the carotid artery during autonomous robotic scanning;

[0072] Figure 2 This is a flowchart of a method for handling missegmentation of the carotid artery during autonomous scanning provided in an embodiment of the present invention;

[0073] Figure 3 This is an example diagram of the cross-sectional contour of a blood vessel obtained by cross-sectional scanning in an embodiment of the present invention;

[0074] Figure 4 The following is an example diagram of the segmentation mask provided in an embodiment of the present invention, wherein the left diagram is a segmentation mask of the carotid artery and the right diagram is a segmentation mask of the jugular vein;

[0075] Figure 5 This is a schematic diagram of a carotid artery missegmentation processing device for autonomous robot scanning provided in an embodiment of the present invention. Detailed Implementation

[0076] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0077] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," "outer," "far," "near," "front," and "rear," etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings and are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0078] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0079] First, some nouns or terms that appear in the description of the embodiments of this application shall be interpreted as follows:

[0080] Transverse contour of blood vessels: The contour of blood vessels in ultrasound images identified by the image detection model during transverse scanning of an ultrasound probe. To facilitate differentiation from the blood vessel contours obtained by longitudinal scanning as described below, the blood vessel contours identified by transverse scanning are collectively referred to as transverse contours of blood vessels, including the transverse contours of the carotid artery and the jugular vein.

[0081] Longitudinal profile of blood vessels: During longitudinal scanning of ultrasound probes, the contours of blood vessels in ultrasound images identified based on image detection models are collectively referred to as longitudinal profiles of blood vessels, including the longitudinal profiles of the carotid artery and the jugular vein.

[0082] Example 1

[0083] This embodiment proposes a method for handling carotid artery missegmentation during robotic autonomous scanning. This method can be applied to, for example... Figure 1 The ultrasonic robot device shown may include a robotic arm and a computer. The robotic arm is equipped with an ultrasonic probe for acquiring ultrasonic images. The computer controls the movement of the robotic arm to control the trajectory of the ultrasonic probe, enabling autonomous scanning of the human body. Generally, Figure 1 There are three coordinate systems in the system, with the root of the robotic arm using the world coordinate system (including X). W Y W Z W (Three coordinate axes), the end effector of the robotic arm uses the tool coordinate system (including X). T Y T Z T The ultrasound image acquired by the ultrasound probe has an ultrasound image coordinate system (including X, Y, and E). I Y I Z I (Three coordinate axes). See also Figure 2 The method in this embodiment may specifically include the following steps:

[0084] Step S101: Control the ultrasound probe to move from the starting point of the transverse scan, use the image detection model to identify the transverse contour of the carotid artery in each frame of ultrasound image acquired in real time, and calculate the height of the transverse contour of the carotid artery until the ultrasound probe moves to the end point of the transverse scan, and calculate the average height based on the height of the transverse contour of each carotid artery.

[0085] Step S102: Control the ultrasound probe to move from the starting point of the longitudinal scan and acquire the current ultrasound image in real time;

[0086] Step S103: Use the image detection model to identify the longitudinal profile of blood vessels in the current ultrasound image, and calculate the mean height and standard deviation of the longitudinal profile of blood vessels.

[0087] Step S104: Based on the height mean, height standard deviation, average height and first threshold set, determine whether the longitudinal profile of the blood vessel is the jugular vein; if yes, proceed to step S105; if no, proceed to step S106.

[0088] Step S105: Based on the mean height, standard deviation of height, average height, and second threshold set, calculate the moving distance along the X-axis of the tool coordinate system at the next moment; and based on the mean height, standard deviation of height, average height, first threshold set, and third threshold set, calculate the applied force at the next moment.

[0089] Step S106: Based on the acquired preset step length and preset force, the moving distance and applied force at the next moment are respectively used as the moving distance and applied force at the next moment, and the moving direction at the next moment is determined based on the direction of the longitudinal profile of the blood vessel.

[0090] Step S107: Based on the moving distance, applied force, and moving direction at the next moment, control the ultrasound probe to move to the position at the next moment, and based on the acquired new ultrasound image, repeat the above steps S103-S106 until the ultrasound probe moves to the end point of the longitudinal scan.

[0091] To provide a clearer explanation of the above-mentioned method for handling carotid artery missegmentation during autonomous ultrasound probe scanning, each step will be explained in detail below.

[0092] In step S101 above, the ultrasound probe is controlled to move from the starting point of the transverse scan. The image detection model is used to identify the transverse contour of the carotid artery in each frame of ultrasound image acquired in real time, and the height of the transverse contour of the carotid artery is calculated until the ultrasound probe moves to the end point of the transverse scan. The specific process of calculating the average height based on the height of the transverse contour of each carotid artery may include the following steps:

[0093] Step S1011: Control the ultrasound probe to move from the starting point of the transverse scan, and use the preset image detection model to identify the transverse contour of the blood vessel based on the real-time acquired ultrasound image.

[0094] In step S1011 above, the image detection model can utilize existing deep learning image segmentation models, such as U-Net and DeepLabV3+. The image detection model is pre-trained and can be used to detect ultrasound images, identify blood vessels in the ultrasound images, and segment them to obtain the cross-sectional contours of the blood vessels.

[0095] Step S1012: If a blood vessel's cross-sectional profile is identified, then the cross-sectional profile of the blood vessel is determined to be the cross-sectional profile of the carotid artery, and the height of the cross-sectional profile of the carotid artery is obtained.

[0096] In step S1012 above, if only the cross-sectional contour of one blood vessel is identified, then the cross-sectional contour of that blood vessel is assumed to be the cross-sectional contour of the carotid artery. The ellipse fitting function fitEllipse() in OpenCV can be used to fit the cross-sectional contour of the carotid artery segmented by the image detection model, and the height of the cross-sectional contour of the carotid artery can be calculated. .

[0097] Step S1013: If the cross-sectional contours of two blood vessels are identified, the cross-sectional contour of the carotid artery and the height of the cross-sectional contour of the carotid artery are determined based on the center point, width and height corresponding to the determined cross-sectional contours of the two blood vessels.

[0098] In step S1013 above, during transverse scanning, the jugular vein and carotid artery can be distinguished anatomically. (See [reference needed]). Figure 3 The jugular vein is typically located further outwards in the body. Therefore, when two blood vessels are identified in their cross-sectional contours, the `fitEllipse()` function from OpenCV is used to fit these contours, calculating the parameters of each contour, including the center point. ,width ,high The cross-sectional contour of the blood vessel with the larger contour area is determined based on the comparison of contour areas. and the cross-sectional profile of blood vessels with smaller outline area The jugular vein is identified by determining which blood vessel's cross-sectional profile is closer to the lateral side of the neck. Specifically, determining the cross-sectional profile and height of the carotid artery can include the following steps:

[0099] Step S10131: Based on the width and height corresponding to the cross-sectional contours of the two blood vessels, calculate the arithmetic mean of the sum of the width values ​​and the sum of the height values ​​of the cross-sectional contours of the two blood vessels according to the following formula (1):

[0100]

[0101] In the above formula (1), Represents the arithmetic mean; Represents the cross-sectional outline of a blood vessel The width; Represents the cross-sectional outline of a blood vessel The width; Represents the cross-sectional outline of a blood vessel Height; Represents the cross-sectional outline of a blood vessel The height.

[0102] Step S10132: Calculate the corresponding contour area based on the width and height of the cross-sectional contour of each blood vessel;

[0103] Step S10133: For the cross-sectional contours of two blood vessels located on the left side of the human body, if the difference between the x-coordinate of the center point of the cross-sectional contour of the blood vessel with the larger contour area and the x-coordinate of the center point of the cross-sectional contour of the blood vessel with the smaller contour area is greater than the arithmetic mean, that is... This indicates that the cross-sectional profile of blood vessels with larger outline areas is closer to the outer side of the neck. This is the cross-sectional outline of the jugular vein, a cross-sectional outline of a vessel with a smaller outline area. The cross-sectional outline of the carotid artery is used; otherwise, the cross-sectional outline of the vessel with a larger outline area is used as the cross-sectional outline of the carotid artery.

[0104] Step S10134: For the cross-sectional contours of two blood vessels located on the right side of the human body, if the difference between the x-coordinate of the center point of the cross-sectional contour of the blood vessel with the smaller contour area and the x-coordinate of the center point of the cross-sectional contour of the blood vessel with the larger contour area is greater than the arithmetic mean, that is... This indicates the cross-sectional profile of a blood vessel with a large outline area. The cross-sectional outline of blood vessels that are closer to the outer side of the neck and have a larger contour area. This is the cross-sectional outline of the jugular vein, a cross-sectional outline of a vessel with a smaller outline area. The cross-sectional outline of the carotid artery is used; otherwise, the cross-sectional outline of the vessel with a larger outline area is used as the cross-sectional outline of the carotid artery.

[0105] Step S1014: During the control of the ultrasound probe movement, based on the new ultrasound images acquired in real time, the process of calculating the height of the transverse profile of the carotid artery is repeated until the ultrasound probe moves to the end point of the transverse scan. The average height is calculated based on the height of the transverse profile of each carotid artery. .

[0106] In step S102 above, the average height of the carotid artery is pre-established through transverse scanning, and then the ultrasound probe is controlled to move from the starting point of longitudinal scanning and the current ultrasound image is acquired in real time.

[0107] In step S103 above, the specific process of using an image detection model to identify the longitudinal profile of blood vessels in the current ultrasound image and calculating the mean height and standard deviation of the longitudinal profile of blood vessels may include the following steps:

[0108] Step S1031: Based on the current ultrasound image, use the image detection model to identify the longitudinal contour of the blood vessel and obtain the height and width data of the longitudinal contour of the blood vessel.

[0109] In step S1031 above, the longitudinal contour of blood vessels in the current ultrasound image is identified using an image detection model, and the longitudinal contour of the blood vessels is segmented to obtain a segmentation mask image. (See reference...) Figure 4 Example images show segmentation masks for the carotid artery and jugular vein, respectively. Projecting these segmentation masks onto the ultrasound image coordinate system yields the height data of the longitudinal contour of the blood vessels, denoted as... ,in, Indicates position Height data at the location, This represents the width data of the longitudinal profile of the blood vessel.

[0110] Step S1032: Based on the height and width data, calculate the average height according to the following formula (2):

[0111]

[0112] In the above formula (2), Indicates the average height; Indicates position Height data at the location; w This represents the width data;

[0113] Step S1033: Based on the mean height, height data, and width data, calculate the standard deviation of height according to the following formula (3):

[0114]

[0115] In the above formula (3), Indicates the standard deviation of height.

[0116] In step S104 above, the first threshold set includes a first standard deviation threshold, a maximum coefficient value, and a minimum coefficient value. Based on the height mean, height standard deviation, average height, and the first threshold set, it is determined whether the longitudinal profile of the blood vessel is a jugular vein in the following manner:

[0117] If the height standard deviation Greater than the first standard deviation threshold , and / or, if the average height Greater than the maximum coefficient value Compared with average height The product of, and / or, if the height mean Less than the minimum coefficient value Compared with average height The product of these two factors results in the longitudinal outline of the blood vessel being the jugular vein.

[0118] That is, if one of the following three conditions is met, the longitudinal outline of a blood vessel is considered to be the jugular vein: , ,in For example, the threshold parameters can be set to 50, 1.2, and 0.8 respectively.

[0119] In medical terms, the carotid artery has a relatively fast blood flow velocity and high blood pressure, so it is not easily compressed. Conversely, the jugular vein has a slower blood flow velocity and low blood pressure, making it susceptible to compression. After determining the type of the longitudinal profile of the blood vessel through step S104, if the profile is indeed that of the jugular vein, step S105 is executed. The ultrasound probe is controlled to search left and right along the X-axis of the tool coordinate system. During the search, the applied force of the ultrasound probe is adjusted in real time to compress the jugular vein to eliminate interference and further locate the correct carotid artery. Once the longitudinal profile is confirmed to be that of the carotid artery, step S106 is executed, using a preset step size and preset force to scan and obtain a true and clear image of the carotid artery, providing a reliable basis for clinical diagnosis.

[0120] In step S105 above, the second threshold set includes the base step size value, the scaling factor of the height difference, the scaling factor of the standard deviation, the step size increment, and the second standard deviation threshold. The specific process of calculating the movement distance along the X-axis of the tool coordinate system at the next moment based on the mean height, the standard deviation of height, the average height, and the second threshold set may include the following steps:

[0121] Step S1051: Based on the base step length value, the proportional coefficient of the height difference, the proportional coefficient of the standard deviation, the second standard deviation threshold, the height mean, the height standard deviation, the step length increment, and the average height, the moving step length is calculated according to the following formula (4):

[0122]

[0123] In the above formula (4), p xstep Indicates the step size; p xstep0 This represents the basic step size value, which can be set to 0.0003m for example; The scaling factor representing the height difference can be set to 0.003, for example; the standard... The proportionality coefficient of the difference can be set to 0.005, for example. This represents the step size increment, which can be set to 0.0002m for example; it represents the step size increment. The standard deviation threshold, the second standard deviation threshold can be the same as the first standard deviation threshold mentioned above; Indicates average height;

[0124] Based on the above formula (4), the speed can be dynamically adjusted according to the jugular vein determination. That is, the more certain it is to be the jugular vein, the larger the step size and the greater the speed of movement, thereby ensuring the efficiency of the search.

[0125] Step S1052: Based on the moving step size, calculate the moving distance using the following formula (5):

[0126]

[0127] In the above formula (5), Indicates the distance traveled; This indicates the direction of movement along the X-axis of the tool coordinate system, with a value of 1 or -1. The initial value is 1, and the direction is reversed when the following conditions are met:

[0128] (1) If the current cumulative total distance moved along the X-axis is greater than the preset maximum search range along the X-axis, i.e. season That is, the reverse search, where, This indicates the maximum range for the X-axis search, which can be set to 6mm for example;

[0129] (2) If the longitudinal outline of the blood vessel is determined to be the jugular vein in N consecutive tests, then let In other words, the search is reversed, and N is a fixed value, which can be set to 10 for example. After N consecutive determinations that the longitudinal outline of the blood vessel is the jugular vein, the region is considered to be the jugular vein, and the search needs to be reversed to the arterial region to effectively improve the search efficiency.

[0130] Furthermore, during the aforementioned mobile search process, the force applied by the ultrasound probe is adjusted in real time. Based on the mean height, standard deviation of height, average height, a first threshold set, and a third threshold set, where the third threshold set includes the proportional coefficients for the minimum mean height, the maximum mean height, the standard deviation of height, the expected force, and the maximum force offset, the specific process of calculating the applied force at the next moment may include the following steps:

[0131] Step S1053: Based on the average height, the proportional coefficient of the mean height, the minimum average height, the proportional coefficient of the maximum average height, the minimum coefficient value, and the maximum coefficient value, calculate the first force offset using the following formula:

[0132]

[0133] in, Indicates the first force bias; and This is a proportionality coefficient for the average height, converting height error into force, where... The scaling factor representing the minimum average height can be set to 0.04, for example. The scaling factor representing the maximum average height can be set to 0.05, for example. Indicates the minimum coefficient value; Indicates the maximum coefficient value;

[0134] Step S1054: Based on the height standard deviation, the scaling factor of the height standard deviation, and the first standard deviation threshold, the second force bias is calculated according to the following formula:

[0135]

[0136] in, Indicates the second force bias; The scaling factor represents the standard deviation of height, converting the standard deviation of height error into strength. Indicates the first standard deviation threshold;

[0137] Step S1055: Based on the first force offset, the second force offset, the expected force of the foundation, and the maximum force offset, calculate the applied force at the next moment according to the following formula:

[0138]

[0139] in, Indicates the application of force; This represents the basic expected force, which is a fixed value and can be set to 2.5N for example. This represents the maximum force offset, a parameter set for safety, which can be exemplarily set to 1.5N.

[0140] When the longitudinal profile of the blood vessel is determined to be the jugular vein, the force of the ultrasound probe can be dynamically adjusted using equations (6)-(8) above, exhibiting strong adaptability. To ensure the stability of force control, a filter can be used to apply the above-mentioned force. Perform filtering (e.g., low-pass filter).

[0141] In step S106 above, when the longitudinal profile of the blood vessel is indeed the carotid artery, a preset step size and a preset force are used as the moving distance and applied force for the next moment, respectively, and the moving direction for the next moment is determined based on the orientation of the longitudinal profile of the blood vessel. It is worth noting that in step S105 above, the moving direction for the next moment was along the X-axis of the tool coordinate system in order to search for the carotid artery. Here, in step S106, the moving direction for the next moment is the orientation of the longitudinal profile of the blood vessel, that is, after the carotid artery is found, the ultrasound probe is controlled to track the carotid artery.

[0142] In step S107 above, based on the moving distance, applied force and moving direction at the next moment, the ultrasound probe is controlled to move to the position at the next moment, and based on the acquired new ultrasound image, the process of steps S103-S106 above is repeated to obtain the new moving distance, new applied force and new moving direction at the next moment, and the cycle continues until the ultrasound probe moves to the end point of the longitudinal scan.

[0143] Compared to existing technologies that rely solely on image detection models to identify blood vessel types, this embodiment, during longitudinal scanning with the ultrasound probe, calculates the mean and standard deviation of the longitudinal profile height of the blood vessel and compares it with the average height established from transverse scanning. This determines the type of the longitudinal profile of the currently identified blood vessel, rather than entirely relying on the recognition accuracy of the image detection model. This effectively reduces the false identification rate of the carotid artery and significantly improves reliability and stability. When the blood vessel is identified as the jugular vein, the applied force is dynamically adjusted. Increasing the applied force flattens the jugular vein to eliminate interference and further search for the correct carotid artery. Once the currently identified blood vessel is confirmed to be the carotid artery, a scan is performed using a preset step size and preset force to obtain a true and clear carotid artery image, providing a reliable basis for clinical diagnosis. Simultaneously, during longitudinal scanning, the type of the longitudinal profile of the blood vessel is continuously assessed to ensure continuous and stable tracking of the carotid artery, avoiding the problem of the ultrasound probe tracking the wrong blood vessel as in existing technologies, thereby effectively improving the overall scanning efficiency. The method in this embodiment effectively solves the problem of unreliable tracking caused by misidentification of image detection models in the autonomous scanning of ultrasound robots, and realizes accurate, stable and efficient scanning of the carotid artery in complex scenarios.

[0144] Example 2

[0145] Based on the same inventive concept, see [reference] Figure 5 This application also proposes a carotid artery missegmentation processing device for autonomous robotic scanning, comprising:

[0146] The transverse scanning movement module 101 is used to control the robot to move from the starting point of the transverse scanning, use the image detection model to identify the transverse contour of the carotid artery in each frame of ultrasound image acquired in real time, and calculate the height of the transverse contour of the carotid artery until the ultrasound probe moves to the end point of the transverse scanning, and calculate the average height based on the height of the transverse contour of each carotid artery.

[0147] The image acquisition module 102 is used to control the ultrasound probe to move from the starting point of the longitudinal scan and to acquire the current ultrasound image in real time.

[0148] The first calculation module 103 is used to identify the longitudinal profile of blood vessels in the current ultrasound image using an image detection model, and to calculate the mean height and standard deviation of the longitudinal profile of blood vessels.

[0149] The judgment module 104 is used to determine whether the longitudinal profile of the blood vessel is the jugular vein based on the height mean, height standard deviation, average height and a first threshold set; if yes, the second calculation module 105 calculates the moving distance and applied force at the next moment; if no, the data acquisition module 106 obtains the moving distance and applied force at the next moment.

[0150] The second calculation module 105 is used to calculate the moving distance along the X-axis of the tool coordinate system at the next moment based on the height mean, height standard deviation, average height, and second threshold set; and to calculate the applied force at the next moment based on the height mean, height standard deviation, average height, first threshold set, and third threshold set.

[0151] The data acquisition module 106 is used to determine the movement direction at the next moment based on the acquired preset step length and preset force, respectively, and to determine the movement direction at the next moment based on the direction of the longitudinal profile of the blood vessel.

[0152] The transverse scanning movement module 107 is used to control the ultrasound probe to move to the position of the next moment based on the moving distance, applied force and moving direction at the next moment, and based on the acquired new ultrasound image, the first calculation module 103, the judgment module 104, the second calculation module 105 and the data acquisition module 106 re-execute the corresponding process until the ultrasound probe moves to the end point of the longitudinal scanning.

[0153] The carotid artery missegmentation processing device for autonomous robot scanning provided in this embodiment of the invention has a similar implementation principle and technical effect to that of Embodiment 1, and will not be repeated here.

[0154] Example 3

[0155] Based on the same inventive concept, this application also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the carotid artery missegmentation processing method for autonomous scanning by an ultrasound probe as described in Embodiment 1.

[0156] The computer-readable storage medium may be included in the device / apparatus described in the above embodiments; or it may exist independently and not assembled into the device / apparatus. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to Embodiment 1 of the present invention.

[0157] According to embodiments of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0158] Example 4

[0159] Based on the same inventive concept, this application also proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the carotid artery missegmentation processing method for robot autonomous scanning as described in Embodiment 1.

[0160] Example 5

[0161] Based on the same inventive concept, this application proposes a computer program product containing instructions that, when the computer program product is run on a computer device, cause the computer device to execute the carotid artery missegmentation processing method for robot autonomous scanning in Embodiment 1.

[0162] The principles by which the above-mentioned devices, clients, media, and related equipment in this embodiment of the invention solve the problem are similar to those of the aforementioned methods. Therefore, their implementation can refer to the implementation of the aforementioned methods, and repeated details will not be repeated.

[0163] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0164] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0165] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0166] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0167] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. This disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims. Thus, if these modifications and variations of the invention fall within the scope of the claims of the invention and their equivalents, the invention is also intended to include these modifications and variations.

Claims

1. A method for handling missegmentation of the carotid artery during robotic autonomous scanning, characterized in that, include: The ultrasound probe is controlled to move from the starting point of the transverse scan. The image detection model is used to identify the transverse contour of the carotid artery in each frame of ultrasound image acquired in real time, and the height of the transverse contour of the carotid artery is calculated until the ultrasound probe moves to the end point of the transverse scan. The average height is calculated based on the height of the transverse contour of each carotid artery. The ultrasound probe is controlled to move from the starting point of the longitudinal scan and to acquire the current ultrasound image in real time. The image detection model is used to identify the longitudinal profile of blood vessels in the current ultrasound image, and the mean height and standard deviation of the longitudinal profile of the blood vessels are calculated. Based on the mean height, the standard deviation of height, the average height, and the first threshold set, determine whether the longitudinal profile of the blood vessel is the jugular vein; If so, the moving distance along the X-axis of the tool coordinate system at the next moment is calculated based on the mean height, the standard deviation of the height, the average height, and the second threshold set; and the applied force at the next moment is calculated based on the mean height, the standard deviation of the height, the average height, the first threshold set, and the third threshold set. Otherwise, the preset step length and preset force are used as the moving distance and applied force at the next moment, respectively, and the moving direction at the next moment is determined based on the direction of the longitudinal profile of the blood vessel. Based on the moving distance, applied force, and moving direction at the next moment, the ultrasound probe is controlled to move to the position at the next moment. Based on the acquired new ultrasound image, the above judgment and the calculation process of moving distance, applied force, and moving direction are repeated until the ultrasound probe moves to the end point of the longitudinal scan.

2. The method for handling missegmentation of the carotid artery for autonomous robotic scanning according to claim 1, characterized in that, The controlled ultrasound probe moves from the starting point of the transverse scan, using an image detection model to identify the transverse contour of the carotid artery in each frame of the real-time acquired ultrasound image, and calculates the height of the transverse contour of the carotid artery, until the ultrasound probe moves to the end point of the transverse scan. Based on the height of the transverse contour of each carotid artery, the average height is calculated, including: The ultrasound probe is controlled to move from the starting point of the transverse scan. Based on the real-time acquired ultrasound images, the transverse contour of the blood vessels is identified using a preset image detection model. If the cross-sectional profile of a blood vessel is identified, the cross-sectional profile of the blood vessel is determined to be the cross-sectional profile of the carotid artery, and the height of the cross-sectional profile of the carotid artery is obtained. If the cross-sectional contours of two blood vessels are identified, the cross-sectional contour of the carotid artery and its height are determined based on the center point, width, and height corresponding to the cross-sectional contours of the two blood vessels. During the control of the ultrasound probe movement, based on the new ultrasound images acquired in real time, the process of calculating the height of the transverse profile of the carotid artery is repeated until the ultrasound probe moves to the end of the transverse scan, and the average height is calculated based on the height of the transverse profile of each carotid artery.

3. The method for handling carotid artery missegmentation in autonomous robotic scanning according to claim 2, characterized in that, The determination of the carotid artery's cross-sectional profile and its height based on the center point, width, and height corresponding to the cross-sectional profiles of the two blood vessels includes: Based on the width and height corresponding to the cross-sectional contours of the two blood vessels, the arithmetic mean of the sum of the width values ​​and the sum of the height values ​​of the cross-sectional contours of the two blood vessels is calculated. The corresponding contour area is calculated based on the width and height of the cross-sectional contour of each blood vessel; For the cross-sectional contours of two blood vessels located on the left side of the human body, if the difference between the x-coordinate of the center point of the cross-sectional contour of the blood vessel with the larger contour area and the x-coordinate of the center point of the cross-sectional contour of the blood vessel with the smaller contour area is greater than the arithmetic mean, then the cross-sectional contour of the blood vessel with the smaller contour area is the cross-sectional contour of the carotid artery; otherwise, the cross-sectional contour of the blood vessel with the larger contour area is the cross-sectional contour of the carotid artery. For the cross-sectional contours of two blood vessels located on the right side of the human body, if the difference between the x-coordinate of the center point of the cross-sectional contour of the blood vessel with smaller contour area and the x-coordinate of the center point of the cross-sectional contour of the blood vessel with larger contour area is greater than the arithmetic mean, then the cross-sectional contour of the blood vessel with smaller contour area is the cross-sectional contour of the carotid artery; otherwise, the cross-sectional contour of the blood vessel with larger contour area is the cross-sectional contour of the carotid artery.

4. The method for handling carotid artery missegmentation for autonomous robotic scanning according to claim 1, characterized in that, The step of using the image detection model to identify the longitudinal profile of blood vessels in the current ultrasound image and calculating the mean height and standard deviation of the longitudinal profile of the blood vessels includes: Based on the current ultrasound image, the image detection model is used to identify the longitudinal contour of the blood vessel, and the height and width data of the longitudinal contour of the blood vessel are obtained. Based on the height and width data, the average height is calculated using the following formula: ； in, Indicates the average height; Indicates position The height data at the location; w represents the width data; Based on the mean height, the height data, and the width data, the standard deviation of height is calculated using the following formula: ； in, Indicates the standard deviation of height.

5. The method for handling carotid artery missegmentation for autonomous robotic scanning according to claim 1, characterized in that, The first threshold set includes a first standard deviation threshold, a maximum coefficient value, and a minimum coefficient value; The step of determining whether the longitudinal profile of the blood vessel is a jugular vein based on the mean height, the standard deviation of the height, the average height, and a first threshold set includes: If the height standard deviation is greater than the first standard deviation threshold, and / or if the height mean is greater than the product of the maximum coefficient value and the average height, and / or if the height mean is less than the product of the minimum coefficient value and the average height, then the longitudinal profile of the blood vessel is the jugular vein.

6. The method for handling carotid artery missegmentation for autonomous robotic scanning according to claim 4, characterized in that, The second threshold set includes the base step size value, the scaling factor of the height difference, the scaling factor of the standard deviation, the step size increment, and the second standard deviation threshold; The calculation of the movement distance along the X-axis at the next moment, based on the mean height, the standard deviation of height, the average height, and the second threshold set, includes: Based on the base step size, the height difference scaling factor, the standard deviation scaling factor, the second standard deviation threshold, the mean height, the standard deviation of height, the step size increment, and the average height, the moving step size is calculated according to the following formula: ； Where, p xstep Indicates the step size; p xstep0 This represents the basic step size value; The scaling factor represents the height difference; The proportionality coefficient representing the standard deviation; This represents the step size increment; This represents the second standard deviation threshold; This represents the average height; Based on the stated step size, the moving distance is calculated using the following formula: ； in, Indicates the distance traveled; This indicates the direction of motion along the X-axis of the tool coordinate system.

7. The method for handling carotid artery missegmentation in autonomous robotic scanning according to claim 6, characterized in that, The third threshold set includes the scaling factor for the minimum average height, the scaling factor for the maximum average height, the scaling factor for the height standard deviation, the expected force of the base, and the maximum force offset. The calculation of the applied force at the next moment based on the mean height, the standard deviation of height, the average height, the first threshold set, and the third threshold set includes: Based on the average height, the height mean, the scaling factor of the minimum average height, the scaling factor of the maximum average height, the minimum scaling factor, and the maximum scaling factor, the first force offset is calculated according to the following formula: ； in, Indicates the first force bias; The scaling factor representing the minimum average height; The scaling factor represents the maximum average height; Indicates the minimum coefficient value; Indicates the maximum coefficient value; Based on the height standard deviation, the scaling factor of the height standard deviation, and the first standard deviation threshold, the second force bias is calculated according to the following formula: ； in, Indicates the second force bias; The proportionality coefficient representing the standard deviation of height; Indicates the first standard deviation threshold; Based on the first force offset, the second force offset, the expected force of the foundation, and the maximum force offset, the applied force at the next moment is calculated according to the following formula: ； in, Indicates the application of force; It represents the basic expectation force; This indicates the maximum force offset.

8. A carotid artery missegmentation processing device for autonomous robotic scanning, characterized in that, include: The transverse scanning movement module is used to control the robot to move from the starting point of the transverse scanning. It uses an image detection model to identify the transverse contour of the carotid artery in each frame of ultrasound image acquired in real time, and calculates the height of the transverse contour of the carotid artery until the ultrasound probe moves to the end point of the transverse scanning. The average height is calculated based on the height of the transverse contour of each carotid artery. The image acquisition module is used to control the ultrasound probe to move from the starting point of the longitudinal scan and to acquire the current ultrasound image in real time. The first calculation module is used to identify the longitudinal profile of blood vessels in the current ultrasound image using the image detection model, and to calculate the mean height and standard deviation of the longitudinal profile of blood vessels. The judgment module is used to determine whether the longitudinal profile of the blood vessel is the jugular vein based on the mean height, the standard deviation of the height, the average height and the first threshold set; if yes, the second calculation module calculates the moving distance and applied force at the next moment; if no, the data acquisition module obtains the moving distance and applied force at the next moment. The second calculation module is used to calculate the moving distance along the X-axis of the tool coordinate system at the next moment based on the mean height, the standard deviation of the height, the average height, and the second threshold set; and to calculate the applied force at the next moment based on the mean height, the standard deviation of the height, the average height, the first threshold set, and the third threshold set. The data acquisition module is used to determine the movement distance and applied force at the next moment based on the acquired preset step length and preset force, respectively, and to determine the movement direction at the next moment based on the direction of the longitudinal profile of the blood vessel. The transverse scanning movement module is used to control the ultrasound probe to move to the position of the next moment based on the moving distance, applied force and moving direction at the next moment, and based on the acquired new ultrasound image, the first calculation module, the judgment module, the second calculation module and the data acquisition module re-execute the corresponding process until the ultrasound probe moves to the end point of the longitudinal scanning.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the carotid artery missegmentation processing method for autonomous robot scanning as described in any one of claims 1-7.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the carotid artery missegmentation processing method for autonomous robot scanning as described in any one of claims 1-7.

11. A computer program product containing instructions that, when run on a computer device, causes the computer device to perform the carotid artery missegmentation processing method for autonomous robotic scanning as described in any one of claims 1-7.

Images