Transfer control method and device for ultrasonic robot to autonomously scan thyroid gland

Abstract

The invention discloses a transfer control method and device for an ultrasonic robot to autonomously scan thyroid gland, and the method comprises the steps: controlling an ultrasonic robot probe to move from an initial position to a target side by a first preset distance, collecting an ultrasonic image in real time, and recording a total movement distance and a distance to a trachea; obtaining a thyroid contour area based on the ultrasonic image, and determining the effectiveness of the ultrasonic image; if the continuous preset number of ultrasonic images are valid, determining that the probe completes two-side transfer; otherwise, contour features of the trachea and the carotid artery are obtained based on ultrasonic image fitting, and whether the probe completes two-side transfer or not is determined by combining the distance from the probe to the center of the neck; if not, whether the distance to the air pipe is larger than a second preset distance is judged; if not, whether the total moving distance is larger than a preset maximum distance or not is judged; if not, transferring is executed again; and if yes, determining that the probe completes two-side transfer. According to the method, the quality and efficiency of thyroid autonomous scanning are improved, and the safety and accuracy of operation are enhanced.

Description

Technical Field

[0001] The invention relates to a transfer control method for autonomously scanning a thyroid gland by an ultrasonic robot. Background Art

[0002] With the development of medical technology, ultrasound examination has been widely used in clinical diagnosis due to its advantages such as non-invasiveness, convenience and low cost, especially for the screening of thyroid diseases. However, the traditional manual operation method has problems such as relying on the doctor's experience and the examination results are greatly affected by subjective factors, which makes it difficult to ensure the consistency and repeatability of the examination. In order to solve these problems, ultrasound robot technology came into being, aiming to improve the quality and efficiency of examinations through automation.

[0003] When performing autonomous thyroid scanning, the ultrasound robot needs to operate on the left and right sides of the neck to complete a comprehensive scan of the left and right lobes of the thyroid. In this process, how to accurately and safely control the robot probe to transfer from one side of the neck to the other has become a key challenge to ensure the integrity of the scan. During the transfer process, the robot must not only accurately identify and track the anatomical structure of the thyroid, but also avoid compression or damage to surrounding tissues to ensure the safety of the operation. In addition, an efficient transfer mechanism can significantly shorten the examination time, improve patient comfort, and reduce the workload of doctors, thus playing an important role in clinical practice. Therefore, designing a reliable ultrasound robot probe transfer control method is of great significance to improving the accuracy and efficiency of thyroid disease screening. Summary of the invention

[0004] In order to enable the ultrasonic robot probe to more accurately complete bilateral transfer during thyroid scanning, an embodiment of the present invention provides a transfer control method for an ultrasonic robot to autonomously scan the thyroid.

[0005] In a first aspect, an embodiment of the present invention provides a transfer control method for autonomously scanning the thyroid gland by an ultrasonic robot, which may include:

[0006] Controlling the probe of the ultrasonic robot to move a first preset distance from an initial position on the starting side to a target side, and acquiring ultrasonic images in real time, and recording and updating the total moving distance and the distance from the trachea in real time;

[0007] Performing a first image segmentation on the ultrasound image to obtain a thyroid contour area and determine the validity of the ultrasound image;

[0008] If a preset number of consecutive ultrasound images are valid, it is determined that the probe has completed the transfer of both sides;

[0009] Otherwise, performing a second image segmentation on the ultrasound image, fitting the contour features of the trachea and the carotid artery, and combining the acquired distance from the probe to the center of the neck to determine whether the probe has completed the transfer to both sides;

[0010] If not, determining whether the distance from the trachea is greater than a second preset distance;

[0011] If not, determining whether the total moving distance is greater than a preset maximum distance;

[0012] If not, re-execute the above transfer process;

[0013] If so, it is determined that the probe has completed the transfer on both sides.

[0014] In one or some optional implementations of the embodiments of the present application, performing a second image segmentation on the ultrasound image, fitting contour features of the trachea and the carotid artery, and determining whether the probe has completed bilateral transfer in combination with the acquired distance from the probe to the center of the neck include:

[0015] Performing a second image segmentation on the ultrasonic image to obtain a carotid artery contour and a trachea contour;

[0016] Performing ellipse fitting on the carotid artery contour and the trachea contour respectively to obtain contour features of the carotid artery and the trachea;

[0017] Determining whether the positions of the carotid artery and the trachea meet a preset conditional relationship according to the contour features of the carotid artery and the trachea;

[0018] Obtaining and determining whether the distance from the probe to the center of the neck reaches a third preset distance;

[0019] If both are true, it is determined that the probe has completed the transfer on both sides.

[0020] In one or some optional implementations of the embodiments of the present application, the contour features of the carotid artery include the contour area of ​​the carotid artery and the coordinates of the center point of the carotid artery; the contour features of the trachea include the contour area of ​​the trachea and the coordinates of the center point of the trachea; the preset conditional relationship includes a first conditional relationship and a second conditional relationship;

[0021] The determining, based on the contour features of the carotid artery and the trachea, whether the positions of the carotid artery and the trachea meet a preset conditional relationship includes:

[0022] Determine whether the carotid artery contour area and the carotid artery center point coordinates satisfy the first conditional relationship; the first conditional relationship is that the carotid artery contour area is greater than a preset carotid artery minimum threshold, and the difference between the carotid artery center point coordinates and the preset carotid artery target center point coordinates is greater than a first preset threshold;

[0023] Determine whether at least one of the trachea center point coordinates and the trachea contour area satisfies a second conditional relationship; the second conditional relationship is that the trachea center point coordinates are located on the target side of the carotid artery center point coordinates, or the trachea contour area is smaller than a preset minimum trachea contour area.

[0024] In one or some optional implementations of the embodiments of the present application, the following further includes:

[0025] Performing real-time collision detection during the transfer of the ultrasonic robot probe, if a collision is detected, obtaining the torque of the X-axis of the tool coordinate system at the end of the ultrasonic robot mechanical arm, and determining whether the torque is less than a preset torque threshold;

[0026] If so, the amount of change in the posture for releasing the limit is calculated according to the torque and the preset torque threshold, and the robotic arm is adjusted according to the amount of change in the posture for releasing the limit.

[0027] In one or some optional implementations of the embodiments of the present application, when the distance from the trachea is recorded in real time, it also includes:

[0028] Acquire the contour features of the trachea; the contour features of the trachea include the trachea contour area and the coordinates of the trachea center point;

[0029] If the difference between the coordinates of the trachea center point and the preset central position is less than the set threshold, and whether the trachea contour area is greater than the preset minimum trachea contour area, the distance from the trachea is set to 0.

[0030] In one or some optional implementations of the embodiment of the present application, performing a first image segmentation on the ultrasound image to obtain a thyroid contour area and determine the validity of the ultrasound image includes:

[0031] A first image segmentation is performed on the ultrasound image to obtain a thyroid contour area. If the thyroid contour area is greater than a preset area threshold, the ultrasound image is determined to be a valid image.

[0032] In a second aspect, an embodiment of the present invention provides a transfer control device for autonomously scanning the thyroid gland by an ultrasonic robot, which may include:

[0033] A mobile acquisition module, used to control the probe of the ultrasonic robot to move from an initial position on the starting side to a first preset distance on the target side, and to acquire ultrasonic images in real time, and to record and update the total moving distance and the distance from the trachea in real time;

[0034] A first judgment module is used to perform a first image segmentation on the ultrasound image to obtain a thyroid contour area and determine the validity of the ultrasound image;

[0035] The second judgment module continues to judge if the ultrasound image is valid, and if a preset number of consecutive ultrasound images are valid, it is determined that the probe has completed the transfer of the two sides;

[0036] The third judgment module, if the ultrasound image is invalid, performs a second image segmentation on the ultrasound image, fits the contour features of the trachea and the carotid artery, and determines whether the probe has completed the transfer on both sides in combination with the distance from the probe to the center of the neck; if so, determines that the probe has completed the transfer on both sides;

[0037] The fourth judgment module, if the probe has not completed the transfer of both sides, determines whether the distance from the trachea is greater than a second preset distance; if so, determines that the probe has completed the transfer of both sides;

[0038] The fifth judgment module determines whether the distance from the trachea is greater than the second preset distance if the distance from the trachea is not greater than the second preset distance; if so, determines that the probe has completed the transfer of both sides; if not, re-executes the mobile acquisition module.

[0039] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program / instruction stored thereon, which, when executed by a processor, implements the metastasis control method for autonomously scanning the thyroid gland by an ultrasonic robot as described above.

[0040] In a fourth aspect, an embodiment of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-mentioned transfer control method for autonomously scanning the thyroid gland with an ultrasonic robot.

[0041] In a fifth aspect, an embodiment of the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory, wherein when the processor executes the computer program, the metastasis control method for autonomously scanning the thyroid gland by an ultrasonic robot as described above is implemented.

[0042] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0043] The embodiment of the present invention provides a transfer control method for autonomous thyroid scanning by an ultrasonic robot. The method controls the probe of the ultrasonic robot to move equidistantly from the initial position to the target side of the thyroid gland, each time moving a first preset distance, and collects ultrasonic images. According to the collected ultrasonic images, the probe position is judged from the area of ​​the thyroid gland, the distance from the probe to the center of the neck, the positional relationship between the trachea and the carotid artery, the distance from the trachea, and the total moving distance. This method realizes safe and efficient transfer from one side of the neck to the other by real-time fitting to the human body surface skin and utilizing the structural characteristics of the human neck. This method not only improves the image quality and efficiency of autonomous thyroid scanning, but also enhances the safety and accuracy of the operation, reduces the dependence on the doctor's experience and skills, shortens the operation time, improves the patient's comfort, and thus improves the overall quality of thyroid disease screening.

[0044] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0045] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0047] Figure 1 A schematic diagram of a flow chart of a method for controlling the transfer of thyroid glands by an ultrasonic robot for autonomous scanning provided by an embodiment of the present invention;

[0048] Figure 2 An example diagram of an ultrasonic robot provided by an embodiment of the present invention;

[0049] Figure 3 A schematic diagram of a thyroid ultrasound image provided by an embodiment of the present invention;

[0050] Figure 4 An example diagram of the conversion of longitudinal cutting to transverse cutting of an ultrasonic robot probe provided in an embodiment of the present invention;

[0051] Figure 5 A schematic diagram of the probe provided in an embodiment of the present invention after completing the transfer on both sides;

[0052] Figure 6 A schematic diagram of an ultrasound image after ellipse fitting provided by an embodiment of the present invention;

[0053] Figure 7 A schematic diagram of a second preset distance provided by an embodiment of the present invention;

[0054] Figure 8 A schematic diagram of a probe provided in an embodiment of the present invention being located in the center of the neck;

[0055] Fig. 9 A schematic diagram of a preset maximum distance provided by an embodiment of the present invention;

[0056] Fig.10 A schematic diagram of the structure of a transfer control device for autonomously scanning the thyroid gland by an ultrasonic robot provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0058] The inventors found that in the prior art, when the robot autonomously scans the thyroid gland, it usually only scans one side of the thyroid gland first. After scanning one side, the robotic arm is lifted, and then the position of the other side is relocated through an external camera, and the robotic arm is controlled to reach the other side. This method is time-consuming and relies on external cameras. It is costly and easily affected by human body differences or ambient light, and has poor reliability. Based on this, the inventors have made the present invention after further research and development, providing a transfer control method and device for autonomous thyroid scanning by an ultrasonic robot.

[0059] Embodiment 1

[0060] In the first embodiment of the present invention, a control method for autonomously scanning the thyroid gland by an ultrasonic robot is provided. Figure 1 As shown, the method may include the following steps S101-S106:

[0061] S101: Control the probe of the ultrasonic robot to move a first preset distance from an initial position on the starting side to a target side, collect ultrasonic images in real time, and record and update the total moving distance and the distance from the trachea in real time.

[0062] S102: Perform a first image segmentation on the ultrasound image to obtain the thyroid contour area and determine the validity of the ultrasound image: if yes, execute step S103; if no, execute step S104.

[0063] S103: If a preset number of consecutive ultrasound images are valid, it is determined that the probe has completed the transfer to both sides.

[0064] S104: Perform a second image segmentation on the ultrasound image, fit the contour features of the trachea and carotid artery, and determine whether the probe has completed the transfer to both sides in combination with the distance from the probe to the center of the neck: if so, determine that the probe has completed the transfer to both sides; if not, execute step S105.

[0065] S105: Determine whether the distance from the trachea is greater than a second preset distance: if so, determine that the probe has completed the transfer of both sides; if not, execute step S106.

[0066] S106: Determine whether the total moving distance is greater than the preset maximum distance: if so, determine that the probe has completed the transfer of both sides; if not, re-execute the above step S101.

[0067] The embodiment of the present invention provides a transfer control method for autonomous thyroid scanning by an ultrasonic robot. The method controls the probe of the ultrasonic robot to move equidistantly from the initial position to the target side of the thyroid gland, each time moving a first preset distance, and collects ultrasonic images. According to the collected ultrasonic images, the probe position is judged from multiple aspects, including: first, the area of ​​the thyroid gland; second, the distance from the probe to the center of the neck, and the positional relationship between the trachea and the carotid artery; third, the distance from the trachea; and fourth, the total moving distance. This method realizes safe and efficient transfer from one side of the neck to the other by real-time fitting to the human body surface skin and utilizing the structural characteristics of the human neck. This method not only improves the image quality and efficiency of autonomous thyroid scanning, but also enhances the safety and accuracy of the operation, reduces the dependence on the doctor's experience and skills, and improves the overall quality of thyroid disease screening.

[0068] In order to facilitate those skilled in the art to understand the present solution, the following first provides an example diagram of the ultrasonic robot and the thyroid structure in the embodiment of the present application: Figure 2 As shown in the figure, there are two sets of coordinate systems, the world coordinate system at the root of the robot arm and the tool coordinate system at the end of the robot arm. Figure 3 As shown, this includes the trachea, left and right thyroid lobes, and left and right carotid arteries.

[0069] In the embodiment of the present application, when the thyroid scan is started based on the ultrasound robot, the probe of the ultrasound robot is first placed in the center of the human neck to perform a preliminary scan of the isthmus of the thyroid gland and determine the coordinates of the center of the neck. Then, the ultrasound robot controls the probe to scan one side of the thyroid gland first. After completing the scan on one side, the probe is controlled to switch from longitudinal cutting to transverse cutting. The example diagram is shown in FIG. Figure 4 As shown in the figure, the probe has completed the scan of the right lobe of the thyroid gland and is located at the lower right position of the neck. It is necessary to basically transfer the probe to the left side of the neck to complete the scan of the left lobe of the thyroid gland, thereby achieving a complete scan of the thyroid gland.

[0070] In the above step S101, the probe of the ultrasonic robot is controlled to move from the initial position on the starting side to the target side by a first preset distance, and an ultrasonic image is collected in real time, and the total moving distance and the distance from the trachea are recorded and updated in real time.

[0071] Specifically, after completing the scan of the starting side of the thyroid gland, the probe is controlled to switch from longitudinal cutting to transverse cutting, and the probe of the ultrasonic robot is controlled to fit the human body, and the probe of the ultrasonic robot is at the initial position of the starting side.

[0072] Start to control the probe of the ultrasonic robot to move in the Y direction of the tool coordinate system at the end of the robot arm toward the target side. Specifically, the translation vector of each movement of the probe is (0, Δp y , Δp z ), where Δp y That is, the first preset distance, if the target side is the left side, the first preset distance can be set to 0.0003m, if the target side is the right side, the first preset distance can be set to -0.0003m, Δp z This method uses a force control algorithm to obtain the displacement in the Z direction in order to ensure that the probe fits the human body surface in real time. The force control algorithm is a mature algorithm and will not be described in detail here.

[0073] After the movement is completed, the total movement distance and the distance from the trachea need to be updated in real time, as shown in the following formulas 1 and 2:

[0074] d=d+Δp y Formula 1

[0075] d tube =d tube +Δp y Formula 2

[0076] In the formula, d is the total moving distance, the initial value is 0, d tube is the distance from the trachea, the initial value is 0, Δp y is the first preset distance.

[0077] In the above step S102, the ultrasound image is segmented into the first image to obtain the thyroid contour area and determine the validity of the ultrasound image: if yes, execute step S103; if no, execute step S104.

[0078] Specifically, when the ultrasonic robot probe moves toward the target side, the first image segmentation network is used to segment the real-time acquired ultrasonic image to determine the contour of the thyroid gland, and the number of pixels in the thyroid gland contour is accumulated to obtain the thyroid gland contour area s. t .

[0079] If the thyroid contour area st Greater than the preset area threshold s max , that is, s t >s max , it means that the ultrasound image contains a valid thyroid gland, and the ultrasound image is a valid image. Add 1 to the number of times the thyroid gland is valid, that is, t s =t s +1, t s It indicates the number of consecutive acquisitions of valid thyroid ultrasound images. t Not greater than the preset area threshold s max , that is, s t ≤s max , then let t s = 0. Among them, s max Can be set to 25000, the unit is pixel squared.

[0080] Those skilled in the art can select a suitable neural network for pre-training based on the detailed description of the prior art to obtain a first image segmentation network. The training process may specifically include:

[0081] In the first step, thyroid ultrasound images are collected and the contours of the thyroid gland in the thyroid ultrasound images are marked respectively, and a thyroid contour dataset is obtained after preprocessing.

[0082] The second step is to select a suitable neural network model as the initial first image segmentation network, such as U-Net model, SegNet model, etc.

[0083] In the third step, the thyroid contour dataset is divided into a training set and a test set.

[0084] The fourth step is to define the loss function (such as cross entropy loss function, mean square error loss function, etc.), optimization algorithm (such as Adam, SGD, etc.), etc.

[0085] The fifth step is to train the selected neural network model using the training set of the thyroid contour dataset to obtain the trained first image segmentation model.

[0086] Repeat the training process of the above image segmentation model until the preset conditions are met, stop training, and obtain the first image segmentation network. The preset conditions can be set to reach a fixed number of iterations, the accuracy reaches a threshold, the accuracy does not change within a preset number of iterations, etc. No specific limitation is made here.

[0087] In the above step S103, if a preset number of consecutive ultrasound images are valid, it is determined that the probe has completed the transfer of both sides, otherwise, step S104 is executed.

[0088] Specifically, if the number of consecutive acquisitions of valid thyroid ultrasound images exceeds a preset valid number, that is, ts >t smax , it means that the probe has been stably moved to the target side of the thyroid gland. Figure 5 As shown, it is confirmed that the probe has completed the transfer on both sides. smax Can be set to 10.

[0089] In the embodiment of the present application, the above steps S102-S103 realize the validity judgment of the ultrasound image by real-time segmentation of the ultrasound image, ensuring that the acquired ultrasound image contains the thyroid gland, thereby reducing the possibility of misdiagnosis and missed diagnosis. By continuously monitoring the number of valid images, the transfer process of the probe from one side to the other is optimized, ensuring the smooth transfer of the two sides of the probe.

[0090] In the above step S104, the ultrasound image is segmented for the second image, and the contour features of the trachea and the carotid artery are fitted. Combined with the distance from the probe to the center of the neck, it is determined whether the probe has completed the transfer on both sides: if so, it is determined that the probe has completed the transfer on both sides; if not, step S105 is executed. Specifically, the following steps S1041-S1045 are included:

[0091] S1041: Perform image segmentation on the ultrasound image to obtain the contours of the carotid artery and the trachea.

[0092] Specifically, when the ultrasonic robot probe moves toward the target side, the second segmentation network is used to segment the ultrasonic image collected in real time to obtain the contour of the carotid artery and the contour of the trachea in the ultrasonic image.

[0093] Those skilled in the art can select a suitable neural network for pre-training based on the detailed description of the prior art to obtain a second image segmentation network. The training process may specifically include:

[0094] In the second step, thyroid ultrasound images are collected and the contours of the thyroid gland in the thyroid ultrasound images are marked respectively, and a thyroid contour dataset is obtained after preprocessing.

[0095] The second step is to select a suitable neural network model as the initial second image segmentation network, such as U-Net model, SegNet model, etc.

[0096] In the third step, the thyroid contour dataset is divided into a training set and a test set.

[0097] The fourth step is to define the loss function (such as cross entropy loss function, mean square error loss function, etc.), optimization algorithm (such as Adam, SGD, etc.), etc.

[0098] The fifth step is to train the selected neural network model using the training set of the thyroid contour dataset to obtain a trained second image segmentation model.

[0099] Repeat the training process of the above image segmentation model until the preset conditions are met, stop training, and obtain the second image segmentation network. The preset conditions can be set to reach a fixed number of iterations, the accuracy reaches a threshold, the accuracy does not change within the preset number of iterations, etc. No specific limitation is made here.

[0100] S1042: Perform ellipse fitting on the carotid artery contour and the trachea contour respectively to obtain contour features of the carotid artery and the trachea.

[0101] Specifically, the contour features of the carotid artery (c ax , a a ) and the contour features of the trachea (c tx , a t ), where c ax The coordinates of the center point of the carotid artery, specifically, the coordinates of the center point of the carotid artery in the X direction of the ultrasound image, a a represents the contour area of ​​the carotid artery, c tx Indicates the coordinates of the trachea center point, specifically, the coordinate position of the trachea center point in the X direction of the ultrasound image, a t Represents the tracheal contour area.

[0102] In order to facilitate those skilled in the art to understand the present invention, a more clear description of the ultrasound image after ellipse fitting is given here, referring to Figure 6 As shown, the figure includes the trachea, the left carotid artery and the right carotid artery after ellipse fitting, and the thyroid contour features, including the left thyroid lobe, the right thyroid lobe and the isthmus of the thyroid. It should be noted that the thyroid contour features in the figure are only for the convenience of understanding of those skilled in the art, and the ultrasound image after ellipse fitting does not include this feature.

[0103] Among them, the cv2.fitEllipse() function in the open source computer vision library OpenCV (Open Source Computer Vision Library) can be used to implement ellipse fitting, and this method is not limited here.

[0104] S1043: Determine whether the positions of the carotid artery and the trachea meet a preset conditional relationship based on the contour features of the carotid artery and the trachea. Specifically, the following steps S10431-S10432 are included:

[0105] S10431: Determine whether the carotid artery contour area and the carotid artery center point coordinates satisfy a first conditional relationship; the first conditional relationship is that the carotid artery contour area is greater than a preset carotid artery minimum threshold, and the difference between the carotid artery center point coordinates and the preset carotid artery target center point coordinates is greater than a first preset threshold.

[0106] Specifically, it can be determined whether the carotid artery contour area a is satisfied at the same time. a Greater than the preset minimum carotid artery threshold a amin , and the coordinates of the center point of the carotid artery are c ax and the preset carotid artery target center point coordinate c ax0 The difference is greater than the first preset threshold d axmin , that is, satisfying a a >a amin And|c ax -c ax0 |>d axmin If yes, it means that there is a carotid artery contour in the ultrasound image, and the carotid artery contour is located on the target side of the ultrasound image, which means that the ultrasound probe has moved to the target side area of ​​the human body. amin Can be set to 500, c ax0 Can be set to 0, d axin Can be set to 100, in pixels.

[0107] In order to facilitate those skilled in the art to understand the present solution, the first conditional relationship is illustrated as follows: when the target side is the left side, the coordinates of the center point of the carotid artery c ax At the preset carotid artery target center point coordinate c ax0 On the left side, c ax <c ax0 , the first conditional relationship can be expressed as a a >a amin and c ax -c ax0 <-d axmin Similarly, when the target side is the right side, the coordinates of the center point of the carotid artery c ax At the preset carotid artery target center point coordinate c ax0 On the right side, c ax >c ax0 , the first conditional relationship can be expressed as a a >a amin and c ax -C ax0 >d axmin .

[0108] S10432: Determine whether at least one of the trachea center point coordinates and the trachea contour area satisfies a second conditional relationship; the second conditional relationship is that the trachea center point coordinates are located on the target side of the carotid artery center point coordinates, or the trachea contour area is smaller than a preset minimum trachea contour area.

[0109] Specifically, it can be determined whether the trachea center point coordinate c is satisfied. tx Is it located at the center of the carotid artery? ax The target side, or the tracheal contour area a tSmaller than the preset minimum tracheal contour area a tmin .

[0110] Among them, the coordinates of the trachea center point c tx Located at the center of the carotid artery coordinate c ax The target side, i.e. c tx <c ax (When the target side is the left side) or c tx >c ax (When the target side is the right side).

[0111] Tracheal contour area t Smaller than the preset minimum tracheal contour area a tmin , that is, a t <a tmin .

[0112] If the second condition relationship is met, it means that there is no tracheal outline in the ultrasound image at this time, or the center point of the tracheal outline is located on the target side of the carotid artery center point, which further indicates that the probe has moved to the target side of the trachea, that is, the target side area of ​​the neck. tmin Can be set to 1000, in pixels.

[0113] S1044: Obtain and determine whether the distance from the probe to the center of the neck reaches a third preset distance.

[0114] Specifically, it can be that, first of all, it should be made clear that when starting to perform thyroid scanning based on an ultrasound robot, the probe of the ultrasound robot will be placed in the center of the human neck to determine the coordinates of the center of the neck. Then, the real-time coordinates of the probe are subtracted from the coordinates of the center of the neck, as shown in the following formula 3, to obtain the distance from the probe to the center of the neck:

[0115] d x = x cur -x init Formula 3

[0116] In the formula, χ cur Indicates the current position of the probe in the X direction of the world coordinate system, χ init Indicates the position of the probe in the X direction of the world coordinate system during the initial scan, d x Indicates the distance from the probe to the center of the neck.

[0117] Determine the distance d from the probe to the center of the neck x Is it greater than the third preset distance d xmin , that is |d x| >d xmin If yes, it means the probe has moved to the target side of the neck. xmin is the third preset distance, which can be set to 0.01m. If the target side is the left side, dx <0, if the target side is the right side d x >0.

[0118] S1045: If the judgments in the above steps S1044-S1045 are all yes, it means that the probe has been moved to the target side of the thyroid gland, and the transfer of the probe to both sides has been completed.

[0119] In an embodiment of the present application, in the above step S104, in the process of transferring the ultrasonic robot probe from one side through the human trachea to the target side, based on the anatomical structure characteristics of the human neck, that is, the trachea is in the center of the neck and the carotid arteries are located on both sides of the neck. The distance from the probe to the center of the neck and the positional relationship between the trachea and the carotid arteries are judged in real time, and the contour features of the trachea and the carotid arteries in the ultrasonic image are used as transfer positioning marks to determine the real-time position of the probe, thereby effectively improving the efficiency and safety of the transfer and further optimizing the overall performance and applicability.

[0120] In the above step S105, it is determined whether the distance from the trachea is greater than the second preset distance: if so, it is determined that the probe has completed the transfer of both sides; if not, step S106 is executed.

[0121] Specifically, it can be that according to the description in the above step S101, the method will record the distance d from the trachea in real time. tube , when the distance from the trachea is d tube Reaching the second preset distance d tmax , that is, d tube >d tmax When the distance between the probe and the trachea has reached a dangerous range, the robot movement may be unpredictable. In order to ensure the safety of the scan, the probe transfer will be terminated and manual control will be performed, or the thyroid scan will be started from the beginning. tmax Please refer to Figure 7 As shown in the figure, the probe on the left is located in the center of the trachea, and the probe on the right is the farthest position from the trachea limited by this method. tmax Can be set to 0.02m.

[0122] In the embodiment of the present application, when the distance from the trachea is recorded in real time, it also includes determining whether the probe has reached the center of the neck, and if so, the distance from the trachea needs to be reset to 0. Specifically, the following steps S1051-S1052 are included:

[0123] S1051: Obtaining the contour features of the trachea. The contour features of the trachea include the trachea contour area and the coordinates of the trachea center point.

[0124] Specifically, the ultrasound image can be segmented in real time to obtain the tracheal contour, and then the tracheal contour is elliptical fitted to obtain the tracheal contour area a. tand the coordinates of the trachea center point c tx The specific implementation of image segmentation and ellipse fitting can refer to the content in the above step S103, which will not be described in detail here.

[0125] S1052: If the difference between the coordinates of the trachea center point and the preset central position is less than the set threshold, and the trachea contour area is greater than the preset minimum trachea contour area, the distance from the trachea is set to 0.

[0126] Specifically, if the coordinates of the tracheal center point c are tx With the preset center position c txmax The difference is less than the set threshold c tx0 , and the tracheal contour area a t Greater than the preset minimum tracheal contour area a tmin , that is, |c tx -c txmax | <c tx0 And a t >a tmin , it means that the center of the trachea is located in the center of the ultrasound image, that is, the probe is located in the center of the neck. Figure 8 As shown, the distance from the trachea needs to be reset to 0 so that the distance from the trachea can be correctly corrected when the probe moves to the target side. txmax Can be set to 10. If the target side is the right side, then c txmax Can be set to -10, c tx0 Can be set to 5.

[0127] In the above step S106, it is determined whether the total moving distance is greater than the preset maximum distance: if so, it is determined that the probe has completed the transfer of both sides; if not, the above step S101 is executed again.

[0128] Specifically, it can be known from the description in the above step S101 that the total moving distance d is recorded in real time in this method. When the total moving distance is greater than the preset maximum distance, that is, d>d max When d is reached, it means that the distance between the probe and the neck has reached a dangerous range, and the robot movement may be unpredictable. In order to ensure the safety of the scan, the probe transfer will be terminated and manual control will be used, or the thyroid scan will be started from the beginning. max Please refer to Fig. 9 As shown in the figure, the probe on the left is the position of the probe at the beginning of this method, and the probe on the right is the position farthest from the initial position limited by this method, d max Can be set to 0.04m.

[0129] In the embodiment of the present application, it should also be noted that in the process of transferring the ultrasonic robot probe from one side to the other, there may be a situation where the movement of the mechanical arm is limited, that is, in order to avoid the collision between the mechanical arm and the body, the ultrasonic robot limits the range of motion of the mechanical arm, resulting in the situation that the probe cannot be moved to the target position. Therefore, in order to ensure that the probe can be smoothly transferred to the target side of the thyroid gland, real-time collision detection is required. If a collision is detected, the movement of the mechanical arm will be limited to avoid the collision between the mechanical arm and other parts. At this time, the posture of the probe needs to be adjusted. This can be achieved specifically through the following steps:

[0130] S107, perform real-time collision detection during the transfer of the ultrasonic robot probe. If it is detected that a collision has caused the robot arm to have motion limit, obtain the torque of the X-axis of the tool coordinate system at the end of the ultrasonic robot robot arm, and determine whether the torque is less than the preset torque threshold. If so, calculate the amount of posture change for releasing the limit based on the torque and the preset torque threshold, and adjust the robot arm based on the amount of posture change for releasing the limit.

[0131] Specifically, real-time collision detection can be performed during the transfer of the ultrasonic robot probe. If a collision is detected that causes the robot arm to have motion limitation, the torque t of the X-axis of the tool coordinate system at the end of the robot arm is obtained from the six-dimensional sensor of the probe at the end of the robot arm. x , determine whether the torque is less than the preset torque threshold t xmax If not, it means that the torque is relatively large at this time, but the limit state has not been released. At this time, it is necessary to switch to manual control or start the thyroid scan from the beginning. If yes, it means that the motion limit can be released by adjusting the posture. According to the torque and the preset torque threshold, the release limit posture change is calculated based on the following formula 4:

[0132]

[0133] In the formula, Δr x is the change in the X-axis position release of the tool coordinate system at the end of the robot arm, and Δt is the torque t x and preset torque threshold t xmax The difference, k p , k i and k d They represent the proportional coefficient, integral coefficient, and derivative coefficient of the PID controller (Proportional-Integral-Derivative Controller), which can be set to 0.15, 0.0001, and 0.00005, respectively.

[0134] Among them, the preset torque threshold t xmaxIt can be set to 0.05N / m to ensure that the probe will not cause excessive squeezing pressure on the human neck organs during movement.

[0135] Based on the change in the posture after releasing the limit, the posture adjustment can be performed to put the robot arm in a non-motion limit state, ensuring successful transfer of the probe to the target side.

[0136] In the embodiment of the present application, the above step S107 can effectively reduce the risk of collision between the robotic arm and the body by real-time monitoring and adjusting the posture of the robotic arm, ensure safe operation, and timely adjust the probe posture when encountering motion limit, increase the range of motion, and improve operational flexibility. The specific application of the PID controller to achieve precise adjustment of the posture makes the probe more sensitive to the change of torque, thereby ensuring that the probe can successfully complete the transfer on both sides, further improving patient safety, and improving the safety and effectiveness of the method.

[0137] Embodiment 2

[0138] Based on the same inventive concept, the embodiment of the present invention also provides a transfer control device for autonomously scanning the thyroid gland by an ultrasonic robot, referring to Fig.10 As shown, the device comprises:

[0139] The mobile acquisition module 101 is used to control the probe of the ultrasonic robot to move from the initial position on the starting side to the target side by a first preset distance, and to acquire ultrasonic images in real time, and to record and update the total moving distance and the distance from the trachea in real time;

[0140] A first judgment module 102 is used to perform a first image segmentation on the ultrasound image to obtain a thyroid contour area and determine the validity of the ultrasound image;

[0141] The second judgment module 103, if the ultrasound image is valid, continues to judge, and if a preset number of consecutive ultrasound images are valid, it is determined that the probe has completed the transfer of the two sides;

[0142] The third judgment module 104, if the ultrasound image is invalid, performs a second image segmentation on the ultrasound image, fits the contour features of the trachea and the carotid artery, and determines whether the probe has completed the transfer on both sides in combination with the distance from the probe to the center of the neck; if so, determines that the probe has completed the transfer on both sides;

[0143] The fourth judgment module 105, if the probe has not completed the transfer of both sides, determines whether the distance from the trachea is greater than a second preset distance; if so, determines that the probe has completed the transfer of both sides;

[0144] The fifth judgment module 106 determines whether the distance from the trachea is greater than the second preset distance if the distance from the trachea is not greater than the second preset distance; if so, determines that the probe has completed the transfer of both sides; if not, re-executes the mobile acquisition module.

[0145] Embodiment 3

[0146] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium having a computer program / instruction stored thereon. When the computer program / instruction is executed by a processor, the method for controlling the transfer of the thyroid gland by an ultrasonic robot for autonomous scanning is implemented as described in the first embodiment above.

[0147] Embodiment 4

[0148] Based on the same inventive concept, an embodiment of the present invention further provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the metastasis control method for autonomously scanning the thyroid gland by an ultrasonic robot as described in the above-mentioned embodiment 1.

[0149] Embodiment 5

[0150] Based on the same inventive concept, an embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory. When the processor executes the computer program, it implements the metastasis control method for autonomously scanning the thyroid gland by an ultrasonic robot as described in the above embodiment 1.

[0151] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0152] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0153] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0154] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0155] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for controlling the transfer of thyroid glands by an ultrasonic robot for autonomous scanning, characterized in that: include: Controlling the probe of the ultrasonic robot to move a first preset distance from an initial position on the starting side to a target side, and acquiring ultrasonic images in real time, and recording and updating the total moving distance and the distance from the trachea in real time; Performing a first image segmentation on the ultrasound image to obtain a thyroid contour area and determine the validity of the ultrasound image; If a preset number of consecutive ultrasound images are valid, it is determined that the probe has completed the transfer of both sides; Otherwise, performing a second image segmentation on the ultrasound image, fitting the contour features of the trachea and the carotid artery, and combining the acquired distance from the probe to the center of the neck to determine whether the probe has completed the transfer to both sides; If not, determining whether the distance from the trachea is greater than a second preset distance; If not, determining whether the total moving distance is greater than a preset maximum distance; If not, re-execute the above transfer process; If so, it is determined that the probe has completed the transfer on both sides.

2. The method according to claim 1, characterized in that The performing a second image segmentation on the ultrasound image, fitting to obtain contour features of the trachea and the carotid artery, and combining the obtained distance from the probe to the center of the neck to determine whether the probe has completed the transfer to both sides, includes: Performing a second image segmentation on the ultrasonic image to obtain a carotid artery contour and a trachea contour; Performing ellipse fitting on the carotid artery contour and the trachea contour respectively to obtain contour features of the carotid artery and the trachea; Determining whether the positions of the carotid artery and the trachea meet a preset conditional relationship according to the contour features of the carotid artery and the trachea; Obtaining and determining whether the distance from the probe to the center of the neck reaches a third preset distance; If both are true, it is determined that the probe has completed the transfer on both sides.

3. The method according to claim 2, characterized in that The contour features of the carotid artery include the contour area of ​​the carotid artery and the coordinates of the center point of the carotid artery; the contour features of the trachea include the contour area of ​​the trachea and the coordinates of the center point of the trachea; the preset conditional relationship includes a first conditional relationship and a second conditional relationship; The determining, based on the contour features of the carotid artery and the trachea, whether the positions of the carotid artery and the trachea meet a preset conditional relationship includes: Determining whether the carotid artery contour area and the carotid artery center point coordinates satisfy the first conditional relationship; The first conditional relationship is that the carotid artery contour area is greater than a preset carotid artery minimum threshold, and the difference between the coordinates of the carotid artery center point and the coordinates of the preset carotid artery target center point is greater than a first preset threshold; Determine whether at least one of the trachea center point coordinates and the trachea contour area satisfies a second conditional relationship; the second conditional relationship is that the trachea center point coordinates are located on the target side of the carotid artery center point coordinates, or the trachea contour area is smaller than a preset minimum trachea contour area.

4. The method according to claim 1, characterized in that Also includes: Performing real-time collision detection during the transfer of the ultrasonic robot probe, if a collision is detected, obtaining the torque of the X-axis of the tool coordinate system at the end of the ultrasonic robot mechanical arm, and determining whether the torque is less than a preset torque threshold; If so, the amount of change in the posture for releasing the limit is calculated according to the torque and the preset torque threshold, and the robotic arm is adjusted according to the amount of change in the posture for releasing the limit.

5. The method according to claim 1, characterized in that When the distance from the trachea is recorded in real time, it also includes: Acquire the contour features of the trachea; the contour features of the trachea include the trachea contour area and the coordinates of the trachea center point; If the difference between the coordinates of the trachea center point and the preset central position is less than the set threshold, and whether the trachea contour area is greater than the preset minimum trachea contour area, the distance from the trachea is set to 0.

6. The method according to claim 1, characterized in that The performing a first image segmentation on the ultrasound image to obtain a thyroid contour area and determine the validity of the ultrasound image includes: A first image segmentation is performed on the ultrasound image to obtain a thyroid contour area. If the thyroid contour area is greater than a preset area threshold, the ultrasound image is determined to be a valid image.

7. A transfer control device for autonomously scanning the thyroid gland by an ultrasonic robot, characterized in that: include: A mobile acquisition module, used to control the probe of the ultrasonic robot to move from an initial position on the starting side to a first preset distance on the target side, and to acquire ultrasonic images in real time, and to record and update the total moving distance and the distance from the trachea in real time; A first judgment module is used to perform a first image segmentation on the ultrasound image to obtain a thyroid contour area and determine the validity of the ultrasound image; The second judgment module continues to judge if the ultrasound image is valid, and if a preset number of consecutive ultrasound images are valid, it is determined that the probe has completed the transfer of the two sides; The third judgment module, if the ultrasound image is invalid, performs a second image segmentation on the ultrasound image, fits the contour features of the trachea and the carotid artery, and determines whether the probe has completed the transfer on both sides in combination with the distance from the probe to the center of the neck; if so, determines that the probe has completed the transfer on both sides; The fourth judgment module, if the probe has not completed the transfer of both sides, determines whether the distance from the trachea is greater than a second preset distance; if so, determines that the probe has completed the transfer of both sides; The fifth judgment module determines whether the distance from the trachea is greater than the second preset distance if the distance from the trachea is not greater than the second preset distance; if so, determines that the probe has completed the transfer of both sides; if not, re-executes the mobile acquisition module.

8. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the transfer control method for autonomously scanning the thyroid gland by an ultrasonic robot as described in any one of claims 1 to 6 is implemented.

9. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the transfer control method for autonomously scanning the thyroid gland by an ultrasonic robot as described in any one of claims 1 to 6 is implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the transfer control method for autonomously scanning the thyroid gland by an ultrasonic robot as described in any one of claims 1-6.

Images