CN115869013A - Blood vessel positioning and navigation method for blood vessel ultrasonic autonomous scanning - Google Patents
Blood vessel positioning and navigation method for blood vessel ultrasonic autonomous scanning Download PDFInfo
- Publication number
- CN115869013A CN115869013A CN202211574474.8A CN202211574474A CN115869013A CN 115869013 A CN115869013 A CN 115869013A CN 202211574474 A CN202211574474 A CN 202211574474A CN 115869013 A CN115869013 A CN 115869013A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- ultrasonic
- probe
- control module
- main control
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 121
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000000523 sample Substances 0.000 claims abstract description 177
- 238000002604 ultrasonography Methods 0.000 claims description 33
- 210000001367 artery Anatomy 0.000 claims description 15
- 210000003462 vein Anatomy 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 10
- 230000004807 localization Effects 0.000 claims 2
- 238000003384 imaging method Methods 0.000 abstract description 6
- 238000012545 processing Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 210000001715 carotid artery Anatomy 0.000 description 17
- 238000001514 detection method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 238000010191 image analysis Methods 0.000 description 3
- 210000001685 thyroid gland Anatomy 0.000 description 3
- 230000017531 blood circulation Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008321 arterial blood flow Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000003109 clavicle Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 210000004373 mandible Anatomy 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000008320 venous blood flow Effects 0.000 description 1
Images
Landscapes
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention relates to a blood vessel positioning and navigation method for blood vessel ultrasonic autonomous scanning, which comprises a main control module, ultrasonic equipment and a robot, wherein the main control module is coupled with an ultrasonic probe and the robot, the ultrasonic probe of the ultrasonic equipment is arranged on the robot and is used for acquiring an ultrasonic image, and the main control module is used for identifying a blood vessel in the ultrasonic image so as to control the ultrasonic probe to move along the blood vessel. To sum up, the above technical scheme has the following beneficial effects: the ultrasonic probe is used for acquiring a two-dimensional ultrasonic image, the ultrasonic probe is combined with the robot, the main control module searches an ideal imaging plane of a blood vessel by adjusting the position and rotation of the ultrasonic probe, and controls the ultrasonic probe to move along the position of the blood vessel, so that the robot capable of automatically scanning is formed, and finally the positioning and navigation of the blood vessel are completed. The scheme does not need to carry out three-dimensional modeling on the blood vessel, and has the characteristics of less consumed computing resources, high processing speed, high scanning precision and the like.
Description
Technical Field
The invention relates to the technical field of ultrasonic imaging, in particular to a blood vessel positioning and navigating method for blood vessel ultrasonic autonomous scanning.
Background
The blood vessel ultrasonic scanning is a cheap, universal, rapid and accurate blood vessel plaque screening method, and the AI robot automatic scanning has important significance for solving the shortage of medical resources in the grassroots and remote areas.
The existing ultrasonic automatic scanning method, such as a three-dimensional neck ultrasonic automatic scanning and evaluating system and method disclosed in the publication No. CN114831664A, comprises an ultrasonic scanning module for obtaining image information of thyroid gland or neck blood vessel scanned by an ultrasonic probe; the ultrasonic imaging module is connected with the ultrasonic scanning module and used for establishing a three-dimensional image of the thyroid or the neck blood vessel based on the acquired image information; and the image analysis module is connected with the ultrasonic imaging module and used for analyzing the established three-dimensional image to obtain an analysis result of the thyroid or the neck blood vessel. The scanning method needs to combine the ultrasonic two-dimensional image with robot operation to generate three-dimensional point cloud and the like for calculation. The method based on three-dimensional reconstruction can enlarge precision errors, and more computing resources are consumed, so that the real-time performance is difficult to meet.
Therefore, how to reduce the computing resources and quickly scan the blood vessel is the technical problem to be solved by the present application.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a blood vessel positioning and navigation method for blood vessel ultrasonic autonomous scanning, which automatically completes the positioning and navigation of a blood vessel according to an ultrasonic two-dimensional picture by adjusting the position of an ultrasonic probe through a control robot.
In order to realize the purpose, the following technical scheme is provided:
a blood vessel positioning and navigation method for blood vessel ultrasonic autonomous scanning comprises a main control module, an ultrasonic device and a robot, wherein the main control module is coupled with an ultrasonic probe and the robot, the ultrasonic probe of the ultrasonic device is arranged on the robot and is used for acquiring an ultrasonic image, and the main control module is used for identifying a blood vessel in the ultrasonic image so as to control the ultrasonic probe to move along the blood vessel.
To sum up, the technical scheme has the following beneficial effects: the main control module is a PC or other equipment with control function, the robot comprises a mechanical arm, a simulation robot and other equipment which can control the movement of the ultrasonic equipment probe, the ultrasonic probe is connected with the conventional medical ultrasonic diagnostic equipment and is used for acquiring two-dimensional ultrasonic images, the ultrasonic probe is combined with the robot, the main control module searches an ideal imaging plane of the blood vessel by controlling the translation and rotation of the ultrasonic probe and controls the ultrasonic probe to move along the position of the blood vessel, so that the robot capable of scanning automatically is formed, and finally the positioning and navigation of the blood vessel are completed. The scheme does not need to carry out three-dimensional modeling on the blood vessel, and has the characteristics of less consumed computing resources, high processing speed, high scanning precision and the like.
Drawings
FIG. 1 is a diagrammatic illustration of a color Doppler ultrasound of a blood vessel;
FIG. 2 is a schematic view of the results of a blood vessel;
FIG. 3 is a schematic diagram of a binarized image of a blood vessel;
FIG. 4 is a schematic diagram of a black region;
FIG. 5 is a schematic view of a flow chart for controlling the movement of a blood vessel to the center of the coordinate system of the ultrasonic image;
FIG. 6 is a schematic view of a flowchart for determining the minimum cross-sectional area of a blood vessel;
FIG. 7 is a schematic diagram of automatic adjustment of an ultrasound probe;
FIG. 8 is a schematic diagram of the movement of the ultrasonic probe;
fig. 9 is a schematic view of the rotation angle of the ultrasonic probe.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. In the following description, numerous specific details are set forth in order to provide a better understanding of the present application. However, those skilled in the art will readily recognize that some of the features may be omitted in different instances or may be replaced by other materials, methods. In some instances, certain operations related to the present application have not been shown or described in detail in order to avoid obscuring the core of the present application from excessive description, and it is not necessary for those skilled in the art to describe these operations in detail, so that they may be fully understood from the description in the specification and the general knowledge in the art.
Furthermore, the described features, operations, or characteristics may be combined in any suitable manner to form various embodiments. Also, the various steps or actions in the method descriptions may be transposed or transposed in order, as will be apparent to one of ordinary skill in the art. Thus, the various sequences in the specification and drawings are for the purpose of describing certain embodiments only and are not intended to imply a required sequence unless otherwise indicated where such sequence must be followed.
A blood vessel positioning and navigation method for blood vessel ultrasonic autonomous scanning comprises a main control module, an ultrasonic device and a robot, wherein the main control module is coupled with an ultrasonic probe and the robot, the ultrasonic probe of the ultrasonic device is arranged on the robot and is used for acquiring an ultrasonic image, and the main control module is used for identifying a blood vessel in the ultrasonic image so as to control the ultrasonic probe to move along the blood vessel. The main control module is a PC or other equipment with control function, the robot comprises a mechanical arm, a simulation robot and other equipment which can control the movement of the ultrasonic equipment probe, the ultrasonic probe is connected with the conventional medical ultrasonic diagnostic equipment and is used for acquiring two-dimensional ultrasonic images, the ultrasonic probe is combined with the robot, the main control module searches an ideal imaging plane of the blood vessel by controlling the translation and rotation of the ultrasonic probe and controls the ultrasonic probe to move along the position of the blood vessel, so that the robot capable of scanning automatically is formed, and finally the positioning and navigation of the blood vessel are completed. The scheme does not need to carry out three-dimensional modeling on the blood vessel, and has the characteristics of less consumed computing resources, high processing speed, high scanning precision and the like. The main control module identifies the blood vessel in the ultrasonic image by the following processes:
as shown in fig. 1-3, the main control module controls each single-frame ultrasound image to be converted from an RGB color space to an HSV color space, a binary image is obtained through a red-blue threshold, and the main control module determines whether a blood vessel is an artery or a vein according to the number of times of occurrence of the binary image in the multi-frame ultrasound images; if the ratio of the occurrence times of the binary image in the multi-frame ultrasonic image is greater than or equal to the artery threshold value, judging that the image is an artery; and if the ratio of the occurrence times of the binary images in the multi-frame ultrasonic image is greater than the vein threshold and smaller than the artery threshold, judging that the image is a vein.
Under the condition that the arteriovenous activity is influenced according to different crowds and different conditions, the artery threshold and the vein threshold can be properly adjusted, wherein the adjustment interval of the artery threshold is between 60% and 90%, for example, the artery threshold is adjusted to 70%, 75% or 85%, and the adjustment interval of the vein threshold is adjusted to 10% to 30%, for example, the vein threshold is adjusted to 15% or 25%. Preferably, the arterial threshold is 80% and the venous threshold is 20%.
The main control module utilizes the characteristics that venous blood flow is stable and can not flow back and arterial blood flow has pulsation by using an arteriovenous recognition algorithm based on a Doppler image. Under Doppler color ultrasound, the blood flow of veins is stable in red and blue, and the blood flow of arteries alternately appears or appears discontinuously to identify arteriovenous vessels. A arteriovenous identification algorithm process, namely, converting a single-frame image from an RGB color space to an HSV color space, obtaining a blue area binary image through a red-blue threshold, counting the occurrence frequency of red or blue at each position of a video frame sequence by taking 20 frames as a window, and if the occurrence frequency of red or blue is more than or equal to 16 times (the proportion is more than or equal to 80%), judging that the pixel is a vein; if the red or blue appears less than 16 times and more than 2 times (the proportion is more than 10 percent and less than 80 percent), judging the pixel as an artery; if the number of occurrences of red or blue is 2 or less (the ratio is 10% or less), it is determined that the pixel is not a blood vessel. The video output module of the ultrasonic equipment is coupled with the main control module, the main control module can complete functions of blood vessel identification, image analysis and the like according to the ultrasonic picture/video, and the image analysis comprises functions of blood vessel identification, plaque identification, intima-media thickness measurement and the like.
The main control module judges whether the ultrasonic probe is positioned on a skin plane normal vector according to whether a black area exists in the ultrasonic image; and when the black area exists in the ultrasonic image, judging that the ultrasonic probe is not positioned on the normal vector of the skin plane, and controlling the ultrasonic probe to move to adjust the ultrasonic image.
As shown in fig. 4, the control module controls the ultrasonic probe to move according to the probe coordinate system; the longitudinal extending direction of the ultrasonic probe picture is the Z axis of the probe coordinate system, the transverse extending direction of the ultrasonic probe picture is the X axis of the probe coordinate system, and the direction vertical to the ultrasonic probe picture is the Y axis of the probe coordinate system; a pixel threshold value is arranged in the main control module, a black area is an area where the pixel value of the ultrasonic image is lower than the pixel threshold value, and the main control module averagely divides the ultrasonic image into a left part and a right part and calculates the pixel average value; when the left part and the right part are judged to have black areas, the ultrasonic probe is controlled to move along the Z axis of the probe coordinate system; when only the left part is judged to have the black area, controlling the ultrasonic probe to rotate around the Y axis of the probe coordinate system to the left side; and when only the right part is judged to have the black area, controlling the ultrasonic probe to rotate around the Y axis of the probe coordinate system to the right side. In order to obtain a clear ultrasound image, the probe surface should remain in contact with the subject's skin. However, the surface of the skin is not flat. Sometimes there is a gap between the skin and a portion of the ultrasound probe surface, resulting in an unclear ultrasound image being acquired. Therefore, if a black region is detected in the ultrasound image, the probe needs to be rotated to eliminate the black region. Specifically, when the left part and the right part are judged to have black areas, the ultrasonic probe is controlled to move 1mm along the Z axis of the probe coordinate system, and when only the left part is judged to have the black areas, the ultrasonic probe is controlled to rotate 5 degrees to the left side around the Y axis of the probe coordinate system; and when only the right part is judged to have the black area, controlling the ultrasonic probe to rotate 5 degrees to the right side around the Y axis of the probe coordinate system. According to the three conditions, the position of the ultrasonic probe is repeatedly adjusted until no black area exists in the ultrasonic image.
The robot is provided with a pressure sensor which is used for detecting the pressure of the ultrasonic probe acting on the skin; the main control module is coupled with the pressure sensor, a pressure threshold value is preset in the main control module, and the main control module is used for collecting a pressure value detected by the pressure sensor and judging whether the pressure value is greater than the pressure threshold value; and when the main control module judges that the pressure value is greater than the pressure threshold value, controlling the ultrasonic probe to stop moving. The pressure sensor has two mounting methods, one is provided with the pressure sensor only at the end of the mechanical arm, and the second is provided with the pressure sensor at each joint. The ultrasonic probe can have different pressure thresholds in different moving directions, for example, the pressure threshold for the ultrasonic probe to press down along the Z axis is 10N, and when the main control module controls the ultrasonic probe to press down along the Z axis and judges that the pressure value in the Z axis direction is greater than 10N, the ultrasonic probe is controlled to stop moving. The pressure threshold value of the ultrasonic probe moving along the Y axis or the X axis is 20N, and when the main control module controls the ultrasonic probe to move along the Y axis or the X axis and judges that the pressure value in the Y axis or the X axis direction is greater than 20N, the ultrasonic probe is controlled to stop moving. In the scanning process, the robot is flexibly controlled and has collision detection and protection functions, when the robot control module detects that the stress of the robot is greater than a set value, the robot is controlled to stop moving, and after the operator confirms safety, collision alarm is relieved, the robot can be controlled to move, so that the safety of a human body is guaranteed.
When the patient moves slightly, the ultrasound probe must be maintained in contact with the surface of the neck. The invention does this by applying force control to the robot in the z-axis direction of the probe coordinate system of the probe, and on the other hand, the force control mode can protect constant contact force and play a role in safety protection. The other axes of the robot adopt a position control mode to keep the scanning track unaffected. Since the force torque of the ultrasonic probe tip needs to be calculated through the joint, defined as F z . The invention is intended to obtain a contact force from the probe to the neck, defined as F d . The contact force is used to maintain the applied force of the ultrasound probe. The robot designs PI controller in scanning z-axis direction for direct force control to maintain stable contact of probe, and inputs tau to stress moment control F Comprises the following steps:
τ F ＝J T (q)(F d +K p F e +K 1 ∫F e (t)dt) (1)
F e ＝F d -F z (2)
in formulae (1) and (2), F e Scanning the robot for contact force deviations, K p And K 1 Proportional gain and product, respectivelyAnd dividing the gain. J. the design is a square T (q) is the transpose of the robot jacobian matrix.
As shown in fig. 5, the process of controlling the ultrasonic probe to move along the artery and vein by the main control module includes the following steps: the main control module determines the position of the ultrasonic probe according to the world coordinate system, and when the main control module judges that the ultrasonic probe is positioned on the normal vector of the skin plane, the main control module records the coordinate of the ultrasonic probe based on the world coordinate system as a scanning start bit; the main control module controls the ultrasonic probe to move in a direction parallel to the blood vessel, and during the movement process, the main control module constantly judges whether the blood vessel exists on the ultrasonic image, whether a black area exists in the ultrasonic image and whether the pressure value of the pressure sensor is greater than a pressure threshold value; the main control module controls the ultrasonic probe to move along an X axis of a probe coordinate system according to the distance between the center of mass coordinate of the blood vessel region and the center line of the ultrasonic image, so that the center of mass of the blood vessel region is moved to the center line of the ultrasonic image; when the main control module judges that the center of mass of the blood vessel region moves to the central line of the ultrasonic image, the ultrasonic probe is controlled to move along the Y axis of the probe coordinate system, and the ultrasonic probe is automatically adjusted to enable the center of mass of the blood vessel region to be located on the central line of the ultrasonic image; and determining the centroid of each frame of blood vessel region according to the world coordinate system, thereby completing the navigation of the blood vessel. The ultrasound image coordinate system in the flowchart of fig. 5 is a control process performed with the image center as the origin of the coordinate system, that is, when the X-axis coordinate of the blood vessel centroid is 0, the blood vessel region centroid is located on the central line of the ultrasound image; if the origin of the ultrasonic image coordinate system changes, the X coordinate of the center of mass of the blood vessel area correspondingly changes, and the X coordinate is equal to the X axis of the central line of the current ultrasonic picture.
As shown in fig. 6, when the main control module judges that the center of mass of the blood vessel region moves to the center line of the ultrasound image for the first time, the ultrasonic probe is controlled to rotate along the Z axis of the probe coordinate system, so as to find the minimum cross section of the blood vessel; when the main control module detects the minimum cross section of the blood vessel, the main control module determines the coordinates of the centroid of the blood vessel area according to the ultrasonic image coordinate system. The ultrasound probe is adjusted at 1 ° each time it is rotated along the Z-axis of the probe coordinate system.
As shown in fig. 7-8, automatically adjusting the ultrasound probe includes the following processes: the main control module controls the ultrasonic probe to probe along the edgeWhen the side line of the blood vessel is judged to be tangent to the center line of the ultrasonic image, recording the moving distance of the ultrasonic probe along the Y axis of the probe coordinate system, and controlling the ultrasonic probe to move along the X axis of the probe coordinate system; when the main control module judges that the center of mass of the blood vessel region moves to the center line of the ultrasonic image again, the moving distance of the ultrasonic probe along the X axis of the probe coordinate system is recorded, and the rotating angle is calculated according to the moving distance of the ultrasonic probe along the Y axis of the probe coordinate system and the moving distance along the X axis of the probe coordinate system; the main control module controls the ultrasonic probe to rotate along the Z axis of the probe coordinate system according to the rotation angle. The main control module needs to repeatedly compare and find the minimum blood vessel cross section according to the rotating ultrasonic probe when detecting the blood vessel for the first time, in the navigation process, the navigation of the blood vessel can be completed only by automatically calculating the rotating angle according to the moving distance, the calculated amount of the blood vessel navigation is reduced, as shown in fig. 8 and 9, the moving distance of the ultrasonic probe along the Y axis of the probe coordinate system is an AB section, the moving distance of the ultrasonic probe along the X axis of the probe coordinate system is a BC section, and the rotating angle theta is calculated according to a trigonometric function. And repeating the steps to realize the vessel navigation of the target length. O is world Expressed as a world coordinate system, O probe Expressed as the probe coordinate system, O image The ultrasonic image coordinate system is represented as an ultrasonic image coordinate system, the ultrasonic image coordinate system and the probe coordinate system can change along with the change of the ultrasonic probe, the world coordinate system is fixed all the time, the world coordinate system is used for determining the position of the ultrasonic probe and the position of a blood vessel, the probe coordinate system is used for conveniently controlling the movement of the probe, and the ultrasonic image coordinate system is used for conveniently determining the position of the centroid of the blood vessel region.
When the main control module detects the minimum cross section of the blood vessel or automatically adjusts the ultrasonic probe each time, the ultrasonic probe is controlled to rotate 90 degrees along the Z axis of the probe coordinate system, so that an ultrasonic image of the longitudinal section of the blood vessel is acquired, the ultrasonic probe is controlled to rotate 90 degrees anticlockwise along the Z axis of the probe coordinate system after the ultrasonic image of the longitudinal section of the blood vessel is acquired each time, and the main control module is used for summarizing the ultrasonic images of all the longitudinal sections of the blood vessel and generating a scanning report. The main control module performs blood vessel identification, plaque identification and measurement of intima-media thickness and the current pose of the robot according to the ultrasonic image of the longitudinal section of the blood vessel, so as to generate a scanning report.
The main control module utilizes an image segmentation network (such as UNet) to identify carotid artery and vein through the manually marked blood vessel region, and then utilizes opencv to distinguish the artery and analyze the black region. The ultrasound image is sampled at a rate of at least 5 frames/second, and an image in RGB format is output. On a Jetson Nano chip, a processing speed of 20 frames per second can be guaranteed.
The ultrasound probe scanning protocol implemented on the robot is based on a program that is actually described by the ultrasound scanning clinic, during which the patient will remain in a supine position. The following scanning procedure of the ultrasound probe by scanning the carotid artery is taken as an example: 1. the ultrasonic probe is manually dragged to a scanning starting position, and the main control module controls the ultrasonic probe to move to a scanning ending position. The starting point for carotid scanning is at the cervical clavicle. The end point of the carotid scan is near the top of the neck of the mandible. 2. And detecting and eliminating the black area, controlling the ultrasonic probe to rotate around the y axis along the direction of the black area when the black area is detected, and eliminating the black area. 3. And detecting the carotid artery, and adjusting the carotid artery to the image center position. 4. The carotid minimum cross section is located and used in the initial position to ensure that the probe is perpendicular to the vessel. 5. A carotid artery profile was obtained with a 90 clockwise rotation around the z-axis. 6. And moving the next scanning point, namely moving the probe along the y axis for 10mm, circulating for more than 10 times, and finishing scanning. 7. And finishing scanning until the blood vessel bifurcation position is found or the pressure sensor judges that the pressure exceeds the threshold value.
To verify the validity of the proposed carotid artery detection model, we applied the proposed detection model to 100 images randomly selected from 25 healthy volunteers (15 men and 10 women). All images contained carotid transverse and longitudinal sections. In all cases, the carotid artery detection model successfully identified the carotid artery in the ultrasound image. We evaluated the accuracy of the detected contour of the carotid wall. In this experiment, the extracted contours were considered accurate when they were just inside or above the carotid wall. Conversely, if any portion of the extracted contour line is outside the carotid artery, it is considered inaccurate.
The accuracy of the carotid cross-sectional examination was 96%. The carotid artery in the ultrasonic image is obvious in transection, and other similar parts consistent with the carotid artery structure are not seen. The accuracy of the carotid longitudinal section examination was 92%.
To verify the effectiveness of the present invention, we performed actual carotid scanning experiments on 10 volunteers. In this experiment, we asked the subject to lie in bed in a supine position. The manipulator of the automated scanning system was then placed by the operator perpendicular to the body centerline at about 5mm from the neck surface of the ultrasound probe. Thereafter, the operator presses the start button, waiting for the entire sequence to complete. Each subject performed 3 trials, 30 trials with 27 successful completions (90%). A carotid artery identification model is obtained by learning a large number of marked carotid artery ultrasonic images. For the detection of carotid artery, it can be concluded that the identification of the transverse and longitudinal features has been successfully achieved, and the success rate of the detection of carotid artery is greater than 90%. According to the invention, a carotid artery identification model is obtained by learning a large number of marked carotid artery ultrasonic images, and identification of the transverse and longitudinal characteristics of the blood vessel can be obtained by rotating the ultrasonic probe, so that the search of the blood vessel is faster and more convenient compared with the three-dimensional search of the blood vessel.
The above are only preferred embodiments of the present invention, and the scope of the present invention is not limited to the above examples, and all technical solutions that fall under the spirit of the present invention belong to the scope of the present invention. It should be noted that modifications and adaptations to those skilled in the art without departing from the principles of the present invention should also be considered as within the scope of the present invention.
Claims (10)
1. A blood vessel positioning and navigating method for blood vessel ultrasonic autonomous scanning is characterized by comprising a main control module, an ultrasonic device and a robot, wherein the main control module is coupled with the ultrasonic device and the robot, an ultrasonic probe of the ultrasonic device is arranged on the robot and is used for acquiring an ultrasonic image, and the main control module is used for identifying a blood vessel in the ultrasonic image so as to control the ultrasonic probe to move along the blood vessel.
2. The blood vessel positioning and navigation method for the ultrasound autonomous scan of blood vessels as claimed in claim 1, wherein the identification of the blood vessel in the ultrasound image by the master control module comprises the following procedures:
the main control module controls each single-frame ultrasonic image to be converted from an RGB color space to an HSV color space, a binary image is obtained through a red-blue threshold value, and the main control module judges whether a blood vessel is an artery or a vein according to the number of times of appearance of the binary image in the multi-frame ultrasonic images;
if the ratio of the occurrence times of the binary image in the multi-frame ultrasonic image is greater than or equal to the artery threshold value, judging that the image is an artery;
and if the ratio of the occurrence times of the binary images in the multi-frame ultrasonic image is greater than the vein threshold and smaller than the artery threshold, judging that the image is a vein.
3. A vessel localization and navigation method for ultrasound autonomous scanning of vessels according to claim 2, characterized in that the arterial threshold is 80% and the venous threshold is 20%.
4. The blood vessel positioning and navigating method for the ultrasonic autonomous scanning of the blood vessel according to claim 1, wherein the main control module judges whether the ultrasonic probe is positioned on a normal vector of a skin plane according to whether a black area exists in the ultrasonic image;
and when the black area exists in the ultrasonic image, judging that the ultrasonic probe is not positioned on the normal vector of the skin plane, and controlling the ultrasonic probe to move to adjust the ultrasonic image.
5. The blood vessel positioning and navigation method for the blood vessel ultrasonic autonomous scanning according to claim 4, characterized in that the main control module controls the ultrasonic probe to move according to a probe coordinate system;
the longitudinal extending direction of the ultrasonic probe picture is the Z axis of the probe coordinate system, the transverse extending direction of the ultrasonic probe picture is the X axis of the probe coordinate system, and the direction vertical to the ultrasonic probe picture is the Y axis of the probe coordinate system;
a pixel threshold value is arranged in the main control module, a black area is an area where the pixel value of the ultrasonic image is lower than the pixel threshold value, and the main control module averagely divides the ultrasonic image into a left part and a right part and calculates the pixel average value;
when the left part and the right part are judged to have black areas, the ultrasonic probe is controlled to move along the Z axis of the probe coordinate system;
when only the left part is judged to have a black area, controlling the ultrasonic probe to rotate around the Y axis of the probe coordinate system to the left side;
and when only the right part is judged to have the black area, controlling the ultrasonic probe to rotate around the Y axis of the probe coordinate system to the right side.
6. The blood vessel positioning and navigating method for the ultrasonic autonomous scan of blood vessels according to claim 5, characterized in that a pressure sensor is arranged on the robot and used for detecting the pressure of the ultrasonic probe acting on the skin;
the main control module is coupled with the pressure sensor, a pressure threshold value is preset in the main control module, and the main control module is used for collecting a pressure value detected by the pressure sensor and judging whether the pressure value is greater than the pressure threshold value;
and when the main control module judges that the pressure value is greater than the pressure threshold value, controlling the ultrasonic probe to stop moving.
7. The blood vessel positioning and navigation method for the blood vessel ultrasonic autonomous scan according to claim 6, characterized in that the main control module controls the ultrasonic probe to move along the blood vessel comprising the following processes:
the main control module determines the position of the ultrasonic probe according to a world coordinate system, and when the main control module judges that the ultrasonic probe is positioned on a skin plane normal vector, the main control module records the coordinate of the ultrasonic probe based on the world coordinate system as a scanning start position;
the main control module controls the ultrasonic probe to move in a direction parallel to the blood vessel, and in the moving process, the main control module constantly judges whether the blood vessel exists on the ultrasonic image, whether a black area exists in the ultrasonic image and whether the pressure value of the pressure sensor is greater than a pressure threshold value;
the main control module controls the ultrasonic probe to move along an X axis of a probe coordinate system according to the distance between the center of mass of the blood vessel region and the center line of the ultrasonic image, so that the center of mass of the blood vessel region is moved to the center line of the ultrasonic image;
when the main control module judges that the center of mass of the blood vessel region moves to the central line of the ultrasonic image, the ultrasonic probe is controlled to move forward along the Y axis of the probe coordinate system, and the ultrasonic probe is automatically adjusted to enable the center of mass of the blood vessel region to be located on the central line of the ultrasonic image;
and determining the centroid of each frame of blood vessel region according to the world coordinate system, thereby completing the navigation of the blood vessel.
8. The blood vessel positioning and navigating method for the ultrasonic autonomous scan of the blood vessel as claimed in claim 7, wherein when the main control module judges for the first time that the center of mass of the blood vessel region moves to the centerline of the ultrasonic image, the ultrasonic probe is controlled to rotate along the Z-axis of the probe coordinate system, so as to find the minimum cross section of the blood vessel;
when the main control module detects the minimum cross section of the blood vessel, the main control module determines the coordinates of the centroid of the blood vessel area according to the ultrasonic image coordinate system.
9. The vessel localization and navigation method for ultrasound autonomous scanning of vessels according to claim 8, characterized in that automatically adjusting the ultrasound probe comprises the following procedures:
the main control module controls the ultrasonic probe to move along the Y axis of the probe coordinate system, when the side line of the blood vessel is judged to be tangent to the center line of the ultrasonic image, the moving distance of the ultrasonic probe along the Y axis of the probe coordinate system is recorded, and the ultrasonic probe is controlled to move along the X axis of the probe coordinate system;
when the main control module judges that the center of mass of the blood vessel region moves to the center line of the ultrasonic image again, recording the moving distance of the ultrasonic probe along the X axis of the probe coordinate system, and calculating a rotating angle according to the moving distance of the ultrasonic probe along the Y axis of the probe coordinate system and the moving distance along the X axis of the probe coordinate system;
and the main control module controls the ultrasonic probe to rotate along the Z axis of the probe coordinate system according to the rotation angle.
10. The method for locating and navigating the blood vessel according to claim 9, wherein the main control module collects the ultrasound image of the longitudinal section of the blood vessel by controlling the ultrasound probe to rotate 90 degrees clockwise along the Z-axis of the probe coordinate system when the main control module detects the minimum cross section of the blood vessel or automatically adjusts the ultrasound probe each time, and controls the ultrasound probe to rotate 90 degrees counterclockwise along the Z-axis of the probe coordinate system after each collection of the ultrasound image of the longitudinal section of the blood vessel, and the main control module is configured to summarize the ultrasound images of all the longitudinal sections of the blood vessel and generate a scanning report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211574474.8A CN115869013B (en) | 2022-12-08 | 2022-12-08 | Blood vessel positioning and navigation method for autonomous scanning of blood vessel ultrasound |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211574474.8A CN115869013B (en) | 2022-12-08 | 2022-12-08 | Blood vessel positioning and navigation method for autonomous scanning of blood vessel ultrasound |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115869013A true CN115869013A (en) | 2023-03-31 |
| CN115869013B CN115869013B (en) | 2024-07-12 |
Family
ID=85766621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211574474.8A Active CN115869013B (en) | 2022-12-08 | 2022-12-08 | Blood vessel positioning and navigation method for autonomous scanning of blood vessel ultrasound |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115869013B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116630256A (en) * | 2023-05-15 | 2023-08-22 | 什维新智医疗科技(上海)有限公司 | Ultrasonic contrast image identification method, system, electronic equipment and storage medium |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1968656A (en) * | 2004-06-11 | 2007-05-23 | 株式会社日立医药 | Ultrasonic curing device |
| CA2575066A1 (en) * | 2006-01-24 | 2007-07-24 | The University Of North Carolina At Chapel Hill | Systems and methods for detecting an image of an object by use of an x-ray beam having a polychromatic distribution |
| JP2008006243A (en) * | 2006-06-26 | 2008-01-17 | Tma Kikaku:Kk | Ultrasonic diagnostic apparatus with ultrasonic probe held by robot |
| CN101697871A (en) * | 2009-11-16 | 2010-04-28 | 华中科技大学 | Laser imaging method and device for automatically cutting artery blood vessel and vein blood vessel |
| CN101833757A (en) * | 2009-03-11 | 2010-09-15 | 深圳迈瑞生物医疗电子股份有限公司 | Method and system for detection edge of blood vessel graphic tissue structure and blood vessel endangium |
| CN102048559A (en) * | 2009-11-05 | 2011-05-11 | 久米伸治 | Processing device for ultrasonic tomographic image |
| US20120116227A1 (en) * | 2009-07-16 | 2012-05-10 | Unex Corporation | Ultrasonic blood vessel inspecting apparatus |
| CN102622587A (en) * | 2012-03-08 | 2012-08-01 | 哈尔滨工程大学 | Hand back vein recognition method based on multi-scale second-order differential structure model and improved watershed algorithm |
| US20120323118A1 (en) * | 2011-06-17 | 2012-12-20 | Carnegie Mellon University | Physics based image processing and evaluation process of perfusion images from radiology imaging |
| US20150049174A1 (en) * | 2013-08-13 | 2015-02-19 | Korea Institute Of Science And Technology | System and method for non-invasive patient-image registration |
| JP2015173899A (en) * | 2014-03-17 | 2015-10-05 | 株式会社東芝 | Ultrasonic diagnostic device, image processor and image processing program |
| CN105072980A (en) * | 2012-12-12 | 2015-11-18 | 光学实验室成像公司 | Method and apparatus for automated determination of a lumen contour of a blood vessel |
| CN105877780A (en) * | 2015-08-25 | 2016-08-24 | 上海深博医疗器械有限公司 | Full-automatic ultrasonic scanner and scanning detection method |
| CN111820917A (en) * | 2020-06-05 | 2020-10-27 | 哈工大机器人(中山)无人装备与人工智能研究院 | Binocular vision blood sampling device and blood sampling robot with same |
| CN112890867A (en) * | 2021-01-06 | 2021-06-04 | 杰杰医疗科技(苏州)有限公司 | Full-automatic peripheral blood vessel three-dimensional ultrasonic image reconstruction system and method |
| CN113349737A (en) * | 2021-06-30 | 2021-09-07 | 深圳英美达医疗技术有限公司 | Method for calibrating OCT image of intravascular dual-mode imaging system |
| CN113499099A (en) * | 2021-07-21 | 2021-10-15 | 上海市同仁医院 | Carotid artery ultrasonic automatic scanning and plaque identification system and method |
| CN114708280A (en) * | 2022-04-12 | 2022-07-05 | 吉林大学 | Cerebrovascular segmentation algorithm applicable to multiple modes |
-
2022
- 2022-12-08 CN CN202211574474.8A patent/CN115869013B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1968656A (en) * | 2004-06-11 | 2007-05-23 | 株式会社日立医药 | Ultrasonic curing device |
| CA2575066A1 (en) * | 2006-01-24 | 2007-07-24 | The University Of North Carolina At Chapel Hill | Systems and methods for detecting an image of an object by use of an x-ray beam having a polychromatic distribution |
| JP2008006243A (en) * | 2006-06-26 | 2008-01-17 | Tma Kikaku:Kk | Ultrasonic diagnostic apparatus with ultrasonic probe held by robot |
| CN101833757A (en) * | 2009-03-11 | 2010-09-15 | 深圳迈瑞生物医疗电子股份有限公司 | Method and system for detection edge of blood vessel graphic tissue structure and blood vessel endangium |
| US20120116227A1 (en) * | 2009-07-16 | 2012-05-10 | Unex Corporation | Ultrasonic blood vessel inspecting apparatus |
| CN102048559A (en) * | 2009-11-05 | 2011-05-11 | 久米伸治 | Processing device for ultrasonic tomographic image |
| CN101697871A (en) * | 2009-11-16 | 2010-04-28 | 华中科技大学 | Laser imaging method and device for automatically cutting artery blood vessel and vein blood vessel |
| US20120323118A1 (en) * | 2011-06-17 | 2012-12-20 | Carnegie Mellon University | Physics based image processing and evaluation process of perfusion images from radiology imaging |
| CN102622587A (en) * | 2012-03-08 | 2012-08-01 | 哈尔滨工程大学 | Hand back vein recognition method based on multi-scale second-order differential structure model and improved watershed algorithm |
| CN105072980A (en) * | 2012-12-12 | 2015-11-18 | 光学实验室成像公司 | Method and apparatus for automated determination of a lumen contour of a blood vessel |
| US20150049174A1 (en) * | 2013-08-13 | 2015-02-19 | Korea Institute Of Science And Technology | System and method for non-invasive patient-image registration |
| JP2015173899A (en) * | 2014-03-17 | 2015-10-05 | 株式会社東芝 | Ultrasonic diagnostic device, image processor and image processing program |
| CN105877780A (en) * | 2015-08-25 | 2016-08-24 | 上海深博医疗器械有限公司 | Full-automatic ultrasonic scanner and scanning detection method |
| CN111820917A (en) * | 2020-06-05 | 2020-10-27 | 哈工大机器人(中山)无人装备与人工智能研究院 | Binocular vision blood sampling device and blood sampling robot with same |
| CN112890867A (en) * | 2021-01-06 | 2021-06-04 | 杰杰医疗科技(苏州)有限公司 | Full-automatic peripheral blood vessel three-dimensional ultrasonic image reconstruction system and method |
| CN113349737A (en) * | 2021-06-30 | 2021-09-07 | 深圳英美达医疗技术有限公司 | Method for calibrating OCT image of intravascular dual-mode imaging system |
| CN113499099A (en) * | 2021-07-21 | 2021-10-15 | 上海市同仁医院 | Carotid artery ultrasonic automatic scanning and plaque identification system and method |
| CN114708280A (en) * | 2022-04-12 | 2022-07-05 | 吉林大学 | Cerebrovascular segmentation algorithm applicable to multiple modes |
Non-Patent Citations (1)
| Title |
|---|
| 张智，杨晨松，孙贵新: "影像辅助设备在穿支皮瓣移植术前血管定位中的作用", 《同济大学学报（医学版）》, vol. 42, no. 2, 30 April 2021 (2021-04-30), pages 278 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116630256A (en) * | 2023-05-15 | 2023-08-22 | 什维新智医疗科技(上海)有限公司 | Ultrasonic contrast image identification method, system, electronic equipment and storage medium |
| CN116630256B (en) * | 2023-05-15 | 2024-09-24 | 什维新智医疗科技(上海)有限公司 | Ultrasonic contrast image identification method, system, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115869013B (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5605155A (en) | Ultrasound system for automatically measuring fetal head size | |
| Zhang et al. | An effective algorithm for extracting serial endocardial borders from 2-dimensional echocardiograms | |
| US20120065499A1 (en) | Medical image diagnosis device and region-of-interest setting method therefore | |
| US20150023577A1 (en) | Device and method for determining physiological parameters based on 3d medical images | |
| JPH08206117A (en) | Ultrasonic diagnostic apparatus | |
| CN115869013B (en) | Blood vessel positioning and navigation method for autonomous scanning of blood vessel ultrasound | |
| CN113842172B (en) | Pharyngeal rear wall visual touch recognition device based on template matching and arithmetic averaging | |
| CN107157515A (en) | Ultrasound detection vascular system and method | |
| CN112998749B (en) | Automatic ultrasonic inspection system based on visual servo | |
| Tan et al. | A flexible and fully autonomous breast ultrasound scanning system | |
| WO2023072146A1 (en) | Transluminal ultrasonic automatic inspection system, control method, computer-readable storage medium and electronic device | |
| CN111820920B (en) | Vein blood sampling data processing method and device and intelligent blood sampling robot | |
| Victorova et al. | Follow the curve: Robotic ultrasound navigation with learning-based localization of spinous processes for scoliosis assessment | |
| CN116807577B (en) | Full-automatic venipuncture equipment and full-automatic venipuncture method | |
| CN117257346A (en) | Ultrasonic probe guiding method and device based on image recognition | |
| CN111839534A (en) | Blood sampling method and blood sampling robot | |
| Liu et al. | Learning-based scan plane identification from fetal head ultrasound images | |
| JP2895414B2 (en) | Ultrasonic volume calculator | |
| Lakshmi et al. | Automated screening for trisomy 21 by measuring nuchal translucency and frontomaxillary facial angle | |
| WO2023133933A1 (en) | Ultrasonic brain standard plane imaging and abnormal area automatic detection and display method | |
| CN114782537A (en) | Human carotid artery positioning method and device based on 3D vision | |
| CN109620142B (en) | Cervical vertebra mobility measuring system and method based on machine vision | |
| Xia et al. | Automatic ultrasound scanning for the Carotid Artery by robotic system | |
| CN116687452B (en) | Early pregnancy fetus ultrasonic autonomous scanning method, system and equipment | |
| CN116309712B (en) | Functional motion analysis system and method based on depth camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |