A method and apparatus for autonomous abdominal lesion scanning by an ultrasound robot

Abstract

The application discloses a method and device for autonomous scanning of abdominal lesions by an ultrasonic robot. The method comprises the following steps: acquiring an ultrasonic image in real time; performing anatomical structure segmentation on the current ultrasonic image to obtain a current lesion contour; judging whether the current lesion contour is a reliable lesion according to the area and position of the current lesion contour; if yes, judging whether a spatiotemporal continuity coefficient is greater than a preset continuity threshold; if yes, judging whether a minimum distance between the position of the current maximum lesion contour and the positions of the lesions that have been precisely scanned is greater than a first preset distance; if yes, judging whether a distance between the position of the current maximum lesion contour and the position of a current mechanical arm is less than a second preset distance; if yes, controlling the mechanical arm to move to the position of the current maximum lesion contour; classifying the current maximum lesion contour and performing adaptive precise scanning of the current maximum lesion contour. The method can ensure the accuracy of lesion tracking and improve the detection accuracy and scanning efficiency of small lesions.

Description

Technical Field

[0001] This invention relates to the field of medical robot technology, and in particular to a method and apparatus for an ultrasound robot to autonomously scan abdominal lesions. Background Technology

[0002] Ultrasound examination, due to its non-invasive, radiation-free, and real-time nature, is a core tool for screening and diagnosing abdominal diseases, playing a crucial role in lesion localization, initial assessment of lesion characteristics, and follow-up of treatment efficacy. With the deep integration of robotics and artificial intelligence, ultrasound robots are gradually moving from concept to clinical application, exhibiting a trend towards remote, automated, and intelligent development. As an embodied intelligent system with autonomous scanning capabilities, ultrasound robots can autonomously plan scanning paths and achieve standardized ultrasound image acquisition of abdominal organs, relying on intelligent planning algorithms and force-position coordinated control technology. However, in clinical applications, lesions generally exhibit characteristics such as small size, low contrast, and significant individual differences. Furthermore, the difficulty in standardizing scanning strategies and the tendency for missegmentation of target areas make achieving accurate autonomous scanning of lesions a significant challenge. Summary of the Invention

[0003] To improve the accuracy and efficiency of autonomous scanning of abdominal lesions, this invention provides a method and apparatus for autonomous scanning of abdominal lesions using an ultrasound robot.

[0004] In a first aspect, embodiments of the present invention provide a method for autonomously scanning abdominal lesions with an ultrasound robot, comprising:

[0005] Real-time acquisition of ultrasound images;

[0006] The current ultrasound image is segmented into anatomical structures, and the segmented contours are fitted to obtain the current lesion contour.

[0007] Based on the area and location of the current lesion outline, determine whether the current lesion outline is a reliable lesion;

[0008] If so, calculate the spatiotemporal continuity coefficient of the currently scanned ultrasound image and update the current largest lesion contour;

[0009] Determine whether the spatiotemporal continuity coefficient is greater than a preset continuity threshold;

[0010] If so, determine whether the minimum distance between the current largest lesion contour and the locations of each lesion that has been precisely scanned is greater than the first preset distance;

[0011] If so, determine whether the distance between the current position of the largest lesion contour and the current position of the robotic arm is less than the second preset distance;

[0012] If so, control the robotic arm to move to the position of the current largest lesion contour;

[0013] The current largest lesion contour is classified using a preset classification model, and an adaptive fine scan of the current largest lesion contour is performed based on the classification results and the area of ​​the current largest lesion contour.

[0014] In one or more optional embodiments, determining whether the current lesion contour is a reliable lesion based on its area and location includes:

[0015] Calculate the area of ​​the current lesion outline and determine whether the area of ​​the current lesion outline is not less than a preset minimum area;

[0016] If so, determine whether the distance between the center point of the current lesion contour and the center point of the preset reference frame is not greater than the third preset distance;

[0017] If so, the current lesion outline is determined to be a reliable lesion.

[0018] In one or more alternative embodiments, the spatiotemporal continuity coefficient of the currently scanned ultrasound image is calculated, and the contour of the current largest lesion is updated, including:

[0019] Calculate the spatiotemporal continuity coefficient of the currently scanned ultrasound image according to Formula 1:

[0020] , formula 1;

[0021] In the formula, For spatiotemporal continuity coefficients; This represents the number of frames in a series of images selected from the current moment backward. for The number of frames in which the lesion is segmented and the lesion area is not less than the preset minimum area;

[0022] In the currently scanned ultrasound images, the area of ​​lesions is compared between different frames, and the outline of the lesion with the largest area is updated as the current largest lesion outline.

[0023] In one or more alternative embodiments, controlling the robotic arm to move to the position of the current largest lesion contour includes:

[0024] Calculate the distance between the current position of the robotic arm and the position of the current largest lesion contour;

[0025] Calculate the moving speed of the robotic arm according to Formula 2:

[0026] , formula 2;

[0027] in, , formula 3;

[0028] In the formula, To return the reference speed coefficient; This is the distance correction factor;

[0029] Based on the calculated speed, the robotic arm is controlled to move to the position of the current largest lesion contour.

[0030] In one or more alternative embodiments, the scanning strategy for adaptive lesion fine scanning includes deceleration scanning, swing scanning, and transverse and longitudinal scanning;

[0031] The step of classifying the current largest lesion contour using a preset classification model, and then performing adaptive fine scanning of the current largest lesion contour based on the classification results and the area of ​​the current largest lesion contour, includes:

[0032] The current largest lesion contour is classified using a preset classification model;

[0033] Select a scanning strategy that matches the current largest lesion contour based on the classification results;

[0034] Based on the selected scanning strategy, the scanning speed and scanning contact force are calculated according to the area of ​​the current largest lesion contour.

[0035] Based on the calculated scanning speed and scanning contact force, an adaptive fine scanning of the current largest lesion contour is performed.

[0036] In one or more alternative embodiments, the scanning speed includes translational scanning speed and rotational scanning speed;

[0037] The scanning speed and scanning contact force are calculated based on the area of ​​the current largest lesion contour, including:

[0038] Based on Formula 4, the translational scanning speed is calculated according to the area of ​​the current largest lesion contour:

[0039] , formula 4;

[0040] In the formula, To improve the speed of translational scanning; These are the initial translational velocity parameters; The area of ​​the current largest lesion contour; This is a preset maximum threshold for lesion area; This is an area correction value;

[0041] Based on Formula 5, the rotational scanning speed is calculated according to the area of ​​the current largest lesion contour:

[0042] , Formula 5;

[0043] In the formula, This refers to the rotational scanning speed; These are the initial rotational speed parameters; The area of ​​the current largest lesion contour; This is a preset maximum threshold for lesion area; This is an area correction value;

[0044] Based on Formula 6, the scanning contact force is calculated according to the area of ​​the current largest lesion contour:

[0045] , Formula 6;

[0046] In the formula, Basic force; This is the contact force correction factor; The area of ​​the current largest lesion contour; and These are the preset maximum area threshold and the preset minimum area threshold, respectively.

[0047] Secondly, embodiments of the present invention provide a device for autonomous ultrasound robot scanning of abdominal lesions, comprising:

[0048] The acquisition module is used to acquire ultrasound images in real time;

[0049] The segmentation module is used to segment the current ultrasound image into anatomical structures and fit the segmented contours to obtain the current lesion contour.

[0050] The first judgment module is used to determine whether the current lesion contour is a reliable lesion based on the area and location of the current lesion contour.

[0051] The calculation module is used to calculate the spatiotemporal continuity coefficient of the currently scanned ultrasound image and update the contour of the current largest lesion.

[0052] The second judgment module is used to determine whether the spatiotemporal continuity coefficient is greater than a preset continuity threshold.

[0053] The third judgment module is used to determine whether the minimum distance between the position of the current largest lesion contour and the positions of each lesion that has been finely scanned is greater than the first preset distance.

[0054] The fourth judgment module determines whether the distance between the current position of the largest lesion contour and the current position of the robotic arm is less than a second preset distance;

[0055] The control module is used to control the robotic arm to move to the position of the current largest lesion contour;

[0056] The fine scanning module is used to classify the current largest lesion contour using a preset classification model, and to perform adaptive fine scanning of the current largest lesion contour based on the classification results and the area of ​​the current largest lesion contour.

[0057] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for autonomously scanning abdominal lesions with an ultrasound robot as described in the first aspect.

[0058] Fourthly, embodiments of the present invention provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for autonomous ultrasound robot scanning of abdominal lesions as described in the first aspect.

[0059] Fifthly, embodiments of the present invention provide a computer program product containing instructions that, when run on a computer device, cause the computer device to perform the method for autonomously scanning abdominal lesions with an ultrasound robot as described in the first aspect.

[0060] The beneficial effects of the above-described technical solutions provided in the embodiments of the present invention include at least the following:

[0061] The method for autonomously scanning abdominal lesions with an ultrasound robot provided in this invention first selects clinically significant and reliable lesions based on the area and location of the lesion contour, eliminating misjudgments caused by artifacts and noise. After confirming the reliability of the lesion, the spatiotemporal continuity coefficient of the scanned ultrasound images is calculated to verify the spatiotemporal continuity of the current lesion in consecutive frames, avoiding misidentification of lesions due to interference from similar anatomical structures and ensuring the continuity of lesion tracking. By determining the distance between the current largest lesion contour position and the already scanned lesions, as well as the distance to the current position of the robotic arm, duplicate scanning is avoided, improving the efficiency of lesion scanning. The lesion with the largest contour is selected from the already scanned effective lesion contours and identified as the target lesion for detailed scanning. Finally, the robotic arm is precisely moved to the position of the current largest lesion contour, and the current largest lesion contour is classified using a preset classification model. Combined with the lesion area size, the scanning parameters and range are adaptively adjusted to achieve targeted detailed scanning of lesions of different types and sizes, allowing lesions to be presented from multiple angles and providing doctors with comprehensive lesion information for diagnosis.

[0062] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0063] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0064] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0065] Figure 1 This is a flowchart illustrating the method for autonomously scanning abdominal lesions with an ultrasound robot provided in an embodiment of the present invention.

[0066] Figure 2 This is a schematic diagram of the coordinate system of the ultrasonic robot end effector provided in an embodiment of the present invention;

[0067] Figure 3 This is a structural block diagram of the device for autonomously scanning abdominal lesions using an ultrasound robot provided in an embodiment of the present invention;

[0068] Figure 4 This is a structural block diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0069] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0070] The inventors discovered that current abdominal ultrasound examinations primarily rely on manual scanning by doctors. However, manual scanning has significant limitations: it heavily depends on the physician's technique and experience, resulting in low image quality, completeness, and repeatability, leading to frequent missed diagnoses and misdiagnoses. Based on this, the inventors conducted further research and development, resulting in this invention, which provides a method and device for autonomous ultrasound robot scanning of abdominal lesions.

[0071] Example 1

[0072] This invention provides a method for autonomous ultrasound robot scanning of abdominal lesions, referring to... Figure 1 As shown, it includes:

[0073] S101: Real-time acquisition of ultrasound images;

[0074] S102: Perform anatomical structure segmentation on the current ultrasound image and fit the segmented contours to obtain the current lesion contour;

[0075] S103: Based on the area and location of the current lesion outline, determine whether the current lesion outline is a reliable lesion; if yes, proceed to step S104; if no, return to step S101 to obtain the next frame of ultrasound image.

[0076] S104: Calculate the spatiotemporal continuity coefficient of the currently scanned ultrasound image and update the current maximum lesion contour;

[0077] S105: Determine whether the spatiotemporal continuity coefficient is greater than the preset continuity threshold; if yes, proceed to step S106; if no, return to step S101 to obtain the next frame of ultrasound image.

[0078] S106: Determine whether the minimum distance between the current location of the largest lesion outline and the locations of each lesion that has been precisely scanned is greater than the first preset distance; if yes, proceed to step S107; if no, return to step S101 to obtain the next frame of ultrasound image.

[0079] S107: Determine whether the distance between the current position of the largest lesion contour and the current position of the robotic arm is less than the second preset distance; if yes, proceed to step S108; if no, return to step S101 to obtain the next frame of ultrasound image.

[0080] S108: Control the robotic arm to move to the position of the current largest lesion outline;

[0081] S109: Classify the current largest lesion contour using a preset classification model, and perform adaptive fine scanning of the current largest lesion contour based on the classification results and the area of ​​the current largest lesion contour.

[0082] The method for autonomously scanning abdominal lesions with an ultrasound robot provided in this invention first selects clinically significant and reliable lesions based on the area and location of the lesion contour, eliminating misjudgments caused by artifacts and noise. After confirming the reliability of the lesion, the spatiotemporal continuity coefficient of the scanned ultrasound images is calculated to verify the spatiotemporal continuity of the current lesion in consecutive frames, avoiding misidentification of lesions due to interference from similar anatomical structures and ensuring the continuity of lesion tracking. By determining the distance between the current largest lesion contour position and the already scanned lesions, as well as the distance to the current position of the robotic arm, duplicate scanning is avoided, improving the efficiency of lesion scanning. The lesion with the largest contour is selected from the already scanned effective lesion contours and identified as the target lesion for detailed scanning. Finally, the robotic arm is precisely moved to the position of the current largest lesion contour, and the current largest lesion contour is classified using a preset classification model. Combined with the lesion area size, the scanning parameters and range are adaptively adjusted to achieve targeted detailed scanning of lesions of different types and sizes, allowing lesions to be presented from multiple angles and providing doctors with comprehensive lesion information for diagnosis.

[0083] It should be noted that the positions described in the embodiments of the present invention are all based on the world coordinate system, and the position of the contour refers to the coordinates of the center point of the contour in the world coordinate system. Figure 2 A schematic diagram of the world coordinate system for the ultrasonic robot is provided.

[0084] In this embodiment of the invention, step S101, "real-time acquisition of ultrasound images," refers to acquiring ultrasound images in real time during the abdominal scan performed by the ultrasound robot according to a preset scanning path. Each acquired ultrasound image triggers the judgment and fine scanning process in steps S102-S109. The preset scanning path can be designed based on the positional and morphological characteristics of the abdomen and the physician's experience; details are omitted here.

[0085] In this embodiment of the invention, in step S102 above, the current ultrasound image is segmented into anatomical structures. This can be done using a preset segmentation network, such as the commonly used U-Net segmentation network, to identify the contours of the liver, gallbladder, pancreas, and lesions. The identified lesion contours are then fitted to obtain the current lesion contour. The fitting method can be a mathematical fitting method such as polynomial fitting or least squares fitting. Anatomical structure segmentation of the current ultrasound image eliminates irrelevant tissue interference, and contour fitting solves the problem of contour discontinuity, clarifying the specific contour shape, area, and location information of the current lesion, providing basic data support for subsequent lesion determination and scanning control.

[0086] In this embodiment of the invention, step S103 above: Based on the area and location of the current lesion outline, determine whether the current lesion outline is a reliable lesion; if yes, proceed to step S104; if no, return to step S101 to obtain the next frame of ultrasound image; specifically, it may include the following steps S1031-S1032:

[0087] S1031: Calculate the area of ​​the current lesion outline and determine whether the area of ​​the current lesion outline is not less than the preset minimum area. If yes, the lesion outline is valid, and the process continues to step S1032. If no, the lesion is too small and may be misidentified; it is not a reliable lesion and will not proceed to the subsequent lesion processing steps. Instead, the process returns to step S101 to process the next frame of ultrasound image. The recommended value for the preset minimum area is 10. .

[0088] S1032: Determine whether the distance between the center point of the current lesion contour and the center point of the preset reference frame is not greater than the third preset distance; if yes, it means that the current lesion contour is in a valid position and is a reliable lesion, and proceed to step S104; if no, it means that the position of the current lesion contour has deviated from the normal scanning range, and return to step S101 to process the next frame of ultrasound image.

[0089] In one specific embodiment, the preset reference frame can be the first frame in which the lesion appears. The algorithm for determining whether the distance between the center point of the current lesion contour and the center point of the preset reference frame is not greater than a third preset distance can be implemented in the following way:

[0090] Define the effective factor of single frame position :

[0091] , Formula 7;

[0092] In the formula, The distance between the center point of the lesion outline in the i-th frame and the center of the lesion in the preset reference frame is in mm. The third preset distance is the maximum physical offset threshold of the lesion center, with a reference value of 50mm.

[0093] In this embodiment of the invention, after confirming that the current lesion contour is a reliable lesion with clinical significance, subsequent discrimination and scanning can be carried out. Step S104 above: Calculating the spatiotemporal continuity coefficient of the currently scanned ultrasound image and updating the current largest lesion contour, specifically may include the following steps S1041-S1042:

[0094] S1041: Count the number of consecutive images selected from the current moment forward in the scanned ultrasound images and the number of frames in which the lesion is segmented and its area is not less than the preset minimum area. Calculate the spatiotemporal continuity coefficient of the currently scanned ultrasound image according to Formula 1.

[0095] , formula 1;

[0096] In the formula, The spatiotemporal continuity coefficient has a value range of [0, 1], and the closer it is to 1, the stronger the spatiotemporal continuity. This represents the number of frames in a series of images selected from the current moment backward. for The number of frames in which the lesion is segmented and the lesion area is not less than the preset minimum area; The effective factor for single-frame position is calculated using Formula 7 above. for Percentage of lesions appearing in the frame; The percentage of valid locations in a frame where a lesion appears.

[0097] S1042: In the currently scanned ultrasound image, compare the area of ​​lesions between different frames, update the contour of the lesion with the largest area to the current largest lesion contour, and determine the position of the current largest lesion contour.

[0098] In this embodiment of the invention, the spatiotemporal continuity coefficient It can reflect the continuity of lesions in the temporal and spatial dimensions of scanned ultrasound images, thus determining whether the current largest lesion contour is a real and stable lesion, rather than a false contour caused by artifacts, noise, or probe displacement. Spatiotemporal continuity coefficient The closer the value is to 1, the stronger the continuity and stability of the lesions in the currently scanned consecutive ultrasound images in both time and space dimensions. Therefore, the preset continuity threshold can be set to 0.8. If the spatiotemporal continuity coefficient... If the value is greater than 0.8, the current largest lesion outline is considered reliable. By judging the spatiotemporal continuity, the continuity of lesion tracking can be ensured, thereby ensuring the authenticity and stability of the current largest lesion outline. This makes up for the shortcoming that it is difficult for manual methods to maintain precise alignment between the probe and the lesion throughout the entire process, providing a reliable basis for subsequent detailed scanning and reducing the risk of missed or misdiagnosed cases.

[0099] In this embodiment of the invention, after verifying the spatiotemporal continuity, it is also necessary to confirm, through position determination, that the current largest lesion contour is not a duplicate scan or a misidentification. Step S106 above: Determine whether the minimum distance between the position of the current largest lesion contour and the positions of each lesion that has been precisely scanned is greater than a first preset distance; if yes, proceed to step S107; if no, return to step S101 to obtain the next frame of ultrasound image, which may specifically include the following steps S1061-S1062:

[0100] S1061: Calculate the location of the current largest lesion contour according to Formula 8. Compared with the locations of each lesion that have been thoroughly scanned Minimum distance between (j=0, 1, 2, ..., i-1):

[0101] , formula 8;

[0102] In the formula, Location of the largest lesion outline Compared with the locations of each lesion that have been thoroughly scanned The minimum distance between them;

[0103] S1062: Judgment Is it greater than the first preset distance? If so, it indicates the location of the current largest lesion outline. Compared with the locations of each lesion that have been thoroughly scanned If the minimum distance between them meets the interval requirement, continue to step S107; otherwise, indicate the location of the current largest lesion outline. If the distance between the ultrasound image and at least one lesion that has already been scanned is too close, and repeated scanning needs to be avoided, then return to step S101 to obtain the next frame of ultrasound image. The recommended value is 40mm.

[0104] In this embodiment of the invention, step S107: determining whether the distance between the current position of the largest lesion contour and the current position of the robotic arm is less than a second preset distance; if yes, proceeding to step S108; if no, returning to step S101 to obtain the next frame of ultrasound image, specifically including the following steps S1071-S1072:

[0105] S1071: Calculate the location of the current largest lesion contour according to Formula 9. With the current position of the robotic arm Distance between:

[0106] , formula 9;

[0107] In the formula, Location of the largest lesion outline With the current position of the robotic arm The distance between them.

[0108] S1072: Judgment Is it less than the second preset distance? If so, it means... If the lesion is within a reasonable range, proceed to step S108; otherwise, indicate the location of the current largest lesion outline. With the current position of the robotic arm If the distance is too far, from the perspective of anatomical spatial relationships, the lesion location may be considered a misidentified lesion. In this case, return to step S101 to obtain the next frame of ultrasound image. The recommended value for the second preset distance is 80mm.

[0109] The method for autonomously scanning abdominal lesions with an ultrasound robot provided in this invention first compares the minimum distance between the current largest lesion contour and the location of the already scanned lesion with a first preset distance to avoid repeated scanning of the same lesion area, thereby effectively reducing invalid operations, shortening the overall scanning time, and improving scanning efficiency. Furthermore, by comparing the distance to the current position of the robotic arm with a second preset distance, it eliminates lesions that may be misidentified due to excessive distance from the perspective of anatomical spatial relationships, preventing the robotic arm from performing invalid or off-target scanning actions. This ensures comprehensive scanning while significantly improving the accuracy of lesion localization and the effectiveness of robotic arm path planning, enhancing the robustness and safety of the automated scanning process.

[0110] In this embodiment of the invention, after determining that the current largest lesion contour is a reliable lesion that has not been scanned, a detailed scan can be performed on the current largest lesion contour. Before the detailed scan, the robotic arm needs to be moved to the position of the current largest lesion contour. The above step S108: controlling the robotic arm to move to the position of the current largest lesion contour can specifically include the following steps S1081-S1083:

[0111] S1081: Calculate the distance between the current robotic arm position and the current position of the largest lesion contour. .

[0112] S1082: Calculate the moving speed of the robotic arm according to Formula 2:

[0113] , formula 2;

[0114] The distance correction factor employs an exponential decay function: , formula 3;

[0115] In the formula, To return the baseline speed coefficient, a value of 0.003 is recommended; This is the distance correction factor, ranging from [0, 1]. As can be seen from Formula 3, the closer the distance... , The moving speed of the robotic arm The smaller the value, the better to ensure that the probe can reach the target position smoothly.

[0116] S1083: Based on the calculated moving speed of the robotic arm, control the robotic arm to move to the position of the current largest lesion contour.

[0117] During abdominal scanning, a classification model can be used to identify the type of lesion contour, thereby outputting the specific lesion type, such as hepatic hemangioma, cyst, gallstones, gallbladder polyps, etc. In this embodiment of the invention, three adaptive lesion fine scanning strategies for abdominal scanning are designed based on the lesion scanning techniques of clinical ultrasound experts, including deceleration scanning, swing scanning, and transverse and longitudinal scanning. Appropriate scanning strategies can be selected for different lesion types to improve scanning accuracy and avoid poor image quality caused by a single scanning method. Based on this, step S109 above: classifying the current largest lesion contour using a preset classification model, and performing adaptive lesion fine scanning on the current largest lesion contour based on the classification results and the area of ​​the current largest lesion contour, specifically includes the following steps S1091-S1092:

[0118] S1091: Classify the current largest lesion contour using a preset classification model; the preset classification model is a conventional deep learning network used for classification.

[0119] S1092: Select a scanning strategy that matches the current largest lesion contour based on the classification results.

[0120] S1093: Based on the selected scanning strategy, calculate the scanning speed and scanning contact force according to the area of ​​the current largest lesion contour.

[0121] S1094: Perform adaptive fine scanning of the current largest lesion contour based on the calculated scanning speed and scanning contact force.

[0122] During the detailed lesion scanning stage, the scanning speed includes translational scanning speed and rotational scanning speed. The larger the lesion area, the greater the required translational scanning speed to ensure the stability and efficiency of the detailed lesion scanning; similarly, the larger the lesion area, the greater the required rotational scanning speed. Furthermore, the contact force during the detailed lesion scanning stage is crucial for ultrasound imaging, and the contact force is positively correlated with the lesion area: large lesions correspond to a large tissue area and can withstand slightly greater contact force (to ensure image clarity); small lesions are small and easily lost by the probe, therefore the force needs to be appropriately reduced to avoid lesion tracking loss. Based on this, in step S1093 above, the scanning speed and scanning contact force are calculated based on the area of ​​the current largest lesion contour, which specifically includes the following steps S10931-S10933:

[0123] S10931: Based on Formula 4, calculate the translational scanning speed according to the area of ​​the current largest lesion contour:

[0124] , formula 4;

[0125] In the formula, The translational scanning speed is in mm / s; The initial translational velocity parameter is recommended to be 15 mm / s; The area of ​​the largest lesion outline at present. ; The recommended value is the maximum threshold for the preset lesion area. ; This is the area correction value; the recommended value is... , used to avoid The scanning speed approaches 0 when the distance is too small.

[0126] S10932: Based on Formula 5, calculate the rotational scanning speed according to the area of ​​the current largest lesion contour:

[0127] , Formula 5;

[0128] In the formula, For rotational scanning speed, ; The initial rotational speed parameter is recommended to be [value missing]. ; The area of ​​the largest lesion outline at present. ; The recommended value is the maximum threshold for the preset lesion area. ; This is the area correction value; the recommended value is... , used to avoid The scanning speed approaches 0 when the distance is too small.

[0129] S10933: Based on Formula 6, calculate the scanning contact force according to the area of ​​the current largest lesion contour:

[0130] , Formula 6;

[0131] In the formula, For basic force, the recommended value is 12N; This is a contact force correction factor; a recommended value is 2N. The area of ​​the largest lesion outline at present ; and These are the preset maximum area threshold and the preset minimum area threshold, respectively. Recommended value , Recommended value .

[0132] It should be noted that different scanning strategies require different scanning speeds. For example, oscillating scanning does not involve probe translation and therefore does not require calculating translation scanning speed. Thus, different scanning strategies can be selected based on the needs of formulas 4 and 5 above. Based on this, the applicable situations and specific scanning methods for the three scanning strategies—deceleration scanning, oscillating scanning, and horizontal / vertical scanning—are as follows:

[0133] Reduced-speed scanning: This is mainly for small lesions (less than 10mm in diameter), such as gallstones, gallbladder polyps, and calcifications. These lesions are very small and easily missed during multi-angle scanning; therefore, only reduced-speed scanning is performed to ensure as many lesion images as possible are captured. The specific scanning process is as follows: The scanning speed is calculated using formulas 4 and 5 above, and the scanning contact force is calculated using formula 6 above. The lesion is then precisely scanned according to the calculated translational scanning speed, rotational scanning speed, and scanning contact force. After completion, subsequent abdominal scanning is performed.

[0134] The swing scan is mainly used for small cysts and hemangiomas (10mm~30mm in diameter). These types of lesions require special attention, but because they are not large, the complete scan of the lesions can be achieved by swinging the device. Figure 2 The coordinate system of the end-effector is illustrated, and the specific scanning process is as follows:

[0135] The scanning contact force is calculated using Formula 6, and the rotational scanning speed is calculated using Formula 5. Based on the calculated rotational scanning speed and scanning contact force, the probe is controlled to rotate around the tool coordinate system Y. t The oscillating search of the axis requires rotation around the Y-axis. t The angle of axis swing is calculated according to the following formula 10:

[0136] , formula 10;

[0137] In the formula, To wrap around Y t The speed of the axis oscillation, i.e. the rotational scanning speed, is calculated according to Formula 5 above; For needing to go around Y t The angle of the axis swing; Indicates the direction of the swing, with an initial value of 1, when the actual lesion area... hour, = - This means scanning in the opposite direction until the swing completes one swing cycle. The swing cycle is the preset maximum swing angle, which can usually be set to 0.4 rad.

[0138] After the detailed scan is completed, the subsequent abdominal scan will be performed.

[0139] Horizontal and vertical scanning is primarily used for larger cysts or solid lesions (e.g., over 30mm in diameter). These types of lesions require close monitoring and, due to their size, necessitate multi-angle scanning to ensure a complete and accurate examination. (Reference) Figure 2 The tool coordinate system shown is used for scanning as follows:

[0140] S1: The scanning contact force is calculated using Formula 6 above, and the translational scanning speed is calculated using Formula 4 above. Based on the calculated translational scanning speed and scanning contact force, the probe is controlled to move along the tool coordinate system X. t The axis is used for translational search to achieve transverse scanning of the lesion. The translational displacement is calculated using the following formula 11:

[0141] , Formula 11;

[0142] In the formula, For along X t The axis translation scanning speed is calculated according to Formula 4; For need along X t The displacement of the axis translation, in mm; The direction of movement, with an initial value of 1, is determined by the actual lesion area. hour, = - In other words, the search is reversed until a translation cycle is completed (i.e., the preset maximum translation displacement is reached), thus achieving a transverse scan of the lesion.

[0143] S2: Control the probe to rotate 90° around its own axis Zt, so that the probe is in a longitudinal scanning state relative to the lesion.

[0144] S3: Control the probe along the tool coordinate system X t The axis is used for translational search to achieve longitudinal scanning of the lesion. The calculation of longitudinal scanning speed and displacement is the same as in step S1.

[0145] S4: Control the probe to return to the initial scanning state, complete the multi-angle fine scanning of the lesion, and continue to perform subsequent abdominal scanning tasks.

[0146] Example 2

[0147] Based on the same inventive concept, this invention also provides a device for autonomous ultrasound robot scanning of abdominal lesions, referring to... Figure 3 As shown, it includes:

[0148] Acquisition module 101 is used to acquire ultrasound images in real time;

[0149] The segmentation module 102 is used to segment the current ultrasound image into anatomical structures and fit the segmented contours to obtain the current lesion contour.

[0150] The first judgment module 103 is used to determine whether the current lesion outline is a reliable lesion based on the area and location of the current lesion outline.

[0151] The calculation module 104 is used to calculate the spatiotemporal continuity coefficient of the currently scanned ultrasound image and update the contour of the current largest lesion.

[0152] The second judgment module 105 is used to determine whether the spatiotemporal continuity coefficient is greater than a preset continuity threshold.

[0153] The third judgment module 106 is used to determine whether the minimum distance between the current position of the largest lesion outline and the positions of each lesion that has been finely scanned is greater than the first preset distance.

[0154] The fourth judgment module 107 determines whether the distance between the current position of the largest lesion contour and the current position of the robotic arm is less than the second preset distance;

[0155] Control module 108 is used to control the robotic arm to move to the position of the current largest lesion contour;

[0156] The fine scanning module 109 is used to classify the current largest lesion contour using a preset classification model, and to perform adaptive fine scanning of the current largest lesion contour based on the classification results and the area of ​​the current largest lesion contour.

[0157] Example 3

[0158] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for autonomously scanning abdominal lesions with an ultrasound robot as described in Embodiment 1.

[0159] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires; a portable computer disk drive; a hard disk drive; a random access memory (RAM); a read-only memory (ROM); an erasable programmable read-only memory (EPROM); a register; a hard disk drive; an optical fiber; a portable compact disc read-only memory (CD-ROM); an optical storage device; a magnetic storage device; or any suitable combination thereof; or any other form of computer-readable storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in an application-specific integrated circuit (ASIC). In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0160] Example 4

[0161] Based on the same inventive concept, this embodiment of the invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the method for autonomously scanning abdominal lesions with an ultrasound robot as described in Embodiment 1.

[0162] Figure 4A possible structural diagram of the computer device involved in the above embodiments is shown. The computer device includes a processor 1002 and a communication interface 1003. The processor 1002 is used to control and manage the operation of the computer device, for example, executing the alarm association method described above, and / or other processes of the technology described herein. The communication interface 1003 is used to support communication between the computer device and other network entities, for example, executing the steps performed by the communication unit 902 described above. The computer device may also include a memory 1001 and a bus 1004, the memory 1001 being used to store the program code and data of the computer device.

[0163] The memory 1001 may be a memory in a computer device, and the memory may include: volatile memory, such as random access memory; the memory may also include: non-volatile memory, such as read-only memory, flash memory, hard disk or solid-state drive; the memory may also include: a combination of the above types of memory.

[0164] The processor 1002 described above can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0165] Bus 1004 can be an Extended Industry Standard Architecture (EISA) bus, etc. Bus 1004 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0166] Example 5

[0167] Based on the same inventive concept, this embodiment of the invention also provides a computer program product containing instructions that, when the computer program product is run on a computer device, cause the computer device to perform the method of autonomously scanning abdominal lesions with an ultrasound robot as described in Embodiment 1.

[0168] The principles by which the above-described apparatus, client, medium, related equipment, and system in this embodiment solve the problem are similar to those of the aforementioned method. Therefore, their implementation can refer to the implementation of the aforementioned method, and repeated details will not be repeated.

[0169] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0170] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0171] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0172] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0173] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for autonomously scanning abdominal lesions with an ultrasound robot, characterized in that, include: Real-time acquisition of ultrasound images; The current ultrasound image is segmented into anatomical structures, and the segmented contours are fitted to obtain the current lesion contour. Based on the area and location of the current lesion outline, determine whether the current lesion outline is a reliable lesion; If so, calculate the spatiotemporal continuity coefficient of the currently scanned ultrasound image and update the current largest lesion contour; Determine whether the spatiotemporal continuity coefficient is greater than a preset continuity threshold; If so, determine whether the minimum distance between the current largest lesion contour and the locations of each lesion that has been precisely scanned is greater than the first preset distance; If so, determine whether the distance between the current position of the largest lesion contour and the current position of the robotic arm is less than the second preset distance; If so, control the robotic arm to move to the position of the current largest lesion contour; The current largest lesion contour is classified using a preset classification model, and an adaptive fine scan of the current largest lesion contour is performed based on the classification results and the area of ​​the current largest lesion contour.

2. The method for autonomously scanning abdominal lesions with an ultrasound robot according to claim 1, characterized in that, The step of determining whether the current lesion contour is a reliable lesion based on its area and location includes: Calculate the area of ​​the current lesion outline and determine whether the area of ​​the current lesion outline is not less than a preset minimum area; If so, determine whether the distance between the center point of the current lesion contour and the center point of the preset reference frame is not greater than the third preset distance; If so, the current lesion outline is determined to be a reliable lesion.

3. The method for autonomously scanning abdominal lesions with an ultrasound robot according to claim 1, characterized in that, Calculate the spatiotemporal continuity coefficients of the currently scanned ultrasound images and update the contour of the current largest lesion, including: Calculate the spatiotemporal continuity coefficient of the currently scanned ultrasound image according to Formula 1: , Formula 1; In the formula, For spatiotemporal continuity coefficients; This represents the number of frames in a series of images selected from the current moment backward. for The number of frames in which the lesion is segmented and the lesion area is not less than the preset minimum area; In the currently scanned ultrasound images, the area of ​​lesions is compared between different frames, and the outline of the lesion with the largest area is updated as the current largest lesion outline.

4. The method for autonomously scanning abdominal lesions with an ultrasound robot according to claim 1, characterized in that, Controlling the robotic arm to move to the position of the current largest lesion contour includes: Calculate the distance between the current position of the robotic arm and the position of the current largest lesion contour; Calculate the moving speed of the robotic arm according to Formula 2: , Formula 2; in, , formula 3; In the formula, To return the reference speed coefficient; This is the distance correction factor; Based on the calculated speed, the robotic arm is controlled to move to the position of the current largest lesion contour.

5. The method for autonomously scanning abdominal lesions with an ultrasound robot according to claim 1, characterized in that, Adaptive lesion scanning strategies include deceleration scanning, swing scanning, and transverse and longitudinal scanning. The step of classifying the current largest lesion contour using a preset classification model, and then performing adaptive fine scanning of the current largest lesion contour based on the classification results and the area of ​​the current largest lesion contour, includes: The current largest lesion contour is classified using a preset classification model; Select a scanning strategy that matches the current largest lesion contour based on the classification results; Based on the selected scanning strategy, the scanning speed and scanning contact force are calculated according to the area of ​​the current largest lesion contour. Based on the calculated scanning speed and scanning contact force, an adaptive fine scanning of the current largest lesion contour is performed.

6. The method for autonomously scanning abdominal lesions with an ultrasound robot according to claim 5, characterized in that, The scanning speed includes translational scanning speed and rotational scanning speed; The scanning speed and scanning contact force are calculated based on the area of ​​the current largest lesion contour, including: Based on Formula 4, the translational scanning speed is calculated according to the area of ​​the current largest lesion contour: , Official 4; In the formula, To improve the speed of translational scanning; These are the initial translational velocity parameters; The area of ​​the current largest lesion contour; This is a preset maximum threshold for lesion area; This is an area correction value; Based on Formula 5, the rotational scanning speed is calculated according to the area of ​​the current largest lesion contour: , Official 5; In the formula, This refers to the rotational scanning speed; These are the initial rotational speed parameters; The area of ​​the current largest lesion contour; This is a preset maximum threshold for lesion area; This is an area correction value; Based on Formula 6, the scanning contact force is calculated according to the area of ​​the current largest lesion contour: , Official 6; In the formula, Basic force; This is the contact force correction factor; The area of ​​the current largest lesion contour; and These are the preset maximum area threshold and the preset minimum area threshold, respectively.

7. A device for autonomously scanning abdominal lesions using an ultrasound robot, characterized in that, include: The acquisition module is used to acquire ultrasound images in real time; The segmentation module is used to segment the current ultrasound image into anatomical structures and fit the segmented contours to obtain the current lesion contour. The first judgment module is used to determine whether the current lesion contour is a reliable lesion based on the area and location of the current lesion contour. The calculation module is used to calculate the spatiotemporal continuity coefficient of the currently scanned ultrasound image and update the contour of the current largest lesion. The second judgment module is used to determine whether the spatiotemporal continuity coefficient is greater than a preset continuity threshold. The third judgment module is used to determine whether the minimum distance between the position of the current largest lesion contour and the positions of each lesion that has been finely scanned is greater than the first preset distance. The fourth judgment module determines whether the distance between the current position of the largest lesion contour and the current position of the robotic arm is less than a second preset distance; The control module is used to control the robotic arm to move to the position of the current largest lesion contour; The fine scanning module is used to classify the current largest lesion contour using a preset classification model, and to perform adaptive fine scanning of the current largest lesion contour based on the classification results and the area of ​​the current largest lesion contour.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the method of autonomously scanning abdominal lesions with an ultrasound robot as described in any one of claims 1-6.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method of autonomously scanning abdominal lesions with an ultrasound robot as described in any one of claims 1-6.

10. A computer program product containing instructions, characterized in that, When the computer program product is run on a computer device, it causes the computer device to perform the method of autonomously scanning abdominal lesions with an ultrasound robot as described in any one of claims 1-6.

Images