Ultrasonic scanning trajectory planning method and system based on variational auto-encoder

Abstract

The invention relates to the technical field of ultrasonic scanning path planning, and discloses an ultrasonic scanning trajectory planning method and system based on a variational auto-encoder. The ultrasonic scanning trajectory planning method is applied to an ultrasonic scanning robot, and specifically comprises the following steps: S101, receiving an ultrasonic image acquisition instruction sent by a user terminal, the ultrasonic image acquisition instruction comprises a command for activating a carried ultrasonic probe, target area data acquired by an ultrasonic image and feature information of the ultrasonic probe during image acquisition; and S102, acquiring ultrasonic image data acquired in a target area, and sequentially placing the ultrasonic image data in the image preprocessing model to complete denoising of the ultrasonic image data in sequence. The ultrasonic diagnosis model is trained and optimized through few-sample learning, the ultrasonic scanning operation is automatically completed through high-precision control and intelligent decision-making track planning of the ultrasonic scanning robot, and the accuracy and stability of the diagnosis result are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ultrasonic scanning path planning, and in particular to an ultrasonic scanning trajectory planning method and system based on a variational autoencoder. Background Art

[0002] Ultrasound scanning is a non-invasive and radiation-free medical imaging technology that is widely used in diagnosis and treatment, especially in obstetrics and gynecology, cardiovascular disease, tumor detection, etc. It uses high-frequency sound waves to image the internal structure of the human body, and has significant advantages in real-time dynamic monitoring and image acquisition.

[0003] Currently, most ultrasound systems rely on manual adjustment of the probe's scanning trajectory or the use of simple mechanical auxiliary devices. These technologies are limited in accuracy, response speed, and adaptability in complex environments, and cannot meet the needs of high precision and high efficiency. Summary of the invention

[0004] The purpose of the present invention is to provide an ultrasonic scanning trajectory planning method and system based on a variational autoencoder, which automatically completes the ultrasonic scanning operation through high-precision control and intelligent decision-making of the ultrasonic scanning robot, improves the accuracy and stability of the diagnostic results, reduces the dependence on operators, and aims to solve the problems in the prior art.

[0005] The present invention is implemented in this way: an ultrasonic scanning trajectory planning method based on a variational autoencoder is applied to an ultrasonic scanning robot, specifically comprising the following steps:

[0006] S101: receiving an ultrasound image acquisition instruction sent by a user terminal, wherein the ultrasound image acquisition instruction includes a command to activate the carried ultrasound probe, target area data acquired by the ultrasound image, and feature information of the ultrasound probe when acquiring the image;

[0007] S102: Acquire ultrasonic image data collected in the target area, place the ultrasonic image data in the image preprocessing model in sequence to perform denoising on the ultrasonic image data in sequence, and obtain balanced ultrasonic image data after denoising;

[0008] S103: placing the acquired balanced ultrasonic image data in a multi-variational autoencoder for image enhancement, obtaining an enhanced image of the multi-variational autoencoder, performing initial global feature fusion on the enhanced image of the multi-variational autoencoder through a fully connected neural network, and obtaining multiple initial global feature matrices;

[0009] S104: adding a preset hidden variable to each of the multiple variational autoencoders, and concatenating the multiple initial global feature matrices extracted by the fully connected neural network with the hidden variables in the multiple variational autoencoders in the first dimension to obtain multiple first feature matrices;

[0010] S105: Input multiple first feature matrices into the fully connected neural network respectively to obtain multiple second feature matrices as outputs, split the multiple second feature matrices separately, retain only the multiple latent feature matrices at the end, and then concatenate the multiple latent feature matrices in the second dimension to obtain a trajectory vector, and input the trajectory vector into the fully connected neural network to obtain the final output scanning trajectory matrix.

[0011] Furthermore, in S101, receiving an ultrasound image acquisition instruction sent by a user terminal includes:

[0012] receiving a connection request sent by a user terminal through a preset network, wherein the connection request is used to request to establish a connection with the ultrasonic scanning robot;

[0013] Detecting whether the current account of the user terminal is the target account;

[0014] If the current account of the user terminal is the target account, a connection is made with the user terminal according to the connection request, and after the connection is completed, an ultrasound image acquisition instruction sent by the user terminal is received.

[0015] Furthermore, the preset network includes one or a combination of a 3G network, a 4G network, a 5G network, and a WIFI network.

[0016] Furthermore, in S102, ultrasonic image data collected in the target area is obtained, including:

[0017] The operator manually controls the ultrasonic scanning robot to move the ultrasonic probe to the starting point Q0 of the area to be scanned;

[0018] The ultrasound image is acquired with the starting point Q0 as the starting point, and the image I(0) at the initial moment is acquired to highlight the key medical features through denoising and image enhancement.

[0019] Further, in S103, the multiple variational autoencoders are at least two, namely a first variational autoencoder and a second variational autoencoder.

[0020] Furthermore, the obtained balanced ultrasonic image data is placed in a multi-variational autoencoder for image enhancement to obtain an enhanced image of the multi-variational autoencoder, including:

[0021] Input X1 and X2 into the first variational autoencoder and the second variational autoencoder respectively, wherein X1 and X2 are the same enhanced image after data enhancement;

[0022] In the first variational autoencoder, the input X1 is a 64×64×1 grayscale image. X1 is deformed into a 4096×1 strip vector through a flattening operation. The strip vector undergoes initial global feature fusion through a fully connected neural network with a network parameter size of 1×512 to obtain an initial global feature A1 of size 4096×512. X2 is also processed in the same way in the second variational autoencoder to obtain an initial global feature A2 of size 4096×512.

[0023] Further, in S104, multiple initial global feature matrices extracted by the fully connected neural network are concatenated with multiple latent variables in the variational autoencoder in the first dimension, including:

[0024] Add a preset latent variable z to the first variational autoencoder and the second variational autoencoder respectively, where z is a 1×512 zero vector;

[0025] The initial global features A1 and A2 extracted by the fully connected neural network are concatenated with their respective latent variables z in the first dimension, and the first feature matrix B1 is obtained in the first variational autoencoder, and the first feature matrix B2 is obtained in the second variational autoencoder.

[0026] Further, in S105, the multiple first feature matrices are respectively input into the fully connected neural network to obtain multiple second feature matrices as output, and the multiple second feature matrices are respectively split to retain only the multiple latent feature matrices at the end, including:

[0027] The first feature matrix B1 and the first feature matrix B2 are respectively input into a fully connected neural network of size 512×32 to obtain the output second feature matrix C1 and the second feature matrix C2. The size of the second feature matrix C1 and the second feature matrix C2 are both 4097×32. Then the second feature matrix C1 and the second feature matrix C2 are respectively split to obtain the latent feature matrix Z1 and the latent feature matrix Z2 at the end.

[0028] Furthermore, multiple latent feature matrices are concatenated in the second dimension to obtain a trajectory vector, and the trajectory vector is input into a fully connected neural network to obtain the final output scanning trajectory matrix, including:

[0029] The latent feature matrix Z1 and the latent feature matrix Z2 are concatenated in the second dimension to obtain a vector V of size 1×64, and the vector V is input into a fully connected neural network of size 64×6 to obtain the final output scanning trajectory matrix Q1=[Sx1, Sy1, Sz1, Rx1, Ry1, Rz1], where Sx1, Sy1, Sz1 represent the coordinates of the three spatial coordinate axes at time t=1, and Rx1, Ry1, Rz1 represent the end posture of the robot arm in the three posture coordinate axes at time t=1;

[0030] After the ultrasonic scanning robot moves to the trajectory coordinate Q1, the steps are repeated to perform trajectory planning for the entire scanning task until the ultrasonic scanning robot is manually stopped, and the ultrasonic scanning trajectory is obtained.

[0031] Compared with the prior art, the ultrasonic scanning trajectory planning method and system based on variational autoencoder provided by the present invention have the following beneficial effects:

[0032] 1. By training the scanning samples of the ultrasound scanning robot, the problem of large image data errors in mechanical ultrasound scanning was solved. Considering that the quality of ultrasound images is highly dependent on the operator's experience and there are significant individual differences, it is necessary to achieve good generalization ability with limited training data and to deal with the differences in geometry and image features of different patients. Therefore, a mutual information learning method based on variational autoencoders was adopted to train and optimize the ultrasound diagnosis model through few-sample learning. Through the high-precision control and intelligent decision-making planning trajectory of the ultrasound scanning robot, the ultrasound scanning operation was automatically completed, which improved the accuracy and stability of the diagnosis results and reduced the dependence on operators.

[0033] 2. Ultrasonic images are acquired in real time through an ultrasonic scanning robot, and the ultrasonic images at each moment are input into the first variational autoencoder and the second variational autoencoder to extract latent features 1 and 2. After latent features 1 and 2 are mutually information disentangled, they are input into a fully connected network to generate scanning trajectories. Subsequently, ultrasonic scanning is performed in accordance with the acquired scanning trajectory, which frees up personnel and at the same time, the collected ultrasonic images have high accuracy.

[0034] An ultrasonic scanning trajectory planning system based on a variational autoencoder is used to execute the above-mentioned ultrasonic scanning trajectory planning method, and the ultrasonic scanning trajectory planning system includes:

[0035] An acquisition module, used for receiving an ultrasound image acquisition instruction sent by a user terminal;

[0036] An acquisition module, used to acquire ultrasonic image data collected in a target area;

[0037] A preprocessing module is used to sequentially place the ultrasonic image data in an image preprocessing model to perform denoising on the ultrasonic image data, and obtain balanced ultrasonic image data after denoising;

[0038] A feature fusion module is used to obtain enhanced images of multiple variational autoencoders. The enhanced images of multiple variational autoencoders are subjected to initial global feature fusion through a fully connected neural network to obtain multiple initial global feature matrices.

[0039] A matrix generation module is used to concatenate multiple initial global feature matrices and multiple latent variables in the variational autoencoder in the first dimension, and to split multiple second feature matrices separately, retaining only the multiple latent feature matrices at the end;

[0040] The generation module is used to concatenate multiple latent feature matrices in the second dimension to obtain a trajectory vector, input the trajectory vector into a fully connected neural network to obtain the final output scanning trajectory matrix, and repeat the steps to plan the trajectory of the entire scanning task until the ultrasonic scanning robot is manually stopped, thus obtaining the ultrasonic scanning trajectory. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the process of preprocessing image data in the ultrasonic scanning trajectory planning method based on variational autoencoder proposed in the present invention;

[0042] Figure 2 A schematic diagram of the process of intelligently generating a planning trajectory for an ultrasonic scanning robot in the ultrasonic scanning trajectory planning method based on a variational autoencoder proposed in the present invention;

[0043] Figure 3 It is an ultrasonic scanning trajectory coordinate diagram generated in the ultrasonic scanning trajectory planning method based on variational autoencoder proposed in the present invention;

[0044] Figure 4 This is a schematic diagram of the structure of the ultrasonic scanning trajectory planning system based on variational autoencoder proposed in the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0046] The implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0047] The same or similar numbers in the drawings of this embodiment correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and cannot be understood as limitations on the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0048] Reference Figure 1-2 As shown, the ultrasonic scanning trajectory planning method based on variational autoencoder is applied to an ultrasonic scanning robot, and specifically includes the following steps:

[0049] S101: receiving an ultrasound image acquisition instruction sent by a user terminal, where the ultrasound image acquisition instruction includes a command to activate the carried ultrasound probe, target area data acquired by the ultrasound image, and feature information of the ultrasound probe when acquiring the image;

[0050] The step of receiving the ultrasound image acquisition instruction sent by the user terminal includes:

[0051] receiving a connection request sent by a user terminal through a preset network, where the connection request is used to request to establish a connection with the ultrasonic scanning robot;

[0052] Check whether the current account of the user terminal is the target account;

[0053] If the current account of the user terminal is the target account, the user terminal is connected according to the connection request, and after the connection is completed, the ultrasound image acquisition instruction sent by the user terminal is received;

[0054] S102: Acquire ultrasonic image data collected in the target area, place the ultrasonic image data in the image preprocessing model in sequence to perform denoising on the ultrasonic image data in sequence, and obtain balanced ultrasonic image data after denoising;

[0055] The step of obtaining ultrasonic image data collected in the target area includes:

[0056] The operator manually controls the ultrasonic scanning robot to move the ultrasonic probe to the starting point Q0 of the area to be scanned;

[0057] The ultrasound image is acquired with the starting point Q0 as the starting point. The image I(0) at the initial moment is then de-noised and enhanced to highlight key medical features. After that, the ultrasound scanning robot moves to the trajectory coordinate Q1 and repeats the steps to plan the trajectory of the entire scanning task until the ultrasound scanning robot is manually stopped, thus obtaining the ultrasound scanning trajectory.

[0058] S103: placing the acquired balanced ultrasonic image data in a multi-variational autoencoder for image enhancement, obtaining an enhanced image of the multi-variational autoencoder, performing initial global feature fusion on the enhanced image of the multi-variational autoencoder through a fully connected neural network, and obtaining multiple initial global feature matrices;

[0059] S104: adding a preset hidden variable to each of the multiple variational autoencoders, and concatenating the multiple initial global feature matrices extracted by the fully connected neural network with the hidden variables in the multiple variational autoencoders in the first dimension to obtain multiple first feature matrices;

[0060] S105: Input multiple first feature matrices into the fully connected neural network respectively to obtain multiple second feature matrices as outputs, split the multiple second feature matrices separately, retain only the multiple latent feature matrices at the end, and then concatenate the multiple latent feature matrices in the second dimension to obtain a trajectory vector, and input the trajectory vector into the fully connected neural network to obtain the final output scanning trajectory matrix.

[0061] In this embodiment, the preset network includes one or a combination of a 3G network, a 4G network, a 5G network, and a WIFI network.

[0062] In this embodiment, in the first step, the multiple variational autoencoders are at least two, namely the first variational autoencoder and the second variational autoencoder, and X1 and X2 are respectively input into the first variational autoencoder and the second variational autoencoder, and X1 and X2 are the same enhanced image after data enhancement; X1 is input into the first variational autoencoder as a 64×64×1 grayscale image, and X1 is deformed into a 4096×1 strip vector through a flattening operation, and the strip vector is subjected to initial global feature fusion through a fully connected neural network with a network parameter size of 1×512 to obtain an initial global feature A1 with a size of 4096×512, and X2 is also processed in the same way in the second variational autoencoder to obtain an initial global feature A2 with a size of 4096×512;

[0063] The second step is to add a preset latent variable z to the first variational autoencoder and the second variational autoencoder respectively, where z is a 1×512 zero vector;

[0064] The initial global features A1 and A2 extracted by the fully connected neural network are concatenated with their respective latent variables z in the first dimension, and the first feature matrix B1 is obtained in the first variational autoencoder, and the first feature matrix B2 is obtained in the second variational autoencoder;

[0065] The third step is to input the first feature matrix B1 and the first feature matrix B2 into a fully connected neural network with a size of 512×32 to obtain the output second feature matrix C1 and the second feature matrix C2 respectively. The size of the second feature matrix C1 and the second feature matrix C2 are both 4097×32. Then, the second feature matrix C1 and the second feature matrix C2 are split separately to obtain the latent feature matrix Z1 and the latent feature matrix Z2 at the end.

[0066] The fourth step is to concatenate the latent feature matrix Z1 and the latent feature matrix Z2 in the second dimension to obtain a vector V of size 1×64, and input the vector V into a fully connected neural network of size 64×6 to obtain the final output scanning trajectory matrix Q1=[Sx1, Sy1, Sz1, Rx1, Ry1, Rz1], where Sx1, Sy1, Sz1 represent the coordinates of the three spatial coordinate axes at time t=1, and Rx1, Ry1, Rz1 represent the end posture of the robot arm in the three posture coordinate axes at time t=1; after the ultrasonic scanning robot moves to the trajectory coordinate Q1, repeat the steps to plan the trajectory of the entire scanning task until the ultrasonic scanning robot is manually stopped, that is, the ultrasonic scanning trajectory is obtained, refer to Figure 3 As shown, it is a trajectory curve diagram of three-dimensional coordinates, which is the connection curve from Q0 to Qn, and each coordinate point is determined by the global feature fusion judgment calculated by the first variational autoencoder and the second variational autoencoder. When performing subsequent ultrasound scanning, the acquired scanning trajectory is followed to perform ultrasound scanning, which frees up personnel and at the same time the collected ultrasound images are more accurate.

[0067] Reference Figure 4 As shown, the ultrasound scanning trajectory planning system based on variational autoencoder is used to execute the above-mentioned ultrasound scanning trajectory planning method. By training the scanning samples of the ultrasound scanning robot, the problem of large image data errors in mechanical ultrasound scanning is solved. Considering that the quality of ultrasound images is highly dependent on the experience of the operator and there are significant individual differences, it is necessary to achieve good generalization ability under limited training data and to deal with the differences in geometry and image features of different patients, a mutual information learning method based on variational autoencoder is adopted. The ultrasound diagnosis model is trained and optimized through few-sample learning. The ultrasound scanning robot is controlled with high precision and intelligent decision-making to plan the trajectory, and the ultrasound scanning operation is automatically completed, thereby improving the accuracy and stability of the diagnosis results and reducing the dependence on the operator. The ultrasound scanning trajectory planning system includes:

[0068] The acquisition module is used to receive the ultrasonic image acquisition instruction sent by the user terminal; the acquisition module is used to acquire the ultrasonic image data acquired in the target area; the preprocessing module is used to place the ultrasonic image data in the image preprocessing model in turn to complete the denoising of the ultrasonic image data in turn, and obtain the balanced ultrasonic image data after the denoising process; the feature fusion module is used to obtain the enhanced image of the multiple variational autoencoders, and the enhanced image of the multiple variational autoencoders is subjected to the initial global feature fusion through the fully connected neural network to obtain multiple initial global feature matrices; the matrix generation module is used to splice the multiple initial global feature matrices with the hidden variables in the multiple variational autoencoders in the first dimension, and to split the multiple second feature matrices respectively, and only retain the multiple hidden features at the end. A feature matrix generation module is used to concatenate multiple latent feature matrices in the second dimension to obtain a trajectory vector, input the trajectory vector into a fully connected neural network to obtain a final output scanning trajectory matrix, repeat the steps to perform trajectory planning for the entire scanning task, until the ultrasonic scanning robot is manually stopped, that is, the ultrasonic scanning trajectory is obtained, the ultrasonic image is acquired in real time by the ultrasonic scanning robot, and the ultrasonic image at each moment is input into the first variational autoencoder and the second variational autoencoder to extract latent feature 1 and latent feature 2, after latent feature 1 and latent feature 2 are mutually information untangled, they are input into the fully connected network to generate the scanning trajectory, and subsequently, when performing ultrasonic scanning, the ultrasonic scanning is performed in accordance with the acquired scanning trajectory, which frees up personnel and at the same time, the collected ultrasonic images have high accuracy.

[0069] In this embodiment, the entire operation process can be controlled by a computer to achieve automatic operation control, and in each operation link, sensors can be set to provide signal feedback to achieve sequential execution of steps. These are all common knowledge of current automatic control and will not be described in detail in this embodiment.

[0070] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. Ultrasonic scanning trajectory planning method based on variational autoencoder, characterized in that: Applied to ultrasonic scanning robots, specifically including the following steps: S101: receiving an ultrasound image acquisition instruction sent by a user terminal, where the ultrasound image acquisition instruction includes a command to activate the carried ultrasound probe, target area data acquired by the ultrasound image, and feature information of the ultrasound probe when acquiring the image; S102: Acquire ultrasonic image data collected in the target area, place the ultrasonic image data in the image preprocessing model in turn to perform denoising on the ultrasonic image data in turn, and obtain balanced ultrasonic image data after denoising; S103: placing the acquired balanced ultrasonic image data in a multi-variational autoencoder for image enhancement, obtaining an enhanced image of the multi-variational autoencoder, performing initial global feature fusion on the enhanced image of the multi-variational autoencoder through a fully connected neural network, and obtaining multiple initial global feature matrices; S104: adding a preset hidden variable to each of the multiple variational autoencoders, and concatenating the multiple initial global feature matrices extracted by the fully connected neural network with the hidden variables in the multiple variational autoencoders in the first dimension to obtain multiple first feature matrices; S105: Input multiple first feature matrices into the fully connected neural network respectively to obtain multiple second feature matrices as outputs, split the multiple second feature matrices separately, retain only the multiple latent feature matrices at the end, and then concatenate the multiple latent feature matrices in the second dimension to obtain a trajectory vector, and input the trajectory vector into the fully connected neural network to obtain the final output scanning trajectory matrix.

2. The ultrasonic scanning trajectory planning method based on variational autoencoder according to claim 1, characterized in that: In S101, receiving an ultrasound image acquisition instruction sent by a user terminal includes: receiving a connection request sent by a user terminal through a preset network, wherein the connection request is used to request to establish a connection with the ultrasonic scanning robot; Detecting whether the current account of the user terminal is the target account; If the current account of the user terminal is the target account, a connection is made with the user terminal according to the connection request, and after the connection is completed, an ultrasound image acquisition instruction sent by the user terminal is received.

3. The ultrasonic scanning trajectory planning method based on variational autoencoder according to claim 2, characterized in that: The preset network includes one or a combination of a 3G network, a 4G network, a 5G network, and a WIFI network.

4. The ultrasonic scanning trajectory planning method based on variational autoencoder according to claim 3, characterized in that: In S102, ultrasonic image data collected in the target area is obtained, including: The operator manually controls the ultrasonic scanning robot to move the ultrasonic probe to the starting point Q0 of the area to be scanned; The ultrasound image is acquired with the starting point Q0 as the starting point, and the image I(0) at the initial moment is acquired to highlight the key medical features through denoising and image enhancement.

5. The ultrasonic scanning trajectory planning method based on variational autoencoder according to claim 4, characterized in that: In S103, the multiple variational autoencoders are at least two, namely a first variational autoencoder and a second variational autoencoder.

6. The ultrasonic scanning trajectory planning method based on variational autoencoder according to claim 5, characterized in that: The acquired balanced ultrasonic image data is placed in a multi-variational autoencoder for image enhancement, and an enhanced image of the multi-variational autoencoder is obtained, including: Input X1 and X2 into the first variational autoencoder and the second variational autoencoder respectively, wherein X1 and X2 are the same enhanced image after data enhancement; In the first variational autoencoder, the input X1 is a 64×64×1 grayscale image. X1 is deformed into a 4096×1 strip vector through a flattening operation. The strip vector undergoes initial global feature fusion through a fully connected neural network with a network parameter size of 1×512 to obtain an initial global feature A1 of size 4096×512. X2 is also processed in the same way in the second variational autoencoder to obtain an initial global feature A2 of size 4096×512.

7. The ultrasonic scanning trajectory planning method based on variational autoencoder according to claim 6, characterized in that: In S104, multiple initial global feature matrices extracted by the fully connected neural network are concatenated with multiple latent variables in the variational autoencoder in the first dimension, including: Add a preset latent variable z to the first variational autoencoder and the second variational autoencoder respectively, where z is a 1×512 zero vector; The initial global features A1 and A2 extracted by the fully connected neural network are concatenated with their respective latent variables z in the first dimension, and the first feature matrix B1 is obtained in the first variational autoencoder, and the first feature matrix B2 is obtained in the second variational autoencoder.

8. The ultrasonic scanning trajectory planning method based on variational autoencoder according to claim 7, characterized in that: In S105, the multiple first feature matrices are respectively input into the fully connected neural network to obtain multiple second feature matrices as output, and the multiple second feature matrices are respectively split to retain only the multiple latent feature matrices at the end, including: The first feature matrix B1 and the first feature matrix B2 are respectively input into a fully connected neural network of size 512×32 to obtain the output second feature matrix C1 and the second feature matrix C2. The size of the second feature matrix C1 and the second feature matrix C2 are both 4097×32. Then the second feature matrix C1 and the second feature matrix C2 are respectively split to obtain the latent feature matrix Z1 and the latent feature matrix Z2 at the end.

9. The ultrasonic scanning trajectory planning method based on variational autoencoder according to claim 8, characterized in that: Then, multiple latent feature matrices are concatenated in the second dimension to obtain the trajectory vector, and the trajectory vector is input into the fully connected neural network to obtain the final output scanning trajectory matrix, including: The latent feature matrix Z1 and the latent feature matrix Z2 are concatenated in the second dimension to obtain a vector V of size 1×64, and the vector V is input into a fully connected neural network of size 64×6 to obtain the final output scanning trajectory matrix Q1=[Sx1, Sy1, Sz1, Rx1, Ry1, Rz1], where Sx1, Sy1, Sz1 represent the coordinates of the three spatial coordinate axes at time t=1, and Rx1, Ry1, Rz1 represent the end posture of the robot arm in the three posture coordinate axes at time t=1; After the ultrasonic scanning robot moves to the trajectory coordinate Q1, the steps are repeated to perform trajectory planning for the entire scanning task until the ultrasonic scanning robot is manually stopped, and the ultrasonic scanning trajectory is obtained.

10. Ultrasonic scanning trajectory planning system based on variational autoencoder, characterized in that: Used to execute the ultrasound scanning trajectory planning method according to any one of claims 1 to 9, the ultrasound scanning trajectory planning system comprises: An acquisition module, used for receiving an ultrasound image acquisition instruction sent by a user terminal; An acquisition module, used to acquire ultrasonic image data collected in a target area; A preprocessing module is used to sequentially place the ultrasonic image data in an image preprocessing model to perform denoising on the ultrasonic image data, and obtain balanced ultrasonic image data after denoising; A feature fusion module is used to obtain enhanced images of multiple variational autoencoders. The enhanced images of multiple variational autoencoders are subjected to initial global feature fusion through a fully connected neural network to obtain multiple initial global feature matrices. A matrix generation module is used to concatenate multiple initial global feature matrices and multiple latent variables in the variational autoencoder in the first dimension, and to split multiple second feature matrices separately, retaining only the multiple latent feature matrices at the end; The generation module is used to concatenate multiple latent feature matrices in the second dimension to obtain a trajectory vector, input the trajectory vector into a fully connected neural network to obtain the final output scanning trajectory matrix, and repeat the steps to plan the trajectory of the entire scanning task until the ultrasonic scanning robot is manually stopped, thus obtaining the ultrasonic scanning trajectory.

Images