Interactive anesthesia puncture auxiliary guidance method and system

Abstract

The invention relates to the technical field of image data processing, in particular to an interactive anesthesia puncture auxiliary guidance method and system, and the method comprises the steps: obtaining an ultrasonic image sequence of a to-be-anesthetized puncture tissue region under the preset initial frequency of an ultrasonic probe, determining the imaging frequency penetrability of each frame of ultrasonic image, and obtaining the optimized frequency of the ultrasonic probe, obtaining an updated ultrasonic image sequence of the to-be-anesthetized puncture tissue area again, fusing the ultrasonic image sequence and images under the same-sequence numerical values in the updated ultrasonic image sequence to obtain a fused ultrasonic image sequence, performing tissue identification on the fused ultrasonic image sequence, and performing puncture path calculation according to a tissue identification result to obtain a puncture path of the to-be-anesthetized puncture tissue area. And generating puncture auxiliary guidance suggestions. According to the method, a new imaging result is obtained by updating the ultrasonic imaging frequency and fusing, so that the problems of imaging blurring and identification errors caused by complex conditions in tissues are solved, and the safety in the anesthesia puncture auxiliary guidance process is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to an interactive anesthesia puncture auxiliary guidance method and system. Background Art

[0002] In the field of anesthesiology, "interactive" anesthesia refers to the system interacting with the doctor in real time during the anesthesia procedure, providing dynamic visualization, positioning, navigation, and feedback to help the doctor complete the puncture or catheterization operation. Specifically, it includes: (1) real-time information feedback: the system displays the needle tip position and tissue structure level in real time based on the data obtained by the imaging device (ultrasound); (2) active prompts: when the needle approaches the target nerve, blood vessel, or spinal canal, the system issues a visual or sound prompt; (3) safety assistance: the system identifies potential risks (such as accidental puncture of a blood vessel) and issues a warning.

[0003] In the existing technology, real-time navigation based on medical images is generally adopted, among which ultrasound guidance is the most common. By acquiring ultrasound images in real time and identifying the puncture area results with existing image analysis algorithms, the brightness of the area to be punctured recommended by the system is improved, thereby achieving the purpose of interactive anesthesia puncture auxiliary guidance.

[0004] Existing problems: During the interactive anesthesia assisted guidance process, the tissue area to be anesthetized is highly complex. When the fat layer is too thick or there is excessive bleeding, the fixed frequency of ultrasound cannot provide a high penetration level to the thicker fat area or clear ultrasound results to the noisy area with excessive bleeding. Therefore, when puncture assisted guidance is performed based on real-time ultrasound image results, it is very easy to have assisted guidance errors caused by image clarity problems, and even medical accidents. Summary of the Invention

[0005] The present invention provides an interactive anesthesia puncture auxiliary guidance method and system to solve the existing problems.

[0006] The interactive anesthesia puncture auxiliary guidance method and system of the present invention adopts the following technical solutions:

[0007] An embodiment of the present invention provides an interactive anesthesia puncture auxiliary guidance method, which includes the following steps:

[0008] Acquire an ultrasound image sequence of the tissue area to be anesthetized and punctured within a preset time period at a preset initial frequency of the ultrasound probe;

[0009] determining the tissue heterogeneity of each frame of ultrasound image according to the gradient amplitude of the pixel points and the edge pixel points in each frame of ultrasound image in the ultrasound image sequence;

[0010] Determining the imaging frequency penetration of each frame of the ultrasound image based on the tissue heterogeneity of each frame of the ultrasound image and the grayscale value of the pixel points in the ultrasound image; obtaining the optimized frequency of the ultrasound probe based on the imaging frequency penetration of all frames of the ultrasound image in the ultrasound image sequence and the preset initial frequency of the ultrasound probe; and reacquiring an updated ultrasound image sequence of the tissue area to be anesthetized and punctured within a preset time period at the optimized frequency of the ultrasound probe;

[0011] The ultrasound image sequence and the images with the same sequence value in the updated ultrasound image sequence are fused to obtain a fused ultrasound image sequence; tissue recognition is performed on the fused ultrasound image sequence, and the puncture path is calculated based on the tissue recognition result to generate puncture auxiliary guidance suggestions.

[0012] Furthermore, the determining of tissue heterogeneity of each frame of ultrasound image includes the following specific steps:

[0013] Determine the tissue absorption degree of each frame of ultrasound image according to the gradient amplitude of all edge pixel points in each frame of ultrasound image;

[0014] Mark the connected domains of all edge pixels in each frame of ultrasound image to obtain several connected domains;

[0015] The tissue heterogeneity of each ultrasound image frame is determined based on the number of connected domains in each ultrasound image frame, the gradient amplitude of all pixels, and the tissue absorption degree of each ultrasound image frame.

[0016] Furthermore, the specific steps of determining the tissue absorption degree of each frame of ultrasound image include the following:

[0017] The inversely proportional normalized value of the mean of the gradient amplitudes of all edge pixels in each frame of ultrasound image is recorded as the tissue absorption degree of each frame of ultrasound image.

[0018] Furthermore, the tissue heterogeneity of each frame of ultrasound image is determined based on the number of connected domains in each frame of ultrasound image, the gradient amplitudes of all pixels, and the degree of tissue absorption in each frame of ultrasound image, including the following specific steps:

[0019] In each frame of ultrasound image, the mean of the gradient amplitudes of all pixels is obtained and recorded as the first mean. The ratio of the number of connected domains to the first mean is obtained and recorded as the first ratio. The normalized value of the product of the first ratio and the tissue absorption degree of each frame of ultrasound image is recorded as the tissue heterogeneity of each frame of ultrasound image.

[0020] Furthermore, the determining of the imaging frequency penetration of each frame of ultrasound image includes the following specific steps:

[0021] In each frame of ultrasound image, the number of pixels whose grayscale values ​​are less than a preset grayscale threshold is counted, recorded as a first quantity value, and the ratio of the first quantity value to the number of all pixels is obtained, recorded as a second ratio;

[0022] The imaging frequency penetration of each frame of ultrasound image is obtained according to the second ratio and the tissue heterogeneity of each frame of ultrasound image.

[0023] Furthermore, the step of obtaining the imaging frequency penetration of each frame of ultrasound image based on the second ratio and the tissue heterogeneity of each frame of ultrasound image includes the following specific steps:

[0024] An inversely proportional normalized value of the product of the second ratio and the tissue heterogeneity of each frame of ultrasound image is recorded as the imaging frequency penetration of each frame of ultrasound image.

[0025] Furthermore, the step of obtaining the optimized frequency of the ultrasound probe includes the following specific steps:

[0026] In the ultrasound image sequence, the average value of the imaging frequency penetration of all frames of ultrasound images is obtained, which is recorded as the second average value;

[0027] When the second mean value is less than the preset penetration threshold, obtaining a frequency adjustment coefficient according to the preset initial frequency of the ultrasound probe and the second mean value;

[0028] The optimized frequency of the ultrasound probe is determined based on the frequency adjustment coefficient and the preset basic frequency.

[0029] Furthermore, the obtaining of the frequency adjustment coefficient includes the following specific steps:

[0030] The product of the preset initial frequency of the ultrasonic probe and the second mean value is obtained and recorded as the frequency adjustment coefficient.

[0031] Furthermore, the step of determining the optimized frequency of the ultrasound probe according to the frequency adjustment coefficient and the preset basic frequency includes the following specific steps:

[0032] The sum of the frequency adjustment coefficient and the preset basic frequency is used as the optimized frequency of the ultrasound probe.

[0033] The present invention also proposes an interactive anesthesia puncture auxiliary guidance system, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. The processor executes the computer program stored in the memory to implement the steps of the aforementioned interactive anesthesia puncture auxiliary guidance method.

[0034] The beneficial effects of the technical solution of the present invention are:

[0035] In an embodiment of the present invention, at a preset initial frequency of the ultrasound probe, an ultrasound image sequence of the tissue area to be anesthetized and punctured is acquired within a preset time period, the imaging frequency penetration of each frame of the ultrasound image is determined, and the optimized frequency of the ultrasound probe is obtained. At the optimized frequency of the ultrasound probe, an updated ultrasound image sequence of the tissue area to be anesthetized and punctured is reacquired within a preset time period, the ultrasound image sequence and the images with the same sequence value in the updated ultrasound image sequence are fused to obtain a fused ultrasound image sequence, tissue recognition is performed on the fused ultrasound image sequence, and the puncture path is calculated based on the tissue recognition result to generate a puncture auxiliary guidance suggestion. Thus, the present invention analyzes the main imaging characteristics of the real-time imaging results to obtain the heterogeneity of the tissue and the penetration corresponding to the ultrasound frequency, and updates the ultrasound imaging frequency according to the penetration, and fuses to obtain a new imaging result, eliminating the problems of imaging blur and recognition error caused by complex conditions in the tissue, improving the safety of the auxiliary guidance process, and in the process of analyzing the penetration effect, by analyzing the basic characteristics of the imaging, combined with the general reflection imaging effect of the tissue area, determining the incompatible frequency and its further recommended frequency update result, and performing image fusion processing on the updated frequency ultrasound imaging result, improving the image recognizability. This allows for targeted fusion processing of key areas (such as fat and other regions), while other areas continue to generate relevant ultrasound images. This reduces hardware energy consumption and increases the efficiency and accuracy of tissue region identification. Finally, after obtaining the image fusion results, the system's terminal neural network identifies them and provides relevant puncture guidance. This improves puncture efficiency and safety during the auxiliary identification process, reduces patient waiting time, and provides a learnable teaching effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A flowchart of the steps of an interactive anesthesia puncture auxiliary guidance method of the present invention;

[0038] Figure 2 Schematic diagram of the fusion process of ultrasound images and updated ultrasound images. DETAILED DESCRIPTION

[0039] To further illustrate the technical means and effectiveness of the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of an interactive anesthesia puncture auxiliary guidance method and system proposed by the present invention. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0040] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0041] The following describes in detail a specific scheme of an interactive anesthesia puncture auxiliary guidance method and system provided by the present invention with reference to the accompanying drawings.

[0042] See also Figure 1 , which shows a flowchart of the steps of an interactive anesthesia puncture auxiliary guidance method provided by one embodiment of the present invention, the method comprising the following steps:

[0043] Step S001: Acquire an ultrasound image sequence of a tissue area to be anesthetized and punctured within a preset time period at a preset initial frequency of the ultrasound probe.

[0044] In this embodiment, an anesthesia puncture auxiliary image data acquisition device and its corresponding analysis system are first configured, and the real-time image data collected is transmitted to the analysis system. Then, a real-time ultrasound image frame is obtained, and the real-time ultrasound imaging frequency penetration is determined based on the image tissue heterogeneity. The ultrasound imaging frequency and its detection angle range are updated according to the penetration, and the regenerated ultrasound image is fused to obtain a high-definition ultrasound image. Finally, combined with the recognition network, the tissue area is identified, and puncture positioning guidance suggestions are provided to improve the safety and efficiency of puncture auxiliary guidance in complex tissue areas.

[0045] It should be noted that: in the process of configuring the anesthesia puncture auxiliary image data acquisition device and its corresponding analysis system, and transmitting the collected real-time image data to the analysis system, an ultrasound probe is used to obtain real-time images of the puncture area. The frequency of the probe part is variable, which is used to subsequently optimize the clarity of the generated ultrasound image. Among them, the high frequency range of the probe is 5 to 15 MHz (megahertz), and the low frequency range is 1 to 5 MHz. In addition, a linear array probe is selected, which is suitable for imaging shallow tissues, such as plane scanning of nerves, blood vessels, etc. The image is processed using an ultrasound machine and the data is transmitted to the analysis system through an interface (USB). The position of the puncture needle is tracked using sensors and puncture guide devices to ensure accuracy. The real-time image data is transmitted to the analysis system using Wi-Fi. The data transmission requires low latency (i.e., less than 50 milliseconds, for this example) to ensure real-time performance. The analysis system includes: (1) Image processing: Real-time image analysis is performed through a deep learning model (CNN) to identify tissue structures. (2) Computing platform: Data processing is performed through an IPGPU workstation. (3) User interface: Displays real-time images and puncture path suggestions to assist doctors in performing accurate punctures. Therefore, the image of the puncture area is first collected in real time, and then the image is transmitted to the analysis system, which analyzes it in real time and gives puncture path suggestions. Finally, the doctor performs precise puncture operations based on the suggestions.

[0046] Thus, a sequence of ultrasound images of the tissue area to be anesthetized and punctured within a preset time period can be obtained at the preset initial frequency of the ultrasound probe.

[0047] It should be noted that in this embodiment, the ultrasound probe's preset initial frequency is 10 MHz. Higher frequencies improve the spatial resolution of the image, but reduce penetration depth. The preset duration is 2 seconds, and the ultrasound image acquisition frequency is 24 frames per second, meaning that the ultrasound image sequence contains 48 frames of ultrasound images, all in grayscale. The interactive puncture guidance device, implemented using the above acquisition configuration, generates real-time ultrasound images of the patient's anesthetized area and provides guidance on the puncture location. During interactive operation, the complexity of the tissue to be punctured, such as excessive fat thickness or hemorrhage, can lead to unclear ultrasound images and excessive noise. The ultrasound imaging principle of the device described above demonstrates that it uses ultrasound reflection from the tissue surface to generate imaging results through comprehensive acquisition and analysis. Different fat thicknesses within tissue have different penetration capabilities for ultrasound. Areas with thicker fat layers or more hemorrhage are best suited for ultrasound waves with stronger penetration, namely, low-frequency ultrasound waves. The resulting ultrasound images lack detail and only capture the basic structure of the tissue within the fat layer. On the contrary, for fat layers or areas with less bleeding, ultrasound with lower penetration but rich ultrasound image details, that is, high-frequency ultrasound, is more suitable. The images generated at this time have higher resolution and can observe superficial structures such as blood vessels and nerves in detail. Therefore, complex tissue areas are often accompanied by blurred and high-noise ultrasound imaging results. In order to solve this problem, first of all, it is necessary to make the system recognize the specific complex tissue areas, that is, because of the complexity or heterogeneity, the ultrasound image is blurred and has other problems.

[0048] Step S002: determining the tissue heterogeneity of each frame of ultrasound image according to the gradient amplitude of the pixel points and the edge pixel points in each frame of ultrasound image in the ultrasound image sequence.

[0049] What needs to be explained is: obtain the real-time ultrasound image frame, judge the heterogeneity of the patient's tissue area reflected by the visual characteristics of the ultrasound image in the current frame, the higher the heterogeneity, that is, the thicker the fat layer corresponding to the puncture area at this time or the higher the amount of bleeding, which will lead to blur or high noise problems in the ultrasound image. Specifically, when the penetration effect is poor, the image will show more regular features for the system to accurately identify, which include: (1) fuzziness of boundaries. Due to the weak penetration ability of low-frequency ultrasound, the image will lack clear boundaries, especially in areas with thick fat layers, and the contrast is insufficient. That is, when low-frequency imaging, shallow tissues (such as skin and fat) have low recognition, making it difficult to distinguish the boundaries between tissues. (2) At the same time, accompanied by the effect of increased noise spots, when the penetration depth is large, the ultrasound echo signal is relatively weak, resulting in an increase in noise spots during imaging, especially in the transition area between the fat layer and the muscle layer, and when there is excessive bleeding, it also presents higher reflection noise.

[0050] Preferably, in one embodiment of the present invention, the method for acquiring tissue heterogeneity of each frame of ultrasound image includes:

[0051] In the ultrasound imaging sequence, Frame ultrasound image is taken as an example, using Canny edge detection algorithm, Frame ultrasound image edge detection is performed to obtain the first The gradient amplitude of each pixel in the frame ultrasound image, as well as several edge pixels.

[0052] Use the connected component marking algorithm (Two-pass algorithm), according to the All edge pixels in the frame ultrasound image are marked as connected domains to obtain several connected domains.

[0053] Among them, the Canny edge detection algorithm and the connected component labeling algorithm (Two-pass algorithm) are both well-known technologies, and the specific methods are not introduced here.

[0054] It should be noted that when ultrasound penetration is poor, the fat layer absorbs ultrasound waves, resulting in extremely blurred edges and low contrast in ultrasound images. Secondly, within the image frame, there are many isolated connected domains globally. This is because excessive bleeding and the inability to penetrate some fat layers lead to increased echo noise blocks or speckle noise, which appear as isolated connected domains within the image. Therefore, a large number of connected domains indicates higher tissue heterogeneity.

[0055] In the Get the mean value of the gradient amplitude of all edge pixels in the frame ultrasound image The inverse proportional normalized value of The degree of tissue absorption in each frame of ultrasound image.

[0056] It should be noted that: in this embodiment, As The inverse normalized value of It is a linear normalization function used to normalize the data value to between 0 and 1. The larger the gradient amplitude of the edge pixel, the clearer the edge in the image. A larger inversely proportional normalized value indicates blurred image edges. This indicates that during the ultrasound image generation process, ultrasound waves are more absorbed by thicker fat layers within the tissue, resulting in higher tissue absorption. Higher tissue absorption indicates greater tissue heterogeneity, increasing the need for accurate analysis of real-time ultrasound penetration and subsequent ultrasound frequency adjustments.

[0057] In the In the frame ultrasound image, the mean of the gradient amplitude of all pixels is obtained, which is recorded as the first mean. The ratio of the number of connected domains to the first mean is obtained, which is recorded as the first ratio. The first ratio is added to the first ratio. The product of the tissue absorption degree of the frame ultrasound image The normalized value of Tissue heterogeneity in frame-by-frame ultrasound imaging.

[0058] What needs to be explained is: As The normalized value of is used to reflect the contrast of the ultrasound image as the average of the gradient amplitudes of all pixels. The smaller the contrast value, the more blurred the image and the higher the tissue heterogeneity. Correspondingly, the more connected domains there are in the image, that is, the more noise blocks or speckle noise there are, the more it indicates that noise speckles are generated due to excessive bleeding and poor echo quality due to excessive fat. The closer the normalized value of The lower the visibility of the frame ultrasound image, the more necessary it is to determine the penetration of the current ultrasound frequency into the tissue and the frequency update result to optimize the recognizability of the ultrasound image.

[0059] Step S003: Determine the imaging frequency penetration of each frame of ultrasound image based on the tissue heterogeneity of each frame of ultrasound image and the size of the grayscale value of the pixel in the ultrasound image; obtain the optimized frequency of the ultrasound probe based on the size of the imaging frequency penetration of all frames of ultrasound image in the ultrasound image sequence, combined with the preset initial frequency of the ultrasound probe; and re-acquire an updated ultrasound image sequence of the tissue area to be anesthetized and punctured within a preset time length at the optimized frequency of the ultrasound probe.

[0060] It should be noted that frequency penetration needs to be determined. First, it can be determined that the frequency penetration of ultrasound imaging decreases in areas with greater tissue heterogeneity. This is because ultrasound cannot penetrate thicker fat layers and noisy areas with more bleeding, resulting in blurred and noisy imaging results. Furthermore, analyzing the real-time ultrasound imaging process reveals that when ultrasound has difficulty penetrating high-attenuation media (such as fat masses or blood clots), "shadow areas" form in the image. These areas appear as hypoechoic or anechoic "black shadows" behind the fat or blood clots, obstructing the display of deeper structures. This translates to imaging results that, for ultrasound frames with high tissue heterogeneity, the presence of more dark pixels indicates a higher number of "black shadows" and lower penetration.

[0061] Preferably, in one embodiment of the present invention, the method for acquiring updated ultrasound image sequences includes:

[0062] The preset grayscale threshold is 30, and this is used as an example for description.

[0063] In the In the frame ultrasound image, the number of pixels whose grayscale value is less than the preset grayscale threshold is counted and recorded as the first quantity value. The ratio of the first quantity value to the number of all pixels is obtained and recorded as the second ratio. The product of tissue heterogeneity in ultrasound images The inverse proportional normalized value of Imaging frequency penetration of frame ultrasound images.

[0064] It should be noted that: in this embodiment, As The inverse proportional normalized value of the second ratio is used to quantify the "shadow" effect caused by the low penetration when facing fat masses and blood clots. The higher the second ratio, the more obvious the "shadow" effect in the image and the lower the penetration. The greater the tissue heterogeneity, the lower the penetration. Therefore, the product The larger the inverse proportional normalized value of , the greater the imaging frequency penetration.

[0065] The preset penetration threshold is 0.2, and the preset base frequency is 2 MHz, which is used as an example for description.

[0066] In the ultrasound image sequence, the mean value of the imaging frequency penetration of all frames of ultrasound images is obtained, which is recorded as the second mean value. When the second mean value is less than the preset penetration threshold value, the product of the preset initial frequency of the ultrasound probe and the second mean value is obtained, which is recorded as the frequency adjustment coefficient. The sum of the frequency adjustment coefficient and the preset basic frequency is used as the optimized frequency of the ultrasound probe.

[0067] At the optimized frequency of the ultrasound probe, an updated ultrasound image sequence of the tissue area to be anesthetized and punctured is reacquired within a preset time length, with an acquisition frequency of 24 frames per second, and the updated ultrasound image is consistent with the size of the ultrasound image.

[0068] It should be noted that when the imaging frequency penetration of all frames in an ultrasound image sequence is generally low, it can be determined that the tissue area is a complex fat mass or blood clot. Therefore, an ultrasound penetration value update operation is required. This involves optimizing the real-time ultrasound frequency to generate a more appropriate and visible ultrasound image. Since the ultrasound probe's preset initial frequency is 10 MHz, the optimized frequency range is 2 to 4 MHz. The lower the penetration value, the lower the corresponding frequency optimization value. This is because low frequencies have stronger tissue penetration and are suitable for imaging deep tissue (such as the abdomen and deep blood vessels). When regenerating the ultrasound image, the imaging probe angle range needs to be increased by 20% of the original probe angle range. This is used as an example. Increasing the probe angle range primarily increases the imaging coverage area, allowing for observation of a wider range of tissue structures. The goal is to achieve clearer imaging results while maintaining the same image size. When the second mean is greater than or equal to the preset penetration threshold, it indicates that the ultrasound image quality in the ultrasound image sequence is appropriate, and subsequent tissue recognition can be performed directly on the ultrasound image sequence, and the puncture path can be calculated based on the tissue recognition results to generate puncture auxiliary guidance suggestions.

[0069] Step S004: Fusing the ultrasound image sequence with the images with the same sequence value in the updated ultrasound image sequence to obtain a fused ultrasound image sequence; performing tissue recognition on the fused ultrasound image sequence, calculating the puncture path based on the tissue recognition result, and generating puncture auxiliary guidance suggestions.

[0070] It should be noted that after obtaining new ultrasound imaging results for complex tissue areas, these images need to be fused with the original high-frequency imaging results. This is because lower frequencies increase image penetration depth but reduce spatial resolution. This means that after optimizing the frequency, the resulting image has higher penetration and is clearer, but lower resolution and imaging details. This advantage is only seen in areas with thick fat and deep structures. The original high-frequency ultrasound images, on the other hand, have higher resolution and can provide detailed observation of superficial structures such as blood vessels and nerves. Therefore, fusion processing is necessary to obtain high-definition local ultrasound images.

[0071] Preferably, in one embodiment of the present invention, the method for obtaining puncture auxiliary guidance suggestions includes:

[0072] The ultrasound image sequence is fused with the ultrasound images of the same sequence value in the updated ultrasound image sequence by using the Alpha fusion algorithm to obtain a fused ultrasound image sequence.

[0073] It should be noted that the Alpha fusion algorithm is a simple image fusion technique that achieves image superposition by adjusting image transparency. The Alpha value is a key parameter in this algorithm and is well known. In this embodiment, the Alpha value is adjusted based on the gradient amplitude of the pixel. Pixels with higher gradient amplitudes represent more critical areas within the tissue, such as blood vessels. This allows for the fusion of high-frequency details, such as blood vessels, to be highlighted.

[0074] Preset base alpha value In the ultrasound image sequence, Frame ultrasound image and update ultrasound image sequence During the fusion process of frame update ultrasound images, the first Frame ultrasound image Updated alpha value of the pixel ,in For the Frame ultrasound image The gradient amplitude of the pixel point, The value range of is 0.5 to 1. Frame fusion ultrasound images Grayscale value of the pixel ,in For the Frame ultrasound image The grayscale value of the pixel, For the Frame update ultrasound image Gray value of pixel point, thus each frame of fused ultrasound image can be obtained in turn to form a fused ultrasound image sequence. Schematic diagram of the fusion process of ultrasound image and updated ultrasound image, as shown in Figure 2 As stated. Figure 2 In the process, the ultrasonic frequency f (the preset initial frequency of the ultrasonic probe) is first used to collect multiple frames of low-penetration images (ultrasound image sequence) for the patient, and then the ultrasonic frequency F (the optimized frequency of the ultrasonic probe) is used to collect multiple frames of high-penetration images (updated ultrasound image sequence). The low-penetration images and the high-penetration images are then fused to obtain the image fusion result. According to the image fusion result, auxiliary guidance positioning is achieved.

[0075] Tissue recognition is performed on the fused ultrasound image sequence, the puncture path is calculated based on the tissue recognition results, and puncture auxiliary guidance suggestions are generated.

[0076] It should be noted that the final fusion result possesses real-time, efficient, and highly recognizable visual features, and tissue region identification is performed through a recognition network. In this embodiment, a U-Net semantic segmentation network is trained on the fused ultrasound image, outputting classification results for each pixel in the fused ultrasound image, such as fat, muscle, blood vessels, and nerves. This results in the identification of tissue regions within the fused ultrasound image. The recognition network uses a dataset consisting of a fused ultrasound image sequence, and its task is classification, so the cross-entropy loss function is used. Based on the recognition results, the Dijkstra algorithm is then used to calculate the shortest and safest puncture path. Finally, a visualization output displays the tissue region, recommended path, puncture angle, and risk indicators, providing real-time feedback and dynamically adjusting the puncture strategy. This generates puncture guidance recommendations, improving puncture safety and efficiency, and possessing practical teaching value. Through these operations, assisted guidance during anesthesia puncture is achieved through real-time interaction based on ultrasound image recognition results. The U-Net semantic segmentation network and the Dijkstra algorithm are both well-known technologies, and their specific methods are not described here.

[0077] The present invention also provides an interactive anesthesia puncture auxiliary guidance system, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. The processor executes the computer program stored in the memory to implement the steps of the aforementioned interactive anesthesia puncture auxiliary guidance method.

[0078] So far, the present invention is completed.

[0079] In summary, in an embodiment of the present invention, at the preset initial frequency of the ultrasound probe, an ultrasound image sequence of the tissue area to be anesthetized and punctured within a preset time length is obtained, the imaging frequency penetration of each frame of the ultrasound image is determined to obtain the optimized frequency of the ultrasound probe, and at the optimized frequency of the ultrasound probe, an updated ultrasound image sequence of the tissue area to be anesthetized and punctured within a preset time length is reacquired, the ultrasound image sequence and the images with the same sequence value in the updated ultrasound image sequence are fused to obtain a fused ultrasound image sequence, tissue recognition is performed on the fused ultrasound image sequence, the puncture path is calculated based on the tissue recognition result, and a puncture auxiliary guidance suggestion is generated. The present invention eliminates the problems of imaging blur and recognition error caused by complex conditions in the tissue by updating the ultrasound imaging frequency and fusing them to obtain new imaging results, thereby improving the safety of the anesthesia puncture auxiliary guidance process.

[0080] 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, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An interactive anesthesia puncture auxiliary guidance method, characterized in that: The method comprises the following steps: Acquire an ultrasound image sequence of the tissue area to be anesthetized and punctured within a preset time period at a preset initial frequency of the ultrasound probe; determining the tissue heterogeneity of each frame of ultrasound image according to the gradient amplitude of the pixel points and the edge pixel points in each frame of ultrasound image in the ultrasound image sequence; Determining the imaging frequency penetration of each frame of the ultrasound image based on the tissue heterogeneity of each frame of the ultrasound image and the grayscale value of the pixel points in the ultrasound image; obtaining the optimized frequency of the ultrasound probe based on the imaging frequency penetration of all frames of the ultrasound image in the ultrasound image sequence and the preset initial frequency of the ultrasound probe; and reacquiring an updated ultrasound image sequence of the tissue area to be anesthetized and punctured within a preset time period at the optimized frequency of the ultrasound probe; The ultrasound image sequence and the images with the same sequence value in the updated ultrasound image sequence are fused to obtain a fused ultrasound image sequence; tissue recognition is performed on the fused ultrasound image sequence, and the puncture path is calculated based on the tissue recognition result to generate puncture auxiliary guidance suggestions.

2. The interactive anesthesia puncture auxiliary guidance method according to claim 1, characterized in that: The specific steps of determining the tissue heterogeneity of each frame of ultrasound image are as follows: Determine the tissue absorption degree of each frame of ultrasound image according to the gradient amplitude of all edge pixel points in each frame of ultrasound image; Mark the connected domains of all edge pixels in each frame of ultrasound image to obtain several connected domains; The tissue heterogeneity of each ultrasound image frame is determined based on the number of connected domains in each ultrasound image frame, the gradient amplitude of all pixels, and the tissue absorption degree of each ultrasound image frame.

3. The interactive anesthesia puncture auxiliary guidance method according to claim 2, characterized in that: Determining the tissue absorption degree of each frame of ultrasound image includes the following specific steps: The inversely proportional normalized value of the mean of the gradient amplitudes of all edge pixels in each frame of ultrasound image is recorded as the tissue absorption degree of each frame of ultrasound image.

4. The interactive anesthesia puncture auxiliary guidance method according to claim 2, characterized in that: The method of determining the tissue heterogeneity of each frame of ultrasound image based on the number of connected domains in each frame of ultrasound image, the gradient amplitudes of all pixels, and the tissue absorption degree of each frame of ultrasound image includes the following specific steps: In each frame of ultrasound image, the mean of the gradient amplitudes of all pixels is obtained and recorded as the first mean. The ratio of the number of connected domains to the first mean is obtained and recorded as the first ratio. The normalized value of the product of the first ratio and the tissue absorption degree of each frame of ultrasound image is recorded as the tissue heterogeneity of each frame of ultrasound image.

5. The interactive anesthesia puncture auxiliary guidance method according to claim 1, characterized in that: The specific steps of determining the imaging frequency penetration of each frame of ultrasound image are as follows: In each frame of ultrasound image, the number of pixels whose grayscale values ​​are less than a preset grayscale threshold is counted, recorded as a first quantity value, and the ratio of the first quantity value to the number of all pixels is obtained, recorded as a second ratio; The imaging frequency penetration of each frame of ultrasound image is obtained according to the second ratio and the tissue heterogeneity of each frame of ultrasound image.

6. The interactive anesthesia puncture auxiliary guidance method according to claim 5, characterized in that: The step of obtaining the imaging frequency penetration of each frame of ultrasound image based on the second ratio and the tissue heterogeneity of each frame of ultrasound image comprises the following specific steps: An inversely proportional normalized value of the product of the second ratio and the tissue heterogeneity of each frame of ultrasound image is recorded as the imaging frequency penetration of each frame of ultrasound image.

7. The interactive anesthesia puncture auxiliary guidance method according to claim 1, characterized in that: The specific steps of obtaining the optimized frequency of the ultrasound probe are as follows: In the ultrasound image sequence, the average value of the imaging frequency penetration of all frames of ultrasound images is obtained, which is recorded as the second average value; When the second mean value is less than the preset penetration threshold, obtaining a frequency adjustment coefficient according to the preset initial frequency of the ultrasound probe and the second mean value; The optimized frequency of the ultrasound probe is determined based on the frequency adjustment coefficient and the preset basic frequency.

8. The interactive anesthesia puncture auxiliary guidance method according to claim 7, characterized in that: The specific steps of obtaining the frequency adjustment coefficient are as follows: The product of the preset initial frequency of the ultrasonic probe and the second mean value is obtained and recorded as the frequency adjustment coefficient.

9. The interactive anesthesia puncture auxiliary guidance method according to claim 7, characterized in that: The step of determining the optimized frequency of the ultrasound probe according to the frequency adjustment coefficient and the preset basic frequency includes the following specific steps: The sum of the frequency adjustment coefficient and the preset basic frequency is used as the optimized frequency of the ultrasound probe.

10. An interactive anesthesia puncture auxiliary guidance system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of an interactive anesthesia puncture auxiliary guidance method as described in any one of claims 1 to 9 are implemented.

Images