Ultrasonic image recognition and puncture guidance method and device for lumbar plexus nerve block

Abstract

The present application discloses an artificial intelligence lumbar plexus nerve block ultrasound image recognition and puncture guidance method and device. Among them, when the site type information of the lumbar plexus nerve block ultrasound image is a preset site type, image segmentation is performed on the lumbar plexus nerve block ultrasound image to obtain multiple tissue segmentation regions, a puncture needle segmentation region, and the region categories of the multiple tissue segmentation regions on the lumbar plexus nerve block ultrasound image; a puncture direction line of the puncture needle is generated based on the puncture needle segmentation region on the lumbar plexus nerve block ultrasound image; it is determined whether the puncture direction line passes through the tissue segmentation regions of the puncturable category; if the puncture direction line passes through the tissue segmentation regions of the puncturable category, it is determined whether the puncture direction line passes through the tissue segmentation regions of the avoidance category; if the puncture direction line does not pass through the tissue segmentation regions of the avoidance category, an instruction to continue puncturing in the current puncture direction is issued. The present application can improve the accuracy of lumbar plexus nerve block ultrasound image recognition and puncture guidance.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and particularly to a method and device for identifying lumbar plexus nerve block ultrasound images and guiding punctures. Background Art

[0002] Traditional lumbar plexus nerve block techniques mainly rely on surface landmarks and doctors' clinical experience. This blind probing operation has a relatively high failure rate and may cause damage to internal organs and major blood vessels in the human body. This has led many inexperienced anesthesiologists to be afraid to attempt it. In recent years, the lumbar plexus nerve block technique under ultrasound guidance has gradually made full use of the lumbar plexus nerve block technique due to its advantages such as visualization, real-time nature, and high success rate. Although ultrasound guidance has made progress in the lumbar plexus nerve block technique, there are still great challenges in practical applications. First, ultrasound images are two-dimensional imaging images based on human structures, and their correct interpretation requires rich clinical experience and spatial imagination ability. It is very difficult for doctors with insufficient experience to accurately identify the lumbar plexus nerve and its surrounding tissue structures. Second, anatomical differences and physiological changes between individuals can lead to ever-changing corresponding ultrasound images. For example, severe fat infiltration of muscles in overweight patients and elderly patients seriously affects the recognition of ultrasound images, making it more difficult to identify lumbar plexus nerve block ultrasound images and lower the puncture accuracy, thereby affecting the nerve block effect. In addition, ordinary ultrasound can only display images of local tissue structures, cannot identify the names of each region and prompt whether puncture operations can be performed; cannot identify the puncture needle; and cannot guide the puncture needle to accurately reach the area where the lumbar plexus nerve is located. Summary of the Invention

[0003] The embodiments of this application provide a method and device for identifying lumbar plexus nerve block ultrasound images and guiding punctures, which can improve the accuracy of identifying lumbar plexus nerve block ultrasound images and guiding punctures.

[0004] In a first aspect, the method for identifying lumbar plexus nerve block ultrasound images and guiding punctures provided by this application includes:

[0005] Obtain a lumbar plexus nerve block ultrasound image collected by an ultrasound device;

[0006] Input the lumbar plexus nerve block ultrasound image into a target image segmentation model to perform image segmentation on the lumbar plexus nerve block ultrasound image, and obtain multiple tissue segmentation regions, a puncture needle segmentation region, and region categories of the multiple tissue segmentation regions on the lumbar plexus nerve block ultrasound image. The region categories of the tissue segmentation regions include a puncturable category and an avoidance category;

[0007] Generate a puncture direction line of the puncture needle on the lumbar plexus nerve block ultrasound image based on the puncture needle segmentation region;

[0008] Determine whether the puncture direction line passes through the tissue segmentation region of the puncturable category;

[0009] If the puncture direction line passes through the tissue segmentation region of the puncturable category, determine whether the puncture direction line passes through the tissue segmentation region of the avoidance category;

[0010] If the puncture direction line does not pass through the tissue segmentation region of the avoidance category, issue an instruction to continue puncturing in the current puncture direction.

[0011] Second, the lumbar plexus nerve block ultrasound image recognition and puncture guidance device provided by this application includes:

[0012] An acquisition module for acquiring lumbar plexus nerve block ultrasound images collected by an ultrasound device;

[0013] A classification module for inputting the lumbar plexus nerve block ultrasound image into a site classification model to obtain the site type information of the lumbar plexus nerve block ultrasound image.

[0014] A segmentation module for, when the site type information of the lumbar plexus nerve block ultrasound image is a preset site type, inputting the lumbar plexus nerve block ultrasound image into a target image segmentation model to perform image segmentation on the lumbar plexus nerve block ultrasound image, obtaining multiple tissue segmentation regions, a puncture needle segmentation region, and the region categories of the multiple tissue segmentation regions on the lumbar plexus nerve block ultrasound image, where the region categories of the tissue segmentation regions include a puncturable category and an avoidance category;

[0015] A generation module for generating a puncture direction line of the puncture needle on the lumbar plexus nerve block ultrasound image based on the puncture needle segmentation region;

[0016] A first judgment module for judging whether the puncture direction line passes through the tissue segmentation region of the puncturable category;

[0017] A second judgment module for judging whether the puncture direction line passes through the tissue segmentation region of the avoidance category if the puncture direction line passes through the tissue segmentation region of the puncturable category;

[0018] An instruction module for issuing an instruction to continue puncturing in the current puncture direction if the puncture direction line does not pass through the tissue segmentation region of the avoidance category.

[0019] Third, the electronic device provided by this application includes a memory and a processor. The memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the lumbar plexus nerve block ultrasound image recognition and puncture guidance method provided by this application.

[0020] Fourthly, the computer-readable storage medium provided by this application stores multiple instructions, which are suitable for being loaded by a processor to implement the steps in the lumbar plexus nerve block ultrasound image recognition and puncture guidance method provided by this application.

[0021] Fifthly, the computer program product provided by this application includes a computer program or instructions. When the computer program or instructions are executed by a processor, the steps in the lumbar plexus nerve block ultrasound image recognition and puncture guidance method provided by this application are implemented.

[0022] In this application, compared with the related technology, the lumbar plexus nerve block ultrasound image collected by an ultrasound device is obtained; the lumbar plexus nerve block ultrasound image is input into a site classification model to obtain the site type information of the lumbar plexus nerve block ultrasound image; when the site type information of the lumbar plexus nerve block ultrasound image is a preset site type, the lumbar plexus nerve block ultrasound image is input into a target image segmentation model to perform image segmentation on the lumbar plexus nerve block ultrasound image, and multiple tissue segmentation regions, a puncture needle segmentation region, and the region categories of the multiple tissue segmentation regions on the lumbar plexus nerve block ultrasound image are obtained. The region categories of the tissue segmentation regions include a puncturable category and an avoidance category; a puncture direction line of the puncture needle is generated on the lumbar plexus nerve block ultrasound image based on the puncture needle segmentation region; it is determined whether the puncture direction line passes through the tissue segmentation region of the puncturable category; if the puncture direction line passes through the tissue segmentation region of the puncturable category, it is determined whether the puncture direction line passes through the tissue segmentation region of the avoidance category; if the puncture direction line does not pass through the tissue segmentation region of the avoidance category, an instruction to continue puncturing in the current puncture direction is issued. This application can improve the accuracy of artificial intelligence recognition and puncture guidance of lumbar plexus nerve block ultrasound images. Description of the Drawings

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0024] Figure 1 is a schematic diagram of the scenario of the lumbar plexus nerve block ultrasound image recognition and puncture guidance system provided by the embodiment of this application;

[0025] Figure 2 is a schematic flowchart of an embodiment of the lumbar plexus nerve block ultrasound image recognition and puncture guidance method provided by the embodiment of this application;

[0026] Figure 3 is a schematic diagram of the lumbar plexus nerve block ultrasound image with the image category of the paravertebral transverse process sagittal plane provided by the embodiment of this application;

[0027] Figure 4 It is a schematic diagram after the adjustment direction of the puncture needle in the lumbar plexus nerve block ultrasound image with the image category of the parasagittal plane of the transverse process beside the spine provided by the embodiments of the present application;

[0028] Figure 5 It is a schematic diagram of the lumbar plexus nerve block ultrasound image with the image category of the cross-section of the transverse process beside the spine provided by the embodiments of the present application;

[0029] Figure 6 It is a schematic diagram of the lumbar plexus nerve block ultrasound image with the image category of the cross-section of the lateral transverse process provided by the embodiments of the present application;

[0030] Figure 7 It is a schematic diagram of the structure of the lumbar plexus nerve block ultrasound image recognition and puncture guidance device provided by the embodiments of the present application;

[0031] Figure 8 It is a schematic diagram of the structure of the electronic device provided by the embodiments of the present application. Detailed implementation manners

[0032] It should be noted that the principle of the present application is illustrated by being implemented in a suitable computing environment. The following description is based on the specific embodiments of the present application illustrated, and it should not be regarded as limiting other specific embodiments not detailed herein of the present application.

[0033] In the following description of the present application, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0034] In the following description of the present application, the terms "first / second / third" are only used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence when allowed, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0036] In order to improve the effect of ultrasound image recognition and puncture guidance for lumbar plexus nerve block, the embodiments of the present application provide a method for ultrasound image recognition and puncture guidance for lumbar plexus nerve block, a device for ultrasound image recognition and puncture guidance for lumbar plexus nerve block, an electronic device, a computer-readable storage medium, and a computer program product. Among them, the method for ultrasound image recognition and puncture guidance for lumbar plexus nerve block can be executed by the device for ultrasound image recognition and puncture guidance for lumbar plexus nerve block, or by an electronic device integrated with the device for ultrasound image recognition and puncture guidance for lumbar plexus nerve block.

[0037] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the protection scope of the present application.

[0038] Please refer to Figure 1 , the present application also provides a system for ultrasound image recognition and puncture guidance for lumbar plexus nerve block. As Figure 1 shown, the system for ultrasound image recognition and puncture guidance for lumbar plexus nerve block includes an electronic device 100. The electronic device 100 integrates the device for ultrasound image recognition and puncture guidance for lumbar plexus nerve block provided by the present application.

[0039] Among them, the electronic device 100 can be any device equipped with a processor and having processing capabilities, such as a mobile electronic device equipped with a processor such as a smart phone, a tablet computer, a handheld computer, a notebook computer, a smart speaker, etc., or a fixed electronic device equipped with a processor such as a desktop computer, a television, a server, an industrial device, etc.

[0040] In addition, as Figure 1 shown, the system for ultrasound image recognition and puncture guidance for lumbar plexus nerve block may further include a memory 200 for storing original data, intermediate data, and result data.

[0041] In the embodiments of the present application, the memory 200 can be a cloud memory. Cloud storage is a new concept extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as a storage system) refers to a storage system that combines a large number of various types of storage devices (storage devices are also called storage nodes) in the network through cluster applications, grid technologies, and distributed file systems, and collaborates through application software or application interfaces to jointly provide data storage and business access functions.

[0042] Currently, the storage method of the storage system is as follows: Create a logical volume. When creating a logical volume, physical storage space is allocated for each logical volume. This physical storage space may be composed of a certain storage device or the disks of several storage devices. The client stores data on a certain logical volume, that is, stores the data on the file system. The file system divides the data into many parts, and each part is an object. The object not only contains data but also contains additional information such as data identifiers (IDs, ID entities), etc. The file system writes each object into the physical storage space of the logical volume respectively, and the file system records the storage location information of each object. Thus, when the client requests to access data, the file system can enable the client to access the data according to the storage location information of each object.

[0043] The process of the storage system allocating physical storage space for the logical volume is specifically as follows: According to the capacity estimation of the objects stored in the logical volume (this estimation often has a large margin relative to the capacity of the actually stored objects) and the group of the redundant array of independent disks (RAID), the physical storage space is pre-divided into stripes. A logical volume can be understood as a stripe, thereby allocating physical storage space for the logical volume.

[0044] It should be noted that Figure 1 The schematic diagram of the scenario of the lumbar plexus nerve block ultrasound image recognition and puncture guidance system shown is only an example. The lumbar plexus nerve block ultrasound image recognition and puncture guidance system and scenario described in the embodiments of the present application are for more clearly explaining the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those of ordinary skill in the art can know that with the evolution of the lumbar plexus nerve block ultrasound image recognition and puncture guidance system and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0045] The following will be described in detail respectively. It should be noted that the serial numbers of the following embodiments do not limit the preferred order of the embodiments.

[0046] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of an embodiment of the lumbar plexus nerve block ultrasound image recognition and puncture guidance method provided by the embodiments of the present application. As Figure 2 shown, the process of the lumbar plexus nerve block ultrasound image recognition and puncture guidance method provided by the present application is as follows:

[0047] 201. Obtain the lumbar plexus nerve block ultrasound image collected by the ultrasound device.

[0048] In the embodiments of this application, the ultrasound device can be operated and moved by a robot or a medical worker. The ultrasound device acquires lumbar plexus nerve block ultrasound images during the movement.

[0049] 202. Input the lumbar plexus nerve block ultrasound image into the site classification model to obtain the site type information of the lumbar plexus nerve block ultrasound image.

[0050] Among them, the site classification model is the YOLOv8 classification model.

[0051] Build the YOLOv8 classification model. The network structure of YOLOv8 mainly consists of the following three major parts:

[0052] Backbone: A series of convolutional and deconvolutional layers are used to extract features. At the same time, residual connections and bottleneck structures are also used to reduce the size of the network and improve performance.

[0053] Neck: The Neck part adopts the Feature Pyramid Network (FPN) structure and uses the multi-scale feature fusion technology to fuse the feature maps from different stages of the Backbone to better capture the information of targets at different scales.

[0054] Head: Responsible for the final object detection and classification tasks, including a detection head and a classification head. The detection head contains a series of convolutional and deconvolutional layers for generating classification results; the classification head uses global average pooling to classify each feature map. Input the marked data into the classification network for training, and use the trained model for site recognition tasks to output the image of the current image site, guiding the doctor to quickly and accurately reach the best puncture position. Among them, the loss function used by the classification model is the cross-entropy loss:

[0055]

[0056] Among them, represents the number of classification categories; represents the true category of the sample ; represents the sample predicted probability.

[0057] 203. When the site type information of the lumbar plexus nerve block ultrasound image is the preset site type, input the lumbar plexus nerve block ultrasound image into the target image segmentation model to perform image segmentation on the lumbar plexus nerve block ultrasound image, and obtain multiple tissue segmentation regions, puncture needle segmentation regions, and the region categories of the multiple tissue segmentation regions on the lumbar plexus nerve block ultrasound image.

[0058] When the image site information indicates that it does not belong to the preset site, a probe movement prompt message is given to guide the operator to reach the preset site.

[0059] The regional categories of the tissue segmentation regions include a puncturable category and an avoidance category.

[0060] In the embodiment of the present application, the target image segmentation model can be a trained UNet++ segmentation model. Specifically, the UNet++ segmentation model is built. The UNet++ model is an encoder-decoder architecture. The encoder uses a context-aware feature encoder with convolutional blocks and residual blocks to extract multi-scale feature maps, that is, the shallow features of the image. The decoder uses a feature decoder with convolution and deconvolution to adjust the size of the multi-scale feature maps, that is, the deep features of the image, to achieve end-to-end segmentation. The labeled data is input into the segmentation network for training to identify the region where the lumbar plexus nerve is located and the important organizational structures around it, and the contour lines of the boundaries of each tissue are output.

[0061] In a specific embodiment, the ultrasonic scanning video of the ultrasonic device is obtained; the ultrasonic scanning video is frame-processed to obtain a plurality of consecutive single-frame ultrasonic images; the labeled ultrasonic image obtained by labeling the single-frame ultrasonic image and the image category of the labeled ultrasonic image are obtained. Among them, the single-frame ultrasonic images obtained from the ultrasonic scanning videos of different sections belong to different image categories. The labeled ultrasonic image includes a labeled region of the puncturable category and a labeled region of the avoidance category. Based on the plurality of labeled ultrasonic images, a preset segmentation model is trained to obtain a target image segmentation model. The lumbar plexus nerve block ultrasonic image is input into the target image segmentation model to perform image segmentation on the lumbar plexus nerve block ultrasonic image, and a plurality of tissue segmentation regions, a puncture needle segmentation region, and the regional categories of the plurality of tissue segmentation regions on the lumbar plexus nerve block ultrasonic image are obtained. The regional categories of the tissue segmentation regions include a puncturable category and an avoidance category.

[0062] In another specific embodiment, ultrasonic scanning videos of multiple different cross-sections of an ultrasonic device are obtained; the ultrasonic scanning videos are frame-processed to obtain a series of consecutive single-frame ultrasonic images; labeled ultrasonic images obtained by labeling the single-frame ultrasonic images and the image categories of the labeled ultrasonic images are obtained. Among them, the single-frame ultrasonic images obtained from the ultrasonic scanning videos of different cross-sections belong to different image categories. The labeled ultrasonic images include labeled regions of the puncturable category and labeled regions of the avoidance category; a preset segmentation model is trained based on the multiple labeled ultrasonic images to obtain a target image segmentation model; the lumbar plexus nerve block ultrasonic image is input into the image classification model to classify the lumbar plexus nerve block ultrasonic image, and the image category of the lumbar plexus nerve block ultrasonic image is obtained. The set of region categories in the lumbar plexus nerve block ultrasonic image is determined based on the image category of the lumbar plexus nerve block ultrasonic image; the lumbar plexus nerve block ultrasonic image is input into the target image segmentation model to perform image segmentation on the lumbar plexus nerve block ultrasonic image, and multiple tissue segmentation regions, a puncture needle segmentation region, and the region categories of the multiple tissue segmentation regions on the lumbar plexus nerve block ultrasonic image are obtained. The region categories of the tissue segmentation regions include the puncturable category and the avoidance category. Among them, the region categories of each tissue segmentation region belong to the set of region categories. Different image categories correspond to different sets of region categories.

[0063] Specifically, data collection is performed first. The data collection can be scanning videos of three different cross-sections: the paravertebral transverse process sagittal plane, the paravertebral transverse process cross-section, and the anterolateral transverse process cross-section. Then, the videos are frame-processed to obtain consecutive single-frame ultrasonic images. Then, data marking is performed. The single-frame ultrasonic images are classified by a nerve block expert based on the ultrasonic image video information combined with the scanning position to mark the site information to be recognized. The boundaries of the anatomical structures to be recognized are manually marked on the ultrasonic images of the ideal puncture interface to display the regions of the corresponding tissues, highlighting the dangerous regions while informing the target regions.

[0064] Specifically, the lumbar plexus nerve block ultrasonic image can be an image of three different image categories: the paravertebral transverse process sagittal plane, the paravertebral transverse process cross-section, and the anterolateral transverse process cross-section, and is obtained by slicing the scanning videos of the paravertebral transverse process sagittal plane, the paravertebral transverse process cross-section, and the anterolateral transverse process cross-section into single-frame images. The single-frame ultrasonic images obtained from the scanning videos of different cross-sections belong to different image categories.

[0065] Furthermore, the image category can be the paravertebral transverse process sagittal plane, the paravertebral transverse process cross-section, or the anterolateral transverse process cross-section. For different image categories, there are corresponding sets of region categories, and the set of region categories includes multiple region categories.

[0066] In an embodiment of the present application, when the image category of the lumbar plexus nerve block ultrasound image is the paravertebral transverse process sagittal plane, the tissue segmentation regions belonging to the puncturable category on the lumbar plexus nerve block ultrasound image include the erector spinae muscle region and the psoas major muscle region, and the tissue segmentation regions belonging to the avoidance category on the lumbar plexus nerve block ultrasound image include multiple transverse process regions and a dangerous region containing abdominal visceral blood vessels. The multiple transverse process regions are arranged at intervals between the erector spinae muscle region and the psoas major muscle region, and the dangerous region is located on the side of the psoas major muscle region away from the erector spinae muscle region.

[0067] As Figure 3 and Figure 4 shown, when the image category of the lumbar plexus nerve block ultrasound image is the paravertebral transverse process sagittal plane, the tissue segmentation regions belonging to the puncturable category on the lumbar plexus nerve block ultrasound image include the erector spinae muscle region (ESM) and the psoas major muscle region (PM), and the tissue segmentation regions belonging to the avoidance category on the lumbar plexus nerve block ultrasound image include multiple transverse process regions (TP) and a dangerous region (Risk Area). The multiple transverse process regions (TP) are arranged at intervals between the erector spinae muscle region (ESM) and the psoas major muscle region (PM), and the dangerous region (Risk Area) is located on the side of the psoas major muscle region (PM) away from the erector spinae muscle region (ESM). TP is a bony structure and is an area to be avoided during the puncture process. Risk Area is an area where the tip of the needle cannot reach during the lumbar plexus nerve block process, that is, the dangerous area where complications occur.

[0068] That is, when the image category of the lumbar plexus nerve block ultrasound image is the paravertebral transverse process sagittal plane, the region categories in the region category set include the puncturable category and the avoidance category. Further, when the image category of the lumbar plexus nerve block ultrasound image is the paravertebral transverse process sagittal plane, the region category set includes the erector spinae muscle category, the psoas major muscle category, the transverse process category, and the dangerous category, which can be set according to specific circumstances.

[0069] In an embodiment of the present application, when the image category of the lumbar plexus nerve block ultrasound image is the paravertebral transverse process cross-section, the tissue segmentation regions belonging to the puncturable category on the lumbar plexus nerve block ultrasound image include the erector spinae muscle region, the psoas major muscle region, and the quadratus lumborum muscle region, and the tissue segmentation regions belonging to the avoidance category on the lumbar plexus nerve block ultrasound image include the vertebra and a dangerous region containing abdominal viscera and blood vessels.

[0070] As Figure 5 shown, when the image category of the lumbar plexus nerve block ultrasound image is the paravertebral transverse process cross-section, the tissue segmentation regions belonging to the puncturable category on the lumbar plexus nerve block ultrasound image include the erector spinae muscle region (ESM), the psoas major muscle region (PM), and the quadratus lumborum muscle region (QLM), and the tissue segmentation regions belonging to the avoidance category on the lumbar plexus nerve block ultrasound image include the vertebra (Vertebra) and the dangerous region (Risk Area).

[0071] In the embodiments of the present application, when the image category of the lumbar plexus nerve block ultrasound image is the cross-section of the lateral transverse process of the abdomen, the tissue segmentation regions belonging to the puncturable category on the lumbar plexus nerve block ultrasound image include the erector spinae muscle region, the psoas major muscle region, and the quadratus lumborum muscle region, and the tissue segmentation regions belonging to the avoidance category on the lumbar plexus nerve block ultrasound image include the vertebra and the dangerous region containing abdominal organs and blood vessels.

[0072] As Figure 6 shown, when the image category of the lumbar plexus nerve block ultrasound image is the cross-section of the lateral transverse process of the abdomen, the tissue segmentation regions belonging to the puncturable category on the lumbar plexus nerve block ultrasound image include the erector spinae muscle region (ESM), the psoas major muscle region (PM), and the quadratus lumborum muscle region (QLM), and the tissue segmentation regions belonging to the avoidance category on the lumbar plexus nerve block ultrasound image include the vertebra (Vertebra) and the dangerous region (Risk Area), and the vertebra (Vertebra), the psoas major muscle region (PM), and the quadratus lumborum muscle region (QLM) are arranged in sequence between the erector spinae muscle region (ESM) and the dangerous region (Risk Area).

[0073] In the embodiments of the present application, training a preset segmentation model based on multiple labeled ultrasound images to obtain a target image segmentation model includes:

[0074] (1) Inputting the labeled ultrasound image into the preset segmentation model to obtain the predicted pixel category of each pixel point on the labeled ultrasound image, where the predicted pixel category is the puncturable category or the avoidance category.

[0075] In the embodiments of the present application, the predicted pixel category is the puncturable category or the avoidance category. Further, when the image category of the lumbar plexus nerve block ultrasound image is the paravertebral transverse process sagittal plane, the predicted pixel category is the erector spinae muscle category, the psoas major muscle category, the transverse process category, and the dangerous category, which can be set according to specific circumstances.

[0076] (2) Determining the predicted region corresponding to the labeled region on the labeled ultrasound image based on the predicted pixel category of each pixel point on the labeled ultrasound image, where the predicted pixel categories within the same predicted region belong to the same category.

[0077] For example, the pixel points in the erector spinae muscle region (ESM) are all of the erector spinae muscle category.

[0078] (3) Obtaining the intersection region and the sum of the region areas between the labeled region and the corresponding predicted region.

[0079] (4) Determining the first loss based on the ratio of the intersection region to the sum of the region areas.

[0080] In the embodiments of the present application, the first loss has the following calculation formula:

[0081]

[0082] Among them, a prediction region composed of a set of pixels representing a prediction result an annotation region of a set of pixels representing a label.

[0083] (5) Using a cross-entropy loss function to determine a second loss based on the annotation pixel category and the prediction pixel category of each pixel point on the annotated ultrasound image, wherein the annotation pixel categories in the annotation regions of the same category belong to the same category.

[0084] Among them, the annotation pixel category of each pixel point is determined according to the category of each annotation region.

[0085] Specifically, the second loss has the following calculation formula

[0086]

[0087] Among them, represents the total number of pixel points, represents the true label of a pixel point, represents the prediction result of a pixel point.

[0088] (6) Determining the total loss based on the first loss and the second loss.

[0089] In a specific embodiment, the first loss and the second loss are added to obtain the total loss.

[0090] In another specific embodiment, the total loss is determined based on the first loss and the second loss; when the total loss is less than a preset loss value after iteratively updating the preset segmentation model, the target image segmentation model is obtained.

[0091] (7) Iteratively updating the preset segmentation model until the total loss is less than a preset loss value, and obtaining the target image segmentation model.

[0092] Among them, the preset loss value can be set according to specific circumstances.

[0093] Further, in order to improve the segmentation accuracy, in another specific embodiment, ultrasonic scanning videos of multiple different cross-sections of an ultrasonic device are obtained; the ultrasonic scanning videos are frame-processed to obtain a plurality of consecutive single-frame ultrasonic images; an annotated ultrasonic image obtained by annotating the single-frame ultrasonic image and the image category of the annotated ultrasonic image are obtained, wherein the single-frame ultrasonic images obtained from the ultrasonic scanning videos of different cross-sections belong to different image categories, and the annotated ultrasonic image includes an annotated area of the puncturable category and an annotated area of the avoidance category; a preset classification model is trained based on the plurality of annotated ultrasonic images and the image categories of the annotated ultrasonic images to obtain an image classification model; a preset segmentation model is trained based on the plurality of annotated ultrasonic images to obtain a target image segmentation model; the lumbar plexus nerve block ultrasonic image is input into the image classification model to classify the lumbar plexus nerve block ultrasonic image, and the image category of the lumbar plexus nerve block ultrasonic image is obtained; a set of region categories in the lumbar plexus nerve block ultrasonic image is determined based on the image category of the lumbar plexus nerve block ultrasonic image; the lumbar plexus nerve block ultrasonic image is input into the target image segmentation model to perform image segmentation on the lumbar plexus nerve block ultrasonic image, and a plurality of tissue segmentation regions, a puncture needle segmentation region, and the region categories of the plurality of tissue segmentation regions on the lumbar plexus nerve block ultrasonic image are obtained. The region categories of the tissue segmentation regions include the puncturable category and the avoidance category, wherein the region categories of each tissue segmentation region belong to the set of region categories.

[0094] In the embodiments of the present application, different image categories correspond to a set of region categories.

[0095] For example, when the image category of the lumbar plexus nerve block ultrasonic image is the paravertebral transverse process sagittal plane, the tissue segmentation regions belonging to the puncturable category on the lumbar plexus nerve block ultrasonic image include the erector spinae muscle region (ESM) and the psoas major muscle region (PM), and the tissue segmentation regions belonging to the avoidance category on the lumbar plexus nerve block ultrasonic image include multiple transverse process regions (TP) and a risk area (Risk Area). When the image category of the lumbar plexus nerve block ultrasonic image is the paravertebral transverse process sagittal plane, the set of region categories includes the erector spinae muscle category, the psoas major muscle category, the transverse process category, and the risk category.

[0096] Specifically, input the lumbar plexus nerve block ultrasound image into the target image segmentation model to perform image segmentation on the lumbar plexus nerve block ultrasound image, obtaining multiple tissue segmentation regions, a puncture needle segmentation region, and the region categories of the multiple tissue segmentation regions on the lumbar plexus nerve block ultrasound image, including: when the region categories of the multiple tissue segmentation regions output by the target image segmentation model are not completely the same as the region categories in the region category set, a prompt message indicating that complete observation is not possible is sent, prompting the user to move the ultrasound device to re - photograph the lumbar plexus nerve block ultrasound image until the region categories of the multiple tissue segmentation regions output by the target image segmentation model are completely the same as the region categories in the region category set. When the region categories of the multiple tissue segmentation regions output by the target image segmentation model are completely the same as the region categories in the region category set, output the multiple tissue segmentation regions, the puncture needle segmentation region, and the region categories of the multiple tissue segmentation regions on the lumbar plexus nerve block ultrasound image.

[0097] Specifically, the image classification model is the YOLOv8 model. The preset classification model is trained based on multiple annotated ultrasound images and the image categories of the annotated ultrasound images using the cross - entropy loss function to obtain the image classification model.

[0098] 204. Generate a puncture direction line of the puncture needle on the lumbar plexus nerve block ultrasound image based on the puncture needle segmentation region.

[0099] In the embodiment of the present application, it is determined whether the puncture needle segmentation region contains the tip region. When the puncture needle segmentation region contains the tip region, a puncture direction line of the puncture needle is generated on the lumbar plexus nerve block ultrasound image based on the puncture needle segmentation region.

[0100] In a specific embodiment, the puncture needle segmentation region is input into the puncture needle segmentation model to obtain a segmentation result. When the tip region is included in the segmentation result, it is determined that the puncture needle segmentation region contains the tip region.

[0101] In a specific embodiment, determining whether the puncture needle segmentation region contains the tip region includes:

[0102] (1) Use the Zhang - Suen thinning algorithm to thin the puncture needle segmentation region to obtain a needle - thinned line segment.

[0103] (2) Perform linear fitting on the needle - thinned line segment to obtain a first fitted line segment.

[0104] Specifically, the least - squares method can be used to perform linear fitting on the needle - thinned line segment to obtain a first fitted line segment.

[0105] (3) Obtain multiple first needle points at equal - interval intervals on the needle - thinned line segment.

[0106] Among them, the multiple first needle points include the two endpoints of the needle - thinned line segment.

[0107] (4) Calculate the perpendicular distances from multiple first needle points to the first fitted straight line segment respectively and sum them up to obtain the first total distance.

[0108] (5) If the first total distance is greater than the first preset distance value, it is determined that the puncture needle segmentation region includes the tip region.

[0109] Among them, the first preset distance value is set according to specific circumstances.

[0110] If the first total distance is greater than the first preset distance value, it indicates that the needle refinement line segment has a large difference from the straight line, indicating that the puncture needle segmentation region includes the tip region.

[0111] In the embodiment of the present application, before determining whether the puncture needle segmentation region includes the tip region, it includes:

[0112] (1) Obtain the segmentation confidence of each segmentation region, where each segmentation region includes the puncture needle segmentation region and multiple tissue segmentation regions.

[0113] Specifically, the segmentation confidence of the segmentation region is the sum of the probabilities that the pixel categories of each pixel point in the segmentation region are predicted correctly.

[0114] (2) Determine the overall confidence based on the segmentation confidence of each segmentation region.

[0115] Specifically, determine the weight coefficient of each segmentation region based on the area size of each segmentation region. Weight and sum the segmentation confidence of each segmentation region based on the weight coefficient of each segmentation region to obtain the overall confidence. Among them, the larger the area of the segmentation region, the smaller the weight coefficient of the segmentation region.

[0116] (3) If the overall confidence is higher than the preset confidence, determine whether the puncture needle segmentation region includes the tip region; if the overall confidence is not higher than the preset confidence, issue an instruction to adjust the posture of the ultrasonic device and re-acquire the collected lumbar plexus nerve block ultrasonic image.

[0117] In a specific embodiment, the first fitted straight line segment is determined as the puncture direction line of the puncture needle.

[0118] In another specific embodiment, generating the puncture direction line of the puncture needle based on the puncture needle segmentation region in the lumbar plexus nerve block ultrasonic image includes:

[0119] (1) Draw a normal line through the midpoint of the first fitted straight line segment to divide the puncture needle segmentation region into two sub-segmentation regions.

[0120] (2) Use the line segment of the needle refinement line segment located in the sub-segmentation region with a larger area as the first line segment.

[0121] (3) Perform linear fitting on the first line segment to obtain a second fitted line segment.

[0122] (4) Determine the straight line where the second fitted line segment is located as the puncture direction line.

[0123] Since the needle is generally triangular, removing the lines within the sub - segmentation region of the smaller area where the needle is located and only retaining the first line segment for fitting can improve the accuracy of the puncture direction line.

[0124] 205. Determine whether the puncture direction line passes through the tissue segmentation region of the puncturable category.

[0125] Specifically, if the extension line of the puncture direction line passes through the tissue segmentation region of the puncturable category, then the puncture direction line passes through the tissue segmentation region of the puncturable category.

[0126] 206. If the puncture direction line passes through the tissue segmentation region of the puncturable category, then determine whether the puncture direction line passes through the tissue segmentation region of the avoidance category.

[0127] Specifically, if the extension line of the puncture direction line passes through the tissue segmentation region of the avoidance category, then the puncture direction line passes through the tissue segmentation region of the avoidance category.

[0128] If the puncture direction line passes through the tissue segmentation region of the puncturable category, then determine whether the puncture direction line passes through the tissue segmentation region of the avoidance category.

[0129] 207. If the puncture direction line does not pass through the tissue segmentation region of the avoidance category, then issue an instruction to continue puncturing in the current puncture direction.

[0130] If the puncture direction line does not pass through the tissue segmentation region of the avoidance category, indicating that puncture can continue, then issue an instruction to continue puncturing in the current puncture direction.

[0131] If the puncture direction line passes through the tissue segmentation region of the avoidance category, then determine whether the tissue segmentation region of the avoidance category that the puncture direction line passes through is located between the puncture needle segmentation region and the target puncture region. If the tissue segmentation region of the avoidance category that the puncture direction line passes through is located between the puncture needle segmentation region and the target puncture region, then issue a prompt signal to prompt the operator to adjust the puncture direction to avoid the avoidance region. If the tissue segmentation region of the avoidance category that the puncture direction line passes through is not located between the puncture needle segmentation region and the target puncture region, then calculate the real - time distance between the tip of the puncture needle segmentation region along the puncture needle direction line and the tissue segmentation region of the avoidance category; if the real - time distance is not less than the second preset distance value, then issue an instruction to continue puncturing in the current puncture direction. If the real - time distance is less than the second preset distance value, then issue an alarm signal.

[0132] Further, if the tissue segmentation area of the avoidance category passed by the puncture direction line is located between the puncture needle segmentation area and the target puncture area, multiple candidate straight paths are obtained, and the candidate straight path with the smallest angle between the multiple candidate straight paths and the puncture direction line is determined as the new puncture direction, and the user is prompted to perform the puncture.

[0133] As Figure 3 and Figure 4 shown, when the image category of the lumbar plexus nerve block ultrasound image is the paravertebral transverse process sagittal plane, the tissue segmentation areas belonging to the puncturable category on the lumbar plexus nerve block ultrasound image include the erector spinae muscle area (ESM) and the psoas major muscle area (PM), and the tissue segmentation areas belonging to the avoidance category on the lumbar plexus nerve block ultrasound image include multiple transverse process areas (TP) and the risk area (Risk Area).

[0134] When the image category of the lumbar plexus nerve block ultrasound image is the paravertebral transverse process sagittal plane, if the tissue segmentation area of the avoidance category passed by the puncture direction line is the transverse process area (TP), and the transverse process area (TP) is located between the puncture needle segmentation area and the target puncture area. The transverse process area (TP) passed by the puncture direction line is determined as the first transverse process area, then the transverse process areas (TP) closest to the puncture direction line are obtained on both sides of the puncture direction line, and are respectively used as the second transverse process area and the third transverse process area, the edge intersection point between the first line segment and the edge of the erector spinae muscle area (ESM) is determined as the edge intersection point, and the first candidate straight line and the second candidate straight line are determined. Among them, both the first candidate straight line and the second candidate straight line pass through the edge intersection point, the first transverse process area and the second transverse process area are located on both sides of the first candidate straight line, and the minimum distance between the first transverse process area and the first candidate straight line is equal to the minimum distance between the second transverse process area and the first candidate straight line; the third transverse process area and the second transverse process area are located on both sides of the second candidate straight line, and the minimum distance between the third transverse process area and the second candidate straight line is equal to the minimum distance between the second transverse process area and the second candidate straight line. If the angle between the first candidate straight line and the puncture direction line is greater than the angle between the second candidate straight line and the puncture direction line, then the second candidate straight line is determined as the new puncture direction, and a prompt message is sent to prompt the user to perform the puncture according to the second candidate straight line.

[0135] In the embodiment of the present application, calculating the real-time distance between the tip of the puncture needle segmentation area along the puncture needle direction line and the tissue segmentation area of the avoidance category includes: determining the end point of the needle thinning line segment located in the sub-segmentation area with a smaller area as the tip point, and determining the minimum distance between the tip point along the puncture needle direction and the tissue segmentation area of the puncturable category as the real-time distance.

[0136] Further, a method for identifying lumbar plexus nerve block ultrasound images and guiding puncture includes: determining a target puncture area on the psoas major muscle area (PM) based on the image category of the lumbar plexus nerve block ultrasound image and the minimum bounding rectangle of the segmented area of the psoas major muscle; and displaying the target puncture area on the lumbar plexus nerve block ultrasound image.

[0137] Specifically, determining the target puncture area on the psoas major muscle area (PM) based on the image category of the lumbar plexus nerve block ultrasound image and the position of the segmented area of the puncture needle includes:

[0138] The lumbar plexus nerve is distributed in the inner posterior 1 / 4 - 1 / 3 area of the psoas major muscle. As Figure 4 shown, when the image category of the lumbar plexus nerve block ultrasound image is the paravertebral transverse process sagittal plane and the segmented area of the puncture needle is on the side of the psoas major muscle area (PM) away from the dangerous area (Risk Area), one-third of the area close to the segmented area of the erector spinae muscle within the minimum bounding rectangle of the psoas major muscle area is determined as the target puncture area.

[0139] As Figure 5 shown, when the image category of the lumbar plexus nerve block ultrasound image is the paravertebral transverse process cross-section and the segmented area of the puncture needle is on the side of the psoas major muscle area (PM) away from the vertebra (Vertebra), one-fourth of the area close to the segmented area between the vertebra and the erector spinae muscle within the minimum bounding rectangle of the psoas major muscle area is determined as the target puncture area.

[0140] Specifically, the minimum bounding rectangle of the psoas major muscle area (PM) is equally divided into 4 quarter rectangles, and one-fourth of the area close to the segmented area between the vertebra and the erector spinae muscle within the minimum bounding rectangle of the psoas major muscle area is determined as the target puncture area.

[0141] As Figure 6 shown, when the image category of the lumbar plexus nerve block ultrasound image is the anterolateral transverse process cross-section and the segmented area of the puncture needle is on the side of the psoas major muscle area (PM) away from the dangerous area (Risk Area), one-fourth of the area close to the vertebra area and the erector spinae muscle area within the minimum bounding rectangle of the psoas major muscle area is determined as the target puncture area.

[0142] To facilitate better implementation of the method for identifying lumbar plexus nerve block ultrasound images and guiding puncture provided in the embodiments of the present application, the embodiments of the present application also provide a device for identifying lumbar plexus nerve block ultrasound images and guiding puncture based on the above method for identifying lumbar plexus nerve block ultrasound images and guiding puncture. The meanings of the nouns are the same as those in the above method for identifying lumbar plexus nerve block ultrasound images and guiding puncture, and the specific implementation details can be referred to the descriptions in the above method embodiments.

[0143] Please refer to Figure 7 , Figure 7This is a schematic structural diagram of the lumbar plexus nerve block ultrasound image recognition and puncture guidance device provided by the embodiments of the present application. The lumbar plexus nerve block ultrasound image recognition and puncture guidance device may include:

[0144] An acquisition module 701, configured to acquire lumbar plexus nerve block ultrasound images collected by an ultrasound device;

[0145] A classification module 702, configured to input the lumbar plexus nerve block ultrasound image into a site classification model to obtain site type information of the lumbar plexus nerve block ultrasound image;

[0146] A segmentation module 703, configured to, when the site type information of the lumbar plexus nerve block ultrasound image is a preset site type, input the lumbar plexus nerve block ultrasound image into a target image segmentation model to perform image segmentation on the lumbar plexus nerve block ultrasound image, so as to obtain multiple tissue segmentation regions, a puncture needle segmentation region, and region categories of the multiple tissue segmentation regions on the lumbar plexus nerve block ultrasound image. The region categories of the tissue segmentation regions include a puncturable category and an avoidance category;

[0147] A generation module 704, configured to generate a puncture direction line of the puncture needle on the lumbar plexus nerve block ultrasound image based on the puncture needle segmentation region;

[0148] A first judgment module 705, configured to judge whether the puncture direction line passes through a tissue segmentation region of the puncturable category;

[0149] A second judgment module 706, configured to, if the puncture direction line passes through a tissue segmentation region of the puncturable category, judge whether the puncture direction line passes through a tissue segmentation region of the avoidance category;

[0150] An instruction module 707, configured to, if the puncture direction line does not pass through a tissue segmentation region of the avoidance category, issue an instruction to continue puncturing in the current puncture direction.

[0151] For the specific implementation of each of the above modules, reference may be made to the previous embodiments, which will not be elaborated herein.

[0152] The embodiments of the present application further provide an electronic device, including a memory and a processor. The processor is configured to execute the steps in the lumbar plexus nerve block ultrasound image recognition and puncture guidance method provided by this embodiment by calling a computer program stored in the memory.

[0153] Please refer to Figure 8 , Figure 8 , which is a schematic structural diagram of the electronic device provided by the embodiments of the present application.

[0154] The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art can understand that the structure of the electronic device shown in the figure does not limit the electronic device, and it may include more or fewer components than shown, or combine certain components, or have different component arrangements. Among them:

[0155] The processor 101 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and circuits. By running or executing software programs and / or modules stored in the memory 102, and by calling data stored in the memory 102, it executes various functions of the electronic device and processes data. Optionally, the processor 101 may include one or more processing cores; optionally, the processor 101 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above modem processor may not be integrated into the processor 101 either.

[0156] The memory 102 can be used to store software programs and modules. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 102. The memory 102 mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as the sound playback function, image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device. In addition, the memory 102 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices. Correspondingly, the memory 102 may also include a memory controller to provide the processor 101 with access to the memory 102.

[0157] The electronic device also includes a power supply 103 that powers each component. Optionally, the power supply 103 can be logically connected to the processor 101 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 103 may also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0158] The electronic device may further include an input unit 104, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0159] Although not shown, the electronic device may further include a display unit 105, an image acquisition component, etc., which will not be elaborated here. Specifically in this embodiment, the processor 101 in the electronic device will load the executable code corresponding to one or more computer programs into the memory 102 according to the following instructions, and the processor 101 will execute the steps in the lumbar plexus nerve block ultrasound image recognition and puncture guidance method provided in this application, such as:

[0160] Obtain the lumbar plexus nerve block ultrasound image collected by the ultrasound device; input the lumbar plexus nerve block ultrasound image into the site classification model to obtain the site type information of the lumbar plexus nerve block ultrasound image; when the site type information of the lumbar plexus nerve block ultrasound image is the preset site type, input the lumbar plexus nerve block ultrasound image into the target image segmentation model to perform image segmentation on the lumbar plexus nerve block ultrasound image, and obtain multiple tissue segmentation regions, a puncture needle segmentation region, and the region categories of the multiple tissue segmentation regions on the lumbar plexus nerve block ultrasound image. The region categories of the tissue segmentation regions include a puncturable category and an avoidance category; generate a puncture direction line of the puncture needle on the lumbar plexus nerve block ultrasound image based on the puncture needle segmentation region; determine whether the puncture direction line passes through the tissue segmentation region of the puncturable category; if the puncture direction line passes through the tissue segmentation region of the puncturable category, then determine whether the puncture direction line passes through the tissue segmentation region of the avoidance category; if the puncture direction line does not pass through the tissue segmentation region of the avoidance category, then issue an instruction to continue puncturing in the current puncture direction.

[0161] It should be noted that the electronic device provided in the embodiment of this application and the lumbar plexus nerve block ultrasound image recognition and puncture guidance method in the above embodiment belong to the same concept. For the specific implementation process, please refer to the above relevant embodiments, which will not be elaborated here.

[0162] This application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program stored thereon is executed by the processor of the electronic device provided in the embodiment of this application, the processor of the electronic device is enabled to execute the steps in the lumbar plexus nerve block ultrasound image recognition and puncture guidance method provided in this application. Among them, the storage medium may be a magnetic disk, an optical disc, a read-only memory (ROM), or a random access memory (RAM), etc.

[0163] This application also provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes various optional implementation manners of the above lumbar plexus nerve block ultrasound image recognition and puncture guidance method.

[0164] The above has introduced in detail a lumbar plexus nerve block ultrasound image recognition and puncture guidance method and device provided by the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

[0165] It should be noted that when the above embodiments of the present application are applied to specific products or technologies, and relevant user data is involved, user permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

Claims

1. A method for ultrasonic image recognition and puncture guidance for lumbar plexus nerve block, characterized in that: include: Obtain lumbar plexus block ultrasound images collected by ultrasound equipment; inputting the lumbar plexus nerve block ultrasound image into a site classification model to obtain site type information of the lumbar plexus nerve block ultrasound image; When the site type information of the lumbar plexus block ultrasound image is a preset site type, the lumbar plexus block ultrasound image is input into a target image segmentation model to perform image segmentation on the lumbar plexus block ultrasound image, thereby obtaining a plurality of tissue segmentation regions, a puncture needle segmentation region, and a plurality of region categories of the tissue segmentation regions on the lumbar plexus block ultrasound image, wherein the region categories of the tissue segmentation regions include a punctureable category and an avoidance category; Determine whether the puncture needle segmentation region includes a needle tip region; if the puncture needle segmentation region includes the needle tip region, generate a puncture direction line of the puncture needle on the lumbar plexus nerve block ultrasound image based on the puncture needle segmentation region, wherein the puncture needle segmentation region is refined using the Zhang-Suen refinement algorithm to obtain a needle refinement line segment, perform straight line fitting on the needle refinement line segment to obtain a first fitted straight line segment, obtain a plurality of first needle points spaced at equal intervals on the needle refinement line segment, wherein the plurality of first needle points include two endpoints of the needle refinement line segment, calculate the vertical distances of the plurality of first needle points from the first fitted straight line segment respectively, and sum them to obtain a first total distance; if the first total distance is greater than a first preset distance value, determine that the puncture needle segmentation region includes the needle tip region; Determining whether the puncture direction line passes through the puncturable tissue segmentation area; If the puncture direction line passes through the tissue segmentation area of the puncturable category, determining whether the puncture direction line passes through the tissue segmentation area of the avoidance category; If the puncture direction line does not pass through the tissue segmentation area of the avoidance category, an instruction to continue puncturing in the current puncture direction is issued.

2. The method for lumbar plexus nerve block ultrasound image recognition and puncture guidance according to claim 1, characterized in that: The lumbar plexus nerve block ultrasound image recognition and puncture guidance method comprises: If the puncture direction line passes through the tissue segmentation area of the avoidance category, determining whether the tissue segmentation area of the avoidance category through which the puncture direction line passes is located between the puncture needle segmentation area and the target puncture area; If the tissue segmentation area of the avoidance category that the puncture direction line passes through is not located between the puncture needle segmentation area and the target puncture area, then calculating the real-time distance between the needle tip of the puncture needle segmentation area along the puncture needle direction line and the tissue segmentation area of the avoidance category; If the real-time distance is not less than the second preset distance value, an instruction to continue puncturing in the current puncture direction is issued.

3. The method for ultrasonic image recognition and puncture guidance of lumbar plexus nerve block according to claim 2, characterized in that: The lumbar plexus nerve block ultrasound image recognition and puncture guidance method comprises: If the tissue segmentation area of the avoidance category through which the puncture direction line passes is located between the puncture needle segmentation area and the target puncture area, a prompt signal is issued to prompt the operator to adjust the puncture direction to avoid the avoidance area.

4. The method for ultrasonic image recognition and puncture guidance of lumbar plexus nerve block according to claim 2, characterized in that: The lumbar plexus nerve block ultrasound image recognition and puncture guidance method comprises: If the real-time distance is less than a second preset distance value, an alarm signal is issued.

5. The method for ultrasonic image recognition and puncture guidance of lumbar plexus nerve block according to claim 4, characterized in that: When the image category of the lumbar plexus block ultrasound image is a paraspinal transverse process sagittal plane, the tissue segmentation areas belonging to the punctureable category on the lumbar plexus block ultrasound image include the erector spinae muscle region and the psoas muscle region, and the tissue segmentation areas belonging to the avoidance category on the lumbar plexus block ultrasound image include multiple transverse process regions and a dangerous area containing abdominal visceral blood vessels, the multiple transverse process regions are arranged at intervals between the erector spinae muscle region and the psoas muscle region, and the dangerous area is located on a side of the psoas muscle region away from the erector spinae muscle region; When the image category of the lumbar plexus block ultrasound image is a paravertebral transverse process cross section, the tissue segmentation areas belonging to the punctureable category on the lumbar plexus block ultrasound image include the erector spinae muscle area, the psoas major muscle area, and the quadratus lumborum muscle area, and the tissue segmentation areas belonging to the avoidance category on the lumbar plexus block ultrasound image include the vertebrae and the dangerous area including abdominal organs and blood vessels; When the image category of the lumbar plexus block ultrasound image is the cross-section of the ventrolateral transverse process, the tissue segmentation areas belonging to the punctureable category on the lumbar plexus block ultrasound image include the erector spinae muscle area, the psoas major muscle area, and the quadratus lumborum muscle area, and the tissue segmentation areas belonging to the avoidance category on the lumbar plexus block ultrasound image include the vertebrae and dangerous areas containing abdominal organs and blood vessels.

6. The method for ultrasonic image recognition and puncture guidance of lumbar plexus nerve block according to claim 5, characterized in that: The lumbar plexus nerve block ultrasound image recognition and puncture guidance method comprises: determining a target puncture area within the psoas major muscle region based on an image category of the lumbar plexus nerve block ultrasound image and a minimum circumscribed rectangle of the psoas major muscle segmentation area; The target puncture area is displayed on the lumbar plexus nerve block ultrasound image.

7. The method for ultrasonic image recognition and puncture guidance of lumbar plexus nerve block according to claim 6, characterized in that: The determining of a target puncture area on the psoas major region based on the image category of the lumbar plexus nerve block ultrasound image and the minimum circumscribed rectangle of the psoas major region comprises: When the image category of the lumbar plexus block ultrasound image is a paraspinal transverse process sagittal plane, and the puncture needle segmentation area is located on a side of the psoas major muscle area away from the dangerous area, one-third of the area within the minimum circumscribed rectangle of the psoas major muscle area close to the erector spinae segmentation area is determined as the target puncture area; When the image category of the lumbar plexus nerve block ultrasound image is a paravertebral transverse process cross section, and the puncture needle segmentation area is located on the side of the psoas major muscle area away from the vertebra, a quarter of the segmentation area close to the vertebra and the erector spinae muscle within the minimum circumscribed rectangle of the psoas major muscle area is determined as the target puncture area; When the image category of the lumbar plexus nerve block ultrasound image is a cross-section of the ventrolateral transverse process, and the puncture needle segmentation area is located on the side of the psoas major muscle area away from the vertebral area, a quarter area within the minimum circumscribed rectangle of the psoas major muscle area close to the vertebral area and the erector spinae muscle area is determined as the target puncture area.

8. A lumbar plexus nerve block ultrasound image recognition and puncture guidance device, characterized in that: include: an acquisition module, used for acquiring lumbar plexus block ultrasound images acquired by an ultrasound device; a classification module, configured to input the lumbar plexus block ultrasound image into a site classification model to obtain site type information of the lumbar plexus block ultrasound image; a segmentation module, configured to determine whether the puncture needle segmentation region includes a needle tip region; when the puncture needle segmentation region includes the needle tip region, and when the site type information of the lumbar plexus block ultrasound image is a preset site type, inputting the lumbar plexus block ultrasound image into a target image segmentation model to perform image segmentation on the lumbar plexus block ultrasound image, thereby obtaining a plurality of tissue segmentation regions, a puncture needle segmentation region, and a plurality of region categories of the tissue segmentation regions on the lumbar plexus block ultrasound image, wherein the region categories of the tissue segmentation regions include a punctureable category and an avoidance category; wherein the puncture needle segmentation region is refined using a Zhang-Suen refinement algorithm to obtain a needle refinement line segment; the needle refinement line segment is linearly fitted to obtain a first fitted straight line segment; a plurality of first needle points spaced at equal intervals are obtained on the needle refinement line segment, wherein the plurality of first needle points include two endpoints of the needle refinement line segment; the perpendicular distances of the plurality of first needle points from the first fitted straight line segment are respectively calculated and summed to obtain a first total distance; and if the first total distance is greater than a first preset distance value, it is determined that the puncture needle segmentation region includes a needle tip region; a generating module, configured to generate a puncture direction line of the puncture needle on the lumbar plexus nerve block ultrasound image based on the puncture needle segmentation area; A first judging module is configured to judge whether the puncture direction line passes through the puncturable tissue segmentation area; a second judgment module, configured to judge whether the puncture direction line passes through the tissue segmentation area of the avoidance category if the puncture direction line passes through the tissue segmentation area of the puncturable category; The instruction module is used to issue an instruction to continue puncturing in the current puncture direction if the puncture direction line does not pass through the tissue segmentation area of the avoidance category.

9. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the steps in the lumbar plexus nerve block ultrasound image recognition and puncture guidance method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a plurality of instructions, which are suitable for being loaded by a processor to execute the steps of the lumbar plexus nerve block ultrasound image recognition and puncture guidance method according to any one of claims 1 to 7.

Images