Method, device and storage medium for determining a marking clip

Abstract

The present invention discloses a method, device, and storage medium for determining a marker clip. The method comprises obtaining a tissue image and tissue feature distribution information of a target tissue; extracting the edge contour shape and area size of the target tissue from the tissue image; extracting the hardness distribution information of the target tissue from the tissue feature distribution information; and inputting the edge contour shape, area size, and hardness distribution information into a marker clip calculation model, which outputs the number of marker clips required for marking the target tissue. The method achieves high efficiency and accuracy in marking the target tissue using the marker clip.

Description

Technical Field

[0001] The present invention relates to the field of biomedicine, and in particular to a method, device and storage medium for determining a marker clip. Background Art

[0002] Tissue treatment methods may include atherectomy and drug therapy. During drug therapy, human tissue (such as tumor tissue, nodules, etc.) can be marked with a marker clip to facilitate observation of the tissue's treatment status. For example, the size and location of the relevant lesion tissue can be marked with a marker clip. In this way, during treatment, the treatment status can be judged based on the range defined by the marker clip.

[0003] The number of marking clips required for different tissue types can vary. Currently, the number of marking clips cannot be determined automatically and must be manually determined by medical personnel during the tissue marking process, which wastes time, affects marking efficiency, and has low accuracy. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, device, apparatus, and computer-readable storage medium for determining a marking clip, which can improve the efficiency and accuracy of tissue marking.

[0005] In one aspect, the present invention provides a method for determining a marker clip, the method comprising:

[0006] Obtaining tissue images and tissue feature distribution information of target tissues;

[0007] Extracting the edge contour shape and area size of the target tissue from the tissue image;

[0008] Extracting the softness and hardness distribution information of the target tissue from the tissue feature distribution information; and

[0009] The edge contour shape, the area size, and the softness and hardness distribution information are input into a marking clip calculation model, and the marking clip calculation model outputs the number of marking clips required when performing a marking operation on the target tissue.

[0010] In some embodiments, extracting the edge contour shape and area size of the target tissue from the tissue image includes:

[0011] Performing semantic segmentation on the tissue image to obtain a semantic segmentation result of the tissue image, wherein the semantic segmentation result is used to characterize the region category to which each pixel in the tissue image belongs, the region category including a target region and a non-target region;

[0012] According to the semantic segmentation result, the edge contour shape and area size of the target tissue are extracted from the tissue image.

[0013] In some embodiments, extracting the edge contour shape and area size of the target tissue from the tissue image according to the semantic segmentation result includes:

[0014] determining, in the tissue image, target pixels whose region category is a target region based on the semantic segmentation result;

[0015] The area size of the region where the target pixel is located is used as the area size of the target tissue, and the edge contour shape of the region where the target pixel is located is used as the edge contour shape of the target tissue.

[0016] In some embodiments, the marker clip computational model is trained based on the following method:

[0017] The edge contour shape, area size, and hardness distribution information of the sample target tissue are input into the marker clip calculation model to be trained, and the marker clip calculation model is trained based on the labeling information of the sample target tissue; wherein the labeling information is used to characterize the number of marker clips required to label the sample target tissue.

[0018] In some embodiments, acquiring a tissue image of the target tissue includes:

[0019] Ultrasonic imaging data of the target tissue is acquired, and a tissue image of the target tissue is obtained based on the ultrasonic imaging data.

[0020] In some embodiments, the tissue characteristic distribution information includes elasticity distribution information of the target tissue;

[0021] Obtaining tissue characteristic distribution information of the target tissue includes:

[0022] Obtaining relative elasticity information and absolute elasticity information of the target tissue at various locations;

[0023] The elasticity information of the target tissue at the corresponding position is determined according to the relative elasticity information and the absolute elasticity information of the target tissue at each position, so as to obtain the elasticity distribution information.

[0024] In some embodiments, obtaining relative elasticity information and absolute elasticity information of the target tissue at various locations includes:

[0025] Acquiring quasi-static elastography data and shear wave elastography data of the target tissue;

[0026] determining relative elasticity information of the target tissue at various locations based on the quasi-static elastic imaging data;

[0027] Based on the shear wave elastography data, the absolute elasticity information of the target tissue at various positions is determined.

[0028] In some embodiments, the tissue characteristic distribution information includes composition distribution information of the target tissue;

[0029] Obtaining tissue characteristic distribution information of the target tissue includes:

[0030] transmitting ultrasonic signals to the target tissue and receiving corresponding ultrasonic echo signals;

[0031] The components and component contents of the target tissue at various locations are determined based on the ultrasonic echo signals, thereby determining the composition distribution information.

[0032] In some embodiments, the tissue characteristic distribution information includes density distribution information of the target tissue;

[0033] Obtaining tissue characteristic distribution information of the target tissue includes:

[0034] transmitting ultrasonic signals to the target tissue and receiving corresponding ultrasonic echo signals;

[0035] The density information of the target tissue at each position is determined according to the ultrasonic echo signal to obtain density distribution information.

[0036] In some embodiments, the tissue characteristic distribution information includes composition distribution information, density distribution information, and elasticity distribution information of the target tissue;

[0037] The step of extracting the softness and hardness distribution information of the target tissue from the tissue feature distribution information includes:

[0038] The composition distribution information, the density distribution information and the elasticity distribution information are input into a learning model, and the learning model fuses the composition distribution information, the density distribution information and the elasticity distribution information based on the weights of the elasticity distribution information, the density distribution information and the elasticity distribution information respectively to obtain the hardness distribution information.

[0039] In some embodiments, the weights of the elasticity distribution information, the density distribution information, and the elasticity distribution information are determined according to the following method:

[0040] The training data and the labeling information of the training data are input into the learning model, and the learning model learns and obtains the weights of the elasticity distribution information, the density distribution information and the elasticity distribution information.

[0041] Another aspect of the present invention further provides a device for determining a marker clip, the device comprising:

[0042] A data acquisition module is used to obtain tissue images and tissue feature distribution information of the target tissue;

[0043] A first data extraction module is used to extract the edge contour shape and area size of the target tissue from the tissue image;

[0044] A second data extraction module is configured to extract the softness and hardness distribution information of the target tissue from the tissue feature distribution information; and

[0045] The result output module is used to input the edge contour shape, the area size and the softness and hardness distribution information into a marker clip calculation model, and the marker clip calculation model outputs the number of marker clips required when performing a marking operation on the target tissue.

[0046] Another aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0047] Another aspect of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the method described above is implemented.

[0048] In some embodiments of the present application, the edge contour shape, area size, and hardness distribution of the target tissue are extracted and input into a trained marker calculation model. The model then outputs the number of markers required to mark the target tissue. This eliminates the need for medical personnel to manually determine the number of markers required during the target tissue marking process, thereby improving marking efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The features and advantages of the present invention will be more clearly understood by referring to the accompanying drawings, which are schematic and should not be construed as limiting the present invention in any way. In the accompanying drawings:

[0050] Figure 1 A schematic flow chart of a method for determining a marker clip provided in one embodiment of the present application is shown;

[0051] Figure 2 A schematic diagram of semantic segmentation results of a tissue image provided by an embodiment of the present application is shown;

[0052] Figure 3 A schematic diagram of dividing the target tissue area provided by one embodiment of the present application is shown;

[0053] Figure 4 A schematic diagram of the functional modules of a device for determining a marker clip provided in one embodiment of the present application is shown;

[0054] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0055] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0056] This application proposes a method for determining tissue marker clips that automatically determines the number of marker clips required when marking target tissue, eliminating the need for medical personnel to manually determine the number of marker clips required during the marking process, thereby achieving the goal of improving marking efficiency and accuracy. Target tissues include, but are not limited to, tumor tissue, nodules, and benign lesions.

[0057] In some embodiments, the length and width of the marker clip may be respectively limited to within a threshold range. Specifically, the threshold range may be within a range less than 5 mm.

[0058] In some embodiments, the surface of the marker clip can be smoothed. A smoothed marker clip can reflect more ultrasound than the target tissue. Thus, the marker clip and the target tissue can be distinguished based on the ultrasound echo signal, thereby determining the position of the marker clip.

[0059] In some other embodiments, the surface of the marker clip may be coated. The coating material may be a highly ultrasonically reflective material. This allows the marker clip to reflect more ultrasonic waves than the target tissue, and the marker clip and target tissue can be distinguished based on the ultrasonic echo signal, thereby determining the position of the marker clip. Furthermore, the marker clip may be a specified shape (e.g., a square). During ultrasonic testing, the location of the specified shape is where the marker clip is located. This allows for better distinction between the marker clip and target tissue.

[0060] In some embodiments, to ensure compatibility between the marker clip and the target tissue, the marker clip may be coated with a biocompatible material, and / or the marker clip may be placed within a biocompatible material. Furthermore, the biocompatible material may include a hemostatic material (e.g., hemostatic cotton), so that after the target tissue is peeled, the marker clip, which marks the peeled location, can provide hemostasis.

[0061] In some embodiments, to prevent the marker clip from causing infection to the target tissue at the marked location, the marker clip may be packaged in a sterile manner.

[0062] The method for determining a tissue marker clip can be applied to an electronic device. The electronic device can be a medical device. Figure 1 , which is a flow chart of a method for determining a tissue marker clip provided in one embodiment of the present application. Figure 1 In the method for determining the tissue marker clip, the steps include:

[0063] Step S11: Acquire the tissue image and tissue feature distribution information of the target tissue.

[0064] In some embodiments, acquiring a tissue image of a target tissue includes:

[0065] Ultrasonic imaging data of the target tissue is acquired, and a tissue image of the target tissue is obtained based on the ultrasonic imaging data.

[0066] Specifically, the ultrasonic imaging data may be B-mode ultrasonic imaging data of the target tissue. A B-mode ultrasonic image of the target tissue may be extracted from the B-mode ultrasonic imaging data. This B-mode ultrasonic image may serve as a tissue image of the target tissue. Those skilled in the art may employ a variety of technical means to obtain B-mode ultrasonic images, which are not described in detail herein. It is understood that the obtained tissue image may include, in addition to the imaging image of the target tissue, imaging images of other tissues surrounding the target tissue. In other words, the imaging image of the target tissue may only occupy a portion of the tissue image.

[0067] In some embodiments, tissue feature distribution information is used to characterize tissue features at different locations of the target tissue. Each tissue feature corresponds to a piece of tissue feature distribution information. Specifically, the tissue feature may be a feature related to the hardness or softness of the target tissue.

[0068] In this embodiment, the elasticity information, composition information, and density information of the target tissue are used as tissue features related to the softness or hardness of the target tissue. Accordingly, the tissue feature distribution information includes elasticity distribution information, composition distribution information, and density distribution information.

[0069] In some embodiments, the relative elasticity information and absolute elasticity information of the target tissue at various positions can be obtained, and based on the relative elasticity information and absolute elasticity information of the target tissue at various positions, the elasticity information of the target tissue at the corresponding position can be determined to obtain elasticity distribution information. Specifically, for any position of the target tissue, relative elasticity can refer to the elasticity of the position relative to the elasticity at the reference position. For example, relative to the elasticity at the reference position, the elasticity at the position is better or worse; and absolute elasticity can refer to the elastic modulus at the position. By fusing the relative elasticity information and the absolute elasticity information at the same position of the target tissue, the elasticity information at the corresponding position can be obtained. The elasticity information at different positions of the target tissue can constitute the elasticity distribution information.

[0070] Furthermore, quasi-static elastic imaging data and shear wave elastic imaging data of the target tissue can be obtained, and based on the quasi-static elastic imaging data, the relative elastic information of the target tissue at various positions can be determined, and based on the shear wave elastic imaging data, the absolute elastic information of the target tissue at various positions can be determined. Specifically, the quasi-static elastic imaging data can be obtained by quasi-static elastic imaging of the target tissue. The shear wave elastic imaging data can be obtained based on the shear wave elastic imaging of the target tissue. The absolute elastic information can be strain, strain distribution characteristics, etc., and the relative elastic information can be elastic modulus, elastic modulus distribution characteristics, etc., which are not specifically limited in this application.

[0071] In some embodiments, an ultrasonic signal may be transmitted to the target tissue and a corresponding ultrasonic echo signal may be received. Based on the ultrasonic echo signal, density information of the target tissue at various locations may be determined to obtain density distribution information. Furthermore, based on the ultrasonic echo signal, the components and component contents at various locations of the target tissue may be determined to obtain composition distribution information. Specifically, the components and component contents at various locations may be extracted from the ultrasonic echo signal.

[0072] Step S12: extracting the edge contour shape and area size of the target tissue from the tissue image.

[0073] As can be seen from the description of step S11, the tissue image includes not only the target tissue but also other surrounding tissues. Therefore, to obtain the edge contour shape and area size of the target tissue, the target tissue must first be identified in the tissue image. This means distinguishing the target tissue from other tissues.

[0074] In some embodiments, semantic segmentation may be performed on the tissue image to obtain a semantic segmentation result of the tissue image. The semantic segmentation result is used to characterize the region category to which each pixel in the tissue image belongs. The region category includes a target region and a non-target region.

[0075] Taking the target tissue as tumor tissue as an example, the target area refers to the tumor area, and the non-target area refers to the non-tumor area.

[0076] Specifically, if the region category to which a pixel belongs is the target region, it may indicate that the pixel is located in the imaging region of the target tissue. If the region category to which a pixel belongs is the non-target region, it may indicate that the pixel is located in the imaging region of tissues other than the target tissue.

[0077] For easier understanding, see Figure 2 , which is a schematic diagram of the semantic segmentation results of a tissue image provided by an embodiment of the present application. Figure 2 In the image, each grid represents a pixel in the tissue image. The number in each pixel represents the region category to which the pixel belongs. For example, the number 1 represents the target region, and 0 represents the non-target region.

[0078] In this way, the edge contour shape and area size of the target tissue are extracted from the tissue image based on the semantic segmentation results. Specifically, based on the semantic segmentation results, the target pixel in the tissue image can be identified as the target area; the area size of the region where the target pixel is located is used as the area size of the target tissue, and the edge contour shape of the region where the target pixel is located is used as the edge contour shape of the target tissue.

[0079] For easier understanding, please refer to Figure 3 , is a schematic diagram of the division of the target tissue area provided in one embodiment of the present application. Figure 3 In the example, assume that the number 1 represents the target area and 0 represents the non-target area. Then, the elements within region 31 can be target pixels. The area of ​​region 31 can be used as the area of ​​the target tissue, and the edge contour of region 31 can be used as the edge contour of the target tissue.

[0080] In this way, based on the semantic segmentation method, the edge contour shape and area size of the target tissue can be extracted from the tissue image. Among them, the above semantic segmentation method can also be called an image segmentation method based on regional features.

[0081] In some other embodiments, an edge detection-based image segmentation method can be used to extract the edge contour and area size of the target tissue from the tissue image. Simply put, the boundary pixels between the target tissue and other tissues can be identified in the tissue image. These boundary pixels are then connected to demarcate the target tissue area from the other tissue areas. Furthermore, the area size and edge contour shape of the target tissue area can be extracted.

[0082] It should be noted that the above are only two exemplary methods for extracting the edge contour shape and area size of the target tissue from the tissue image. It is understood that any method capable of extracting the edge contour shape and area size of the target tissue should be within the scope of protection of this application.

[0083] Step S13: extracting the softness and hardness distribution information of the target tissue from the tissue feature distribution information.

[0084] In some embodiments, the hardness distribution information characterizes the hardness at different locations of the target tissue. The tissue feature distribution information may include composition distribution information, density distribution information, and elasticity distribution information of the target tissue. The hardness distribution information can be obtained by inputting the composition distribution information, density distribution information, and elasticity distribution information into a learning model, which then fuses the composition distribution information, density distribution information, and elasticity distribution information based on the weights assigned to the elasticity distribution information, density distribution information, and elasticity distribution information, to obtain the hardness distribution information.

[0085] Specifically, the weights of the elasticity distribution information, the density distribution information, and the elasticity distribution information can be determined according to the following method:

[0086] The training data and the labeled information of the training data are input into the learning model, and the learning model learns the weights of the elasticity distribution information, the density distribution information and the elasticity distribution information.

[0087] In step S14 , the edge contour shape, area size, and hardness distribution information are input into a marker clip calculation model, and the marker clip calculation model outputs the number of marker clips required for marking the target tissue.

[0088] In some embodiments, the edge contour shape, area size, and elasticity at different locations of the target tissue are factors affecting the number of marker clips.

[0089] For example, if the target tissue has many protrusions and a large area, it may be necessary to mark at least these protrusions to distinguish the target tissue area. In this case, more marking clips may be used. However, if the target tissue has a regular shape (such as a regular circle) and a small area, it is sufficient to mark the center of the target tissue. In this case, fewer marking clips may be used.

[0090] For example, based on the elasticity of the target tissue, areas with a high degree of hardening (i.e., areas with severe calcification, fibrosis, etc.) may need to be marked for special attention. Since the elasticity of different target tissues can vary, the number of marking clips required for different target tissues may also vary.

[0091] The marker clip calculation model can comprehensively evaluate the edge contour shape, area size, and elasticity at different locations, and output the number of marker clips required for the target tissue. The marker clip calculation model can be trained using machine learning methods.

[0092] The marker clip calculation model can be pre-trained. Specifically, target tissues with different edge contour shapes, different area sizes, and different elasticity conditions can be selected as sample target tissues, and the number of marker clips required for the sample target tissues can be annotated. The edge contour shape, area size, and elasticity at different locations of the sample target tissues are then input into the marker clip calculation model to be trained. The marker clip calculation model is trained based on the annotated information of the sample target tissues; the annotated information is used to indicate the number of marker clips required to mark the sample target tissues.

[0093] After training, the marker calculation model can learn the number of markers required for target tissues with different edge contour shapes, different area sizes, and different elasticity conditions. Thus, for any target tissue to be marked, the marker calculation model can determine the required number of markers based on the target tissue's edge contour shape, area size, and elasticity.

[0094] In some embodiments of the present application, the edge contour shape, area size, and hardness distribution of the target tissue are extracted and input into a trained marker calculation model. The model then outputs the number of markers required to mark the target tissue. This eliminates the need for medical personnel to manually determine the number of markers required during the target tissue marking process, thereby improving marking efficiency and accuracy.

[0095] See also Figure 4, is a functional module diagram of a device for determining a marker clip provided in one embodiment of the present application. The device for determining a marker clip includes:

[0096] A data acquisition module is used to obtain tissue images and tissue feature distribution information of the target tissue;

[0097] A first data extraction module is used to extract the edge contour shape and area size of the target tissue from the tissue image;

[0098] A second data extraction module is used to extract the softness and hardness distribution information of the target tissue from the tissue feature distribution information; and

[0099] The result output module is used to input the edge contour shape, area size and hardness distribution information into the marker clip calculation model, and the marker clip calculation model outputs the number of marker clips required when performing the marking operation on the target tissue.

[0100] See also Figure 5 , is a schematic diagram of the structure of an electronic device provided in one embodiment of the present application. The electronic device includes a processor and a memory, wherein the memory is used to store a computer program. When the computer program is executed by the processor, the above-mentioned method for determining the marking clip is implemented.

[0101] The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0102] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods described in the embodiments of the present invention. The processor executes the non-transitory software programs, instructions, and modules stored in the memory to perform various processor functions and data processing, thereby implementing the methods described in the aforementioned method embodiments.

[0103] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely located relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0104] One embodiment of the present application further provides a computer-readable storage medium, which is used to store a computer program. When the computer program is executed by a processor, the above-mentioned method for determining the marking clip is implemented.

[0105] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for determining a marking clip, characterized in that: The method comprises: Obtaining tissue images and tissue feature distribution information of target tissues; Extracting the edge contour shape and area size of the target tissue from the tissue image; Extracting the softness and hardness distribution information of the target tissue from the tissue feature distribution information; and Inputting the edge contour shape, the area size, and the softness and hardness distribution information into a marker clip calculation model, and having the marker clip calculation model output the number of marker clips required for performing a marking operation on the target tissue; The tissue characteristic distribution information includes the composition distribution information, density distribution information and elasticity distribution information of the target tissue; The step of extracting the softness and hardness distribution information of the target tissue from the tissue feature distribution information includes: The composition distribution information, the density distribution information and the elasticity distribution information are input into a learning model, and the learning model fuses the composition distribution information, the density distribution information and the elasticity distribution information based on the weights of the elasticity distribution information, the density distribution information and the elasticity distribution information respectively to obtain the hardness distribution information.

2. The method according to claim 1, wherein The step of extracting the edge contour shape and area size of the target tissue from the tissue image includes: Performing semantic segmentation on the tissue image to obtain a semantic segmentation result of the tissue image, wherein the semantic segmentation result is used to characterize the region category to which each pixel in the tissue image belongs, the region category including a target region and a non-target region; According to the semantic segmentation result, the edge contour shape and area size of the target tissue are extracted from the tissue image.

3. The method according to claim 2, wherein Extracting the edge contour shape and area size of the target tissue from the tissue image according to the semantic segmentation result includes: determining, in the tissue image, target pixels whose region category is a target region based on the semantic segmentation result; The area size of the region where the target pixel is located is used as the area size of the target tissue, and the edge contour shape of the region where the target pixel is located is used as the edge contour shape of the target tissue.

4. The method according to claim 1, wherein The marker clip calculation model is trained based on the following method: The edge contour shape, area size, and hardness distribution information of the sample target tissue are input into the marker clip calculation model to be trained, and the marker clip calculation model is trained based on the labeling information of the sample target tissue; wherein the labeling information is used to characterize the number of marker clips required to label the sample target tissue.

5. The method according to claim 1, wherein Acquiring a tissue image of the target tissue, comprising: Ultrasonic imaging data of the target tissue is acquired, and a tissue image of the target tissue is obtained based on the ultrasonic imaging data.

6. The method according to claim 1, wherein Obtaining tissue characteristic distribution information of the target tissue includes: Obtaining relative elasticity information and absolute elasticity information of the target tissue at various locations; The elasticity information of the target tissue at the corresponding position is determined according to the relative elasticity information and the absolute elasticity information of the target tissue at each position, so as to obtain the elasticity distribution information.

7. The method according to claim 6, wherein The obtaining of relative elasticity information and absolute elasticity information of the target tissue at various locations includes: Acquiring quasi-static elastography data and shear wave elastography data of the target tissue; determining relative elasticity information of the target tissue at various locations based on the quasi-static elastic imaging data; Based on the shear wave elastography data, the absolute elasticity information of the target tissue at various positions is determined.

8. The method according to claim 1, wherein Obtaining tissue characteristic distribution information of the target tissue includes: transmitting ultrasonic signals to the target tissue and receiving corresponding ultrasonic echo signals; The components and component contents of the target tissue at various locations are determined based on the ultrasonic echo signals, thereby determining the composition distribution information.

9. The method according to claim 1, wherein Obtaining tissue characteristic distribution information of the target tissue includes: transmitting ultrasonic signals to the target tissue and receiving corresponding ultrasonic echo signals; The density information of the target tissue at each position is determined according to the ultrasonic echo signal to obtain density distribution information.

10. The method according to claim 1, wherein The weights of the elasticity distribution information, the density distribution information, and the elasticity distribution information are determined according to the following method: The training data and the labeling information of the training data are input into the learning model, and the learning model learns and obtains the weights of the elasticity distribution information, the density distribution information and the elasticity distribution information.

11. A device for determining a marking clip, characterized in that: The device comprises: A data acquisition module is used to obtain tissue images and tissue feature distribution information of the target tissue; A first data extraction module is used to extract the edge contour shape and area size of the target tissue from the tissue image; A second data extraction module is configured to extract the softness and hardness distribution information of the target tissue from the tissue feature distribution information; and A result output module is used to input the edge contour shape, the area size, and the softness and hardness distribution information into a marker clip calculation model, and the marker clip calculation model outputs the number of marker clips required when performing a marking operation on the target tissue; The tissue characteristic distribution information includes the composition distribution information, density distribution information and elasticity distribution information of the target tissue. The second data extraction module is also used to input the composition distribution information, the density distribution information and the elasticity distribution information into a learning model, and the learning model fuses the composition distribution information, the density distribution information and the elasticity distribution information based on the weights of the elasticity distribution information, the density distribution information and the elasticity distribution information respectively to obtain the hardness distribution information.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

13. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the method according to any one of claims 1 to 10 is implemented.

Images