Carotid plaque image processing method and system based on ultrasonic image

Abstract

The invention provides a carotid plaque image processing method and system based on an ultrasonic image. The method comprises the following steps: carrying out ultrasonic image-based image acquisition on a carotid artery tissue of a patient to obtain a three-dimensional ultrasonic image corresponding to the carotid artery tissue; performing image recognition based on the three-dimensional ultrasonic image, determining a plaque region corresponding to a carotid plaque in the carotid artery tissue, and performing feature extraction based on multiple dimensions on the plaque region to obtain feature data corresponding to different dimensions; determining morphological attributes of the plaque region based on the feature data corresponding to different dimensions, and generating a recommended operation mode for executing medical operation on the plaque region based on the morphological attributes; and constructing a surgical operation model corresponding to the three-dimensional ultrasonic image based on a digital twinning technology, and instructing the medical care terminal to execute a simulated operation on a model part corresponding to the plaque area in the surgical operation model based on the recommended operation mode. The success rate of the simulated operation is at least improved.

Description

Technical Field

[0001] The present invention relates to data processing technology, and in particular to a method and system for processing carotid artery plaque images based on ultrasonic imaging. Background Art

[0002] Carotid plaques are manifestations of carotid atherosclerosis, which are more likely to occur at the bifurcation of the common carotid artery and are believed to be closely related to the occurrence of ischemic stroke in the elderly. The mechanism of ischemic stroke may be: the enlargement of plaques leads to stenosis of the carotid artery, causing intracranial hypoperfusion and plaque shedding to form emboli, leading to intracranial artery embolism. Therefore, carotid plaques need to be closely observed and treated accordingly.

[0003] The inventors found in their research that surgical treatment of carotid artery plaques may involve certain surgical risks. If the surgical situation can be rehearsed in advance through simulated surgery before the surgery, the surgical risks can be greatly reduced. Summary of the invention

[0004] Based on the above problems, the present invention is proposed to provide a method and system for processing carotid plaque images based on ultrasound imaging, which overcomes the above problems or at least partially solves the above problems.

[0005] According to one aspect of the present invention, a method for processing a carotid artery plaque image based on ultrasound imaging is provided, comprising the following steps: Acquiring an ultrasound-based image of the patient's carotid artery tissue to obtain a three-dimensional ultrasound image corresponding to the carotid artery tissue; Performing image recognition based on the three-dimensional ultrasound image to determine a plaque area corresponding to a carotid plaque located in the carotid artery tissue, and performing multi-dimensional feature extraction on the plaque area to obtain feature data corresponding to different dimensions; Determining the morphological attributes of the plaque area based on the feature data corresponding to the different dimensions, and generating a recommended operation method for performing a medical operation on the plaque area based on the morphological attributes; A surgical operation model corresponding to the three-dimensional ultrasound image is constructed based on the digital twin technology, and based on the recommended operation method, the medical staff is instructed to perform a simulated operation on the model part corresponding to the plaque area in the surgical operation model.

[0006] Optionally, in the method according to the present invention, image recognition is performed based on the three-dimensional ultrasound image to determine a plaque area corresponding to a carotid plaque located in the carotid artery tissue, and multi-dimensional feature extraction is performed on the plaque area to obtain feature data corresponding to different dimensions, including: Inputting the three-dimensional ultrasound image into a trained image recognition model for image recognition to determine a plaque area corresponding to a carotid artery plaque located in the carotid artery tissue; Determine a carotid artery region having an attachment relationship with the plaque region in the three-dimensional ultrasound image, and acquire a first region endpoint and a second region endpoint corresponding to the carotid artery region based on a tissue extension direction of the carotid artery tissue; Connecting the first region endpoint and the second region endpoint, and determining the obtained endpoint connection line as the horizontal reference line; Based on the horizontal reference line, multi-dimensional feature extraction is performed on the patch area to obtain feature data corresponding to different dimensions.

[0007] Optionally, in the method according to the present invention, multi-dimensional feature extraction is performed on the plaque area based on the horizontal reference line to obtain feature data corresponding to different dimensions, including: Performing feature extraction based on the length dimension based on the horizontal reference line to obtain the line segment length corresponding to the horizontal reference line, and retrieving the reference point multiple; The length of the line segment is multiplied by the multiple of the reference point to obtain the number of point divisions; Dividing the horizontal reference line into points along the extension direction of the horizontal reference line to obtain line segment points corresponding to the number of point divisions, wherein adjacent line segment points have the same point distance; Mapping each line segment point to the corresponding plaque area along a direction perpendicular to the extension direction to obtain each regional point located on the plaque area, and performing feature extraction based on the thickness dimension based on each regional point to obtain the thickness of each regional point from each point on the horizontal reference line; The length of the line segment is determined as the characteristic data of the length dimension corresponding to the plaque area, and the thickness of each point is determined as the characteristic data of the thickness dimension corresponding to the plaque area.

[0008] Optionally, in the method according to the present invention, determining the morphological attributes of the plaque area based on the feature data corresponding to different dimensions, and generating a recommended operation mode for performing a medical operation on the plaque area based on the morphological attributes, includes: Based on the thickness of each point corresponding to each point in each area, the average thickness is calculated to obtain the average thickness; Acquiring the area based on the plaque area to obtain the area of ​​the region corresponding to the plaque area, and calculating the ratio of the area of ​​the region to the mean thickness to obtain the aggregation length; Calculate the difference between the aggregate length and the line segment length to obtain a length difference, and compare the length difference with the retrieved preset difference interval; When the length difference is within the preset difference interval, the plaque area is determined to be in an aggregation state, and the tissue resection method is determined as a recommended operation method for performing a medical operation on the plaque area; When the length difference is outside the preset difference interval, the plaque region is determined to be in a dispersed state, and the stent filling method is determined to be a recommended operation method for performing a medical operation on the plaque region.

[0009] Optionally, in the method according to the present invention, determining the morphological attributes of the plaque area based on the feature data corresponding to different dimensions, and generating a recommended operation mode for performing a medical operation on the plaque area based on the morphological attributes, includes: Based on the thickness of each point corresponding to each point in each area, the average thickness is calculated to obtain the average thickness; Calculate the difference between the thickness of each point and the average thickness to obtain the thickness difference; The thickness differences are summed up to obtain the total value of the differences; Calculate the ratio of the total difference value to the number of point divisions to obtain a regional aggregation value, and compare the regional aggregation value with a preset aggregation threshold; When the regional aggregation value is less than or equal to the preset aggregation threshold, the plaque region is determined to be in an aggregation state, and the tissue resection method is determined as a recommended operation method for performing a medical operation on the plaque region; When the regional aggregation value is greater than the preset aggregation threshold, the plaque region is determined to be in a dispersed state, and the stent filling method is determined as a recommended operation method for performing a medical operation on the plaque region.

[0010] Optionally, in the method according to the present invention, a surgical operation model corresponding to the three-dimensional ultrasound image is constructed based on the digital twin technology, and based on the recommended operation mode, a medical terminal is instructed to perform a simulated operation on a model portion corresponding to the plaque area in the surgical operation model, including: Performing coordinate processing on the three-dimensional ultrasound image based on the horizontal reference line to obtain a three-dimensional image coordinate system, wherein any one of an X axis, a Y axis or a Z axis in the three-dimensional image coordinate system is parallel to the horizontal reference line; Based on the three-dimensional image coordinate system, each plaque coordinate point constituting the plaque area is obtained, and the X-axis extreme value coordinate point corresponding to the X-axis, the Y-axis extreme value coordinate point corresponding to the Y-axis, and the Z-axis extreme value coordinate point corresponding to the Z-axis located at each plaque coordinate point are respectively obtained, and a rectangular enclosing block enclosing the plaque area is generated based on the corresponding X-axis extreme value coordinate point, the corresponding Y-axis extreme value coordinate point, and the corresponding Z-axis extreme value coordinate point; Acquire an enclosing center point corresponding to the rectangular enclosing block, and magnify the enclosing center point by a preset multiple to obtain an enlarged enclosing block; Acquire digital twin data corresponding to the enlarged enclosing block, and construct a surgical operation model corresponding to the enlarged enclosing block based on the digital twin data; Establishing an operation display interface, wherein the operation display interface includes an operation interaction sub-interface and an operation display sub-interface; Filling the surgical operation model into the operation display sub-interface for display; Based on the recommended operation mode, different operation nodes corresponding to the recommended attributes are generated in the operation interaction sub-interface, and based on the different operation nodes corresponding to the recommended attributes, the medical staff is instructed to perform simulated surgery on the model part corresponding to the plaque area in the surgical operation model.

[0011] Optionally, in the method according to the present invention, generating different operation nodes corresponding to the recommended attributes in the operation interaction sub-interface based on the recommended operation mode, and instructing the medical terminal to perform a simulated operation on the model part corresponding to the plaque area in the surgical operation model based on the different operation nodes corresponding to the recommended attributes, including: A hierarchical distribution tree is established in the operation interaction sub-interface based on preset simulated surgical data corresponding to the tissue resection method and the stent filling method, wherein the hierarchical distribution tree includes different surgical method nodes corresponding to the parent level, and operation nodes corresponding to the child level generated downward based on each surgical method node; Determining the attributes of each node based on the recommended operation mode to obtain operation attributes corresponding to each node, wherein the operation attributes include recommended attributes and non-recommended attributes; In response to the medical end's interaction with any node, the node is determined as a target node, and based on the fact that the operation attribute of the target node is a non-recommended attribute, the medical end is indicated with a node whose corresponding operation attribute is a recommended attribute and is located at the same level as the target node, so as to perform a simulated surgery on the model portion corresponding to the plaque area in the surgical operation model.

[0012] Optionally, in the method according to the present invention, in response to the interaction of the medical terminal with any node, the node is determined as a target node, and based on the operation attribute of the target node being a non-recommended attribute, a node whose corresponding operation attribute is a recommended attribute and is located at the same level as the target node is indicated to the medical terminal, so as to perform a simulated surgery on a model portion corresponding to the plaque area in the surgical operation model, comprising: In response to the medical terminal interacting with any node for a preset time, determining the node as a target node, and determining an operation attribute corresponding to the target node; When the operation attribute of the target node is a non-recommended attribute, performing multi-dimensional specification adjustment on nodes whose corresponding operation attributes are recommended attributes and are located at the same level as the target node in the hierarchical distribution tree; When the operation attribute of the target node is a recommended attribute, a data display sub-interface is created in the operation display interface, and the obtained feature data corresponding to different dimensions are filled into the data display sub-interface for display; Based on the interaction of the medical end with the node whose corresponding operation attribute is the recommended attribute, a simulated operation is performed on the model part corresponding to the plaque area in the surgical operation model.

[0013] Optionally, in the method according to the present invention, based on the interaction of the medical terminal with the node whose corresponding operation attribute is the recommended attribute, performing a simulated operation on the model part corresponding to the plaque area in the surgical operation model includes: Based on the interaction of the medical terminal with the surgical method node whose corresponding operation attribute is a recommended attribute, hiding the surgical method node whose corresponding operation attribute is a non-recommended attribute in the hierarchical distribution tree; Based on the interaction of the medical terminal with the operation node whose corresponding operation attribute is a recommended attribute, calling the node tool corresponding to the operation node; In response to the medical end performing a simulated surgery on the model portion corresponding to the plaque area in the surgical operation model based on the node tool, obtaining peripheral impact data corresponding to the simulated surgery; Model modification is performed on other parts of the surgical operation model except the model part based on the peripheral influence data.

[0014] Optionally, in the method according to the present invention, the method further comprises: Determine a surgical operation surface for the medical staff to perform a simulated operation on the surgical operation model based on the node tool, and map a model portion corresponding to the plaque area in the surgical operation model to the surgical operation surface to form a plaque mapping contour; Determining a surgical section contour corresponding to the surgical operation surface based on the simulated surgery, and comparing the surgical section contour with the plaque mapping contour; In response to the surgical section contour and the plaque mapping contour having a partial overlapping relationship, a mapping contour segment located in the plaque mapping contour and not overlapping with the surgical section contour is flashed and displayed on the surgical operation surface based on a preset frequency; In response to the surgical section contour not having an overlapping relationship with the plaque mapping contour, displaying the plaque mapping contour on the surgical operation surface by flashing at a preset frequency; In response to the surgical section contour covering the plaque mapping contour, a difference is calculated between a first contour area corresponding to the surgical section contour and a second contour area corresponding to the plaque mapping contour, and when the obtained area difference is greater than the preset area difference, the plaque mapping contour is displayed on the surgical operation surface by flashing based on a preset frequency.

[0015] Optionally, in the method according to the present invention, the method further comprises: Acquiring a model mapping distance between a model portion corresponding to a plaque region and the surgical operation surface in the surgical operation model, and determining a surgical incision depth corresponding to the surgical operation surface based on the simulated surgery; Calculate the difference between the model mapping distance and the surgical section depth to obtain a distance difference; When the distance difference is not a positive number, determining a first surgical section corresponding to the simulated surgery in the surgical operation model based on the surgical section contour and the surgical section depth, and displaying the first surgical section in a color corresponding to a preset first pixel value; When the distance difference is a positive number and is greater than a preset distance difference, a second surgical section corresponding to the simulated surgery is determined in the surgical operation model based on the surgical section contour and the surgical section depth, and the second surgical section is displayed in a color corresponding to a preset second pixel value.

[0016] Optionally, in the method according to the present invention, the method further comprises: In response to a surgery completion signal sent by the medical end based on the simulated surgery, determining a cleaning area corresponding to the model part based on the simulated surgery, and comparing the retrieved model area corresponding to the model part with the cleaning area; When the model area is larger than the clearing area, all parts except the model part corresponding to the plaque area are hidden and displayed in the surgical operation model.

[0017] According to another aspect of the present invention, there is provided a carotid artery plaque image processing system based on ultrasound imaging, comprising: An image acquisition module is configured to acquire an image of the patient's carotid artery tissue based on ultrasound images to obtain a three-dimensional ultrasound image corresponding to the carotid artery tissue; a feature extraction module configured to perform image recognition based on the three-dimensional ultrasound image, determine a plaque area corresponding to a carotid plaque located in the carotid artery tissue, and perform multi-dimensional feature extraction on the plaque area to obtain feature data corresponding to different dimensions; an operation determination module, configured to determine the morphological attributes of the plaque area based on the feature data corresponding to the different dimensions, and generate a recommended operation mode for performing a medical operation on the plaque area based on the morphological attributes; The simulated surgery module is configured to construct a surgical operation model corresponding to the three-dimensional ultrasound image based on the digital twin technology, and to instruct the medical staff to perform a simulated surgery on the model part corresponding to the plaque area in the surgical operation model based on the recommended operation method.

[0018] According to the solution of the present invention, the server will first collect images of the patient's carotid artery tissue by means of ultrasonic imaging, thereby obtaining a three-dimensional ultrasonic image corresponding to the carotid artery tissue. After the server performs image recognition on the three-dimensional ultrasonic image, it can determine the plaque area corresponding to the carotid plaque located in the carotid artery tissue. Then, the server will perform multi-dimensional feature extraction on the plaque area, thereby obtaining two feature data corresponding to different dimensions, namely the length and thickness of the plaque area. And the server can determine the morphological attributes of the plaque area in two ways, thereby generating a recommended operation method for performing medical operations on the plaque area. Then, the server will construct a surgical operation model corresponding to the patient's three-dimensional ultrasonic image based on digital twin technology, and instruct the medical end to perform simulated surgery on the model part corresponding to the plaque area in the surgical operation model according to the recommended operation method. The present invention can improve the success rate of simulated surgery, thereby providing a certain reference for medical staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flow chart of a method for processing carotid artery plaque images based on ultrasound images according to an embodiment of the present invention is shown; Figure 2 A schematic diagram showing an operation display interface according to an embodiment of the present invention is shown; Figure 3 A structural block diagram of a carotid artery plaque image processing system based on ultrasound imaging according to another embodiment of the present invention is shown. DETAILED DESCRIPTION

[0020] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0021] Carotid plaques are manifestations of carotid atherosclerosis, which are more likely to occur at the bifurcation of the common carotid artery and are believed to be closely related to the occurrence of ischemic stroke in the elderly. The mechanism of ischemic stroke may be: the enlargement of plaques leads to stenosis of the carotid artery, causing intracranial hypoperfusion and plaque shedding to form emboli, leading to intracranial artery embolism. Therefore, carotid plaques need to be closely observed and treated accordingly.

[0022] The inventors found in their research that surgical treatment of carotid artery plaques may involve certain surgical risks. If the surgical situation can be rehearsed in advance through simulated surgery before the surgery, the surgical risks can be greatly reduced.

[0023] To solve the above problems in the prior art, the inventor proposes a solution of the present invention. An embodiment of the present invention provides a method for processing carotid artery plaque images based on ultrasound images, which can be executed in a computing device.

[0024] Figure 1 A flowchart of a method for processing a carotid artery plaque image based on ultrasound images according to an embodiment of the present invention is shown. The method is suitable for being executed in a computing device.

[0025] like Figure 1 As shown, the purpose of this embodiment is to implement a method for processing carotid artery plaque images based on ultrasound images, starting from step S102, in which the following steps are included: The patient's carotid artery tissue is imaged based on ultrasound imaging to obtain a three-dimensional ultrasound image corresponding to the carotid artery tissue.

[0026] For example, in this embodiment, the server first collects images of the patient's carotid artery tissue by means of ultrasonic imaging, thereby obtaining a three-dimensional ultrasonic image corresponding to the carotid artery tissue.

[0027] In step S104, the following contents are included: Image recognition is performed based on the three-dimensional ultrasound image to determine the plaque area corresponding to the carotid plaque located in the carotid artery tissue, and multi-dimensional feature extraction is performed on the plaque area to obtain feature data corresponding to different dimensions.

[0028] For example, in this embodiment, the server will perform image recognition on the obtained three-dimensional ultrasound image to determine the plaque area corresponding to the carotid plaque located in the carotid artery tissue, and perform multi-dimensional feature extraction on the plaque area to obtain feature data corresponding to each different dimension, so that the subsequent server can further analyze the plaque area according to the feature data of different dimensions.

[0029] Furthermore, the above-mentioned “performing image recognition based on the three-dimensional ultrasound image, determining the plaque area corresponding to the carotid plaque located in the carotid artery tissue, and performing multi-dimensional feature extraction on the plaque area to obtain feature data corresponding to different dimensions” also includes the following steps: Performing image recognition based on the three-dimensional ultrasound image to determine a plaque area corresponding to a carotid plaque located in the carotid artery tissue, and performing multi-dimensional feature extraction on the plaque area to obtain feature data corresponding to different dimensions, including: Inputting the three-dimensional ultrasound image into a trained image recognition model for image recognition to determine a plaque area corresponding to a carotid artery plaque located in the carotid artery tissue; Determine a carotid artery region having an attachment relationship with the plaque region in the three-dimensional ultrasound image, and acquire a first region endpoint and a second region endpoint corresponding to the carotid artery region based on a tissue extension direction of the carotid artery tissue; Connecting the first region endpoint and the second region endpoint, and determining the obtained endpoint connection line as the horizontal reference line; Based on the horizontal reference line, multi-dimensional feature extraction is performed on the patch area to obtain feature data corresponding to different dimensions.

[0030] For example, in this embodiment, after obtaining the three-dimensional ultrasound image, the server will first input the three-dimensional ultrasound image into a trained image recognition model for image recognition, thereby determining the plaque area corresponding to the carotid artery plaque located in the carotid artery tissue.

[0031] Then, the server determines the carotid artery region to which the plaque region is attached in the three-dimensional ultrasound image, and then determines two endpoints of the carotid artery region in the tissue extension direction of the carotid artery tissue, namely, a first region endpoint and a second region endpoint; Finally, by connecting the endpoints of the first area and the second area, a corresponding endpoint connection line can be obtained, and the endpoint connection line can be determined as a horizontal reference line, so that corresponding multi-dimensional feature extraction can be performed based on the horizontal reference line to obtain feature data corresponding to different dimensions.

[0032] Furthermore, the above-mentioned “extracting features of the patch area based on multiple dimensions based on the horizontal reference line to obtain feature data corresponding to different dimensions” further includes the following steps: Performing feature extraction based on the length dimension based on the horizontal reference line to obtain the line segment length corresponding to the horizontal reference line, and retrieving the reference point multiple; The length of the line segment is multiplied by the multiple of the reference point to obtain the number of point divisions; Dividing the horizontal reference line into points along the extension direction of the horizontal reference line to obtain line segment points corresponding to the number of point divisions, wherein adjacent line segment points have the same point distance; Mapping each line segment point to the corresponding plaque area along a direction perpendicular to the extension direction to obtain each regional point located on the plaque area, and performing feature extraction based on the thickness dimension based on each regional point to obtain the thickness of each regional point from each point on the horizontal reference line; The length of the line segment is determined as the characteristic data of the length dimension corresponding to the plaque area, and the thickness of each point is determined as the characteristic data of the thickness dimension corresponding to the plaque area.

[0033] For example, in this embodiment, the server will perform feature extraction based on the length dimension on the horizontal reference line, that is, obtain the line segment length of the horizontal reference line. At this time, the server will also retrieve the reference point multiple, so that the server can obtain the number of point divisions after multiplying the line segment length and the reference point multiple. At this time, the server will divide the horizontal reference line into points according to the number of point divisions along the extension direction of the horizontal reference line, thereby obtaining line segment points corresponding to the number of point divisions, and the point distances between adjacent line segment points are the same.

[0034] Next, the server will map each line segment point to the corresponding plaque area along a direction perpendicular to the extension direction, thereby obtaining each regional point located on the plaque area. At this point, the server can perform feature extraction based on the thickness dimension on the plaque area at each regional point, thereby obtaining the distance of each regional point from the horizontal reference line, that is, the thickness of each point. Furthermore, the server will determine the line segment length as the feature data of the plaque area corresponding to the length dimension, and determine the thickness of each point as the feature data of the plaque area corresponding to the thickness dimension.

[0035] In step S106, the following contents are included: The morphological attributes of the plaque area are determined based on the feature data corresponding to different dimensions, and a recommended operation method for performing a medical operation on the plaque area is generated based on the morphological attributes.

[0036] For example, in this embodiment, since the recommended operating methods for performing medical operations on plaque areas of different shapes are different, for example, when the shape of the plaque area is relatively flat, the recommended operating method for the server to perform medical operations on the plaque area is to remove the plaque area as a whole, that is, the tissue resection method; when the shape of the plaque area is not flat but uneven, if the recommended operating method for performing medical operations on the plaque area at this time is the tissue resection method, it is possible that part of the plaque area will fall off and flow with the blood when the plaque area is removed, thereby causing corresponding surgical accidents. Therefore, when the shape of the plaque area is not flat but uneven, the recommended operating method for the server to perform medical operations on the plaque area is the stent filling method.

[0037] Therefore, the server will first determine the morphological attributes of the plaque area based on the feature data corresponding to different dimensions, and then generate a recommended operation method for performing medical operations on the plaque area based on the morphological attributes.

[0038] Furthermore, the above-mentioned “determining the morphological attributes of the plaque area based on the feature data corresponding to the different dimensions, and generating a recommended operation method for performing a medical operation on the plaque area based on the morphological attributes” also includes the following steps: Based on the thickness of each point corresponding to each point in each area, the average thickness is calculated to obtain the average thickness; Acquiring the area based on the plaque area to obtain the area of ​​the region corresponding to the plaque area, and calculating the ratio of the area of ​​the region to the mean thickness to obtain the aggregation length; Calculate the difference between the aggregate length and the line segment length to obtain a length difference, and compare the length difference with the retrieved preset difference interval; When the length difference is within the preset difference interval, the plaque area is determined to be in an aggregation state, and the tissue resection method is determined as a recommended operation method for performing a medical operation on the plaque area; When the length difference is outside the preset difference interval, the plaque region is determined to be in a dispersed state, and the stent filling method is determined to be a recommended operation method for performing a medical operation on the plaque region.

[0039] For example, in this embodiment, the server first calculates the average thickness of each point to obtain the average thickness. Then, the area of ​​the plaque area is obtained, and the ratio of the area to the average thickness is calculated to obtain the aggregate length. Next, the server calculates the difference between the aggregate length and the line segment length to obtain the length difference, and then compares the length difference with the preset difference interval.

[0040] When the length difference is within the preset difference interval, it means that the difference between the aggregation length and the line segment length is not large, that is, the shape of the plaque area is relatively flat, so the server will determine the plaque area as having an aggregation state, and determine the tissue resection method as the recommended operation method for performing medical operations on the plaque area; when the length difference is outside the preset difference interval, it means that the difference between the aggregation length and the line segment length is large, that is, the shape of the plaque area is relatively uneven, so the server will determine the plaque area as having a dispersed state, and determine the stent filling method as the recommended operation method for performing medical operations on the plaque area.

[0041] This embodiment can determine the morphological attributes of the plaque area according to the difference between the aggregation length and the line segment length, thereby generating a recommended operation method for performing a medical operation on the plaque area. In addition to using the above scheme to determine the morphological attributes of the plaque area, the following scheme can also be used.

[0042] Furthermore, the above-mentioned “determining the morphological attributes of the plaque area based on the feature data corresponding to the different dimensions, and generating a recommended operation method for performing a medical operation on the plaque area based on the morphological attributes” further includes the following steps: Based on the thickness of each point corresponding to each point in each area, the average thickness is calculated to obtain the average thickness; Calculate the difference between the thickness of each point and the average thickness to obtain the thickness difference; The thickness differences are summed up to obtain the total value of the differences; Calculate the ratio of the total difference value to the number of point divisions to obtain a regional aggregation value, and compare the regional aggregation value with a preset aggregation threshold; When the regional aggregation value is less than or equal to the preset aggregation threshold, the plaque region is determined to be in an aggregation state, and the tissue resection method is determined as a recommended operation method for performing a medical operation on the plaque region; When the regional aggregation value is greater than the preset aggregation threshold, the plaque region is determined to be in a dispersed state, and the stent filling method is determined as a recommended operation method for performing a medical operation on the plaque region.

[0043] For example, in this embodiment, the server will first calculate the average thickness of each point to obtain the average thickness. Then, the difference between each point thickness and the average thickness is calculated to obtain each thickness difference, and the thickness difference is summed to obtain the total difference value. At this time, the server will calculate the ratio of the total difference value to the number of point divisions to obtain the regional aggregation value, and compare the regional aggregation value with the preset aggregation threshold.

[0044] When the regional aggregation value is less than or equal to the preset aggregation threshold, it means that the shape of the plaque area is relatively flat, so the server will determine the plaque area as having an aggregation state, and determine the tissue resection method as the recommended operation method for performing medical operations on the plaque area; when the regional aggregation value is greater than the preset aggregation threshold, it means that the shape of the plaque area is relatively uneven, so the server will determine the plaque area as having a dispersed state, and determine the stent filling method as the recommended operation method for performing medical operations on the plaque area.

[0045] In step S108, the following contents are included: A surgical operation model corresponding to the three-dimensional ultrasound image is constructed based on the digital twin technology, and based on the recommended operation method, the medical staff is instructed to perform a simulated operation on the model part corresponding to the plaque area in the surgical operation model.

[0046] For example, in this embodiment, the server will construct a surgical operation model corresponding to the patient's three-dimensional ultrasound image based on digital twin technology, and instruct the medical staff to perform simulated surgery on the model part corresponding to the plaque area in the surgical operation model according to the recommended operation method.

[0047] Furthermore, the above-mentioned “building a surgical operation model corresponding to the three-dimensional ultrasound image based on the digital twin technology, and instructing the medical end to perform a simulated operation on the model part corresponding to the plaque area in the surgical operation model based on the recommended operation method” also includes the following steps: Performing coordinate processing on the three-dimensional ultrasound image based on the horizontal reference line to obtain a three-dimensional image coordinate system, wherein any one of an X axis, a Y axis or a Z axis in the three-dimensional image coordinate system is parallel to the horizontal reference line; Based on the three-dimensional image coordinate system, each plaque coordinate point constituting the plaque area is obtained, and the X-axis extreme value coordinate point corresponding to the X-axis, the Y-axis extreme value coordinate point corresponding to the Y-axis, and the Z-axis extreme value coordinate point corresponding to the Z-axis located at each plaque coordinate point are respectively obtained, and a rectangular enclosing block enclosing the plaque area is generated based on the corresponding X-axis extreme value coordinate point, the corresponding Y-axis extreme value coordinate point, and the corresponding Z-axis extreme value coordinate point; Acquire an enclosing center point corresponding to the rectangular enclosing block, and magnify the enclosing center point by a preset multiple to obtain an enlarged enclosing block; Acquire digital twin data corresponding to the enlarged enclosing block, and construct a surgical operation model corresponding to the enlarged enclosing block based on the digital twin data; Establishing an operation display interface, wherein the operation display interface includes an operation interaction sub-interface and an operation display sub-interface; Filling the surgical operation model into the operation display sub-interface for display; Based on the recommended operation mode, different operation nodes corresponding to the recommended attributes are generated in the operation interaction sub-interface, and based on the different operation nodes corresponding to the recommended attributes, the medical staff is instructed to perform simulated surgery on the model part corresponding to the plaque area in the surgical operation model.

[0048] For example, in this embodiment, since the three-dimensional ultrasound image is acquired based on the patient's carotid artery tissue, more carotid artery tissue will be displayed in the three-dimensional ultrasound image. However, the plaque area may only occupy a small part of the three-dimensional ultrasound image. Therefore, the server will perform regional cropping on the three-dimensional ultrasound image to facilitate subsequent corresponding processing of the plaque area.

[0049] First, the server will coordinate the three-dimensional ultrasound image according to the horizontal reference line to obtain a three-dimensional image coordinate system, and any one of the X-axis, Y-axis or Z-axis in the three-dimensional image coordinate system is parallel to the horizontal reference line. At this time, the server will obtain the coordinate points of each plaque area according to the three-dimensional image coordinate system, and respectively obtain the X-axis extreme value coordinate point corresponding to the X-axis, the Y-axis extreme value coordinate point corresponding to the Y-axis, and the Z-axis extreme value coordinate point corresponding to the Z-axis in each plaque coordinate point, and then generate a rectangular enclosing block enclosing the plaque area based on the corresponding X-axis extreme value coordinate point, the corresponding Y-axis extreme value coordinate point, and the corresponding Z-axis extreme value coordinate point.

[0050] Since it is necessary to take into account that part of the plaque area may fall off when the plaque area is subsequently processed accordingly, in order to be able to observe the specific situation of the falling of part of the plaque area, the server will obtain the center point of the rectangular enclosing block, and then magnify the center point by a preset multiple to obtain an enlarged enclosing block, and then obtain the digital twin data corresponding to the enlarged enclosing block, so as to construct a surgical operation model corresponding to the enlarged enclosing block based on the digital twin data.

[0051] Next, the server will create an operation display interface, such as Figure 2 As shown, the operation display interface includes an operation interaction sub-interface and an operation display sub-interface. The server will fill the surgical operation model into the operation display sub-interface and display it, and generate various operation nodes corresponding to the recommended attributes in the operation interaction sub-interface according to the recommended operation method, such as various surgical operation tools such as scalpels. And the server will instruct the medical end to perform simulated surgery on the model part corresponding to the plaque area in the surgical operation model according to the various operation nodes corresponding to the recommended attributes.

[0052] Furthermore, the above-mentioned "generating different operation nodes corresponding to the recommended attributes in the operation interaction sub-interface based on the recommended operation mode, and instructing the medical terminal to perform a simulated operation on the model part corresponding to the plaque area in the surgical operation model based on the different operation nodes corresponding to the recommended attributes" also includes the following steps: A hierarchical distribution tree is established in the operation interaction sub-interface based on preset simulated surgical data corresponding to the tissue resection method and the stent filling method, wherein the hierarchical distribution tree includes different surgical method nodes corresponding to the parent level, and operation nodes corresponding to the child level generated downward based on each surgical method node; Determining the attributes of each node based on the recommended operation mode to obtain operation attributes corresponding to each node, wherein the operation attributes include recommended attributes and non-recommended attributes; In response to the medical end's interaction with any node, the node is determined as a target node, and based on the fact that the operation attribute of the target node is a non-recommended attribute, the medical end is indicated with a node whose corresponding operation attribute is a recommended attribute and is located at the same level as the target node, so as to perform a simulated surgery on the model portion corresponding to the plaque area in the surgical operation model.

[0053] For example, in this embodiment, the server will first establish a hierarchical distribution tree in the operation interaction sub-interface according to the preset simulated surgical data of the tissue resection method and the stent filling method. The hierarchical distribution tree includes different surgical method nodes corresponding to the parent level, that is, the surgical method node A corresponding to the tissue resection method and the surgical method node B corresponding to the stent filling method; the hierarchical distribution tree also includes the corresponding child level operation nodes generated downward from each surgical method node, such as the operation node A-1 corresponding to the scalpel, the operation node A-2 corresponding to the forceps, and other operation nodes corresponding to different surgical operation tools.

[0054] The server will determine the attributes of each node according to the recommended operation method, thereby obtaining the operation attributes corresponding to each node, and the operation attributes include recommended attributes and non-recommended attributes. For example, if the recommended operation method is tissue resection, the server will determine the surgical method node corresponding to the tissue resection method as a recommended attribute, and determine the surgical method node corresponding to the stent filling method as a non-recommended attribute.

[0055] When the medical terminal interacts with any of the surgical method nodes and operation nodes, the server will determine the node as the target node. When the operation attribute of the target node is a non-recommended attribute, the server will indicate to the medical terminal the node with the recommended attribute corresponding to the operation attribute at the same level as the target node. For example, when the surgical method node corresponding to the tissue resection method is a recommended attribute, but the medical terminal clicks on an operation node generated downward from the surgical method node corresponding to the stent filling method, the server will indicate to the medical terminal the operation node generated downward from the surgical method node corresponding to the tissue resection method, so that the medical terminal can smoothly perform simulated surgery on the model part corresponding to the plaque area in the surgical operation model, thereby improving the success rate of simulated surgery.

[0056] Furthermore, the above-mentioned "in response to the interaction of the medical end with any node, determining the node as a target node, and based on the operation attribute of the target node being a non-recommended attribute, indicating to the medical end a node whose corresponding operation attribute is a recommended attribute and is located at the same level as the target node, so as to perform a simulated surgery on the model portion corresponding to the plaque area in the surgical operation model", further includes the following steps: In response to the medical terminal interacting with any node for a preset time, determining the node as a target node, and determining an operation attribute corresponding to the target node; When the operation attribute of the target node is a non-recommended attribute, performing multi-dimensional specification adjustment on nodes whose corresponding operation attributes are recommended attributes and are located at the same level as the target node in the hierarchical distribution tree; When the operation attribute of the target node is a recommended attribute, a data display sub-interface is created in the operation display interface, and the obtained feature data corresponding to different dimensions are filled into the data display sub-interface for display; Based on the interaction of the medical end with the node whose corresponding operation attribute is the recommended attribute, a simulated operation is performed on the model part corresponding to the plaque area in the surgical operation model.

[0057] For example, in this embodiment, when the medical staff interacts with any node for a preset time, the server will determine the node as a target node and determine the operation attribute corresponding to the target node.

[0058] When the operation attribute of the target node is a non-recommended attribute, the server will make multi-dimensional specification adjustments to the nodes whose corresponding operation attributes are recommended attributes and are located at the same level as the target node in the hierarchical distribution tree, such as enlarging the size of the node or changing the color of the node, so as to improve a certain degree of identification.

[0059] When the operation attribute of the target node is a recommended attribute, the server will create a data display sub-interface on the operation display interface, so as to fill the obtained feature data corresponding to different dimensions into the data display sub-interface and display them.

[0060] Next, when the medical staff interacts with the node whose corresponding operation attribute is the recommended attribute, the server performs a simulated operation on the model part corresponding to the plaque area in the surgical operation model.

[0061] Furthermore, the above-mentioned “based on the interaction of the medical end with the node whose corresponding operation attribute is the recommended attribute, performing a simulated operation on the model portion corresponding to the plaque area in the surgical operation model” also includes the following steps: Based on the interaction of the medical terminal with the surgical method node whose corresponding operation attribute is a recommended attribute, hiding the surgical method node whose corresponding operation attribute is a non-recommended attribute in the hierarchical distribution tree; Based on the interaction of the medical terminal with the operation node whose corresponding operation attribute is a recommended attribute, calling the node tool corresponding to the operation node; In response to the medical end performing a simulated surgery on the model portion corresponding to the plaque area in the surgical operation model based on the node tool, obtaining peripheral impact data corresponding to the simulated surgery; Model modification is performed on other parts of the surgical operation model except the model part based on the peripheral influence data.

[0062] For example, in this embodiment, when the medical staff interacts with the node whose corresponding operation attribute is a recommended attribute, the server hides the surgical method node whose corresponding operation attribute is a non-recommended attribute in the hierarchical distribution tree.

[0063] Furthermore, when the medical terminal interacts with an operation node whose corresponding operation attribute is a recommended attribute, the server will call the node tool corresponding to the operation node. For example, when the medical terminal interacts with the operation node of a scalpel, the server will call the scalpel so that the medical terminal can use the scalpel to perform a simulated operation on the model part corresponding to the plaque area in the surgical operation model.

[0064] Since part of the plaque area may fall off and flow with the blood, the server will also obtain the peripheral impact data corresponding to the simulated surgery, so as to display the situation of part of the plaque area falling off accordingly. That is, the model of other parts except the model part in the surgical operation model is modified according to the peripheral impact data to ensure the integrity of the simulated surgery.

[0065] Furthermore, in this embodiment, when the medical staff performs the corresponding simulated surgery on the surgical operation model, in order to monitor the operation process to determine whether the simulated surgery of the medical staff meets the corresponding medical standards, the following technical solutions can also be adopted: Determine a surgical operation surface for the medical staff to perform a simulated operation on the surgical operation model based on the node tool, and map a model portion corresponding to the plaque area in the surgical operation model to the surgical operation surface to form a plaque mapping contour; Determining a surgical section contour corresponding to the surgical operation surface based on the simulated surgery, and comparing the surgical section contour with the plaque mapping contour; In response to the surgical section contour and the plaque mapping contour having a partial overlapping relationship, a mapping contour segment located in the plaque mapping contour and not overlapping with the surgical section contour is flashed and displayed on the surgical operation surface based on a preset frequency; In response to the surgical section contour not having an overlapping relationship with the plaque mapping contour, displaying the plaque mapping contour on the surgical operation surface by flashing at a preset frequency; In response to the surgical section contour covering the plaque mapping contour, a difference is calculated between a first contour area corresponding to the surgical section contour and a second contour area corresponding to the plaque mapping contour, and when the obtained area difference is greater than the preset area difference, the plaque mapping contour is displayed on the surgical operation surface by flashing based on a preset frequency.

[0066] For example, in the actual operation process, in order to be able to remove the plaque area located in the carotid artery tissue, it is necessary to first perform a corresponding opening operation to expose the corresponding carotid artery tissue, so that the plaque area can be removed. Based on this, it can be known that when the medical end performs the corresponding simulated operation on the surgical operation model, it is also necessary to perform the same opening operation. Since the surgical operation model is a corresponding rectangular shape, in order to facilitate the execution of the corresponding opening operation, the medical end will determine any model surface of the surgical operation model as a surgical operation surface based on the node tool to perform the corresponding simulated operation. Therefore, in this embodiment, the model can be determined as the corresponding surgical operation surface, and the model part corresponding to the plaque area in the surgical operation model is mapped to the surgical operation surface, thereby forming a corresponding plaque mapping contour, and further determine the surgical section contour of the corresponding surgical operation surface based on the simulated operation performed by the medical end; Under normal circumstances, in order to ensure that the plaque area is fully exposed, it is necessary to determine that the corresponding surgical section contour and the plaque mapping contour should be at least fully covered; and in order to determine whether the simulated surgery performed by the medical staff meets the corresponding medical standards, the surgical section contour can be compared with the plaque mapping contour; When the surgical section contour and the plaque mapping contour have a partial overlapping relationship, it indicates that the opening operation has not achieved complete exposure of the plaque area. Therefore, in order to give corresponding prompts to the medical staff, the mapping contour segment that is not overlapped with the surgical section contour in the plaque mapping contour can be displayed by flashing at a preset frequency, so that the medical staff can be prompted to improve the operation of the simulated surgery based on the dimension of visualization; When the surgical section contour and the plaque mapping contour have no overlapping relationship at all, the corresponding plaque mapping contour can also be displayed on the surgical operation surface by flashing at a preset frequency; When the surgical section contour covers the plaque mapping contour, it indicates that the opening operation can completely expose the plaque area, but a corresponding contour comparison between the surgical section contour and the plaque mapping contour is required to determine whether the surgical section contour is more matched with the plaque mapping contour. If the surgical section contour is much larger than the plaque mapping contour, it indicates that the surgical trauma area below the surgical operation model is too large, which also indicates that the simulated operation performed by the medical staff has not met the corresponding medical standards. Therefore, the first contour area corresponding to the surgical section contour and the second contour area corresponding to the plaque mapping contour can be obtained respectively, and the difference between the first contour area and the second contour area is calculated. When the obtained area difference is greater than the preset area difference, it indicates that the surgical section contour and the plaque mapping contour do not match. At this time, the plaque mapping contour will also be controlled to flash on the surgical operation surface based on a preset frequency, thereby indicating that the medical staff needs to make corresponding simulated surgical operation improvements.

[0067] Further, in this embodiment, the above-mentioned opening operation is based on the opening operation to determine whether the corresponding surgical section contour can achieve complete exposure of the plaque area. It is based on the surface dimension of the surgical section contour. After completing the acquisition of the surgical section contour, the medical end also needs to use the corresponding node tool to perform a model cutting based on the depth dimension based on the surgical section contour, so as to obtain the corresponding surgical section depth to determine whether the plaque area can be fully exposed. In order to determine whether the corresponding surgical section depth can meet the corresponding medical standards, the following method steps can be used: Acquiring a model mapping distance between a model portion corresponding to a plaque region and the surgical operation surface in the surgical operation model, and determining a surgical incision depth corresponding to the surgical operation surface based on the simulated surgery; Calculate the difference between the model mapping distance and the surgical section depth to obtain a distance difference; When the distance difference is not a positive number, determining a first surgical section corresponding to the simulated surgery in the surgical operation model based on the surgical section contour and the surgical section depth, and displaying the first surgical section in a color corresponding to a preset first pixel value; When the distance difference is a positive number and is greater than a preset distance difference, a second surgical section corresponding to the simulated surgery is determined in the surgical operation model based on the surgical section contour and the surgical section depth, and the second surgical section is displayed in a color corresponding to a preset second pixel value.

[0068] For example, in this embodiment, after obtaining the corresponding surgical incision depth, it is necessary to further obtain the model mapping distance between the model part corresponding to the plaque area and the surgical operation surface in the surgical operation model, and further perform a difference calculation between the model mapping distance and the surgical incision depth. When the obtained distance difference is not a positive number, it indicates that the medical end has cut too deep into the surgical operation surface. At this time, in order to prompt the medical end, the first surgical section corresponding to the simulated operation can be determined in the surgical operation model based on the surgical incision contour and the surgical incision depth, and the first surgical section is displayed in a color corresponding to the preset first pixel value. Here, the preset first pixel value can be a pixel value corresponding to red. Similarly, when the distance difference obtained is a positive number and is greater than the preset distance difference, it indicates that the cutting depth of the surgical operation surface by the medical staff is too shallow. At this time, in order to be able to prompt the medical staff, the second surgical section corresponding to the simulated operation can be determined in the surgical operation model based on the surgical section contour and the surgical section depth, and the second surgical section can be displayed in the color corresponding to the preset second pixel value. Here, the preset second pixel value can be the corresponding red pixel value.

[0069] Furthermore, in this embodiment, after the medical staff completes the simulated surgery on the surgical operation model, in order to judge the cleaning effect of the medical staff on the plaque area, it can be achieved based on the following method steps: In response to a surgery completion signal sent by the medical end based on the simulated surgery, determining a cleaning area corresponding to the model part based on the simulated surgery, and comparing the retrieved model area corresponding to the model part with the cleaning area; When the model area is larger than the clearing area, all parts except the model part corresponding to the plaque area are hidden and displayed in the surgical operation model.

[0070] For example, in this embodiment, when the medical end determines that the simulated operation has been completed, a corresponding operation completion signal can be sent to the server, so that the server will determine the cleaning area of ​​the model part corresponding to the plaque area in the surgical operation model based on the simulated operation, and retrieve the model area corresponding to the model part; the cleaning area is compared with the model area. When the model area is larger than the cleaning area, it indicates that the medical end has not completely cleaned the plaque area. At this time, in order to facilitate the medical end to understand the location of the area that has not been cleaned, the model part of the corresponding model area can be determined in the surgical operation model, and further all parts except the model part corresponding to the plaque area can be hidden and displayed in the surgical operation model, so as to help the medical end to make subsequent surgical improvements and improve the corresponding medical assistance effect.

[0071] According to the solution of the present invention, the server will first collect images of the patient's carotid artery tissue by means of ultrasonic imaging, thereby obtaining a three-dimensional ultrasonic image corresponding to the carotid artery tissue. After the server performs image recognition on the three-dimensional ultrasonic image, it can determine the plaque area corresponding to the carotid plaque located in the carotid artery tissue. Then, the server will perform multi-dimensional feature extraction on the plaque area, thereby obtaining two feature data corresponding to different dimensions, namely the length and thickness of the plaque area. And the server can determine the morphological attributes of the plaque area in two ways, thereby generating a recommended operation method for performing medical operations on the plaque area. Then, the server will construct a surgical operation model corresponding to the patient's three-dimensional ultrasonic image based on digital twin technology, and instruct the medical end to perform simulated surgery on the model part corresponding to the plaque area in the surgical operation model according to the recommended operation method. The present invention can improve the success rate of simulated surgery, thereby providing a certain reference for medical staff.

[0072] Another embodiment of the present invention provides a carotid artery plaque image processing system based on ultrasound imaging. Figure 3 As the corresponding system block diagram, the system includes: An image acquisition module is configured to acquire an image of the patient's carotid artery tissue based on ultrasound images to obtain a three-dimensional ultrasound image corresponding to the carotid artery tissue; a feature extraction module configured to perform image recognition based on the three-dimensional ultrasound image, determine a plaque area corresponding to a carotid plaque located in the carotid artery tissue, and perform multi-dimensional feature extraction on the plaque area to obtain feature data corresponding to different dimensions; an operation determination module, configured to determine the morphological attributes of the plaque area based on the feature data corresponding to the different dimensions, and generate a recommended operation mode for performing a medical operation on the plaque area based on the morphological attributes; The simulated surgery module is configured to construct a surgical operation model corresponding to the three-dimensional ultrasound image based on the digital twin technology, and to instruct the medical staff to perform a simulated surgery on the model part corresponding to the plaque area in the surgical operation model based on the recommended operation method.

[0073] In the description provided herein, algorithms and displays are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the examples of the present invention. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to implement the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the preferred embodiment of the present invention.

[0074] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0075] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof.

[0076] Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in the devices described in the embodiment, or alternatively may be located in one or more devices different from the devices in the examples. The modules in the foregoing examples may be combined into one module or may be divided into multiple submodules.

[0077] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of submodules or subunits or subcomponents.

[0078] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features from different embodiments is meant to be within the scope of the present invention and to form different embodiments.

[0079] In addition, some of the embodiments are described herein as methods or combinations of method elements that can be implemented by a processor of a computer system or by other devices that perform the functions. Therefore, a processor with necessary instructions for implementing the method or method elements forms a device for implementing the method or method elements. In addition, the elements described herein of the device embodiments are examples of devices for implementing the functions performed by the elements for the purpose of implementing the invention.

[0080] As used herein, unless otherwise specified, the use of ordinal numbers "first," "second," "third," etc. to describe common objects merely indicates that different instances of similar objects are involved, and is not intended to imply that the objects so described must have a given order in time, space, order, or in any other manner.

[0081] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is primarily selected for readability and instructional purposes, rather than for explaining or limiting the subject matter of the present invention.

Claims

1. A method for processing carotid artery plaque images based on ultrasound imaging, characterized in that: The following steps are involved: Acquiring an ultrasound-based image of the patient's carotid artery tissue to obtain a three-dimensional ultrasound image corresponding to the carotid artery tissue; Performing image recognition based on the three-dimensional ultrasound image to determine a plaque area corresponding to a carotid plaque located in the carotid artery tissue, and performing multi-dimensional feature extraction on the plaque area to obtain feature data corresponding to different dimensions; Determining the morphological attributes of the plaque area based on the feature data corresponding to the different dimensions, and generating a recommended operation method for performing a medical operation on the plaque area based on the morphological attributes; A surgical operation model corresponding to the three-dimensional ultrasound image is constructed based on the digital twin technology, and based on the recommended operation method, the medical staff is instructed to perform a simulated operation on the model part corresponding to the plaque area in the surgical operation model.

2. The method for processing carotid artery plaque images based on ultrasound imaging according to claim 1, characterized in that: Performing image recognition based on the three-dimensional ultrasound image to determine a plaque area corresponding to a carotid plaque located in the carotid artery tissue, and performing multi-dimensional feature extraction on the plaque area to obtain feature data corresponding to different dimensions, including: Inputting the three-dimensional ultrasound image into a trained image recognition model for image recognition to determine a plaque area corresponding to a carotid artery plaque located in the carotid artery tissue; Determine a carotid artery region having an attachment relationship with the plaque region in the three-dimensional ultrasound image, and acquire a first region endpoint and a second region endpoint corresponding to the carotid artery region based on a tissue extension direction of the carotid artery tissue; Connecting the first region endpoint and the second region endpoint, and determining the obtained endpoint connection line as the horizontal reference line; Based on the horizontal reference line, multi-dimensional feature extraction is performed on the patch area to obtain feature data corresponding to different dimensions.

3. The method for processing carotid artery plaque images based on ultrasound imaging according to claim 2, characterized in that: Based on the horizontal reference line, multi-dimensional feature extraction is performed on the plaque area to obtain feature data corresponding to different dimensions, including: Performing feature extraction based on the length dimension based on the horizontal reference line to obtain the line segment length corresponding to the horizontal reference line, and retrieving the reference point multiple; The length of the line segment is multiplied by the multiple of the reference point to obtain the number of point divisions; Dividing the horizontal reference line into points along the extension direction of the horizontal reference line to obtain line segment points corresponding to the number of point divisions, wherein adjacent line segment points have the same point distance; Mapping each line segment point to the corresponding plaque area along a direction perpendicular to the extension direction to obtain each regional point located on the plaque area, and performing feature extraction based on the thickness dimension based on each regional point to obtain the thickness of each regional point from each point on the horizontal reference line; The length of the line segment is determined as the characteristic data of the length dimension corresponding to the plaque area, and the thickness of each point is determined as the characteristic data of the thickness dimension corresponding to the plaque area.

4. The method for processing carotid artery plaque images based on ultrasound imaging according to claim 3, characterized in that: Determining the morphological attributes of the plaque area based on the feature data corresponding to different dimensions, and generating a recommended operation method for performing a medical operation on the plaque area based on the morphological attributes, including: Based on the thickness of each point corresponding to each point in each area, the average thickness is calculated to obtain the average thickness; Acquiring the area based on the plaque area to obtain the area of ​​the region corresponding to the plaque area, and calculating the ratio of the area of ​​the region to the mean thickness to obtain the aggregation length; Calculate the difference between the aggregate length and the line segment length to obtain a length difference, and compare the length difference with the retrieved preset difference interval; When the length difference is within the preset difference interval, the plaque area is determined to be in an aggregation state, and the tissue resection method is determined as a recommended operation method for performing a medical operation on the plaque area; When the length difference is outside the preset difference interval, the plaque region is determined to be in a dispersed state, and the stent filling method is determined to be a recommended operation method for performing a medical operation on the plaque region.

5. The method for processing carotid artery plaque images based on ultrasound imaging according to claim 3, characterized in that: Determining the morphological attributes of the plaque area based on the feature data corresponding to different dimensions, and generating a recommended operation method for performing a medical operation on the plaque area based on the morphological attributes, including: Based on the thickness of each point corresponding to each point in each area, the average thickness is calculated to obtain the average thickness; Calculate the difference between the thickness of each point and the average thickness to obtain the thickness difference; The thickness differences are summed up to obtain the total value of the differences; Calculate the ratio of the total difference value to the number of point divisions to obtain a regional aggregation value, and compare the regional aggregation value with a preset aggregation threshold; When the regional aggregation value is less than or equal to the preset aggregation threshold, the plaque region is determined to be in an aggregation state, and the tissue resection method is determined as a recommended operation method for performing a medical operation on the plaque region; When the regional aggregation value is greater than the preset aggregation threshold, the plaque region is determined to be in a dispersed state, and the stent filling method is determined as a recommended operation method for performing a medical operation on the plaque region.

6. The method for processing carotid artery plaque images based on ultrasound imaging according to claim 4 or 5, characterized in that: A surgical operation model corresponding to the three-dimensional ultrasound image is constructed based on the digital twin technology, and based on the recommended operation mode, a medical staff is instructed to perform a simulated operation on a model portion corresponding to the plaque area in the surgical operation model, including: Performing coordinate processing on the three-dimensional ultrasound image based on the horizontal reference line to obtain a three-dimensional image coordinate system, wherein any one of an X axis, a Y axis or a Z axis in the three-dimensional image coordinate system is parallel to the horizontal reference line; Based on the three-dimensional image coordinate system, each plaque coordinate point constituting the plaque area is obtained, and the X-axis extreme value coordinate point corresponding to the X-axis, the Y-axis extreme value coordinate point corresponding to the Y-axis, and the Z-axis extreme value coordinate point corresponding to the Z-axis located at each plaque coordinate point are respectively obtained, and a rectangular enclosing block enclosing the plaque area is generated based on the corresponding X-axis extreme value coordinate point, the corresponding Y-axis extreme value coordinate point, and the corresponding Z-axis extreme value coordinate point; Acquire an enclosing center point corresponding to the rectangular enclosing block, and magnify the enclosing center point by a preset multiple to obtain an enlarged enclosing block; Acquire digital twin data corresponding to the enlarged enclosing block, and construct a surgical operation model corresponding to the enlarged enclosing block based on the digital twin data; Establishing an operation display interface, wherein the operation display interface includes an operation interaction sub-interface and an operation display sub-interface; Filling the surgical operation model into the operation display sub-interface for display; Based on the recommended operation mode, different operation nodes corresponding to the recommended attributes are generated in the operation interaction sub-interface, and based on the different operation nodes corresponding to the recommended attributes, the medical staff is instructed to perform simulated surgery on the model part corresponding to the plaque area in the surgical operation model.

7. The method for processing carotid artery plaque images based on ultrasound imaging according to claim 6, characterized in that: Generating different operation nodes corresponding to the recommended attributes in the operation interaction sub-interface based on the recommended operation mode, and instructing the medical terminal to perform a simulated operation on the model part corresponding to the plaque area in the surgical operation model based on the different operation nodes corresponding to the recommended attributes, including: A hierarchical distribution tree is established in the operation interaction sub-interface based on preset simulated surgical data corresponding to the tissue resection method and the stent filling method, wherein the hierarchical distribution tree includes different surgical method nodes corresponding to the parent level, and operation nodes corresponding to the child level generated downward based on each surgical method node; Determining the attributes of each node based on the recommended operation mode to obtain operation attributes corresponding to each node, wherein the operation attributes include recommended attributes and non-recommended attributes; In response to the medical end's interaction with any node, the node is determined as a target node, and based on the fact that the operation attribute of the target node is a non-recommended attribute, the medical end is indicated with a node whose corresponding operation attribute is a recommended attribute and is located at the same level as the target node, so as to perform a simulated surgery on the model portion corresponding to the plaque area in the surgical operation model.

8. The method for processing carotid artery plaque images based on ultrasound imaging according to claim 7, characterized in that: In response to the interaction of the medical end with any node, the node is determined as a target node, and based on the operation attribute of the target node being a non-recommended attribute, a node whose corresponding operation attribute is a recommended attribute and is located at the same level as the target node is indicated to the medical end, so as to perform a simulated surgery on a model portion corresponding to the plaque area in the surgical operation model, including: In response to the medical terminal interacting with any node for a preset time, determining the node as a target node, and determining an operation attribute corresponding to the target node; When the operation attribute of the target node is a non-recommended attribute, performing multi-dimensional specification adjustment on nodes whose corresponding operation attributes are recommended attributes and are located at the same level as the target node in the hierarchical distribution tree; When the operation attribute of the target node is a recommended attribute, a data display sub-interface is created in the operation display interface, and the obtained feature data corresponding to different dimensions are filled into the data display sub-interface for display; Based on the interaction of the medical end with the node whose corresponding operation attribute is the recommended attribute, a simulated operation is performed on the model part corresponding to the plaque area in the surgical operation model.

9. The method for processing carotid artery plaque images based on ultrasound imaging according to claim 8, characterized in that: Based on the interaction of the medical end with the node whose corresponding operation attribute is the recommended attribute, a simulated operation is performed on the model part corresponding to the plaque area in the surgical operation model, including: Based on the interaction of the medical terminal with the surgical method node whose corresponding operation attribute is a recommended attribute, hiding the surgical method node whose corresponding operation attribute is a non-recommended attribute in the hierarchical distribution tree; Based on the interaction of the medical terminal with the operation node whose corresponding operation attribute is a recommended attribute, calling the node tool corresponding to the operation node; In response to the medical end performing a simulated surgery on the model portion corresponding to the plaque area in the surgical operation model based on the node tool, obtaining peripheral impact data corresponding to the simulated surgery; Model modification is performed on other parts of the surgical operation model except the model part based on the peripheral influence data.

10. The method for processing carotid artery plaque images based on ultrasound imaging according to claim 9, characterized in that: The method further comprises: Determine a surgical operation surface for the medical staff to perform a simulated operation on the surgical operation model based on the node tool, and map a model portion corresponding to the plaque area in the surgical operation model to the surgical operation surface to form a plaque mapping contour; Determining a surgical section contour corresponding to the surgical operation surface based on the simulated surgery, and comparing the surgical section contour with the plaque mapping contour; In response to the surgical section contour and the plaque mapping contour having a partial overlapping relationship, a mapping contour segment located in the plaque mapping contour and not overlapping with the surgical section contour is flashed and displayed on the surgical operation surface based on a preset frequency; In response to the surgical section contour not having an overlapping relationship with the plaque mapping contour, displaying the plaque mapping contour on the surgical operation surface by flashing at a preset frequency; In response to the surgical section contour covering the plaque mapping contour, a difference is calculated between a first contour area corresponding to the surgical section contour and a second contour area corresponding to the plaque mapping contour, and when the obtained area difference is greater than the preset area difference, the plaque mapping contour is displayed on the surgical operation surface by flashing based on a preset frequency.

11. The method for processing carotid artery plaque images based on ultrasound imaging according to claim 10, characterized in that: The method further comprises: Acquiring a model mapping distance between a model portion corresponding to a plaque region and the surgical operation surface in the surgical operation model, and determining a surgical incision depth corresponding to the surgical operation surface based on the simulated surgery; Performing difference calculation between the model mapping distance and the surgical section depth to obtain a distance difference; When the distance difference is not a positive number, determining a first surgical section corresponding to the simulated surgery in the surgical operation model based on the surgical section contour and the surgical section depth, and displaying the first surgical section in a color corresponding to a preset first pixel value; When the distance difference is a positive number and is greater than a preset distance difference, a second surgical section corresponding to the simulated surgery is determined in the surgical operation model based on the surgical section contour and the surgical section depth, and the second surgical section is displayed in a color corresponding to a preset second pixel value.

12. The method for processing carotid artery images based on ultrasonic imaging according to claim 11, characterized in that: The method further comprises: In response to a surgery completion signal sent by the medical end based on the simulated surgery, determining a cleaning area corresponding to the model part based on the simulated surgery, and comparing the retrieved model area corresponding to the model part with the cleaning area; When the model area is larger than the clearing area, all parts except the model part corresponding to the plaque area are hidden and displayed in the surgical operation model.

13. A carotid artery plaque image processing system based on ultrasound imaging, characterized in that: include: An image acquisition module is configured to acquire an image of the patient's carotid artery tissue based on ultrasound images to obtain a three-dimensional ultrasound image corresponding to the carotid artery tissue; a feature extraction module configured to perform image recognition based on the three-dimensional ultrasound image, determine a plaque area corresponding to a carotid plaque located in the carotid artery tissue, and perform multi-dimensional feature extraction on the plaque area to obtain feature data corresponding to different dimensions; an operation determination module, configured to determine the morphological attributes of the plaque area based on the feature data corresponding to the different dimensions, and generate a recommended operation mode for performing a medical operation on the plaque area based on the morphological attributes; The simulated surgery module is configured to construct a surgical operation model corresponding to the three-dimensional ultrasound image based on the digital twin technology, and to instruct the medical staff to perform a simulated surgery on the model part corresponding to the plaque area in the surgical operation model based on the recommended operation method.

Images