Processing method and device based on three-dimensional mesh model and related equipment

Abstract

The application provides a processing method and device based on a three-dimensional grid model and related equipment, a boundary pixel image representing a target tissue contour is determined, a discrete pixel image of the target tissue is determined based on the boundary pixel image, a triangular facet image of the target tissue is determined according to the positional relationship between the boundary pixel image and the discrete pixel image of the target tissue contour, a three-dimensional reconstruction of a stereoscopic image of the target tissue is performed using the triangular facet image based on the positional relationship between the centroid of the triangular facet image and the boundary pixel image, and a closed image of the target tissue is determined according to the three-dimensional reconstruction image. This method extracts pixel points on a target tissue contour image and corresponding discrete pixel images in a projection plane coordinate system, performs three-dimensional image reconstruction using a triangular facet image formed by the pixel points, removes noise points in the obtained target tissue image, and obtains a closed image with accurate details and good closure.

Description

TECHNICAL FIELD

[0001] The present application relates to the medical imaging field, and in particular to a processing method and device based on a three-dimensional mesh model and related equipment. BACKGROUND

[0002] With the aggravation of social aging and the increase of population, the demand for treatment of oral diseases such as teeth and gums is increasing. In the treatment process of patient lesion sites, such as tooth lesion sites, high-end medical equipment has been applied for treatment, especially for oral treatment. Tooth implant surgery robots have been used for high-precision assisted surgery. In order to improve the precision of dental implant surgery and other oral surgery treatments, it is often necessary to scan the patient's oral tissue to generate a three-dimensional modeling image of the patient's oral tissue to more accurately register with the positioning equipment used in surgery. However, in the prior art, when generating a three-dimensional model based on the acquired oral tissue, due to the difficulty in arranging the oral scanning equipment, the generated oral tissue image is not closed, and may also include some noise images that are not target tissues. The accuracy of the generated three-dimensional image is poor, and there is a certain difference between the actual target tissue image. Using the traditional method to determine the three-dimensional image for surgery will affect the effect of the doctor's surgery on the oral lesion site. SUMMARY

[0003] Therefore, the embodiments of the present application provide a processing method and device based on a three-dimensional mesh model and related equipment to at least partially solve the above problems.

[0004] In a first aspect, the embodiments of the present application provide a processing method based on a three-dimensional mesh model, comprising:

[0005] determining a boundary pixel image for representing a target tissue contour;

[0006] determining a discrete pixel image of the target tissue based on the boundary pixel image;

[0007] determining a triangular facet image of the target tissue according to the position relationship between the boundary pixel image and the discrete pixel image of the target tissue contour;

[0008] performing three-dimensional reconstruction on a three-dimensional image of the target tissue using the triangular facet image based on the position relationship between the centroid of the triangular facet image and the boundary pixel image;

[0009] determining a closed image of the target tissue according to the three-dimensional reconstructed image.

[0010] Optionally, in an embodiment of the present application, the determining the triangular facet image of the target tissue according to the positional relationship between the boundary pixel image of the target tissue contour and the discrete pixel image comprises:

[0011] performing a triangulation process based on the set of pixel points in the boundary pixel image of the target tissue contour and the set of pixel points in the discrete pixel image to obtain a triangular mesh image;

[0012] determining the triangular facet image of the target tissue according to the triangular mesh image and the positions of the corresponding centroids.

[0013] Optionally, in an embodiment of the present application, the determining the discrete pixel image of the target tissue based on the boundary pixel image comprises:

[0014] determining a projection plane image in the planar coordinates of the contour projection of the target tissue in the spatial coordinates;

[0015] segmenting the projection plane image based on the distances between the pixel points in the boundary pixel image;

[0016] determining the discrete pixel image according to the segmentation result.

[0017] Optionally, in an embodiment of the present application, the using the positional relationship between the centroid of the triangular facet image and the boundary pixel image to perform three-dimensional reconstruction on the stereoscopic image of the target tissue using the triangular facet to obtain a three-dimensional reconstruction image comprises:

[0018] eliminating the triangular facet image whose centroid is located outside the closed curve generated by the projection of the boundary pixel image to screen the triangular facet image;

[0019] mapping the triangular facet image retained after the screening to a three-dimensional space;

[0020] performing three-dimensional reconstruction on the stereoscopic image of the target tissue according to the mapping result and the positional relationship between the boundary pixel and the three-dimensional space.

[0021] Optionally, in an embodiment of the present application, the centroid is the center of the triangular facet image.

[0022] Optionally, in an embodiment of the present application, the determining the boundary pixel image for representing the contour of the target tissue comprises:

[0023] performing planar cutting on the target tissue;

[0024] The intersection pixel of the plane when being cut and the target tissue is taken as the boundary pixel image for representing the target tissue contour.

[0025] Optionally, in an embodiment of the present application, the step of determining the closed image of the target tissue according to the three-dimensional reconstruction image comprises:

[0026] The topology of the triangular facet contained in the three-dimensional reconstruction image is added to the target tissue to determine the closed image of the target tissue.

[0027] In a second aspect, based on the processing method based on the three-dimensional mesh model in the first aspect of the present application, an embodiment of the present application further provides a processing device based on a three-dimensional mesh model, comprising:

[0028] A first determining module is configured to determine a boundary pixel image for representing a target tissue contour;

[0029] A second determining module is configured to determine a discrete pixel image of the target tissue based on the boundary pixel image;

[0030] A segmentation module is configured to determine a triangular facet image of the target tissue according to the positional relationship between the boundary pixel image and the discrete pixel image of the target tissue contour;

[0031] A reconstruction module is configured to perform three-dimensional reconstruction on a stereoscopic image of the target tissue using the triangular facet image based on the positional relationship between the centroid of the triangular facet image and the boundary pixel image;

[0032] A closing module is configured to determine a closed image of the target tissue according to the three-dimensional reconstruction image.

[0033] In a third aspect, an embodiment of the present application further provides a storage medium having a computer program stored thereon, and the program is executed by a processor to implement the processing method based on the three-dimensional mesh model in any one of the first aspect of the present application.

[0034] The application provides a processing method and device based on a three-dimensional grid model and a storage medium, and the processing method based on the three-dimensional grid model comprises the following steps: determining a boundary pixel image for representing a target tissue contour, determining a discrete pixel image of the target tissue based on the boundary pixel image, determining a triangular facet image of the target tissue according to the position relationship between the boundary pixel image and the discrete pixel image of the target tissue contour, performing three-dimensional reconstruction on a stereoscopic image of the target tissue based on the position relationship between the centroid of the triangular facet image and the boundary pixel image, and determining a closed image of the target tissue according to the three-dimensional reconstruction image. The processing method based on the three-dimensional grid model disclosed in the application extracts the pixel points on the target tissue contour image and the corresponding discrete pixel image in the projection plane coordinate system, and performs three-dimensional image reconstruction according to the triangular facet image formed by the pixel points, so that the noise points in the target tissue image are removed, the details in the stereoscopic three-dimensional image for representing the target tissue are more accurate, the closedness is better, the accuracy of 3D printing of the target tissue is improved, the preoperative registration work is facilitated, such as a dental implant surgery, and the precision of the oral surgery is significantly improved. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art based on these drawings.

[0036] Figure 1 A workflow diagram of a processing method based on a three-dimensional grid model provided by the present application;

[0037] Figure 2 A structural schematic diagram of a processing device based on a three-dimensional grid model provided by the present application. DETAILED DESCRIPTION

[0038] In order to make the person in the art better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments in the present application should belong to the scope of protection of the present application.

[0039] It should be understood that the various steps in the method embodiments of the present application can be performed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit performing the steps shown. The scope of the present application is not limited in this regard.

[0040] Embodiment one,

[0041] The embodiment of the present application provides a processing method based on a three-dimensional grid model, such as Figure 1 As shown in the figure, Figure 1 The embodiment of the present application provides a workflow diagram of a processing method based on a three-dimensional grid model, which includes:

[0042] Step S101, determine the boundary pixel image for representing the target tissue contour.

[0043] Specifically, in an optional implementation of the embodiment of the present application, the boundary pixel image of the target tissue contour is obtained by projecting the acquired scan image of the target tissue in the three-dimensional space in the stereoscopic image. Specifically, in the scenario defined in the embodiment of the present application, the target tissue contour can be a three-dimensional grid model image obtained by projecting the scan image of the target tissue in the three-dimensional space. When the target tissue is scanned, due to the limitation of the scanning angle or the device field of view, there is a certain difference between the detail image contained in the obtained three-dimensional grid model image and the details of the real target tissue contour. The technical scheme of the embodiment of the present application improves the authenticity and detail integrity of the obtained image by acquiring the boundary pixel image for representing the target tissue contour and optimizing the image details of the three-dimensional grid model based on the boundary pixel image.

[0044] In the embodiment of the present application, the boundary pixel image is a collection of all pixel points for representing the outer contour of the target tissue in the three-dimensional space. Thus, the comprehensiveness of the target tissue contour information represented by the determined pixel image is ensured when the image processing is performed.

[0045] Optionally, in an implementation of the embodiment of the present application, the boundary pixel image for representing the target tissue contour is determined, including: performing plane cutting on the target tissue, and taking the intersection pixels of the plane cutting and the target tissue as the boundary pixel image for representing the target tissue contour, also called the boundary point set of the target tissue image. The target tissue herein refers to a stereoscopic image composed of all pixels contained in the stereoscopic image obtained by projecting the scan image of the target tissue in the three-dimensional space. The embodiment of the present application can better ensure the integrity of the obtained pixel image for representing the target tissue contour information in this way.

[0046] In the use scenario of the embodiment of the present application, the outer contour of the target tissue is not regular, and in the obtained boundary pixel image for representing the contour of the target tissue, the pixel points are not necessarily uniformly distributed in the three-dimensional space. For example, when the outer contour of the target tissue is not uniform or not smooth enough, there can be one or more concave-convex surfaces or burrs. In the three-dimensional image of the target tissue obtained by scanning the target tissue, there are some pixel images for representing the positions of the concave-convex surfaces or burrs. The positions of these pixel images are discrete pixel images that are relatively discrete in the image of the target tissue. At this time, the discrete pixel images are identified and positioned, and are added to the three-dimensional image of the target tissue, so as to further ensure the accuracy of details in the determined three-dimensional image of the target tissue, and make the details of the three-dimensional image more real and more consistent with the actual situation.

[0047] Optionally, in an embodiment of the present application, the determining the discrete pixel image of the target tissue based on the boundary pixel image comprises: projecting the contour of the target tissue in the spatial coordinates into the planar coordinates to determine a projection planar image, segmenting the projection planar image based on the distances between the pixel points in the boundary pixel image, and determining the discrete pixel image according to the segmentation result. In this way, the contour pixel image for representing the non-uniform distribution of the contour surface pixels is determined based on the distances between the projected pixel points, and the abnormal image pixels such as noise points are removed, so as to ensure the integrity of the details of the three-dimensional image of the target tissue determined finally, and to reduce the data amount of image pixels to be processed in the image processing process to a certain extent, that is, to reduce the image data processing calculation amount and complexity in the three-dimensional reconstruction process, and to improve the efficiency of the three-dimensional reconstruction of the target tissue.

[0048] Step S103: determining a triangular facet image of the target tissue according to the positional relationship between the boundary pixel image and the discrete pixel image of the contour of the target tissue. In the polygon mesh facet, the triangular facet is the smallest unit of segmentation, and is relatively simple, flexible and convenient for topological description. In this embodiment, the positional relationship between the determined boundary pixel image and the discrete pixel is used to reconstruct and perfect the space of the target tissue in the manner of constructing the triangular facet image, so that the finally determined three-dimensional image can be more consistent with the actual situation of the target tissue.

[0049] Optionally, in an embodiment of the present application, the position relationship between the boundary pixel image of the target tissue contour and the discrete pixel image is used to determine the triangular facet image of the target tissue, which includes: performing a triangulation process based on the set of pixel points in the boundary pixel image of the target tissue contour and the set of pixel points in the discrete pixel image to obtain a triangular mesh image, and determining the triangular facet image of the target tissue according to the position of the triangular mesh image and the corresponding centroid. It is known from the study of topology that any surface can be triangulated. In the embodiment of the present application, the target tissue contour is meshed by the triangulation process, so that the details of the target tissue contour are more accurate.

[0050] In step S104, the triangular facet image is used to perform three-dimensional reconstruction on the stereoscopic image of the target tissue based on the position relationship between the centroid of the triangular facet image and the boundary pixel image. In the embodiment of the present application, the triangular facet image representing the minimum unit of the target tissue is used to determine its spatial position according to the position relationship between its centroid and the boundary pixel image, and then three-dimensional reconstruction is performed, which can completely and accurately depict the stereoscopic topological structure of the target contour tissue, so that the stereoscopic model of the target tissue constructed using the topological structure can be processed, such as 3D printing, to ensure the consistency between the real stereoscopic model printed by 3D printing and the details of the target tissue.

[0051] Optionally, in an embodiment of the present application, based on the position relationship between the centroid of the triangular facet image and the boundary pixel image, the three-dimensional reconstruction of the stereoscopic image of the target tissue using the triangular facet image comprises: eliminating the triangular facet image whose centroid is located outside the closed curve generated by the projection of the boundary pixel, screening the triangular facet image, mapping the triangular facet image retained after the screening to the three-dimensional space, and performing the three-dimensional reconstruction of the stereoscopic image of the target tissue according to the mapping result and the position relationship between the boundary pixel and the three-dimensional space. In the implementation scenario of the embodiment of the present application, there may be a triangular facet image of the target tissue which is not a segmentation image representing the target tissue, but an image data containing all the boundary pixels and the discrete pixels generated according to the position relationship between the boundary pixel image and the discrete pixel image. If all the triangular facet images contained in this data are used for three-dimensional reconstruction, the accuracy of the three-dimensional reconstruction image representing the contour of the target tissue will be seriously affected. At this time, it is necessary to screen the triangular facet image before three-dimensional reconstruction. The embodiment of the present application determines the position relationship between the centroid position of each triangular facet image and the closed curve generated by the projection of the corresponding boundary pixel, and retains the triangular facet image if the centroid position is within the closed curve generated by the mapping of the boundary pixel to the three-dimensional space, and determines the triangular facet image corresponding to the centroid as an abnormal image if the centroid position is not within the closed curve, and eliminates the triangular facet outside the contour of the target tissue, thereby realizing the screening of the triangular facet image, and making the three-dimensional reconstruction image directly related to the image details of the target tissue.

[0052] Optionally, in an embodiment of the present application, the centroid is the center of the triangular facet. This implementation process is simpler, improves the efficiency of determining the centroid of the triangular facet, and improves the efficiency of the processing method based on the three-dimensional grid model provided by the embodiment of the present application for constructing the closed image of the target tissue.

[0053] Step S105, determining the closed image of the target tissue according to the three-dimensional reconstruction image.

[0054] Optionally, in an embodiment of the present application, the determination of the closed image of the target tissue according to the three-dimensional reconstruction image comprises: adding the topological structure of the triangular facet contained in the three-dimensional reconstruction image to the target tissue contour image obtained by scanning, and determining the closed image of the target tissue. Through this method, the embodiment of the present application makes the determined target tissue contour image have good closure, and the details of the contour are more consistent with the real image, which is convenient for the printing use of the three-dimensional grid model image generated in the scene of 3D printing and the like which is more consistent with the real target tissue.

[0055] The application provides a processing method based on a three-dimensional grid model, including: determining a boundary pixel image for representing a target tissue contour, determining a discrete pixel image of the target tissue based on the boundary pixel image, determining a triangular facet image of the target tissue according to a positional relationship between the boundary pixel image and the discrete pixel image of the target tissue contour, performing three-dimensional reconstruction on a stereoscopic image of the target tissue by using the triangular facet image based on a positional relationship between a centroid of the triangular facet image and the boundary pixel image, generating a three-dimensional reconstruction image, and determining a closed image of the target tissue according to the three-dimensional reconstruction image. The processing method based on the three-dimensional grid model disclosed in the embodiments of the application removes noise points in a target tissue image obtained by scanning, makes details in a three-dimensional image for representing the target tissue more accurate, and has better closure, is helpful to the accuracy of 3D printing of the target tissue, and is convenient for preoperative registration, such as dental surgery, and improves the precision of oral surgery.

[0056] Embodiment two:

[0057] Based on the processing method based on the three-dimensional grid model of the first aspect of the application, the embodiments of the application further provide a processing device based on the three-dimensional grid model, as shown in Figure 2 Figure 2 FIG. 2 is a structural schematic diagram of a processing device 20 based on the three-dimensional grid model provided in Embodiment 2 of the application, and the processing device 20 based on the three-dimensional grid model includes:

[0058] A first determining module 201 is configured to determine a boundary pixel image for representing a target tissue contour.

[0059] A second determining module 202 is configured to determine a discrete pixel image of the target tissue based on the boundary pixel image.

[0060] A segmentation module 203 is configured to determine a triangular facet image of the target tissue according to a positional relationship between the boundary pixel image and the discrete pixel image of the target tissue contour.

[0061] A reconstruction module 204 is configured to perform three-dimensional reconstruction on a stereoscopic image of the target tissue by using the triangular facet image based on a positional relationship between a centroid of the triangular facet image and the boundary pixel image, and generate a three-dimensional reconstruction image.

[0062] A closing module 205 is configured to determine a closed image of the target tissue according to the three-dimensional reconstruction image.

[0063] ​Optionally, in an implementation form of the embodiment of the application, the segmentation module 203 is further configured to:

[0064] triangulate the set of pixels in the boundary pixel image of the target tissue contour and the set of pixels in the discrete pixel image to obtain a triangular mesh image;

[0065] determine a triangular patch image of the target tissue according to the triangular mesh image and the positions of the corresponding centroids.

[0066] Optionally, in an implementation form of the embodiment of the application, the segmentation module 203 is further configured to:

[0067] project the contour of the target tissue in the spatial coordinates into a planar coordinate to determine a projection plane image;

[0068] segment the projection plane image based on distances between the pixels in the boundary pixel image;

[0069] determine the discrete pixel image according to the segmentation result.

[0070] Optionally, in an implementation form of the embodiment of the application, the reconstruction module 204 is further configured to:

[0071] cull triangular patches whose centroids are located outside a closed curve generated by projecting the boundary pixel image, and filter the triangular patch image;

[0072] map the triangular patch image retained after the filtering to a three-dimensional space;

[0073] perform three-dimensional reconstruction on a three-dimensional image of the target tissue according to a mapping result and a positional relationship of the boundary pixels in the three-dimensional space.

[0074] Optionally, in an implementation form of the embodiment of the application, the centroid is a center of the triangular patch.

[0075] Optionally, in an implementation form of the embodiment of the application, the first determination module 201 is further configured to:

[0076] perform planar cutting on the target tissue;

[0077] determine the intersection pixels of the target tissue during the planar cutting as the boundary pixel image for representing the contour of the target tissue.

[0078] Optionally, in an implementation form of the embodiment of the application, the closing module 205 is further configured to:

[0079] add a topological structure of a triangular facet contained in the three-dimensional reconstruction image to the target tissue to determine a closed image of the target tissue.

[0080] The application provides a processing device based on a three-dimensional grid model. A first determining module is configured to determine a boundary pixel image representing a contour of a target tissue. A second determining module is configured to determine a discrete pixel image of the target tissue based on the boundary pixel image. A segmentation module is configured to determine a triangular facet image of the target tissue according to a positional relationship between the boundary pixel image and the discrete pixel image of the contour of the target tissue. A reconstruction module is configured to perform three-dimensional reconstruction on a stereoscopic image of the target tissue using the triangular facet image to generate a three-dimensional reconstruction image based on a positional relationship between a centroid of the triangular facet image and the boundary pixel image. A closing module is configured to determine a closed image of the target tissue according to the three-dimensional reconstruction image. The processing device based on the three-dimensional grid model disclosed in the embodiments of the application extracts pixel points on a contour image of a target tissue and corresponding discrete pixel images in a projection plane coordinate system, and reconstructs a three-dimensional image according to triangular facets formed by the pixel points, so that noise in a target tissue image obtained by scanning is removed, details in a three-dimensional image representing the target tissue are more accurate, the three-dimensional image is better closed, the working functions of the modules are targeted and orderly, the device is convenient for users to operate, the accuracy of 3D printing of the target tissue and the image processing efficiency are improved, and the closed image obtained by processing according to the embodiments of the application is convenient for preoperative registration work, such as oral surgery, and the precision of oral surgery is improved.

[0081] Embodiment three,

[0082] Based on the processing method based on the three-dimensional grid model described in Embodiment One of the application, the application further provides a storage medium having a computer program stored thereon, the program being executed by a processor to implement the processing method based on the three-dimensional grid model as described in any of the method embodiments of the application. The processing method based on the three-dimensional grid model includes but is not limited to:

[0083] determining a boundary pixel image representing a contour of a target tissue;

[0084] determining a discrete pixel image of the target tissue based on the boundary pixel image;

[0085] determining a triangular facet image of the target tissue according to a positional relationship between the boundary pixel image and the discrete pixel image of the contour of the target tissue;

[0086] based on a position relationship between the centroid of the triangular facet image and the boundary pixel image, performing three-dimensional reconstruction on a stereoscopic image of the target tissue using the triangular facet image to generate a three-dimensional reconstruction image;

[0087] based on the three-dimensional reconstruction image, determining a closed image of the target tissue.

[0088] To this end, specific embodiments of the present subject matter have been described herein. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0089] The systems, apparatuses, modules, or units illustrated by the above embodiments can be specifically implemented by a computer chip or entity, or by a product with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0090] For the sake of description, the above apparatuses are described in various units with functions respectively. Of course, the functions of the units can be implemented in one or more software and / or hardware in implementing the present application.

[0091] Those skilled in the art will understand that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer usable program code.

[0092] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, an element defined by the phrase "comprising a" does not exclude the existence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0093] The various embodiments in the specification are described in progressive manner, and the same or similar parts among the various embodiments can be mutually referred to, and each embodiment focuses on the difference from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiments.

[0094] The above merely describes the embodiments of the present application, and is not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A processing method based on a three-dimensional mesh model, characterized by, The method comprises the following steps: determining a boundary pixel image for representing a target tissue contour, comprising: performing planar cutting on the target tissue; and taking intersection pixels between the target tissue and the planar cutting as the boundary pixel image for representing the target tissue contour; determining a discrete pixel image of the target tissue based on the boundary pixel image, comprising: projecting the contour of the target tissue in a spatial coordinate into a planar coordinate to determine a projected planar image; segmenting the projected planar image based on distances between pixel points in the boundary pixel image; and determining the discrete pixel image according to a segmentation result; determining a triangular facet image of the target tissue according to a positional relationship between the boundary pixel image and the discrete pixel image of the target tissue contour, comprising: performing triangular partitioning processing based on a set of pixel points in the boundary pixel image and a set of pixel points in the discrete pixel image to obtain a triangular mesh image; and determining the triangular facet image of the target tissue according to positions of the triangular mesh image and corresponding centroids; performing three-dimensional reconstruction on a stereoscopic image of the target tissue using the triangular facet image to generate a three-dimensional reconstruction image based on a positional relationship between the centroids of the triangular facet image and the boundary pixel image, comprising: screening the triangular facet image by removing triangular facet images whose centroids are located outside a closed curve generated by projecting the boundary pixel image; mapping the triangular facet image remaining after the screening to a three-dimensional space; and performing three-dimensional reconstruction on the stereoscopic image of the target tissue according to a mapping result and a positional relationship between the boundary pixel and the three-dimensional space; determining a closed image of the target tissue according to the three-dimensional reconstruction image.

2. The processing method based on a three-dimensional mesh model according to claim 1, characterized in that, The centroid is a center of the triangular facet image.

3. The processing method based on a three-dimensional mesh model according to claim 1, characterized by, The determination of the closed image of the target tissue according to the three-dimensional reconstruction image comprises: adding a topological structure of a triangular facet contained in the three-dimensional reconstruction image to the target tissue to determine the closed image of the target tissue.

4. A processing device based on a three-dimensional mesh model, characterized by, The method comprises the following steps: a first determining module configured to determine a boundary pixel image for representing a target tissue contour, comprising: performing planar cutting on the target tissue; and taking intersection pixels between the target tissue and the planar cutting as the boundary pixel image for representing the target tissue contour; a second determining module configured to determine a discrete pixel image of the target tissue based on the boundary pixel image, comprising: projecting the contour of the target tissue in a spatial coordinate into a planar coordinate to determine a projected planar image; segmenting the projected planar image based on distances between pixel points in the boundary pixel image; and determining the discrete pixel image according to a segmentation result; The segmentation module is configured to determine a triangular facet image of the target tissue according to a position relationship between the boundary pixel image of the target tissue contour and the discrete pixel image, and includes: performing a triangular partitioning process based on a set of pixel points in the boundary pixel image of the target tissue contour and a set of pixel points in the discrete pixel image to obtain a triangular mesh image; and determining the triangular facet image of the target tissue according to a position of the triangular mesh image and a corresponding centroid. The reconstruction module is configured to perform three-dimensional reconstruction on the stereoscopic image of the target tissue based on a position relationship between the centroid of the triangular facet image and the boundary pixel image, and combine the triangular facet image to generate a three-dimensional reconstruction image, and includes: performing screening on the triangular facet image by eliminating triangular facet images in the position relationship in which the centroid is located outside a closed curve generated by projection of the boundary pixel image; mapping the triangular facet image remaining after the screening to a three-dimensional space; and performing three-dimensional reconstruction on the stereoscopic image of the target tissue according to a mapping result and a position relationship between the boundary pixel and the three-dimensional space. The closing module is configured to determine a closed image of the target tissue according to the three-dimensional reconstruction image.

5. A storage medium having a computer program stored thereon, the program being executed by a processor to implement the processing method based on a three-dimensional mesh model according to any one of claims 1 to 3.

6. An electronic device for performing image processing, comprising: A processor, a memory and a bus, the processor and the memory being in communication with each other through the bus; The memory is configured to store at least one executable instruction, and the executable instruction causes the processor to execute the processing method based on a three-dimensional mesh model according to any one of claims 1 to 3.

Images