Organ model-oriented geometric materialization method and system

Abstract

The invention provides an organ model-oriented geometric materialization method and system. The method comprises the following steps of: obtaining a three-dimensional surface grid model of a target organ; carrying out organ anatomical feature recognition and classification on the three-dimensional surface grid model, and determining a classification result; the classification result comprises physiologic holes, sharp anatomical features, parenchymal tissues and non-physiologic defects; according to a classification result, carrying out differential repair and optimization processing on the three-dimensional grid model to obtain a processed grid model; and performing curved surface reconstruction and materialization on the processed grid model to obtain a geometric materialization model of the target organ. According to the method, the surface mesh model can be converted into a solid model with clear internal and external spaces, the applicability and simulation precision of the model in finite element analysis are remarkably improved, and reliable technical support is provided for biothermotics, mechanical behavior research and medical simulation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer-aided modeling and simulation, and particularly relates to a geometric solidification method for an organ model. BACKGROUND

[0002] With the development of computer three-dimensional modeling and biological simulation technology, obtaining a real organ structure model by scanning technology has become an important means for studying the thermal and mechanical behavior of organisms. However, these scanning data are usually in the form of polygon mesh files (such as.obj,.stl, etc.) through image segmentation and three-dimensional reconstruction, and only contain surface geometric information, lacking solid volume data, and therefore cannot be directly used as an effective calculation domain for finite element analysis. SUMMARY

[0003] The present application provides a geometric solidification method and system for an organ model, to solve the defect that three-dimensional scanning data (such as MRI, CT, optical scanning) in the prior art can only provide surface geometric information, lack solid volume data, and cannot be directly used for finite element analysis. The present application can convert a surface mesh model into a solid model with clear inside and outside space, significantly improving the applicability and simulation accuracy of the model in finite element analysis, and providing reliable technical support for biological thermal and mechanical behavior research and medical simulation.

[0004] The present application provides a geometric solidification method for an organ model, comprising: obtaining a three-dimensional surface mesh model of a target organ; identifying and classifying organ anatomical features of the three-dimensional surface mesh model to determine a classification result; the classification result includes physiological pores, sharp anatomical features, thin-walled tissues and non-physiological defects; according to the classification result, differentially repairing and optimizing the three-dimensional mesh model to obtain a processed mesh model; performing surface reconstruction and solidification on the processed mesh model to obtain a geometric solidification model of the target organ.

[0005] According to the geometric solidification method for an organ model provided by the present application, before the step of identifying and classifying organ anatomical features of the three-dimensional surface mesh model, the method further comprises: performing multi-modal data fusion on the three-dimensional surface mesh model to perform the steps of feature identification and classification based on the three-dimensional surface mesh model after data fusion; the multi-modal data includes MRI, CT, and ultrasonic imaging data.

[0006] According to the organ model-oriented geometric solidification method, the three-dimensional surface mesh model is subjected to organ anatomical feature recognition and classification to obtain a classification result, including: based on an anatomical feature recognition algorithm, anatomical geometric feature recognition is performed on the three-dimensional surface mesh model, and a geometric descriptor of the mesh is calculated; the geometric descriptor includes a shape diameter function value, a curvature, and a hole boundary size; according to a corresponding relationship between the geometric descriptor and an organ pipe anatomical topological template, geometric feature classification is performed on the three-dimensional surface mesh model to obtain the classification result.

[0007] According to the organ model-oriented geometric solidification method, the three-dimensional mesh model is subjected to differential repair and optimization processing according to the classification result, including: in the case that the three-dimensional mesh model has a physiological hole, boundary ring extension and Boolean fusion are performed on the physiological hole; in the case that the three-dimensional mesh model has a sharp anatomical feature, feature protection smoothing is performed on the sharp anatomical feature; in the case that the three-dimensional mesh model has a thin-walled tissue, anisotropic smoothing is performed on the thin-walled tissue; and in the case that the three-dimensional mesh model has a non-physiological defect, standard hole filling is performed on the non-physiological defect.

[0008] According to the organ model-oriented geometric solidification method, the processed mesh model is subjected to surface reconstruction and solidification, including: a parametric surface fitting technology is used to perform surface reconstruction on the processed mesh model to generate a boundary representation solid model; and topological optimization is performed on the boundary representation solid model to ensure the water tightness of the solid model.

[0009] According to the organ model-oriented geometric solidification method, the processed mesh model is subjected to surface reconstruction and solidification, including: a parametric surface fitting technology is used to perform surface reconstruction on the processed mesh model to generate a boundary representation solid model; and topological optimization is performed on the boundary representation solid model to ensure the water tightness of the solid model.

[0010] The application further provides an organ model-oriented geometric solidification system, including: an acquisition module configured to acquire a three-dimensional surface mesh model of a target organ; a classification result determination module configured to perform organ anatomical feature recognition and classification on the three-dimensional surface mesh model to determine a classification result; the classification result includes a physiological hole, a sharp anatomical feature, a thin-walled tissue, and a non-physiological defect; a processing module configured to perform differential repair and optimization processing on the three-dimensional mesh model according to the classification result to obtain a processed mesh model; and a solidification module configured to perform surface reconstruction and solidification on the processed mesh model to obtain a geometric solidification model of the target organ.

[0011] The application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the organ model-oriented geometric materialization method when executing the computer program.

[0012] The application further provides a non-transitory computer-readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the organ model-oriented geometric materialization method.

[0013] The application further provides a computer program product, comprising a computer program, wherein the computer program is executed by a processor to implement the organ model-oriented geometric materialization method.

[0014] The application provides an organ model-oriented geometric materialization method and system, which can convert a surface mesh model into a solid model with clear internal and external spaces, significantly improves the applicability and simulation accuracy of the model in finite element analysis, and provides reliable technical support for biological thermal, mechanical behavior research and medical simulation. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0016] Figure 1 is a flowchart of an organ model-oriented geometric materialization method provided by the application.

[0017] Figure 2 is a structural schematic diagram of an organ model-oriented geometric materialization system provided by the application.

[0018] Figure 3 is a structural schematic diagram of an electronic device provided by the application. DETAILED DESCRIPTION

[0019] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, but not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0020] Currently, in the field of finite element analysis, it is difficult to obtain a three-dimensional model with high fidelity and directly imported into the finite element simulation software for the research object with complex geometric structure such as biological organs. The existing research usually only simulates and analyzes based on the external contour or surface shape of the organ, and lacks effective modeling and calculation of the internal tissue structure (such as the cavity and the inner wall tissue). Although this simplified model can reflect the overall shape characteristics, in the analysis involving heat transfer, fluid coupling and multi-layer tissue response, the results often deviate significantly from the real physiological conditions, and it is difficult to meet the needs of accurate simulation.

[0021] Reference is made to Figure 1 , Figure 1 A flowchart of a geometric solidification method for an organ model provided by the present application.

[0022] The present application provides a geometric solidification method for an organ model, comprising: 101: obtaining a three-dimensional surface mesh model of a target organ.

[0023] In order to solve the technical problems existing in the prior art, the present application provides a geometric solidification method for an organ model, which first obtains a general three-dimensional surface mesh model (such as OBJ, STL, PLY format, which has good availability and universality, and can be directly exported through various medical or modeling platforms) of a target organ from a public resource library or a three-dimensional scanning device. The three-dimensional surface mesh model of the target organ is used as the input data of the technical solution of the present application. Then, the input mesh is preliminarily diagnosed automatically, and the defective area is identified and marked, which lays a foundation for subsequent accurate repair. The present application realizes seamless conversion of biological data to engineering simulation data, and can be widely applied to the fields of low-temperature biological preservation, tissue mechanics, biological heat conduction, surgical planning and tissue engineering simulation.

[0024] Of course, the three-dimensional surface mesh model can also come from a public human organ three-dimensional database; point cloud scanning data generated by scientific research institutions or laboratories.

[0025] The three-dimensional surface mesh model can be imported into Geomagic Wrap software, which can automatically identify and load the organ surface mesh structure to provide input data for subsequent topological repair.

[0026] As a preferred embodiment, before the three-dimensional surface mesh model is subjected to organ dissection feature recognition and classification, it further comprises: performing multi-modal data fusion on the three-dimensional surface mesh model, so as to perform the steps of feature recognition and classification based on the three-dimensional surface mesh model after the fusion data; the multi-modal data includes MRI, CT, and ultrasonic imaging data.

[0027] In order to enhance the geometric and anatomical information of the three-dimensional surface mesh model, in the embodiment, multi-modal image data of the target organ is acquired, including MRI (Magnetic Resonance Imaging), CT (Computed Tomography) and ultrasound imaging data. These data provide different anatomical information and tissue characteristics, respectively. The acquired multi-modal data is preprocessed (such as data registration, data normalization) to ensure the consistency and fusibility of the data. Finally, the three-dimensional surface mesh model is fused based on the preprocessed multi-modal data, and the three-dimensional surface mesh model after fusion is obtained. The embodiment can make full use of the advantages of different modal data, and generate a three-dimensional surface mesh model containing rich anatomical information. This not only improves the accuracy of feature recognition and classification, but also provides a more reliable basis for subsequent differentiated repair and solidification processing, thereby significantly improving the quality and simulation accuracy of the finally generated geometric solidification model.

[0028] 102: organ anatomical feature recognition and classification is performed on the three-dimensional surface mesh model, and a classification result is determined; the classification result includes physiological holes, sharp anatomical features, thin-walled tissues and non-physiological defects.

[0029] As a preferred embodiment, organ anatomical feature recognition and classification is performed on the three-dimensional surface mesh model to obtain a classification result, including: based on an anatomical feature recognition algorithm, anatomical geometric feature recognition is performed on the three-dimensional surface mesh model, and geometric descriptors of the mesh are calculated; the geometric descriptors include shape diameter function values, curvatures and hole boundary sizes; based on the correspondence between the geometric descriptors and organ anatomical topological templates, geometric feature classification is performed on the three-dimensional surface mesh model, and the classification result is obtained.

[0030] In the embodiment, the surface model is automatically repaired and closed, and its inner and outer wall surfaces are constructed, and algorithm design is performed for the complex conditions of the organ, the important original features of the organ are preserved during geometric repair, and finally a closed boundary representation is formed.

[0031] After the three-dimensional surface mesh model is imported, an application programming interface (API, Application Programming Interface) or a script function provided by Geomagic Wrap software can be used to run the anatomical feature recognition algorithm and the classification algorithm. The anatomical feature recognition algorithm performs anatomical geometric feature recognition on the three-dimensional surface mesh model, and calculates geometric descriptors (including but not limited to shape diameter function SDF, curvature and hole boundary size) of the mesh. And combined with a pre-defined organ anatomical topological template, through a special rule-based classifier, the mesh region is automatically classified into: physiological holes, sharp anatomical features, thin-walled tissues and non-physiological defects.

[0032] Specifically, in hole boundary detection, all the edges of the grid are traversed to identify the edges connected by only one patch, and they are grouped into a set of boundary loops {Bi} according to connectivity. For each boundary loop, its perimeter Li and approximate enclosed area Ai are calculated.

[0033] In local thickness estimation (SDF), for each triangular patch, rays are emitted along the positive and negative directions of its normal vector and intersected with the grid. The average value of the shortest distances is taken as the value of the shape diameter function (SDF) of this patch, which is used to judge the tissue thickness.

[0034] In curvature calculation and characteristic edge recognition, through the discrete curvature estimation algorithm, the Gaussian curvature K and the mean curvature H of each vertex are calculated, and the continuous high-curvature paths are extracted as candidate sharp anatomical feature regions. The Gaussian curvature is used to identify the concave and convex features of the surface, and the mean curvature is used to identify edges and folds.

[0035] The organ anatomical topology template includes the positions of vascular interfaces, annulus positions, ridge line distributions, etc.

[0036] According to the relationship between the geometric descriptors and the template positions, the model regions are automatically divided into: Physiological holes (vascular interface type), satisfying Li > TL and Ai > TA; Sharp anatomical features (continuous high-curvature paths satisfying ); Thin-walled tissues (connected regions with SDF < TSDF); Non-physiological defects (small-sized boundary loops that do not satisfy the above rules).

[0037] Among them, TL is the preset hole perimeter threshold, TA is the preset hole area threshold, TH is the preset mean curvature threshold, and TSDF is the preset shape diameter function threshold. The specific values of these thresholds are determined through statistical analysis and optimization of a large amount of three-dimensional model data of typical organs to achieve the best discrimination of various anatomical features and geometric defects.

[0038] 103: According to the classification results, the three-dimensional grid model is differentially repaired and optimized to obtain the processed grid model.

[0039] As a preferred embodiment, based on the classification results, the three-dimensional mesh model is subjected to differentiated repair and optimization processing, including: when the three-dimensional mesh model has physiological holes, the physiological holes are extended by boundary loops and Boolean fusion is performed; when the three-dimensional mesh model has sharp anatomical features, the sharp anatomical features are smoothed for feature protection; when the three-dimensional mesh model has thin-walled tissues, the thin-walled tissues are smoothed anisotropically; when the three-dimensional mesh model has non-physiological defects, the non-physiological defects are filled with standard holes.

[0040] In this embodiment, a differentiated geometric repair and optimization strategy is driven based on the above classification results.

[0041] For the boundary ring Bi classified as a physiological cavity, its center point and average normal are calculated, a cylindrical extension segment is generated along this direction, and Boolean fusion is performed with the original model at the boundary to construct a virtual blood vessel interface structure, rather than performing cavity filling.

[0042] For boundary loops classified as non-physiological defects, the geometric repair module is invoked to perform minimum area triangulation or Geomagic Wrap full filling / filling of individual holes, achieving rapid closure while maintaining local smoothness.

[0043] To maintain smoothness in sharp features, positional constraints are added to the vertices of the feature region during Laplacian smoothing, ensuring that their coordinate updates satisfy the following: (For example, significantly reducing the smoothing weight coefficient of the vertex in Laplace smoothing.) This achieves feature-protective smoothing, preventing distortion of key anatomical features while denoising. As vertex The updated coordinates As vertex The original coordinates, The Laplace smoothed translation vector is the average coordinate difference between a vertex and its neighboring vertices, with parameters... This is the smoothing intensity coefficient, and its value range is generally 0.5–1.0.

[0044] The parameter H mentioned above is used to guide the smoothing intensity. The selection. When a high curvature region is detected. The algorithm automatically reduces the area The value of is thus suppressed. The effect of vertex position preserves sharp anatomical features; in flat areas, however... Take a larger value to enhance the smoothing effect.

[0045] On the anisotropic smoothing of thin-walled structures, the smoothing vector Decomposed into normal component and tangential component, only the tangential component is updated to avoid changing the local thickness of the thin-walled area, and the real thickness of the biological tissue is maintained.

[0046] For small fragments or tissue residue parts, a small continuous area can be selected by the full selection and bounded component function of the Geomagic wrap software, and after using the bounded component, the selection area is reversed, so that all fragments can be accurately and completely selected, and the fragments and residues can be removed by clicking delete.

[0047] In the topology error correction, after some hole repair and fairing operation on the organ surface, mesh detection can be performed in real time, and the detected non-manifold edges, suspended surfaces, overlapping surfaces, broken boundaries and other geometric defects are modified in a targeted manner until the mesh detection is no problem again.

[0048] The present application realizes automatic differentiation and differential processing of physiological structure and geometric defects by combining local geometric description to give anatomical topology priori, so that the final model can meet the requirements of water tightness, structural continuity and anatomical feature fidelity for numerical simulation.

[0049] 104: Surface reconstruction and solidification are performed on the processed mesh model to obtain a geometric solidification model of the target organ.

[0050] As a preferred embodiment, surface reconstruction and solidification are performed on the processed mesh model, including: using a parametric surface fitting technology to perform surface reconstruction on the processed mesh model to generate a boundary representation solid model; and performing topology optimization on the boundary representation solid model to ensure the water tightness of the solid model.

[0051] In order to realize the conversion from a set of triangular facets to a boundary representation solid, the model is given a clear internal space and external space, and in this embodiment, the processed mesh model is used as the basis for surface reconstruction. Precise surface and automatic surface of Geomagic Wrap can directly generate a surface. For problems that occur during the surface patch construction process, detection contour line, grid construction and fitting surface are used for repair. Finally, a complete and closed (i.e. water tight) boundary representation solid is formed. This solid model clearly distinguishes the internal and external space of the model in mathematics, and meets the basic requirements of finite element analysis software for the calculation domain.

[0052] As a preferred embodiment, it further includes: exporting and compatibility simulation verification of the geometric solidification model of the target organ.

[0053] In the present embodiment, the generated geometric solid model of the target organ is exported in a standard data exchange format (such as STEP, IGES) suitable for finite element analysis. After being imported into a finite element software (such as ANSYS, ABAQUS or COMSOL), the model is subjected to feasibility verification.

[0054] Specifically, the meshing test is performed using the constructed mesh, and no error message indicates that the model can be identified as a valid calculation domain for subsequent structural mechanics, heat conduction, biological fluid or multi-physical field simulation analysis.

[0055] Meshing detection: In the finite element software, the imported organ solid model is subjected to standard physical field control meshing or adaptive tetrahedral meshing, an initial, moderate element size is set for automatic mesh generation. If there is no error or warning during the meshing process, and continuous mesh is generated, it is determined that "meshing is successful". If the software reports a geometry error (such as the presence of a small feature, invalid edge, etc.) leading to meshing failure, it is determined that "not passed" and the polygon needs to be converted in the finite element software or in the Geomagic wrap software. At the same time, the qualified threshold of the preset mesh quality parameter (for example, the minimum value of the Jacobian matrix > 0.7, the maximum skewness < 0.8) can also be set. The system automatically counts the number and proportion of elements that do not meet the quality threshold. If the proportion of poor quality elements exceeds the preset value (such as 5%), it is determined that "the quality is unqualified", and the model needs to be returned to the previous step for geometric optimization.

[0056] Key size and volume verification: The total volume and key size of the output model are compared with the original mesh or anatomical standard data to ensure that no significant geometric distortion is introduced during the conversion process.

[0057] The model constructed through the process not only has accuracy in external morphology, but also retains internal cavities and tissue layer structures, has high quality and high fidelity, and can be directly imported into finite element software such as COMSOL, Abaqus and ANSYS, thereby significantly improving the authenticity and result accuracy of simulation calculation, and providing a more reliable geometric basis for low-temperature heat exchange, biological heat transfer and fluid-structure coupling related research.

[0058] The organ model-oriented geometric solidification system provided by the present application is described below. The organ model-oriented geometric solidification system described below can be correspondingly referred to the organ model-oriented geometric solidification method described above.

[0059] Please refer to Figure 2 , Figure 2 The structure diagram of the organ model-oriented geometric solidification system provided by the present application is shown.

[0060] The application further provides an organ model-oriented geometric solidification system, comprising: an acquisition module 201, configured to acquire a three-dimensional surface mesh model of a target organ; a classification result determination module 202, configured to perform organ anatomical feature recognition and classification on the three-dimensional surface mesh model, and determine a classification result; the classification result comprises physiological pores, sharp anatomical features, thin-walled tissues, and non-physiological defects; a processing module 203, configured to perform differential repair and optimization processing on the three-dimensional mesh model according to the classification result, and obtain a processed mesh model; and a solidification module 204, configured to perform surface reconstruction and solidification on the processed mesh model, and obtain a geometric solidification model of the target organ.

[0061] The application has the following beneficial effects: (1) A reliable solid model of an organ complex structure is provided for finite element analysis: The application provides an organ three-dimensional solidification method for finite element analysis, which can convert original organ surface data (such as OBJ format) into a geometric solid with complete topology and clear volume definition. The method is particularly suitable for organ models with complex anatomical structures and sharp curvature changes, enabling the finite element software to accurately identify and perform mesh division, and providing a reliable geometric basis for subsequent stress, temperature simulation, etc.

[0062] (2) High-fidelity conversion from general three-dimensional data to simulation models is realized: The application uses the high-precision surface fitting and hole repair functions of Geomagic Wrap to reconstruct and volume-encapsulate the surface mesh data, and designs an algorithm process for complex organ structures, so that the model forms a closed solid while retaining the original anatomical features. Compared with existing direct import or simplified modeling methods, the solid model generated by the application significantly improves the local shape restoration degree and overall smoothness, and can more realistically reflect the geometric characteristics of biological tissues, thereby improving the physical credibility of finite element analysis.

[0063] (3) The simulation compatibility and calculation stability of the model are ensured: By performing defect detection and modification multiple times during the solidification process, the model obtained by the application avoids common geometric defects such as open surfaces, overlapping surfaces, and non-manifold edges. It has been verified that the model can be directly recognized and meshed by mainstream finite element software such as ANSYS and COMSOL, and exhibits better convergence characteristics and stability during calculation.

[0064] (4) The OBJ and other general format resources are fully utilized to reduce the data preparation threshold: The entity process established by the application can directly process the disclosed three-dimensional data of organs, and supports input in common formats such as OBJ and STL. Because the data sources are extensive and easy to obtain, users can quickly construct high-precision organ models meeting simulation requirements without relying on expensive scanning equipment or professional modeling personnel, thereby greatly reducing the application threshold of finite element analysis in the biological field.

[0065] (5) The application range of finite element analysis in the field of biological engineering and medical simulation is expanded. The method breaks through the technical barrier between three-dimensional reconstruction of biology and engineering simulation, so that finite element analysis can be directly applied to research scenes such as thermal response, mechanical response, biocompatibility and cryopreservation of organs. The method provides a standardized geometric input basis for biological simulation, and has wide application value in scientific research and engineering.

[0066] Figure 3 An example of a structural schematic diagram of an electronic device is shown in Figure 3 As shown, the electronic device can include a processor (processor) 301, a communication interface (Communications Interface) 302, a memory (memory) 303 and a communication bus 304, wherein the processor 301, the communication interface 302 and the memory 303 complete mutual communication through the communication bus 304. The processor 301 can call the logical instructions in the memory 303 to execute the organ model-oriented geometric entity method, which includes: obtaining a three-dimensional surface mesh model of a target organ; performing organ dissection feature recognition and classification on the three-dimensional surface mesh model to determine a classification result; the classification result includes physiological pores, sharp dissection features, thin-walled tissues and non-physiological defects; according to the classification result, differentially repairing and optimizing the three-dimensional mesh model to obtain a processed mesh model; performing surface reconstruction and entity on the processed mesh model to obtain a geometric entity model of the target organ.

[0067] Moreover, the logical instructions in the memory 303 described above can be implemented in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0068] In another aspect, the present application also provides a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program can be executed by a processor to enable a computer to execute the organ model oriented geometric solidification method provided by the above-mentioned methods. The method comprises: obtaining a three-dimensional surface mesh model of a target organ; performing organ anatomical feature recognition and classification on the three-dimensional surface mesh model to determine a classification result; the classification result comprises physiological holes, sharp anatomical features, thin-walled tissues and non-physiological defects; according to the classification result, performing differential repair and optimization processing on the three-dimensional mesh model to obtain a processed mesh model; performing surface reconstruction and solidification on the processed mesh model to obtain a geometric solidification model of the target organ.

[0069] In another aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the organ model oriented geometric solidification method provided by the above-mentioned methods. The method comprises: obtaining a three-dimensional surface mesh model of a target organ; performing organ anatomical feature recognition and classification on the three-dimensional surface mesh model to determine a classification result; the classification result comprises physiological holes, sharp anatomical features, thin-walled tissues and non-physiological defects; according to the classification result, performing differential repair and optimization processing on the three-dimensional mesh model to obtain a processed mesh model; performing surface reconstruction and solidification on the processed mesh model to obtain a geometric solidification model of the target organ.

[0070] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0071] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0072] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A geometric solidification method for organ models, characterized in that, include: Obtain a three-dimensional surface mesh model of the target organ; The organ anatomical features of the three-dimensional surface mesh model are identified and classified, and the classification results are determined. The classification results include physiological holes, sharp anatomical features, thin-walled tissues, and non-physiological defects; Based on the classification results, the three-dimensional mesh model is subjected to differential repair and optimization processing to obtain the processed mesh model; The processed mesh model is then reconstructed and solidified to obtain a geometric solidified model of the target organ.

2. The geometric solidification method for organ-oriented models according to claim 1, characterized in that, Before performing organ anatomical feature recognition and classification on the three-dimensional surface mesh model, the following steps are also included: The three-dimensional surface mesh model is subjected to multimodal data fusion, and feature recognition and classification steps are performed based on the fused three-dimensional surface mesh model; the multimodal data includes MRI, CT and ultrasound imaging data.

3. The geometric solidification method for organ-oriented models according to claim 1, characterized in that, The process of identifying and classifying organ anatomical features from the three-dimensional surface mesh model to obtain classification results includes: Based on the anatomical feature recognition algorithm, the anatomical geometric features of the three-dimensional surface network model are identified, and the geometric descriptor of the mesh is calculated; the geometric descriptor includes the shape diameter function value, curvature, and hole boundary size; Based on the correspondence between the geometric descriptors and the organ anatomy topology templates, the three-dimensional surface mesh model is classified according to its geometric features to obtain the classification results.

4. The geometric solidification method for organ-oriented models according to claim 1, characterized in that, The step of performing differential repair and optimization processing on the 3D mesh model based on the classification results includes: In the case of physiological pores in the three-dimensional mesh model, boundary loop extension and Boolean fusion are performed on the physiological pores; In the case where the three-dimensional mesh model has sharp anatomical features, the sharp anatomical features are subjected to feature-protective smoothing. In the case where the three-dimensional mesh model contains thin-walled structures, the thin-walled structures are anisotropically smoothed. In the case of non-physiological defects in the three-dimensional mesh model, standard holes are filled to fill the non-physiological defects.

5. The geometric solidification method for organ-oriented models according to claim 1, characterized in that, The process of reconstructing and solidifying the processed mesh model includes: Using parametric surface fitting technology, the processed mesh model is reconstructed to generate a boundary representation solid model; Topology optimization is performed on the boundary representation entity model to ensure the watertightness of the entity model.

6. The geometric solidification method for organ-oriented models according to any one of claims 1 to 5, characterized in that, Also includes: The geometric solid model of the target organ is exported and its compatibility is verified through simulation.

7. A geometric solidification system for organ models, characterized in that, include: The acquisition module is used to acquire the three-dimensional surface mesh model of the target organ; The classification result determination module is used to identify and classify organ anatomical features of the three-dimensional surface mesh model and determine the classification result; the classification result includes physiological holes, sharp anatomical features, thin-walled tissues and non-physiological defects; The processing module is used to perform differential repair and optimization processing on the three-dimensional mesh model based on the classification results, so as to obtain the processed mesh model; The solidification module is used to reconstruct and solidify the processed mesh model to obtain a geometric solidification model of the target organ.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the geometric solidification method for organ-oriented models as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the geometric solidification method for organ-oriented models as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the geometric solidification method for organ-oriented models as described in any one of claims 1 to 6.

Images