Intestinal tract three-dimensional model reconstruction method and system

Abstract

The invention relates to the field of three-dimensional modeling, in particular to an intestinal tract three-dimensional model reconstruction method and system. Constructing an intestinal tract three-dimensional voxel model; for each voxel edge intersecting with the contour surface in the intestinal tract three-dimensional voxel model, obtaining an intersection point of the contour surface and the voxel edge, and calculating according to a preset method to obtain a vertex of each voxel sharing the voxel edge; if the vertexes corresponding to all the voxels sharing the voxel edges are in the same plane, calculating the distance from the intersection point to the plane and the area of a region formed by all the vertexes, and determining a contour surface fitting mode according to the ratio of the distance to the area; performing contour surface fitting according to the determined contour surface fitting mode to complete contour surface extraction of the intestinal tract; and smoothing the generated three-dimensional surface of the intestinal tract, and rendering and displaying on a display device. According to the invention, the extraction of the contour surface of the intestinal tract is more accurate, and the three-dimensional model of the intestinal tract is more

Description

Technical Field

[0001] The present invention relates to the field of three-dimensional model reconstruction, and in particular to a method and system for reconstructing a three-dimensional model of the intestine. Background Art

[0002] 3D reconstruction is the process of using raw data such as patient CT or MRI data to create a 3D model and form a 3D visualization model. 3D model reconstruction of the digestive tract provides doctors with richer and more intuitive lesion information, helping them make more accurate diagnoses. It not only improves the accuracy of disease diagnosis and the efficiency of surgical planning, but also promotes the development of personalized treatment plans. Furthermore, intestinal 3D modeling technology provides doctors with unprecedented perspectives and tools to better understand, diagnose, and treat various medical conditions. It also helps students improve their surgical skills through simulated surgeries and prepare for actual operations. However, existing 3D reconstruction methods based on CT images are not accurate enough in fitting the actual intestine. They can only depict the general shape of the intestine and are not precise enough in preserving details. Summary of the Invention

[0003] In order to solve the above problems, in a first aspect, the present invention provides a method for reconstructing a three-dimensional model of the intestine, the method comprising the following steps:

[0004] S1, obtaining a captured intestinal CT image, performing image segmentation on the pre-processed CT image to obtain an intestinal region image corresponding to each CT image; stacking the segmented intestinal region images in the order of the CT images to construct a three-dimensional voxel model of the intestine;

[0005] S2, for each voxel edge in the three-dimensional voxel model of the intestine that intersects with the isosurface, obtain the intersection point of the isosurface and the voxel edge, and calculate the vertex of each voxel sharing the voxel edge according to a preset method; if the vertices corresponding to all voxels sharing the voxel edge are in the same plane, calculate the distance from the intersection point to the plane and the area of the region formed by all the vertices, and determine the isosurface fitting method according to the ratio of the distance to the area;

[0006] S3, fitting the isosurface according to the determined isosurface fitting method to complete the isosurface extraction of the intestine; smoothing the generated three-dimensional surface of the intestine and rendering it on a display device.

[0007] Preferably, the isosurface fitting method is determined according to the ratio of the distance to the area, specifically:

[0008] If the ratio is less than a threshold, dividing the region consisting of the vertices corresponding to each voxel that shares the voxel edge into two triangular facets;

[0009] Otherwise, the intersection point is taken as the pyramid vertex and the side surfaces of the pyramid are taken as the triangular facets.

[0010] Preferably, the smoothing process is specifically:

[0011] The angle between the normal vectors of all the triangular facets sharing a common edge is calculated. If the angle is greater than a preset value, two endpoints of the common edge are obtained, and each of the two endpoints is smoothed.

[0012] Preferably, the smoothing process is performed on each of the two endpoints, specifically:

[0013] After the two endpoints are smoothed using the first smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before the smoothing is used as the first angle;

[0014] After the two segment points are smoothed using the second smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before smoothing is used as the second angle;

[0015] A smoothing process corresponding to the minimum value of the first angle and the second angle is used as the two endpoint smoothing process to perform smoothing on each of the two endpoints.

[0016] Preferably, the preset method is a Dual Contouring isosurface extraction method, the first smoothing method is a Laplace-based smoothing method, and the second smoothing method is a curvature-based smoothing method.

[0017] In another aspect, the present invention provides a system for reconstructing a three-dimensional intestinal model, the system comprising the following modules:

[0018] a voxel model construction module for acquiring captured intestinal CT images, performing image segmentation on the pre-processed CT images to obtain an intestinal region image corresponding to each CT image; and stacking the segmented intestinal region images in the order of the CT images to construct a three-dimensional voxel model of the intestine;

[0019] An isosurface fitting method determination module is used to obtain the intersection point of the isosurface and each voxel edge intersecting with the isosurface in the three-dimensional voxel model of the intestine, and calculate the vertex of each voxel sharing the voxel edge according to a preset method; if the vertices corresponding to all voxels sharing the voxel edge are in the same plane, the distance from the intersection point to the plane and the area of the region formed by all the vertices are calculated, and the isosurface fitting method is determined according to the ratio of the distance to the area;

[0020] The isosurface extraction and rendering module is used to fit the isosurface according to the determined isosurface fitting method to complete the isosurface extraction of the intestine; the generated three-dimensional surface of the intestine is smoothed and then rendered and displayed on the display device.

[0021] Preferably, the isosurface fitting method is determined according to the ratio of the distance to the area, specifically:

[0022] If the ratio is less than a threshold, dividing the region consisting of the vertices corresponding to each voxel that shares the voxel edge into two triangular facets;

[0023] Otherwise, the intersection point is taken as the pyramid vertex and the side surfaces of the pyramid are taken as the triangular facets.

[0024] Preferably, the smoothing process is specifically:

[0025] The angle between the normal vectors of all the triangular facets sharing a common edge is calculated. If the angle is greater than a preset value, two endpoints of the common edge are obtained, and each of the two endpoints is smoothed.

[0026] Preferably, the smoothing process is performed on each of the two endpoints, specifically:

[0027] After the two endpoints are smoothed using the first smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before the smoothing is used as the first angle;

[0028] After the two segment points are smoothed using the second smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before smoothing is used as the second angle;

[0029] A smoothing process corresponding to the minimum value of the first angle and the second angle is used as the two endpoint smoothing process to perform smoothing on each of the two endpoints.

[0030] Preferably, the preset method is a Dual Contouring isosurface extraction method, the first smoothing method is a Laplace-based smoothing method, and the second smoothing method is a curvature-based smoothing method.

[0031] In addition, the present invention also provides a computer program product, which implements the above method when executed by a processor.

[0032] There are many bends in the intestines, for example, there are many wrinkles on the surface of the intestines. The existing technology does not process these wrinkles smoothly enough. If you zoom in on the three-dimensional model of the intestine, you will find many jagged shapes. The present invention improves the extraction of isosurfaces. Specifically, for each voxel edge that intersects with the isosurface in the three-dimensional voxel model of the intestine, the intersection of the isosurface and the voxel edge is obtained, and the vertices of each voxel sharing the voxel edge are calculated according to a preset method; if the vertices corresponding to all voxels sharing the voxel edge are in the same plane, the distance from the intersection to the plane and the area of the region composed of all the vertices are calculated, and the isosurface fitting method is determined according to the ratio of the distance to the area. This can better complete the surface drawing of the intestine, make the details more realistic, and be less different from the real intestine. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of Example 1;

[0034] Figure 2 Schematic diagram of the intestinal 3D voxel model;

[0035] Figure 3 Schematic diagram of voxels, intersections, and vertices;

[0036] Figure 4 This is a schematic diagram of smoothing processing. DETAILED DESCRIPTION

[0037] In this document, relational terms such as first and second are used solely to distinguish one entity or operation from another, and do not necessarily require or imply any actual relationship or order between these entities or operations. Furthermore, the terms "comprise," "include," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. Without further restriction, an element defined by the phrase "comprising a..." does not preclude the presence of other identical elements in the process, method, article, or device comprising the element. In the present invention, if the collection of personal privacy data involves, for example, facial features, mobile phone usage information, etc., the individual's permission will be obtained in advance, including but not limited to verbal reminders, posters, mobile phone reminders, etc.; if there is a conflict with laws and regulations, production or use will be within the scope permitted by laws and regulations.

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0039] In the first embodiment, the present invention provides a method for reconstructing a three-dimensional intestinal model. Figure 1 As shown, the method includes the following steps:

[0040] S1, obtaining a captured intestinal CT image, performing image segmentation on the pre-processed CT image to obtain an intestinal region image corresponding to each CT image; stacking the segmented intestinal region images in the order of the CT images to construct a three-dimensional voxel model of the intestine;

[0041] A CT image captured by a CT device is an image set, with each slice representing a CT image. CT images include not only the intestines but also non-intestinal areas such as the kidneys and spine. Image segmentation is performed on the CT images to preserve the intestinal region of the CT image. Since CT scans have thick slices, the segmented CT images are stacked sequentially to represent the user's intestinal space. Voxels are similar to pixels, except that a voxel is a three-dimensional space with a certain volume, typically a cube. Figure 2 A voxel is shown, formed by two CT images. The cube has eight vertices, each representing the pixel values at the corresponding locations in the two CT images. By stacking all the segmented images of the consumption system region, a 3D voxel model of the consumption system can be obtained using the voxel generation method.

[0042] S2, for each voxel edge in the three-dimensional voxel model of the intestine that intersects with the isosurface, obtain the intersection point of the isosurface and the voxel edge, and calculate the vertex of each voxel sharing the voxel edge according to a preset method; if the vertices corresponding to all voxels sharing the voxel edge are in the same plane, calculate the distance from the intersection point to the plane and the area of the region formed by all the vertices, and determine the isosurface fitting method according to the ratio of the distance to the area;

[0043] Isosurface extraction is an important step in surface rendering and is directly related to the final surface rendering effect or the rendering effect of the intestine. The edges of the voxels that have intersections with the isosurface are calculated to obtain the vertices of the voxels. In the MarchingCubes algorithm, the intersections are directly used as vertices, but there are problems with model ambiguity and inaccurate features. The present invention uses a preset algorithm to calculate the vertices of each voxel that shares the voxel edge. Among them, each voxel that shares the voxel refers to all voxels that contain this edge if the edge of a voxel intersects with the isosurface. It should be noted that the vertices mentioned here do not refer to the vertices of the voxel cube, but refer to the vertices of the triangle. According to the preset method, the vertices of each voxel that shares the voxel edge are calculated, where the vertices refer to the vertices of the triangle located in the voxel. Of course, it is not limited to triangle meshes. If a four-corner mesh is used, the vertices refer to the vertices of the four-corner mesh. In a more specific embodiment, the preset method is the Dual Contouring isosurface extraction method.

[0044] There will be four voxels around a shared voxel edge, and each voxel will have a vertex, so there will be four vertices in the end, such as Figure 3 As shown, the four vertices may or may not be coplanar. When they are coplanar, the distance from the intersection to the plane and the area of the region formed by all the vertices are further calculated, and the isosurface fitting method is determined based on the ratio of the distance to the area.

[0045] In a specific embodiment, the isosurface fitting method is determined according to the ratio of the distance to the area, specifically:

[0046] If the ratio is less than a threshold, dividing the region consisting of the vertices corresponding to each voxel that shares the voxel edge into two triangular facets;

[0047] Otherwise, the intersection point is taken as the pyramid vertex and the side surfaces of the pyramid are taken as the triangular facets.

[0048] If the ratio of height to area is less than the threshold, the pyramid formed by the four coplanar vertices and the intersection is relatively flat, and the area formed by the vertices corresponding to each voxel, that is, the quadrilateral, is divided into two triangular facets. If the ratio is not less than the threshold, it indicates that the quadrilateral is significantly different from the isosurface. In this case, a further division is performed to obtain multiple triangular facets, that is, the intersection is used as the pyramid vertex and the side of the pyramid as the triangular facets. This method divides the triangular facets into finer pieces and more closely matches the isosurface.

[0049] In another embodiment, if the vertices corresponding to all voxels that share a voxel edge are not in the same plane, the Marching Cubes algorithm is still used to extract triangular facets.

[0050] S3, fitting the isosurface according to the determined isosurface fitting method to complete the isosurface extraction of the intestine; smoothing the generated three-dimensional surface of the intestine and rendering it on a display device.

[0051] After obtaining the triangular facets of the isosurface of the 3D intestinal voxel model, the isosurface is extracted and then smoothed using various methods, including but not limited to Laplace-based smoothing and curvature-based smoothing. The model is then displayed on a display device, such as a monitor, allowing medical staff to view the 3D intestinal model.

[0052] In another embodiment, the smoothing process is specifically:

[0053] The angle between the normal vectors of all the triangular facets sharing a common edge is calculated. If the angle is greater than a preset value, two endpoints of the common edge are obtained, and each of the two endpoints is smoothed.

[0054] For all triangles, determine the angle between the normal vectors of the triangles with the same edge. If the angle is greater than the preset value, it means that the angle between the two triangles is smaller. Figure 4 The angle between the normal vectors of two triangles is shown. When the angle is small, the area formed by the two triangles sharing a common edge is less smooth, meaning the edges are more prominent. Therefore, when the angle is greater than a preset value, the two endpoints of the shared edge are obtained and smoothed separately. There are various smoothing methods, including but not limited to Laplace-based smoothing and curvature-based smoothing.

[0055] In order to make the line segment formed by the two endpoints after smoothing closer to the line segment formed by the two endpoints before smoothing, in a specific embodiment, the smoothing process is performed on each of the two endpoints as follows:

[0056] After the two endpoints are smoothed using the first smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before the smoothing is used as the first angle;

[0057] After the two segment points are smoothed using the second smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before smoothing is used as the second angle;

[0058] A smoothing process corresponding to the minimum value of the first angle and the second angle is used as the two endpoint smoothing process to perform smoothing on each of the two endpoints.

[0059] Preferably, the first smoothing method is Laplace-based smoothing, and the second smoothing method is curvature-based smoothing.

[0060] In another embodiment, the first endpoint is processed using the first smoothing method and the second smoothing method respectively to obtain two coordinates P11 and P12 corresponding to the first endpoint;

[0061] The second endpoint is processed using the first smoothing processing method and the second smoothing processing method respectively to obtain two coordinates P21 and P22 corresponding to the second endpoint.

[0062] The two coordinates P11 and P12 corresponding to the first endpoint and the two coordinates P21 and P22 corresponding to the second endpoint are combined into four straight lines. The straight line with the smallest angle with the straight line containing the two endpoints before smoothing is determined, and the coordinates corresponding to the corresponding straight line are used as the smoothing result of the first and second endpoints.

[0063] Specifically, P11 and P21 form a straight line, P11 and P22 form a straight line, P12 and P21 form a straight line, and P12 and P22 form a straight line. The angles between each of these four lines and the line containing the two endpoints before smoothing are calculated. The coordinates corresponding to the line with the smallest angle are the smoothing result. For example, if the line formed by P12 and P22 has the smallest angle with the line containing the two endpoints before smoothing, P12 is used as the smoothing result for the first endpoint, and P22 is used as the smoothing result for the second endpoint.

[0064] In a second embodiment, the present invention provides a system for reconstructing a three-dimensional intestinal model, the system comprising the following modules:

[0065] a voxel model construction module for acquiring captured intestinal CT images, performing image segmentation on the pre-processed CT images to obtain an intestinal region image corresponding to each CT image; and stacking the segmented intestinal region images in the order of the CT images to construct a three-dimensional voxel model of the intestine;

[0066] An isosurface fitting method determination module is used to obtain the intersection point of the isosurface and each voxel edge intersecting with the isosurface in the three-dimensional voxel model of the intestine, and calculate the vertex of each voxel sharing the voxel edge according to a preset method; if the vertices corresponding to all voxels sharing the voxel edge are in the same plane, the distance from the intersection point to the plane and the area of the region formed by all the vertices are calculated, and the isosurface fitting method is determined according to the ratio of the distance to the area;

[0067] The isosurface extraction and rendering module is used to fit the isosurface according to the determined isosurface fitting method to complete the isosurface extraction of the intestine; the generated three-dimensional surface of the intestine is smoothed and then rendered and displayed on the display device.

[0068] Preferably, the isosurface fitting method is determined according to the ratio of the distance to the area, specifically:

[0069] If the ratio is less than a threshold, dividing the region consisting of the vertices corresponding to each voxel that shares the voxel edge into two triangular facets;

[0070] Otherwise, the intersection point is taken as the pyramid vertex and the side surfaces of the pyramid are taken as the triangular facets.

[0071] Preferably, the smoothing process is specifically:

[0072] The angle between the normal vectors of all the triangular facets sharing a common edge is calculated. If the angle is greater than a preset value, two endpoints of the common edge are obtained, and each of the two endpoints is smoothed.

[0073] Preferably, the smoothing process is performed on each of the two endpoints, specifically:

[0074] After the two endpoints are smoothed using the first smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before the smoothing is used as the first angle;

[0075] After the two segment points are smoothed using the second smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before smoothing is used as the second angle;

[0076] A smoothing process corresponding to the minimum value of the first angle and the second angle is used as the two endpoint smoothing process to perform smoothing on each of the two endpoints.

[0077] Preferably, the preset method is a Dual Contouring isosurface extraction method, the first smoothing method is a Laplace-based smoothing method, and the second smoothing method is a curvature-based smoothing method.

[0078] Finally, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0079] Through the description of the above embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by adding the necessary general hardware platform, or of course, by combining hardware and software. Based on this understanding, the essence of the above technical solution or the portion that contributes to the prior art can be embodied in the form of a computer product. The present invention 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-ROM, optical storage, etc.) containing computer-usable program code.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it, and other embodiments may also be used. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for reconstructing a three-dimensional intestinal model, characterized in that: The method comprises the following steps: S1, obtaining a captured intestinal CT image, performing image segmentation on the pre-processed CT image to obtain an intestinal region image corresponding to each CT image; stacking the segmented intestinal region images in the order of the CT images to construct a three-dimensional voxel model of the intestine; S2, for each voxel edge in the three-dimensional voxel model of the intestine that intersects with the isosurface, obtain the intersection point of the isosurface and the voxel edge, and calculate the vertex of each voxel sharing the voxel edge according to a preset method; if the vertices corresponding to all voxels sharing the voxel edge are in the same plane, calculate the distance from the intersection point to the plane and the area of the region formed by all the vertices, and determine the isosurface fitting method according to the ratio of the distance to the area; S3, fitting the isosurface according to the determined isosurface fitting method to complete the isosurface extraction of the intestine; smoothing the generated three-dimensional surface of the intestine and rendering it on a display device.

2. The method according to claim 1, wherein The isosurface fitting method is determined according to the ratio of the distance to the area, specifically: If the ratio is less than a threshold, dividing the region consisting of the vertices corresponding to each voxel sharing the voxel edge into two triangular facets; Otherwise, the intersection point is taken as the pyramid vertex and the side surfaces of the pyramid are taken as the triangular facets.

3. The method according to claim 1, wherein The smoothing process is specifically as follows: The angle between the normal vectors of all the triangular facets sharing a common edge is calculated. If the angle is greater than a preset value, two endpoints of the common edge are obtained, and each of the two endpoints is smoothed.

4. The method according to claim 1, wherein The smoothing process for each of the two endpoints is specifically as follows: After the two endpoints are smoothed using the first smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before the smoothing is used as the first angle; After the two segment points are smoothed using the second smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before smoothing is used as the second angle; A smoothing process corresponding to the minimum value of the first angle and the second angle is used as the two endpoint smoothing process to perform smoothing on each of the two endpoints.

5. The method according to claim 4, wherein The preset method is the Dual Contouring isosurface extraction method, the first smoothing method is Laplace-based smoothing, and the second smoothing method is curvature-based smoothing.

6. A system for reconstructing a three-dimensional intestinal model, characterized in that: The system includes the following modules: a voxel model construction module for acquiring captured intestinal CT images, performing image segmentation on the pre-processed CT images to obtain an intestinal region image corresponding to each CT image; and stacking the segmented intestinal region images in the order of the CT images to construct a three-dimensional voxel model of the intestine; An isosurface fitting method determination module is used to obtain the intersection point of the isosurface and each voxel edge intersecting with the isosurface in the three-dimensional voxel model of the intestine, and calculate the vertex of each voxel sharing the voxel edge according to a preset method; if the vertices corresponding to all voxels sharing the voxel edge are in the same plane, the distance from the intersection point to the plane and the area of the region formed by all the vertices are calculated, and the isosurface fitting method is determined according to the ratio of the distance to the area; The isosurface extraction and rendering module is used to fit the isosurface according to the determined isosurface fitting method to complete the isosurface extraction of the intestine; the generated three-dimensional surface of the intestine is smoothed and then rendered and displayed on the display device.

7. The system according to claim 6, wherein: The isosurface fitting method is determined according to the ratio of the distance to the area, specifically: If the ratio is less than a threshold, dividing the region consisting of the vertices corresponding to each voxel sharing the voxel edge into two triangular facets; Otherwise, the intersection point is taken as the pyramid vertex and the side surfaces of the pyramid are taken as the triangular facets.

8. The system according to claim 6, wherein: The smoothing process is specifically as follows: The angle between the normal vectors of all the triangular facets sharing a common edge is calculated. If the angle is greater than a preset value, two endpoints of the common edge are obtained, and each of the two endpoints is smoothed.

9. The system according to claim 6, wherein: The smoothing process for each of the two endpoints is specifically as follows: After the two endpoints are smoothed using the first smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before the smoothing is used as the first angle; After the two segment points are smoothed using the second smoothing method, the angle between the straight line where the two endpoints are located and the straight line where the two endpoints are located before smoothing is used as the second angle; A smoothing process corresponding to the minimum value of the first angle and the second angle is used as the two endpoint smoothing process to perform smoothing on each of the two endpoints.

10. A computer program product, characterized in that When the computer program product is executed by a processor, the computer program product implements the method according to any one of claims 1 to 5.

Images