Method for three-dimensional reconstruction of tubular structures, surgical robot and related products

Abstract

The application discloses a three-dimensional reconstruction method of tubular tissue, a surgical robot and related products. The method comprises the following steps: acquiring a first three-dimensional image, the first three-dimensional image comprising a first three-dimensional region corresponding to a first tubular tissue, the first tubular tissue being a tubular-shaped tissue, the first three-dimensional image being obtained by three-dimensional reconstruction on x two-dimensional segmentation results of the first tubular tissue, the first three-dimensional region comprising a first cross section, x being an integer greater than 1. Adjusting the boundary of the first cross section in the first three-dimensional image to obtain a second three-dimensional image, the second cross section in the second three-dimensional image being obtained by adjusting the boundary of the first cross section, the difference between the distance from the center of the second cross section to any two pixels in the boundary of the second cross section being less than or equal to a first threshold. According to the method, the surface of the first tubular tissue can be smoother.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, and in particular to a method for three-dimensional reconstruction of tubular tissues, a surgical robot, and related products. Background Technology

[0002] In the medical field, to enable doctors to better observe tubular tissues (such as blood vessels and trachea), multiple two-dimensional segmentation results are typically obtained by segmenting the tubular tissue in multiple two-dimensional images. Then, three-dimensional reconstruction is performed based on these multiple two-dimensional segmentation results to obtain a three-dimensional image of the tubular tissue. However, the surface of the tubular tissue in the three-dimensional image is rough. Summary of the Invention

[0003] This application provides a three-dimensional reconstruction method for tubular tissue, a surgical robot, and related products to reduce the surface roughness of tubular tissue and make the surface of the first tubular tissue smoother.

[0004] In a first aspect, a method for three-dimensional reconstruction of tubular tissue is provided, the method comprising:

[0005] A first three-dimensional image is obtained, the first three-dimensional image includes a first three-dimensional region corresponding to a first tubular tissue, the first tubular tissue is a tissue with a tubular shape, the first three-dimensional image is obtained by three-dimensional reconstruction of x two-dimensional segmentation results of the first tubular tissue, the first three-dimensional region includes a first cross-section, and x is an integer greater than 1;

[0006] The boundary of the first cross section in the first three-dimensional image is adjusted to obtain a second three-dimensional image. The second cross section in the second three-dimensional image is obtained by adjusting the boundary of the first cross section. The difference between the center of the second cross section and any two pixels in the boundary of the second cross section is less than or equal to a first threshold.

[0007] In conjunction with any embodiment of this application, adjusting the boundary of the first cross-section in the first three-dimensional image to obtain the second three-dimensional image includes:

[0008] For each pixel in the boundary of the first cross section, a nearest pixel is determined from the first background region to obtain n first background pixels. The first background region is the three-dimensional region in the first three-dimensional image other than the first three-dimensional region.

[0009] Determine the distance between the center of the first cross-section and the n first background pixels to obtain n first distances;

[0010] Based on the n first distances, the expected distance between the center of the first cross-section and the boundary of the first cross-section is obtained;

[0011] Based on the desired distance, the boundary of the first cross-section in the first three-dimensional image is adjusted to obtain the second three-dimensional image.

[0012] In conjunction with any embodiment of this application, obtaining the desired distance between the center of the first cross-section and the boundary of the first cross-section based on the n first distances includes:

[0013] The expected distance is obtained based on the minimum value of the n first distances;

[0014] Alternatively, the desired distance can be obtained based on the maximum value of the n first distances;

[0015] Alternatively, the desired distance can be obtained based on the average of the n first distances.

[0016] In any embodiment of this application, the distance between the center of the second cross section and the pixels in the boundary of the second cross section is the desired distance.

[0017] In conjunction with any embodiment of this application, obtaining the desired distance between the center of the first cross-section and the boundary of the first cross-section based on the n first distances includes:

[0018] From the n first distances, m second distances are determined, wherein the m second distances are the distances between the center of the first cross-section and the m second background pixels among the n first background pixels, the m second background pixels are the m pixels in the first background region that are closest to the m first boundary pixels, the m first boundary pixels are the m adjacent pixels in the boundary of the first interface, where m is an integer greater than 1 and less than s, and s is the number of pixels in the first interface;

[0019] If the variance of the m second distances is greater than or equal to the second threshold, the distance between the center of the first cross-section and the m first boundary pixels is obtained based on the average of the m second distances.

[0020] If the variance of the m second distances is less than the second threshold, the distance between the center of the first cross-section and the m first boundary pixels is obtained based on the m second distances.

[0021] The desired distance is obtained based on the distance between the center of the first cross section and the m first boundary pixels, and the distance between the center of the first cross section and the t second boundary pixels. The t second boundary pixels are the pixels in the boundary of the first interface other than the m first boundary pixels. The first distance includes the distance between the center of the first cross section and the m first boundary pixels, and the distance between the center of the first cross section and the t second boundary pixels.

[0022] In conjunction with any embodiment of this application, adjusting the boundary of the first cross-section in the first three-dimensional image based on the desired distance to obtain the second three-dimensional image includes:

[0023] Obtain the third distance between the center of the third cross section and the boundary of the third cross section, wherein the third cross section is the cross section adjacent to the first cross section in the first three-dimensional region;

[0024] If the difference between the expected distance and the third distance is greater than a third threshold, the expected distance is reduced to obtain a fourth distance, and the difference between the fourth distance and the third distance is equal to the third threshold.

[0025] The distance between the center of the first cross-section and the boundary of the first cross-section is adjusted to the fourth distance to obtain the second three-dimensional image;

[0026] If the difference between the desired distance and the third distance is less than or equal to the third threshold, the distance between the center of the first cross-section and the boundary of the first cross-section is adjusted to the desired distance to obtain the second three-dimensional image.

[0027] Secondly, a three-dimensional reconstruction apparatus for tubular tissue is provided, the apparatus comprising:

[0028] The acquisition unit is used to acquire a first three-dimensional image, the first three-dimensional image including a first three-dimensional region corresponding to a first tubular tissue, the first tubular tissue being a tissue with a tubular shape, the first three-dimensional image being obtained by three-dimensional reconstruction of x two-dimensional segmentation results of the first tubular tissue, the first three-dimensional region including a first cross-section, and x being an integer greater than 1;

[0029] An adjustment unit is used to adjust the boundary of the first cross section in the first three-dimensional image to obtain a second three-dimensional image. The second cross section in the second three-dimensional image is obtained by adjusting the boundary of the first cross section. The difference between the center of the second cross section and any two pixels in the boundary of the second cross section is less than or equal to a first threshold.

[0030] In conjunction with any embodiment of this application, the adjustment unit is further configured to:

[0031] For each pixel in the boundary of the first cross section, a nearest pixel is determined from the first background region to obtain n first background pixels. The first background region is the three-dimensional region in the first three-dimensional image other than the first three-dimensional region.

[0032] Determine the distance between the center of the first cross-section and the n first background pixels to obtain n first distances;

[0033] Based on the n first distances, the expected distance between the center of the first cross-section and the boundary of the first cross-section is obtained;

[0034] Based on the desired distance, the boundary of the first cross-section in the first three-dimensional image is adjusted to obtain the second three-dimensional image.

[0035] In conjunction with any embodiment of this application, the adjustment unit is further configured to:

[0036] The expected distance is obtained based on the minimum value of the n first distances;

[0037] Alternatively, the desired distance can be obtained based on the maximum value of the n first distances;

[0038] Alternatively, the desired distance can be obtained based on the average of the n first distances.

[0039] In any embodiment of this application, the distance between the center of the second cross section and the pixels in the boundary of the second cross section is the desired distance.

[0040] In conjunction with any embodiment of this application, the adjustment unit is further configured to:

[0041] From the n first distances, m second distances are determined, wherein the m second distances are the distances between the center of the first cross-section and the m second background pixels among the n first background pixels, the m second background pixels are the m pixels in the first background region that are closest to the m first boundary pixels, the m first boundary pixels are the m adjacent pixels in the boundary of the first interface, where m is an integer greater than 1 and less than s, and s is the number of pixels in the first interface;

[0042] If the variance of the m second distances is greater than or equal to the second threshold, the distance between the center of the first cross-section and the m first boundary pixels is obtained based on the average of the m second distances.

[0043] If the variance of the m second distances is less than the second threshold, the distance between the center of the first cross-section and the m first boundary pixels is obtained based on the m second distances.

[0044] The desired distance is obtained based on the distance between the center of the first cross section and the m first boundary pixels, and the distance between the center of the first cross section and the t second boundary pixels. The t second boundary pixels are the pixels in the boundary of the first interface other than the m first boundary pixels. The first distance includes the distance between the center of the first cross section and the m first boundary pixels, and the distance between the center of the first cross section and the t second boundary pixels.

[0045] In conjunction with any embodiment of this application, the adjustment unit is further configured to:

[0046] Obtain the third distance between the center of the third cross section and the boundary of the third cross section, wherein the third cross section is the cross section adjacent to the first cross section in the first three-dimensional region;

[0047] If the difference between the expected distance and the third distance is greater than a third threshold, the expected distance is reduced to obtain a fourth distance, and the difference between the fourth distance and the third distance is equal to the third threshold.

[0048] The distance between the center of the first cross-section and the boundary of the first cross-section is adjusted to the fourth distance to obtain the second three-dimensional image;

[0049] If the difference between the desired distance and the third distance is less than or equal to the third threshold, the distance between the center of the first cross-section and the boundary of the first cross-section is adjusted to the desired distance to obtain the second three-dimensional image.

[0050] Thirdly, a surgical robot is provided, including a three-dimensional reconstruction device for tubular tissue as described in the second aspect. In this third aspect, the surgical robot can perform a three-dimensional reconstruction method for tubular tissue using the three-dimensional reconstruction device for tubular tissue, thereby achieving a smoother surface for the first tubular tissue.

[0051] Fourthly, an electronic device is provided, comprising: a processor and a memory, the memory for storing computer program code, the computer program code including computer instructions, wherein, when the processor executes the computer instructions, the electronic device performs a method as described in the first aspect above and any possible implementation thereof.

[0052] Fifthly, another electronic device is provided, comprising: a processor, a transmitting device, an input device, an output device, and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein, when the processor executes the computer instructions, the electronic device performs a method as described in the first aspect above and any possible implementation thereof.

[0053] In a sixth aspect, a computer-readable storage medium is provided, wherein a computer program is stored therein, the computer program including program instructions that, when executed by a processor, cause the processor to perform a method as described in the first aspect above and any possible implementation thereof.

[0054] In a seventh aspect, a computer program product is provided, the computer program product comprising a computer program or instructions, wherein, when the computer program or instructions are executed on a computer, the computer performs the method described in the first aspect and any possible implementation thereof.

[0055] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this application. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of this application or the background art, the accompanying drawings used in the embodiments of this application or the background art will be described below.

[0057] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the technical solutions of this application.

[0058] Figure 1 A schematic flowchart illustrating a three-dimensional reconstruction method for tubular tissue provided in an embodiment of this application;

[0059] Figure 2a A schematic diagram of a first three-dimensional image provided in an embodiment of this application;

[0060] Figure 2b A schematic diagram of another first three-dimensional image provided in an embodiment of this application;

[0061] Figure 2c A schematic diagram of yet another first three-dimensional image provided in an embodiment of this application;

[0062] Figure 3a A schematic diagram of a second three-dimensional image provided in an embodiment of this application;

[0063] Figure 3b A schematic diagram of another second three-dimensional image provided in an embodiment of this application;

[0064] Figure 4a A schematic diagram of yet another first three-dimensional image provided in an embodiment of this application;

[0065] Figure 4b A schematic diagram of a first skeleton image provided in an embodiment of this application;

[0066] Figure 5 A schematic diagram of yet another first three-dimensional image provided in an embodiment of this application;

[0067] Figure 6 A schematic diagram of a third three-dimensional image provided in an embodiment of this application;

[0068] Figure 7 A schematic diagram illustrating a process for obtaining a directed graph based on a second skeleton image, provided for an embodiment of this application;

[0069] Figure 8 A schematic diagram of a three-dimensional reconstruction device for tubular tissue provided in an embodiment of this application;

[0070] Figure 9 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0071] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0072] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0073] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. It should be understood that in this application, "at least one" means one or more, "more" means two or more, and "at least two" means two or three or more.

[0074] The execution subject of this application embodiment is a three-dimensional reconstruction method apparatus for tubular tissue (hereinafter referred to as a three-dimensional reconstruction apparatus). The three-dimensional reconstruction apparatus can be any electronic device capable of executing the technical solutions disclosed in the method embodiments of this application. Optionally, the three-dimensional reconstruction apparatus can be one of the following: a mobile phone, a computer, a tablet computer, or a wearable smart device.

[0075] It should be understood that the method embodiments of this application can also be implemented by a processor executing computer program code. The embodiments of this application are described below with reference to the accompanying drawings. Please refer to... Figure 1 , Figure 1 This is a flowchart illustrating a three-dimensional reconstruction method for tubular tissue provided in an embodiment of this application.

[0076] 101. Obtain a first three-dimensional image, wherein the first three-dimensional image includes a first three-dimensional region corresponding to the first tubular tissue, the first tubular tissue is a tissue with a tubular shape, the first three-dimensional image is obtained by three-dimensional reconstruction of x two-dimensional segmentation results of the first tubular tissue, the first three-dimensional region includes a first cross-section, and x is an integer greater than 1.

[0077] In this embodiment, the first three-dimensional image is obtained by three-dimensional reconstruction of x two-dimensional segmentation results of the first tubular tissue. Optionally, the x two-dimensional segmentation results are obtained by segmenting x two-dimensional computed tomography (CT) images including the first tubular tissue. In this case, the x two-dimensional segmentation results are the segmentation results of x two-dimensional CT images, that is, each of the x two-dimensional segmentation results is a two-dimensional CT image. Accordingly, the first three-dimensional image obtained by three-dimensional reconstruction of the x two-dimensional segmentation results is a three-dimensional CT image. Optionally, when each of the x two-dimensional segmentation results is a two-dimensional CT image, the first three-dimensional image is obtained by stacking the x two-dimensional segmentation results to achieve three-dimensional reconstruction of the x two-dimensional segmentation results.

[0078] The first tubular tissue can be a blood vessel or a trachea. The first three-dimensional region is the three-dimensional image region in the first three-dimensional image that corresponds to the first tubular tissue. For example, if the first tubular tissue is a blood vessel, the first three-dimensional region is the three-dimensional blood vessel in the first three-dimensional image.

[0079] The first three-dimensional region includes a first cross-section, wherein the first cross-section is any cross-section within the first three-dimensional region. For example, if the first tubular tissue is a blood vessel, then the first cross-section is the cross-section of the blood vessel. Optionally, the cross-section of the first tubular tissue refers to the section perpendicular to the axis of the first tubular tissue.

[0080] 102. Adjust the boundary of the first cross section in the first three-dimensional image to obtain the second three-dimensional image, wherein the second cross section in the second three-dimensional image is obtained by adjusting the boundary of the first cross section, and the difference between the center of the second cross section and any two pixels in the boundary of the second cross section is less than or equal to the first threshold.

[0081] As mentioned earlier, the first 3D image is obtained by 3D reconstruction of x 2D segmentation results of the first tubular tissue. Since each of the x 2D segmentation results contains errors, the first 3D image obtained by 3D reconstruction of these x 2D segmentation results is prone to having a rough surface of the first tubular tissue, i.e., an uneven surface. In other words, there is at least one set of differing pixels at the boundary of the cross-section of the first tubular tissue. Each set of differing pixels includes two differing pixels, which are pixels within the boundary of the cross-section. The difference in distance between the two differing pixels in the same set and the center is relatively large. Optionally, the distance between the two differing pixels in the same set and the center is greater than a first threshold.

[0082] In step 102, the 3D reconstruction device obtains a second cross-section by adjusting the boundary of the first cross-section. The difference in distance between the center of the second cross-section and any two pixels within its boundary is less than or equal to a first threshold, thereby making the surface of the second cross-section smoother than the surface of the first cross-section. Optionally, the center of the first cross-section and the center of the second cross-section are the same; that is, the 3D reconstruction device uses the center of the first cross-section as a reference to adjust the boundary of the first cross-section to obtain the second cross-section.

[0083] In one possible implementation, the 3D reconstruction apparatus determines the average distance between the center of the first cross section and all pixels on the boundary of the first cross section, and adjusts the boundary of the first cross section based on the average distance to obtain a second cross section, such that the distance between the center of the second cross section and any pixel on the boundary of the second cross section is the average distance.

[0084] In another possible implementation, the 3D reconstruction device determines the median distance between the center of the first cross section and all pixels on the boundary of the first cross section, and adjusts the boundary of the first cross section based on the median value to obtain a second cross section, such that the distance between the center of the second cross section and any pixel on the boundary of the second cross section is the median value.

[0085] In this embodiment, the first three-dimensional image includes a first three-dimensional region corresponding to the first tubular tissue, wherein the first tubular tissue is a tissue with a tubular shape. The first three-dimensional image is obtained by three-dimensional reconstruction of x two-dimensional segmentation results of the first tubular tissue, and the first three-dimensional region includes a first cross-section. Because each of the x two-dimensional segmentation results has errors, that is, the surface of the first tubular tissue in each two-dimensional segmentation result has uneven areas, the first three-dimensional image obtained by three-dimensional reconstruction of x two-dimensional segmentation results is prone to the accumulation of errors in the two-dimensional segmentation results, thereby making the surface of the first tubular tissue in the first three-dimensional segmentation result rough. For example, Figure 2a This is a schematic diagram of a first three-dimensional image provided in an embodiment of this application, wherein, Figure 2a In the middle, the first tubular tissue is the trachea, and the surface of the trachea is rough. Figure 2b A schematic diagram of another first three-dimensional image provided in an embodiment of this application, wherein, Figure 2b In the middle, the first tubular tissue is the blood vessel, and the surface of the blood vessel is rough. Figure 2c A schematic diagram of yet another first three-dimensional image provided in an embodiment of this application, wherein, Figure 2c In the middle, the first tubular tissue is the blood vessel, and the surface of the blood vessel is rough.

[0086] exist Figure 1 In the illustrated three-dimensional reconstruction method for tubular tissue, after acquiring a first three-dimensional image, the three-dimensional reconstruction device adjusts the boundary of a first cross-section in the first three-dimensional image to obtain a second three-dimensional image. The second cross-section in the second three-dimensional image is obtained by adjusting the boundary of the first cross-section. The difference in distance between the center of the second cross-section and any two pixels within the boundary of the second cross-section is less than or equal to a first threshold. This makes the surface of the first tubular tissue smoother.

[0087] For example, Figure 3a This is a schematic diagram of a second three-dimensional image provided in an embodiment of this application. Wherein, Figure 3a The second three-dimensional image shown is based on Figure 1 The method shown is for Figure 2a The first 3D image shown is obtained after processing. (Comparison) Figure 2a and Figure 3a It can be seen that, Figure 3a The surface area of ​​the trachea in the middle is greater than Figure 2a The surface of the trachea is smooth. For example, Figure 3b This is a schematic diagram of another second three-dimensional image provided in an embodiment of this application. Wherein, Figure 3b The second three-dimensional image shown is based on Figure 1 The method shown is for Figure 2c The first 3D image shown is obtained after processing. (Comparison) Figure 3b and Figure 2c It can be seen that, Figure 3b The surface area of ​​blood vessels in Figure 2c The surface of the trachea is smooth.

[0088] It should be understood that the first cross section in the embodiments of this application is a descriptive object selected for the purpose of concisely describing the technical solution, and should not be understood as the three-dimensional reconstruction device only adjusting the boundary of one cross section in the first three-dimensional region. In practical applications, the three-dimensional reconstruction device can adjust the boundary of each cross section in the first three-dimensional region in the same way as adjusting the boundary of the first cross section to obtain the second three-dimensional image.

[0089] As an optional implementation, the three-dimensional reconstruction device performs the following steps during step 102:

[0090] 1021. For each pixel in the boundary of the first cross section, determine the nearest pixel from the first background region to obtain n first background pixels, wherein the first background region is the three-dimensional region in the first three-dimensional image other than the first three-dimensional region.

[0091] 1022. Determine the distance between the center of the first cross section and n first background pixels to obtain n first distances.

[0092] 1023. Based on n first distances, obtain the expected distance of the boundary of the first cross section.

[0093] 1024. Based on the desired distance, adjust the boundary of the first cross section in the first three-dimensional image to obtain the second three-dimensional image.

[0094] In this embodiment, since the n first background pixels are the n pixels in the first background region closest to the boundary of the first cross-section, the n first distances can be used to determine the lateral dimension of the first cross-section, where the first cross-section is parallel to the lateral direction. The lateral dimension of the first cross-section is related to the distance between the center of the first cross-section and its boundary. Therefore, after obtaining the n first distances, the 3D reconstruction device can determine the desired distance between the center of the first cross-section and its boundary based on these n first distances.

[0095] In one alternative implementation, the three-dimensional reconstruction apparatus can determine a first three-dimensional region and a first background region in the first three-dimensional image by segmenting the first tubular tissue in the first three-dimensional image.

[0096] In one optional implementation, the 3D reconstruction apparatus processes a first 3D image based on a 3D skeleton extraction method to obtain a first skeleton image, wherein the first skeleton image includes a skeleton of a first 3D region, and the shape of the skeleton of the first 3D region matches the shape of the first 3D region. Based on the skeleton points in the first skeleton image, the centers of each cross-section in the first 3D region are obtained, wherein the skeleton points are points in the skeleton of the first 3D region, and the centers of each cross-section in the first 3D region include the center of the first cross-section.

[0097] Optionally, the 3D skeleton extraction method is a 3D binary thinning image filter (itkBinaryThinningImageFilter3D). For example, Figure 4a This is a schematic diagram of yet another first three-dimensional image provided in an embodiment of this application. Figure 4a In the image, the first tubular tissue is the trachea, and the first three-dimensional region is the three-dimensional image region of the trachea. Figure 4a The framework of the trachea is also shown. The points in the framework of the first tubular tissue are the centers of the various cross-sections of the trachea. Figure 4b This is a schematic diagram of a first skeleton image provided in an embodiment of this application, wherein, Figure 4b The first skeleton image shown is based on a 3D skeleton extraction method. Figure 4a The first three-dimensional region shown is obtained by processing.

[0098] In this embodiment, the 3D reconstruction device processes a first 3D image using a 3D skeleton extraction method to obtain a first skeleton image, which matches the shape of the skeleton in the first skeleton image with the shape of the first 3D region. Therefore, based on the skeleton points in the first skeleton image, the centers of each cross-section in the first 3D region are obtained, allowing the shape formed by the centers of each cross-section in the first 3D region to match the shape of the first 3D region. Then, based on the center of the first cross-section in the first 3D region, the boundary of the first cross-section is adjusted, making the shape formed by the adjusted first cross-section (i.e., the second cross-section) and other cross-sections more closely match the shape of the first 3D region. For example, if the first 3D region includes a first cross-section adjacent to the first cross-section, obtaining the center of the first cross-section and the center of the third cross-section based on the skeleton points in the first skeleton image allows the relative lateral positions of the centers of the first and third cross-sections to better match the relative lateral positions of the first and third cross-sections. Furthermore, when adjusting the boundary of the first cross-section based on its center, and adjusting the boundary of the third cross-section based on its center, the difference between the adjusted relative lateral positions of the first and third cross-sections and their original relative lateral positions can be reduced.

[0099] In some embodiments, the first tubular tissue belongs to the first object, and the first 3D image is used to plan the target path. The starting point of the target path is a point in the skin region of the first object, and the ending point is a point in the tissue within the first object. Moving the target object along the target path allows it to move from the skin region of the first object to the tissue within the first object; exemplarily, the target object is a needle. Considering that if the target path passes through the first tubular tissue within the first object, it is likely that the target object will collide with the first tubular tissue while moving along the target path, causing damage to the first tubular tissue and thus endangering the first object.

[0100] Adjusting the boundary of the first cross-section in the first 3D image may reduce the lateral dimension of the first cross-section boundary. This reduction in lateral dimension increases the probability of the target path colliding with the actual first tubular tissue. Since the n first distances are larger than the pixel distance between the center and the boundary of the first cross-section, in this embodiment, the 3D reconstruction device obtains the desired distance of the first cross-section boundary based on the n first distances. This reduces the amount of lateral dimension reduction of the first cross-section boundary, thereby lowering the probability of the target path colliding with the actual first tubular tissue.

[0101] As an optional implementation, step 1023 includes the following scheme: obtaining the desired distance based on the minimum value of n first distances. Step 1023 may also include the following scheme: obtaining the desired distance based on the maximum value of n first distances. Step 1023 may also include the following scheme: obtaining the desired distance based on the average value of n first distances.

[0102] In this embodiment, the distance between the center of the second cross section and the pixels in the boundary of the second cross section is the desired distance. At this time, the difference between the distance between the center of the second cross section and any two pixels in the boundary of the second cross section is 0, that is, the shape of the second cross section is circular, and the center of the second cross section is the center of the circle.

[0103] As an optional implementation, step 1023 includes the following scheme: determining m second distances from n first distances, wherein the m second distances are the distances between the center of the first cross-section and m second background pixels out of the n first background pixels, the m second background pixels are the m pixels in the first background region closest to the m first boundary pixels, the m first boundary pixels are the m adjacent pixels in the boundary of the first interface, m is an integer greater than 1 and less than s, and s is the number of pixels in the first interface. If the variance of the m second distances is greater than or equal to a second threshold, the distance between the center of the first cross-section and the m first boundary pixels is obtained based on the average of the m second distances. If the variance of the m second distances is less than the second threshold, the distance between the center of the first cross-section and the m first boundary pixels is obtained based on the m second distances. The desired distance is obtained based on the distance between the center of the first cross section and m first boundary pixels, and the distance between the center of the first cross section and t second boundary pixels. The t second boundary pixels are the pixels in the boundary of the first interface other than the m first boundary pixels. The first distance includes the distance between the center of the first cross section and m first boundary pixels, and the distance between the center of the first cross section and t second boundary pixels.

[0104] In this scheme, since the m second background pixels are the m pixels in the first background region closest to the m first boundary pixels, and the m first boundary pixels are the m adjacent pixels on the boundary of the first interface, the m second distances between the center of the first cross-section and the m second background pixels among the n first background pixels are related to the distance from the center of the first cross-section to the m first boundary pixels. If the variance of the m second distances is large, it indicates that the roughness of the region formed by the m first boundary pixels is large. In this case, the 3D reconstruction device obtains the distance between the center of the first cross-section and the m first boundary pixels based on the average value of the m second distances, thereby reducing the roughness of the region formed by the m first boundary pixels. If the variance of the m second distances is small, it indicates that the roughness of the region formed by the m first boundary pixels is small. In this case, the 3D reconstruction device obtains the distance between the center of the first cross-section and the m first boundary pixels based on the m second distances, thereby reducing the roughness of the region formed by the m first boundary pixels.

[0105] The 3D reconstruction device uses a second threshold as a basis to determine whether the variance of the m second distances is large or small. Specifically, if the variance of the m second distances is greater than or equal to the second threshold, it indicates that the variance of the m second distances is large. If the variance of the m second distances is less than the second threshold, it indicates that the variance of the m second distances is small.

[0106] Therefore, when the variance of the m second distances is greater than or equal to the second threshold, the 3D reconstruction device obtains the distance between the center of the first cross-section and the m first boundary pixels based on the average of the m second distances. When the variance of the m second distances is less than the second threshold, the device obtains the distance between the center of the first cross-section and the m first boundary pixels based on the m second distances. Then, based on the distance between the center of the first cross-section and the m first boundary pixels, and the distance between the center of the first cross-section and the t second boundary pixels, the desired distance is obtained. Thus, the desired distance between the center of the first cross-section and the first cross-section includes the desired distance between the center of the first cross-section and each pixel in the boundary of the first cross-section. At this point, based on the desired distance between the center of the first cross-section and each pixel in the boundary of the first cross-section, the distance between the pixels in the first cross-section and the boundary of the first cross-section is adjusted respectively, thereby adjusting the boundary of the first cross-section to obtain the second cross-section. This reduces the roughness of the boundary of the second cross-section, making the boundary of the second cross-section smoother.

[0107] In some schemes, the 3D reconstruction device acquires a sliding window, wherein the span of the sliding window is m pixels. The starting position of the sliding window is determined from the boundary of a first cross-section, wherein the starting position includes m consecutive pixels of the boundary of the first cross-section, and the endpoints of the m consecutive pixels in the starting position include first endpoint pixels and second endpoint pixels. The direction of movement from the first endpoint pixel to the second endpoint pixel is a first direction, wherein the first direction is either clockwise or counterclockwise. The sliding window is controlled to slide along the boundary of the first cross-section from the starting position in the first direction until the sliding window stops sliding at a termination pixel, wherein the termination pixel is a pixel adjacent to the first endpoint pixel in the boundary of the first cross-section, and the termination pixel does not belong to the m consecutive pixels of the starting position. The step size of the sliding window is r pixels, where r is a positive integer less than nm. During the sliding of the sliding window along the boundary of the first cross-section, the m pixels within the sliding window are taken as m first boundary pixels, where r is a positive integer less than nm. Optionally, r is 1.

[0108] During the sliding window's movement, each slide yields m first boundary pixels. The 3D reconstruction device determines the distances between these m first boundary pixels and the center of the first cross-section based on this scheme, thus making the first cross-section smoother. For example, the boundary of the first cross-section includes pixels a, b, and c, where m=2. At the initial position of the sliding window, which includes pixels a and b, the distances between the center of the first cross-section and pixel a, and between the center of the first cross-section and pixel b, can be obtained using this implementation. After the sliding window slides one pixel, it includes pixels b and c, having now slid along the boundary of the first cross-section. The distances between the center of the first cross-section and pixel b, and between the center of the first cross-section and pixel c, can be obtained using this implementation. It should be understood that the distance between the center of the first cross-section and pixel b can be obtained both at the initial position and after the sliding window has slid. In the expected distance between the center of the first cross-section and the boundary of the first cross-section, the distance between the pixel of the center of the first cross-section and the boundary of the first cross-section is the final distance obtained, that is, the distance between the center of the first cross-section and pixel b is obtained based on the sliding window sliding one pixel.

[0109] In other schemes, the 3D reconstruction device acquires a sliding window, wherein the span of the sliding window is m pixels. The starting position of the sliding window is determined from the boundary of a first cross-section, wherein the starting position includes m consecutive pixels of the boundary of the first cross-section. The sliding window is controlled to slide along the boundary of the first cross-section in a first direction from the starting position until the variance of the distances between the m pixels within the sliding window and the center of the first cross-section is less than a second threshold, wherein the step size of the sliding window is r pixels. During the sliding process of the sliding window along the boundary of the first cross-section, the m pixels within the sliding window are designated as m first boundary pixels.

[0110] In this scheme, the sliding window stops sliding when the variance of the distances between m pixels and the center of the first cross-section is less than a second threshold, which makes the first cross-section smoother. It should be understood that when the sliding window includes a pixel in the boundary again, the distance between that pixel and the center of the first cross-section will be updated. Specifically, the distance between the center of the first cross-section and the pixels at the boundary of the first cross-section is obtained by considering the distances between the m pixels in the sliding window and the center of the first cross-section when the sliding window last includes that pixel.

[0111] As an optional implementation, step 1024 includes the following: obtaining a third distance between the center of a third cross-section and its boundary, wherein the third cross-section is a cross-section adjacent to the first cross-section in the first three-dimensional region. If the difference between the desired distance and the third distance is greater than a third threshold, the desired distance is reduced to obtain a fourth distance, wherein the difference between the fourth distance and the third distance is equal to the third threshold. The boundary of the first cross-section in the distance between the center of the first three-dimensional image cross-section and its boundary is adjusted to the fourth distance to obtain a second three-dimensional image. If the difference between the desired distance and the third distance is less than or equal to the third threshold, the distance between the center of the first cross-section and its boundary is adjusted to the desired distance to obtain the second three-dimensional image.

[0112] Because there are cross-sections other than the first cross-section in the first three-dimensional region, adjusting the boundary of the first cross-section may result in a large difference between the lateral dimensions of the first cross-section and the third cross-section, i.e., a large difference between the distance between the center and the boundary of the first cross-section and the distance between the center and the boundary of the third cross-section. This can easily lead to a large roughness of the first tubular tissue in the first three-dimensional region, where the third cross-section is the cross-section adjacent to the first cross-section in the first three-dimensional region. Optionally, both the third cross-section and the first cross-section are parallel to the lateral direction. Therefore, in this embodiment, after obtaining the desired distance and the distance between the center and the boundary of the third cross-section (i.e., the aforementioned third distance), the three-dimensional reconstruction device first determines whether the difference between the desired distance and the third distance is large or small. If the difference is large, the distance between the center and the boundary of the first cross-section is adjusted based on the desired distance to make the difference between the adjusted distance and the third distance smaller, thereby reducing the roughness of the first tubular tissue in the first three-dimensional region and making the first tubular tissue in the first three-dimensional region smooth.

[0113] In this embodiment, the 3D reconstruction device uses a third threshold as a basis to determine whether the difference between the distance between the center of the first cross-section and the boundary of the first cross-section is large or small, that is, whether the difference between the expected distance and the third distance is large or small. Specifically, if the difference between the expected distance and the third distance is greater than the third threshold, it indicates that the difference between the expected distance and the third distance is large; if the difference between the expected distance and the third distance is less than or equal to the third threshold, it indicates that the difference between the expected distance and the third distance is small. Based on this embodiment, the 3D reconstruction device adjusts the boundary of the first cross-section to obtain a second 3D image, which can make the surface of the first tubular tissue in the second 3D image smoother.

[0114] To better understand the three-dimensional reconstruction method for tubular tissues provided in this application's embodiments, the following description will use the trachea as an example of the first tubular tissue. Please refer to... Figure 5 , Figure 5This is a schematic diagram of yet another first three-dimensional image provided in an embodiment of this application. Figure 5 In the middle, the first tubular tissue is the trachea, such as Figure 5 As shown, the surface of the trachea is rough, and there are discontinuous regions within the trachea. First, a first three-dimensional region is determined from the first three-dimensional image, and then the volume of each connected region within the first three-dimensional region is determined. Connected regions in the first three-dimensional image with a volume less than or equal to a fourth threshold are removed to obtain a third three-dimensional image. This allows for the removal of some discontinuous regions in the trachea, for example... Figure 6 This is a schematic diagram of a third three-dimensional image provided in an embodiment of this application. A second three-dimensional region and a second background region corresponding to the first tubular tissue are determined in the third three-dimensional image, wherein the second background region is the image region in the third three-dimensional image excluding the second three-dimensional region. The distance between each pixel in the second three-dimensional region and the nearest pixel in the second background region is determined, obtaining a sixth distance for each pixel in the second three-dimensional region. The third three-dimensional image is processed based on a three-dimensional skeleton extraction method to obtain a second skeleton image, wherein the second skeleton image includes the skeleton of the second three-dimensional region, and the shape of the skeleton of the second three-dimensional region matches the shape of the second three-dimensional region. A directed graph is obtained based on the second skeleton image, wherein the nodes in the directed graph correspond one-to-one with the skeleton points in the skeleton of the second three-dimensional region, and the weight of the node is the sixth distance to the corresponding skeleton point. An edge between two nodes in the directed graph indicates that the two skeleton points corresponding to the two nodes are adjacent skeleton points. Based on the topological relationship and node weights in the directed graph, a second three-dimensional image is generated, wherein the center of each cross-section in the second three-dimensional image is a node in the finite graph, and the distance between the center of each cross-section and the boundary of each cross-section is the node weight.

[0115] Optional, Figure 7 This is a schematic diagram illustrating a process for obtaining a directed graph based on a second skeleton image, as provided in an embodiment of this application. Figure 7 As shown, after the process begins, the second skeleton image is traversed first, that is, the pixels in the second skeleton image are traversed. During the traversal, each pixel in the second skeleton image is sequentially checked to see if it is a skeleton point. If the result is yes, otherwise, the traversal of other pixels in the second skeleton image continues. If the result is yes, a node corresponding to the skeleton point is added to the directed graph, and the weight of the node is determined. The weight of the determined node is the sixth distance of the skeleton point. Then, a neighborhood search is performed on the skeleton point to determine whether a skeleton point exists in its neighborhood. Specifically, it is checked whether a skeleton point exists among the pixels adjacent to the skeleton point in the second skeleton image. If a skeleton point exists in the neighborhood, the node corresponding to the skeleton point in the neighborhood is added to the directed graph, and an edge is added between the node corresponding to the skeleton point and the node corresponding to the skeleton point found in the neighborhood search. If no skeleton point exists in the neighborhood, the traversal of other pixels in the second skeleton image continues.

[0116] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0117] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, while using clear signs / information to inform users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, personal information processing may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0118] The methods of the embodiments of this application have been described in detail above, and the apparatus of the embodiments of this application is provided below.

[0119] Please see Figure 8 , Figure 8 This is a schematic diagram of a three-dimensional reconstruction device for tubular tissue provided in an embodiment of this application. The three-dimensional reconstruction device 1 for tubular tissue includes: an acquisition unit 11 and an adjustment unit 12, wherein:

[0120] The acquisition unit 11 is used to acquire a first three-dimensional image, the first three-dimensional image including a first three-dimensional region corresponding to a first tubular tissue, the first tubular tissue being a tissue with a tubular shape, the first three-dimensional image being obtained by three-dimensional reconstruction of x two-dimensional segmentation results of the first tubular tissue, the first three-dimensional region including a first cross-section, and x being an integer greater than 1;

[0121] The adjustment unit 12 is used to adjust the boundary of the first cross section in the first three-dimensional image to obtain a second three-dimensional image. The second cross section in the second three-dimensional image is obtained by adjusting the boundary of the first cross section. The difference between the center of the second cross section and any two pixels in the boundary of the second cross section is less than or equal to a first threshold.

[0122] In conjunction with any embodiment of this application, the adjustment unit 12 is further configured to:

[0123] For each pixel in the boundary of the first cross section, a nearest pixel is determined from the first background region to obtain n first background pixels. The first background region is the three-dimensional region in the first three-dimensional image other than the first three-dimensional region.

[0124] Determine the distance between the center of the first cross-section and the n first background pixels to obtain n first distances;

[0125] Based on the n first distances, the expected distance between the center of the first cross-section and the boundary of the first cross-section is obtained;

[0126] Based on the desired distance, the boundary of the first cross-section in the first three-dimensional image is adjusted to obtain the second three-dimensional image.

[0127] In conjunction with any embodiment of this application, the adjustment unit 12 is further configured to:

[0128] The expected distance is obtained based on the minimum value of the n first distances;

[0129] Alternatively, the desired distance can be obtained based on the maximum value of the n first distances;

[0130] Alternatively, the desired distance can be obtained based on the average of the n first distances.

[0131] In any embodiment of this application, the distance between the center of the second cross section and the pixels in the boundary of the second cross section is the desired distance.

[0132] In conjunction with any embodiment of this application, the adjustment unit 12 is further configured to:

[0133] From the n first distances, m second distances are determined, wherein the m second distances are the distances between the center of the first cross-section and the m second background pixels among the n first background pixels, the m second background pixels are the m pixels in the first background region that are closest to the m first boundary pixels, the m first boundary pixels are the m adjacent pixels in the boundary of the first interface, where m is an integer greater than 1 and less than s, and s is the number of pixels in the first interface;

[0134] If the variance of the m second distances is greater than or equal to the second threshold, the distance between the center of the first cross-section and the m first boundary pixels is obtained based on the average of the m second distances.

[0135] If the variance of the m second distances is less than the second threshold, the distance between the center of the first cross-section and the m first boundary pixels is obtained based on the m second distances.

[0136] The desired distance is obtained based on the distance between the center of the first cross section and the m first boundary pixels, and the distance between the center of the first cross section and the t second boundary pixels. The t second boundary pixels are the pixels in the boundary of the first interface other than the m first boundary pixels. The first distance includes the distance between the center of the first cross section and the m first boundary pixels, and the distance between the center of the first cross section and the t second boundary pixels.

[0137] In conjunction with any embodiment of this application, the adjustment unit 12 is further configured to:

[0138] Obtain the third distance between the center of the third cross section and the boundary of the third cross section, wherein the third cross section is the cross section adjacent to the first cross section in the first three-dimensional region;

[0139] If the difference between the expected distance and the third distance is greater than a third threshold, the expected distance is reduced to obtain a fourth distance, and the difference between the fourth distance and the third distance is equal to the third threshold.

[0140] The distance between the center of the first cross-section and the boundary of the first cross-section is adjusted to the fourth distance to obtain the second three-dimensional image;

[0141] If the difference between the desired distance and the third distance is less than or equal to the third threshold, the distance between the center of the first cross-section and the boundary of the first cross-section is adjusted to the desired distance to obtain the second three-dimensional image.

[0142] In this embodiment, the first three-dimensional image includes a first three-dimensional region corresponding to the first tubular tissue, wherein the first tubular tissue is a tissue with a tubular shape. The first three-dimensional image is obtained by three-dimensional reconstruction of x two-dimensional segmentation results of the first tubular tissue, and the first three-dimensional region includes a first cross-section. Because each of the x two-dimensional segmentation results has errors, that is, the surface of the first tubular tissue in each two-dimensional segmentation result has uneven areas, the first three-dimensional image obtained by three-dimensional reconstruction of x two-dimensional segmentation results is prone to the accumulation of errors in the two-dimensional segmentation results, thereby making the surface of the first tubular tissue in the first three-dimensional segmentation result rough.

[0143] After acquiring a first three-dimensional image, the three-dimensional reconstruction device for tubular tissue adjusts the boundary of a first cross-section in the first three-dimensional image to obtain a second three-dimensional image. The second cross-section in the second three-dimensional image is obtained by adjusting the boundary of the first cross-section. The difference in distance between the center of the second cross-section and any two pixels within the boundary of the second cross-section is less than or equal to a first threshold. This makes the surface of the first tubular tissue smoother.

[0144] In some embodiments, the functions or modules of the apparatus provided in this application can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0145] Figure 9 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. The electronic device 2 includes a processor 21 and a memory 22. Optionally, the electronic device 2 also includes an input device 23 and an output device 24. The processor 21, memory 22, input device 23, and output device 24 are coupled together via connectors, which include various interfaces, transmission lines, or buses, etc., and are not limited in this embodiment. It should be understood that in the various embodiments of this application, coupling refers to mutual connection in a specific way, including direct connection or indirect connection through other devices, such as through various interfaces, transmission lines, buses, etc.

[0146] The processor 21 can be one or more graphics processing units (GPUs). If the processor 21 is a GPU, the GPU can be a single-core GPU or a multi-core GPU. Optionally, the processor 21 can be a processor group composed of multiple GPUs, with the multiple processors coupled to each other via one or more buses. Optionally, the processor can also be other types of processors, etc., which are not limited in this embodiment.

[0147] The memory 22 can be used to store computer program instructions, as well as various types of computer program code, including program code for executing the scheme of this application. Optionally, the memory includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), which is used for related instructions and data.

[0148] Input device 23 is used to input data and / or signals, and output device 24 is used to output data and / or signals. Input device 23 and output device 24 can be independent devices or an integrated device.

[0149] It is understood that in this embodiment of the application, the memory 22 can be used not only to store related instructions, but also to store related data. For example, the memory 22 can be used to store the first three-dimensional image obtained by the input device 23, or the memory 22 can also be used to store the second three-dimensional image obtained by the processor 21, etc. This embodiment of the application does not limit the specific data stored in the memory.

[0150] Understandable Figure 9 This is merely a simplified design of an electronic device. In practical applications, the electronic device may also include other necessary components, including, but not limited to, any number of input / output devices, processors, memories, etc., and all electronic devices that can implement the embodiments of this application are within the protection scope of this application.

[0151] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0152] Those skilled in the art will readily understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. Those skilled in the art will also readily understand that the various embodiments of this application have different focuses, and for the sake of convenience and brevity, the same or similar parts may not be repeated in different embodiments. Therefore, parts not described or not described in detail in one embodiment can be referred to the descriptions in other embodiments.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0154] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0155] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0156] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital versatile discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0157] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for three-dimensional reconstruction of tubular tissue, characterized in that, The method includes: A first three-dimensional image is obtained, the first three-dimensional image includes a first three-dimensional region corresponding to a first tubular tissue, the first tubular tissue is a tissue with a tubular shape, the first three-dimensional image is obtained by three-dimensional reconstruction of x two-dimensional segmentation results of the first tubular tissue, the first three-dimensional region includes a first cross-section, and x is an integer greater than 1; The boundary of the first cross section in the first three-dimensional image is adjusted to obtain the second three-dimensional image. The second cross section in the second three-dimensional image is obtained by adjusting the boundary of the first cross section. The difference between the center of the second cross section and any two pixels in the boundary of the second cross section is less than or equal to a first threshold. The step of adjusting the boundary of the first cross-section in the first three-dimensional image to obtain the second three-dimensional image includes: for each pixel in the boundary of the first cross-section, determining the nearest pixel from a first background region to obtain n first background pixels, wherein the first background region is a three-dimensional region in the first three-dimensional image other than the first three-dimensional region; determining the distance between the center of the first cross-section and the n first background pixels to obtain n first distances; based on the n first distances, obtaining the desired distance between the center of the first cross-section and the boundary of the first cross-section; and adjusting the boundary of the first cross-section in the first three-dimensional image based on the desired distance to obtain the second three-dimensional image. The step of obtaining the expected distance between the center of the first cross-section and the boundary of the first cross-section based on the n first distances includes: determining m second distances from the n first distances, wherein the m second distances are the distances between the center of the first cross-section and m second background pixels among the n first background pixels, the m second background pixels are the m pixels in the first background region closest to the m first boundary pixels, the m first boundary pixels are the m adjacent pixels on the boundary of the first cross-section, m is an integer greater than 1 and less than s, and s is the number of pixels in the first cross-section; and if the variance of the m second distances is greater than or equal to a second threshold, the expected distance is determined based on the average variance of the m second distances. The mean is used to obtain the distance between the center of the first cross-section and the m first boundary pixels. If the variance of the m second distances is less than the second threshold, the distance between the center of the first cross-section and the m first boundary pixels is obtained based on the m second distances. The expected distance is obtained based on the distance between the center of the first cross-section and the m first boundary pixels and the distance between the center of the first cross-section and t second boundary pixels, where the t second boundary pixels are the pixels in the boundary of the first cross-section other than the m first boundary pixels. The expected distance includes the distance between the center of the first cross-section and the m first boundary pixels and the distance between the center of the first cross-section and the t second boundary pixels.

2. The method according to claim 1, characterized in that, The step of adjusting the boundary of the first cross-section in the first three-dimensional image based on the desired distance to obtain the second three-dimensional image includes: Obtain the third distance between the center of the third cross section and the boundary of the third cross section, wherein the third cross section is the cross section adjacent to the first cross section in the first three-dimensional region; If the difference between the expected distance and the third distance is greater than a third threshold, the expected distance is reduced to obtain a fourth distance, and the difference between the fourth distance and the third distance is equal to the third threshold. The distance between the center of the first cross-section and the boundary of the first cross-section is adjusted to the fourth distance to obtain the second three-dimensional image; If the difference between the desired distance and the third distance is less than or equal to the third threshold, the distance between the center of the first cross-section and the boundary of the first cross-section is adjusted to the desired distance to obtain the second three-dimensional image.

3. A three-dimensional reconstruction device for tubular tissue, characterized in that, The three-dimensional reconstruction device for the tubular tissue includes: The acquisition unit is used to acquire a first three-dimensional image, the first three-dimensional image including a first three-dimensional region corresponding to a first tubular tissue, the first tubular tissue being a tissue with a tubular shape, the first three-dimensional image being obtained by three-dimensional reconstruction of x two-dimensional segmentation results of the first tubular tissue, the first three-dimensional region including a first cross-section, and x being an integer greater than 1; An adjustment unit is used to adjust the boundary of the first cross section in the first three-dimensional image to obtain a second three-dimensional image. The second cross section in the second three-dimensional image is obtained by adjusting the boundary of the first cross section. The difference between the center of the second cross section and any two pixels in the boundary of the second cross section is less than or equal to a first threshold. The step of adjusting the boundary of the first cross-section in the first three-dimensional image to obtain the second three-dimensional image includes: for each pixel in the boundary of the first cross-section, determining the nearest pixel from a first background region to obtain n first background pixels, wherein the first background region is a three-dimensional region in the first three-dimensional image other than the first three-dimensional region; determining the distance between the center of the first cross-section and the n first background pixels to obtain n first distances; based on the n first distances, obtaining the desired distance between the center of the first cross-section and the boundary of the first cross-section; and adjusting the boundary of the first cross-section in the first three-dimensional image based on the desired distance to obtain the second three-dimensional image. The step of obtaining the expected distance between the center of the first cross-section and the boundary of the first cross-section based on the n first distances includes: determining m second distances from the n first distances, wherein the m second distances are the distances between the center of the first cross-section and m second background pixels among the n first background pixels, the m second background pixels are the m pixels in the first background region closest to the m first boundary pixels, the m first boundary pixels are the m adjacent pixels on the boundary of the first cross-section, m is an integer greater than 1 and less than s, and s is the number of pixels in the first cross-section; and if the variance of the m second distances is greater than or equal to a second threshold, the expected distance is determined based on the average variance of the m second distances. The mean is used to obtain the distance between the center of the first cross-section and the m first boundary pixels. If the variance of the m second distances is less than the second threshold, the distance between the center of the first cross-section and the m first boundary pixels is obtained based on the m second distances. The expected distance is obtained based on the distance between the center of the first cross-section and the m first boundary pixels and the distance between the center of the first cross-section and t second boundary pixels, where the t second boundary pixels are the pixels in the boundary of the first cross-section other than the m first boundary pixels. The expected distance includes the distance between the center of the first cross-section and the m first boundary pixels and the distance between the center of the first cross-section and the t second boundary pixels.

4. A surgical robot, characterized in that, Includes the three-dimensional reconstruction device for tubular tissue as described in claim 3.

5. An electronic device, characterized in that, include: A processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein, when the processor executes the computer instructions, the electronic device performs the method as described in claim 1 or 2.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method of claim 1 or 2.

Images