Surface reconstruction method, computer device and storage medium

Abstract

The application relates to a curved surface reconstruction method, a computer device and a storage medium. The method comprises the following steps: performing segmentation processing on an acquired medical image of a to-be-tested object to determine a target segmentation image corresponding to the medical image; determining a plurality of target sampling points on a target tissue and the positions of the target sampling points according to the target segmentation image; determining a plurality of sampling planes perpendicular to tangent lines at the target sampling points according to the positions of the target sampling points; determining plane images corresponding to the sampling planes in the medical image, and stacking the plane images in sequence to determine a curved surface reconstruction image corresponding to the medical image; the target segmentation image comprises a target tissue or a target structure, and the target segmentation image is a curved surface image; and the sampling planes of the target sampling points all pass through the corresponding target sampling points. The method can ensure the accuracy of the obtained curved surface reconstruction image.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to a curved surface reconstruction method, a computer device and a storage medium. BACKGROUND

[0002] The spine is an important support for maintaining the shape of the human body, so the spine is very important to the human body. The good or bad of the spine shape also represents the good or bad of the human body condition to some extent. Through observation and analysis of the shape of the spine, the body condition of the human body can be known in time, so it is particularly important to observe and analyze the shape of the spine.

[0003] In the related art, when analyzing and observing the spine of a patient, an image of the spine part of the patient is usually first obtained by shooting, and then a doctor can select a more appropriate point on the spine in the image according to experience to perform curved surface reconstruction of the spine part, to obtain a curved surface reconstruction image of the spine, and then observe and analyze the spine of the patient through the curved surface reconstruction image to obtain an analysis result of the spine.

[0004] However, the accuracy of the curved surface reconstruction image obtained by using the above-mentioned technology cannot be guaranteed, so the accuracy of the analysis result obtained by observing and analyzing through the curved surface reconstruction image cannot be guaranteed. SUMMARY

[0005] Therefore, it is necessary to provide a curved surface reconstruction method, a computer device and a storage medium which can guarantee the accuracy of the obtained curved surface reconstruction image, so as to guarantee the accuracy of the analysis result obtained by observing and analyzing through the curved surface reconstruction image.

[0006] In a first aspect, the present application provides a curved surface reconstruction method, which comprises:

[0007] segmenting a medical image of an acquired object to be tested to determine a target segmentation image corresponding to the medical image; the target segmentation image includes a target tissue or a target structure, and the target segmentation image is a curved surface image;

[0008] determining a plurality of target sampling points on the target tissue and positions of the target sampling points according to the target segmentation image;

[0009] determining a sampling plane perpendicular to a tangent line at each target sampling point according to the position of each target sampling point; the sampling plane of each target sampling point passes through the corresponding target sampling point;

[0010] determining a plane image corresponding to each sampling plane in the medical image, and stacking each plane image in sequence to determine a curved surface reconstruction image corresponding to the medical image.

[0011] In one of the embodiments, the determining the sampling planes perpendicular to the tangents at the target sampling points according to the positions of the target sampling points comprises:

[0012] calculating the tangents at the target sampling points in the transverse plane, and / or, the sagittal plane, and / or, the coronal plane according to the positions of the target sampling points;

[0013] constructing the sampling planes passing through the corresponding target sampling points with the tangents as the normal directions, to obtain the sampling planes.

[0014] In one of the embodiments, the determining the target sampling points on the target tissue according to the target segmentation image comprises:

[0015] performing centerline extraction processing on the target tissue according to the target segmentation image to determine a plurality of initial sampling points constituting a centerline of the target tissue; the distances between the initial sampling points are not all equal;

[0016] re-sampling the plurality of initial sampling points to determine a plurality of target sampling points; the distances between the target sampling points are all equal.

[0017] In one of the embodiments, the re-sampling the plurality of initial sampling points to determine the plurality of target sampling points comprises:

[0018] performing curve fitting processing on the plurality of initial sampling points to determine a reference centerline corresponding to the target tissue, and determining a target centerline according to the reference centerline;

[0019] re-sampling the target centerline at equal distances with a preset sampling size to determine the plurality of target sampling points.

[0020] In one of the embodiments, the determining the target centerline according to the reference centerline comprises:

[0021] determining the reference centerline as the target centerline; or,

[0022] projecting the reference centerline onto a sagittal plane to obtain a sagittal centerline, and determining the sagittal centerline as the target centerline; or,

[0023] projecting the reference centerline onto a coronal plane to obtain a coronal centerline, and determining the coronal centerline as the target centerline.

[0024] In one of the embodiments, before the sequentially stacking the plane images, the method further comprises:

[0025] performing a rotation operation, the rotation operation comprising: rotating each target sampling point corresponding planar image along a first axis by a corresponding initial rotation angle to obtain a new target sampling point corresponding planar image;

[0026] determining whether the new planar image meets an iteration stop condition, and when the new planar image does not meet the iteration stop condition, adjusting the initial rotation angle by a set step to obtain a new initial rotation angle, and returning to perform the rotation operation until the new planar image meets the iteration stop condition;

[0027] The iteration stop condition is that each new planar image is symmetrically distributed along a second axis, and a plane formed by the first axis and the second axis is a transverse plane.

[0028] In one embodiment, the stacking of the planar images comprises:

[0029] stacking the new planar images in sequence.

[0030] In one embodiment, the curved surface reconstruction image comprises at least one of a transverse curved surface reconstruction image, a sagittal curved surface reconstruction image, and a coronal curved surface reconstruction image.

[0031] In a second aspect, the present application further provides a curved surface reconstruction device, the device comprising:

[0032] a segmentation module configured to perform segmentation processing on an obtained medical image of a to-be-tested object to determine a target segmentation image corresponding to the medical image, wherein the target segmentation image comprises a target tissue or a target structure, and the target segmentation image is a curved surface image;

[0033] a sampling point determination module configured to determine a plurality of target sampling points on the target tissue and positions of the target sampling points according to the target segmentation image;

[0034] a sampling plane determination module configured to determine a plurality of sampling planes perpendicular to tangent lines at the target sampling points according to the positions of the target sampling points, wherein each sampling plane of each target sampling point passes through the corresponding target sampling point;

[0035] a reconstruction module configured to determine a plurality of planar images corresponding to the sampling planes in the medical image, and stack the planar images in sequence to determine a curved surface reconstruction image corresponding to the medical image.

[0036] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0037] Segmenting the obtained medical image of the to-be-tested object to determine a target segmentation image corresponding to the medical image; the target segmentation image includes a target tissue or a target structure, and the target segmentation image is a curved surface image;

[0038] According to the target segmentation image, a plurality of target sampling points on the target tissue and positions of the target sampling points are determined;

[0039] According to the positions of the target sampling points, sampling planes perpendicular to tangent lines at the target sampling points are determined; the sampling planes of the target sampling points all pass through the corresponding target sampling points;

[0040] Plane images corresponding to the sampling planes are determined in the medical image, and the plane images are stacked in sequence to determine a curved surface reconstruction image corresponding to the medical image.

[0041] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0042] Segmenting the obtained medical image of the to-be-tested object to determine a target segmentation image corresponding to the medical image; the target segmentation image includes a target tissue or a target structure, and the target segmentation image is a curved surface image;

[0043] According to the target segmentation image, a plurality of target sampling points on the target tissue and positions of the target sampling points are determined;

[0044] According to the positions of the target sampling points, sampling planes perpendicular to tangent lines at the target sampling points are determined; the sampling planes of the target sampling points all pass through the corresponding target sampling points;

[0045] Plane images corresponding to the sampling planes are determined in the medical image, and the plane images are stacked in sequence to determine a curved surface reconstruction image corresponding to the medical image.

[0046] In a fifth aspect, the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the following steps:

[0047] Segmenting the obtained medical image of the to-be-tested object to determine a target segmentation image corresponding to the medical image; the target segmentation image includes a target tissue or a target structure, and the target segmentation image is a curved surface image;

[0048] According to the target segmentation image, a plurality of target sampling points on the target tissue and positions of the target sampling points are determined;

[0049] According to the positions of the target sampling points, sampling planes perpendicular to tangent lines at the target sampling points are determined; the sampling plane of each target sampling point passes through the corresponding target sampling point;

[0050] Plane images corresponding to the sampling planes are determined in the medical image, and the plane images are stacked in sequence to determine a curved surface reconstruction image corresponding to the medical image.

[0051] The curved surface reconstruction method, the computer device and the storage medium, by segmenting the obtained medical image of the to-be-tested object, determining a target segmentation image including a target tissue or a target structure, and determining a plurality of target sampling points corresponding to the target tissue and their positions according to the target segmentation image, determining a sampling plane perpendicular to a tangent line at each target sampling point according to the position of each target sampling point, and stacking in sequence the plane images corresponding to the sampling planes determined in the medical image to obtain a curved surface reconstruction image; wherein the target segmentation image is a curved surface image, and the sampling plane of each target sampling point passes through the corresponding target sampling point. In this method, since a corresponding sampling plane can be set at each of the plurality of sampling points corresponding to the target tissue, and then a plurality of plane images are obtained in the medical image through the plurality of sampling planes to obtain a curved surface reconstruction image, the curved surface reconstruction image determined in this way considers more sampling points than the curved surface reconstruction image obtained for one sampling point, and the obtained curved surface reconstruction image is more accurate, so that the analysis result obtained after observing and analyzing the curved surface reconstruction images obtained for the plurality of sampling points is more accurate. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 It is an internal structure diagram of the computer device in one embodiment;

[0053] Figure 2 It is a flowchart of the curved surface reconstruction method in one embodiment;

[0054] Figure 3 It is an example diagram of spinal cord segmentation based on a neural network model in one embodiment;

[0055] Figure 4 It is a flowchart of the curved surface reconstruction method in another embodiment;

[0056] Figure 5 It is a flowchart of the curved surface reconstruction method in another embodiment;

[0057] Figure 6 It is an example diagram of the spinal cord body center line in the transverse position in another embodiment;

[0058] Figure 7 It is an example diagram of the spinal cord body center line in the sagittal position in another embodiment;

[0059] Figure 8Fig. 6 is an example diagram of a spinal cord body centerline in a coronal view in another embodiment;

[0060] Figure 9 Fig. 7 is a flowchart of a surface reconstruction method in another embodiment;

[0061] Figure 10 Fig. 8 is an example diagram of a spinal cord body three-dimensional transverse surface reconstruction image in another embodiment;

[0062] Figure 11 Fig. 9 is an example diagram of a spinal cord body three-dimensional sagittal surface reconstruction image in another embodiment;

[0063] Figure 12 Fig. 10 is an example diagram of a spinal cord body three-dimensional coronal surface reconstruction image in another embodiment;

[0064] Figure 13 Fig. 11 is a specific flowchart of a surface reconstruction method in another embodiment;

[0065] Figure 14 Fig. 12 is a structural block diagram of a surface reconstruction device in an embodiment. DETAILED DESCRIPTION

[0066] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0067] The surface reconstruction method provided by the embodiments of the present application can be applied to an image scanning system, which includes a scanning device and a computer device connected with each other. The scanning device can be a CT device, an Mr device, etc. The scanning device is mainly used for scanning a to-be-measured object to obtain scanning data and sending the scanning data to the computer device for processing. After receiving the scanning data sent by the scanning device, the computer device can perform image reconstruction, image post-processing, etc. on the scanning data to obtain corresponding image reconstruction results, image processing results, etc. The computer device can be a terminal or a server. Taking the terminal as an example, its internal structure diagram can be as shown in Fig. 1. Figure 1As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is used for wired or wireless communication with external terminals. Wireless communication can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement a curved surface reconstruction method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad provided on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0068] Those skilled in the art can understand that, Figure 1 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0069] In one embodiment, as Figure 2 shown, a curved surface reconstruction method is provided. The method is applied to Figure 1 a computer device in the figure. The method can include the following steps:

[0070] S202, segmenting the obtained medical image of the to-be-tested object to determine the target segmentation image corresponding to the medical image.

[0071] The medical image of the to-be-tested object can be obtained by image reconstruction of the scanning data after real-time scanning of the to-be-tested object; it can also be pre-stored in the cloud or server, and the medical image of the to-be-tested object can be obtained by calling the cloud or server when needed. Of course, the medical image of the to-be-tested object can also be obtained by other methods, which are not limited here. The medical image here can be a CT image, an X-ray image, etc.

[0072] In addition, the medical image of the to-be-tested object can be segmented by using a segmentation algorithm, or a segmentation model composed of a neural network model, or other manual segmentation methods, as long as the target segmentation image corresponding to the medical image can be obtained.

[0073] The target segmentation image obtained above includes a target tissue or a target structure, which can be a spine or a vertebra, can be a spinal cord in the vertebra, and of course can be a tissue or structure in other parts. For the medical image and the target segmentation image, the medical image and the target segmentation image can both be curved surface images. Here, the curved surface image refers to that the target tissue or the target structure included in the medical image and the target segmentation image is imaged in a natural curved surface state.

[0074] For example, taking the target tissue or the target structure as the spinal cord as an example, the target segmentation image obtained after the image segmentation processing by the segmentation model constituted by the neural network model can be seen from FIG. 1, wherein the target segmentation image includes a target tissue or a target structure in different anatomical positions, and a mask image of the target tissue or the target structure. Figure 3 Figure 3 The target segmentation image includes a target tissue or a target structure in different anatomical positions, and a mask image of the target tissue or the target structure.

[0075] S204, according to the target segmentation image, determining a plurality of target sampling points corresponding to the target tissue and positions of the target sampling points.

[0076] The following mainly takes the target included in the target segmentation image as an example to illustrate the target segmentation image, which is similar to the target structure included in the target segmentation image. Generally, the obtained target segmentation image can be a mask image of the target tissue, and the pixel value of the target tissue part and the pixel value of the non-target tissue part (i.e. the background part) in the mask image are different.

[0077] After obtaining the target segmentation image, the target tissue in the target segmentation image can be obtained, and then sampling point extraction processing can be performed at each position of the target tissue to obtain a plurality of target sampling points corresponding to the target tissue. The number of the plurality of target sampling points can be set according to actual conditions, which is not specifically limited here. At the same time, since the target segmentation image includes the positions of each point on the target tissue, after the plurality of target sampling points are extracted, the positions of the plurality of target sampling points can also be obtained at the same time.

[0078] In addition, for the plurality of target sampling points, the distance between any two target sampling points can be equal, that is, the target sampling points are equidistant, so that the information on each layer of medical image can be considered when the curved surface is reconstructed, and the information on a certain layer of medical image can be avoided to be missed, so that the accuracy of the curved surface reconstruction image obtained subsequently can be improved.

[0079] S206, according to the positions of the target sampling points, determining a plurality of sampling planes perpendicular to the tangent lines at the target sampling points.

[0080] ​After the plurality of target sampling points and their positions are determined, which generally correspond to different positions on the target tissue, the tangent lines at the target sampling points can be obtained through the positions of the target sampling points, and the sampling planes perpendicular to the tangent lines at the target sampling points can be obtained through the tangent lines.

[0081] Here, the sampling planes of the target sampling points all pass through the corresponding target sampling points, that is, each sampling point corresponds to a sampling plane, and the corresponding sampling plane includes the corresponding sampling point.

[0082] S208, determining the plane images corresponding to the sampling planes in the medical image, and stacking the plane images in sequence to determine the curved surface reconstruction image corresponding to the medical image.

[0083] After obtaining the sampling planes corresponding to the target sampling points, the medical image can be projected onto each sampling plane, that is, the target tissue in the curved surface medical image is stretched or projected, and a plurality of plane images are obtained. Then, the plane images can be stacked in sequence according to the sequence of the positions of the target sampling points, that is, the curved surface reconstruction image corresponding to the medical image is obtained.

[0084] In the above curved surface reconstruction method, the target segmentation image including the target tissue or the target structure is determined by segmenting the obtained medical image of the object to be tested, and the plurality of target sampling points and their positions corresponding to the target tissue are determined according to the target segmentation image. The sampling planes perpendicular to the tangent lines at the target sampling points are determined according to the positions of the target sampling points, and the plane images corresponding to the sampling planes determined in the medical image are stacked in sequence to obtain the curved surface reconstruction image. The target segmentation image is a curved surface image, and the sampling planes of the target sampling points all pass through the corresponding target sampling points. In this method, since the corresponding sampling planes can be set at the plurality of sampling points of the target tissue, the plurality of plane images in the medical image can be obtained through the plurality of sampling planes to obtain the curved surface reconstruction image. The curved surface reconstruction image obtained by considering more sampling points is more accurate, so the analysis result obtained after observing and analyzing the curved surface reconstruction images obtained at the plurality of sampling points is more accurate.

[0085] In the above embodiment, the content of obtaining the sampling planes is simply mentioned, and the process of obtaining the sampling planes through the target sampling points will be described below.

[0086] In another embodiment, another curved surface reconstruction method is provided, which is based on the above embodiment, as shown in Figure 4 S206 can include the following steps:

[0087] S302, calculate a tangent line at each target sampling point according to the position of each target sampling point in the transverse position, and / or the sagittal position, and / or the coronal position.

[0088] In this step, the plurality of target sampling points and their positions can be obtained by the above-mentioned sampling point extraction on the target tissue or the target structure. Then, the tangent lines corresponding to the target sampling points can be calculated according to the positions of the target sampling points and the tangent line calculation method. Each tangent line corresponding to a target sampling point is a tangent line passing through the corresponding target sampling point.

[0089] In addition, since the target tissue or the target structure is reconstructed by the surface, the purpose is to better observe and analyze the target tissue or the target structure by the surface reconstruction image. The morphology of the target tissue or the target structure in different anatomical positions may not be the same, and the results of observation and analysis are also different. Therefore, in order to facilitate the observation and analysis of the target tissue or the target structure in different anatomical positions, the tangent lines at the target sampling points in different anatomical positions can be calculated respectively.

[0090] For example, assuming that the different anatomical positions include the transverse position, the sagittal position and the coronal position, the tangent lines corresponding to the target sampling points in the three different anatomical positions can be calculated respectively, that is, each target sampling point will calculate a corresponding tangent line in each anatomical position.

[0091] S304, construct a sampling plane passing through the corresponding target sampling point with the tangent line as the normal direction to obtain a plurality of sampling planes.

[0092] In this step, for each anatomical position, after obtaining the tangent line at the target sampling point in the corresponding anatomical position, a sampling plane passing through the corresponding target sampling point can be constructed with the tangent line at the target sampling point as the normal direction, that is, a plurality of sampling planes in each anatomical position can be obtained.

[0093] In this embodiment, the tangent lines at the target sampling points are calculated according to the positions of the target sampling points in the transverse position, and / or the sagittal position, and / or the coronal position, and the sampling planes passing through the corresponding target sampling points are constructed with the tangent lines as the normal direction to obtain a plurality of sampling planes. By calculating the tangent lines of the plurality of target sampling points and then calculating the corresponding sampling planes, the accuracy of the obtained sampling planes can be improved, and the accuracy of the surface reconstruction image obtained by the sampling planes can be improved.

[0094] The above embodiment briefly mentions the content of obtaining the target sampling points. The process of how to obtain the target sampling points on the target tissue will be described below.

[0095] In another embodiment, another curved surface reconstruction method is provided, which is based on the above-mentioned embodiments, as shown in Figure 5 S204 can include the following steps:

[0096] S402, performing center line extraction processing on the target tissue according to the target segmented image to determine a plurality of initial sampling points constituting a center line of the target tissue.

[0097] In the center line extraction processing on the target tissue, the morphological skeletonization method is preferably used for center line extraction processing in this embodiment, so that the morphological features of the target tissue or the target structure can be maximally retained, and the related features of the target tissue or the target structure can be accurately analyzed subsequently.

[0098] Specifically, after obtaining the target segmented image, the target tissue in the target segmented image can be obtained, and the morphological skeletonization method is used to perform center line extraction processing on the target tissue to obtain the center line of the target tissue. The center line of the target tissue obtained here is constituted by a plurality of initial sampling points, that is, a plurality of initial sampling points on the target tissue are obtained, which can constitute the center line of the target tissue.

[0099] In addition, it should be noted that the distances between the initial sampling points constituting the center line obtained after the center line extraction processing on the target tissue are not all equal. That is, the distances between the initial sampling points can be equal between some initial sampling points, or the distances between any two initial sampling points can be unequal. The number of the plurality of initial sampling points can be set according to actual conditions, which is not limited here.

[0100] S404, resampling the plurality of initial sampling points to determine a plurality of target sampling points; the distances between the target sampling points are all equal.

[0101] In the resampling of the plurality of initial sampling points into the plurality of target sampling points with equal distances, the following steps A1-A2 can be optionally used:

[0102] A1, performing curve fitting processing on the plurality of initial sampling points to determine a reference center line corresponding to the target tissue, and determining a target center line according to the reference center line.

[0103] In this step, the B-spline curve fitting method can be used to perform curve fitting processing on the plurality of initial sampling points to obtain a smooth curve, which is the center line of the target tissue, denoted as the reference center line.

[0104] After the reference centerline of the target tissue is obtained, the target centerline of the target tissue can be determined through the reference centerline. Here, the target centerline corresponds to the anatomical position corresponding to the final surface reconstruction image, that is, different anatomical positions have different target centerlines.

[0105] For the way of determining the target centerline through the reference centerline here, optionally, assuming that the anatomical position corresponding to the final surface reconstruction image is a transverse position, the reference centerline can be directly determined as the target centerline, and the surface reconstruction image under the transverse position can be directly reconstructed through the reference centerline subsequently, so that the anatomical features of the target tissue under the transverse position can be observed. For example, taking the target tissue or target structure as a spinal cord, the centerline of the spinal cord under the transverse position can be seen from FIG. 3, wherein the centerline of the spinal cord and the tangent at each initial sampling point on the centerline of the spinal cord and the cross section at each tangent are given. Figure 6

[0106] Alternatively, assuming that the anatomical position corresponding to the final surface reconstruction image is a sagittal position, the reference centerline can be projected onto a sagittal plane to obtain a sagittal centerline, and the sagittal centerline is determined as the target centerline. Here, the sagittal plane can be the plane of x = 0, that is, the plane constituted by yz; during the projection, the plurality of initial sampling points constituting the reference centerline can be projected on the sagittal plane respectively, and then the B-spline curve fitting method is used to perform curve fitting processing on the plurality of initial sampling points projected on the sagittal plane to obtain the sagittal centerline, and the sagittal centerline is taken as the target centerline, and the surface reconstruction image under the sagittal position can be directly reconstructed through the sagittal centerline subsequently, so that the anatomical features of the target tissue under the sagittal position can be observed. For example, taking the target tissue or target structure as a spinal cord, the centerline of the spinal cord under the sagittal position can be seen from FIG. 4, wherein the projection of the tangent at each initial sampling point on the centerline of the spinal cord on the yz plane and the cross section at each tangent are given. Figure 7

[0107] Alternatively, assuming that the anatomical position corresponding to the final surface reconstruction image is a coronal position, the reference centerline can be projected onto a coronal plane to obtain a coronal centerline, and the coronal centerline is determined as the target centerline. Here, the coronal plane can be the plane of y = 0, that is, the plane constituted by xz; during the projection, the plurality of initial sampling points constituting the reference centerline can be projected on the coronal plane respectively, and then the B-spline curve fitting method is used to perform curve fitting processing on the plurality of initial sampling points projected on the coronal plane to obtain the coronal centerline, and the coronal centerline is taken as the target centerline, and the surface reconstruction image under the coronal position can be directly reconstructed through the coronal centerline subsequently, so that the anatomical features of the target tissue under the coronal position can be observed. For example, taking the target tissue or target structure as a spinal cord, the centerline of the spinal cord under the coronal position can be seen from FIG. 5, wherein the projection of the tangent at each initial sampling point on the centerline of the spinal cord on the xz plane and the cross section at each tangent are given.​​Figure 8 As shown in FIG. 8, the projection of the tangent line at each initial sampling point on the center line of the spinal cord in the xz plane and the cross section at each tangent line are given.

[0108] A2, the target center line is re-sampled at equal intervals with a preset sampling size to determine a plurality of target sampling points.

[0109] In this step, the preset sampling size here can be set according to actual conditions, which is not specifically limited. The interval during equal-interval re-sampling can also be set according to actual conditions, which is not specifically limited. Generally, the number of target sampling points obtained after re-sampling here is greater than the number of initial sampling points, so that the subsequent planar images for surface reconstruction are more intensive, the feature information of the target tissue or target structure is more, and the results obtained after subsequent observation and analysis of the surface reconstruction images are more accurate.

[0110] In this embodiment, the center line of the target tissue in the segmented image is extracted to determine a plurality of initial sampling points constituting the center line, and the plurality of initial sampling points are re-sampled to obtain a plurality of target sampling points, wherein the distances between the initial sampling points are not all equal, and the distances between the target sampling points are all equal, so that the subsequent planar images for surface reconstruction are more intensive, and the feature distribution is more uniform, and the results obtained after subsequent observation and analysis of the surface reconstruction images are more accurate. In addition, the center line obtained by curve fitting processing of the plurality of initial sampling points is re-sampled at equal intervals with a preset sampling size, so that the equal-interval distance re-sampling can be quickly realized, and the efficiency of obtaining target sampling points is improved. Further, the target center line under different anatomical positions is obtained by the reference center line according to different anatomical positions, so that the surface reconstruction can be quickly and accurately performed on each different anatomy in the subsequent.

[0111] During the actual scanning of the patient, for the target tissue or target structure being the spine as an example, the patient may not lie flat when scanning, so that the imaging of the spine will have a certain offset angle. In order to eliminate the influence of the offset angle on the subsequent surface reconstruction image, the planar images of the patient in the correct posture need to be obtained before obtaining the surface reconstruction image, and the following embodiment describes the process.

[0112] In another embodiment, another surface reconstruction method is provided, which is based on the above-mentioned embodiment, as shown in FIG. 9, before stacking the images in S208, the method can further include the following steps: Figure 9

[0113] ​S502, performing a rotating operation, the rotating operation comprising: rotating each target sampling point corresponding planar image along a first axis by a corresponding initial rotation angle to obtain a new planar image corresponding to each target sampling point.

[0114] S504, judging whether the new planar image meets an iteration stop condition, if not, adjusting the initial rotation angle by a set step to obtain a new initial rotation angle, and returning to perform the rotating operation until the new planar image meets the iteration stop condition.

[0115] Here, the initial rotation angle corresponding to each target sampling point can be the same or different, and each initial rotation angle can be pre-set according to experience. The set step can also be pre-set, and the specific size is not limited here.

[0116] Specifically, when adjusting each planar image, each planar image under the transverse position can be rotated along the first axis by the corresponding initial rotation angle to obtain each new planar image. After each new planar image is obtained, it can be judged whether the new planar image meets the iteration stop condition. If the iteration stop condition is met, iteration is not performed, and the final rotation angle corresponding to each target sampling point is recorded and saved. If the iteration stop condition is not met, each new initial rotation angle is obtained by adding or subtracting each initial rotation angle and the set step, and the rotation of each new planar image is continued to obtain again each new planar image, and then it is continuously judged whether the iteration stop condition is met to obtain the final rotation angle corresponding to each target sampling point when the iteration stop condition is met.

[0117] The iteration stop condition is that each new planar image is symmetrically distributed along a second axis, and the plane formed by the first axis and the second axis is the transverse position plane. Here, the first axis can be the y-axis, and the second axis can be the x-axis. The symmetric distribution of the new planar image along the x-axis means that one new planar image is divided into left and right parts along the x-axis, and the left and right parts have the minimum loss in the L1 norm.

[0118] When obtaining the rotation angle corresponding to each target sampling point, after obtaining each planar image under the corresponding anatomical position, each planar image can be rotated along the y-axis by the corresponding rotation angle to obtain each new planar image under the corresponding anatomical position.

[0119] Correspondingly, the stacking of each planar image in S208 can comprise: stacking each new planar image in sequence. That is, each new planar image under each anatomical structure can be stacked in sequence to obtain a curved surface reconstruction image under each anatomical structure.

[0120] In this embodiment, by performing the rotation operation, each planar image is rotated along the first axis according to the initial rotation angle and the set step size to obtain each new planar image, and when each new planar image meets the iterative stop condition of the symmetric distribution along the second axis, each new initial rotation angle is obtained, so that subsequent rotation of each planar image can be performed according to the determined new initial rotation angle to obtain each new planar image, and the curved surface reconstruction image is obtained after stacking, which can avoid imaging errors caused by incorrect patient shooting poses, and further improve the accuracy of the finally determined curved surface reconstruction image.

[0121] The above embodiments mention that different anatomical positions have different target center lines, and the target center line is also used to obtain target sampling points, and then obtain each sampling plane and the curved surface reconstruction image. Accordingly, there are different curved surface reconstruction images for different target center lines. The following embodiments will be described in detail.

[0122] In another embodiment, the curved surface reconstruction image includes at least one of a transverse curved surface reconstruction image, a sagittal curved surface reconstruction image, and a coronal curved surface reconstruction image. Here, the transverse curved surface reconstruction image, the sagittal curved surface reconstruction image, and the coronal curved surface reconstruction image refer to the curved surface reconstruction images of the target tissue or the target structure at different anatomical positions (transverse, sagittal, and coronal). That is, in the embodiments of the present application, the images of the target tissue or the target structure at the transverse, sagittal, and coronal positions can be curved surface reconstructed respectively to obtain respective curved surface reconstruction images.

[0123] For example, taking the target tissue or the target structure as a spine, the spine can be curved surface reconstructed on the transverse position to facilitate subsequent rapid observation and analysis of anatomical features on the cross section of the spine. Taking the target tissue or the target structure as a spinal cord body, referring to FIG. 6, a three-dimensional transverse curved surface reconstruction image corresponding to the spinal cord body center line and the spinal cross section is shown. Figure 10 For example, taking the target tissue or the target structure as a spine, the spine can be curved surface reconstructed on the transverse position to facilitate subsequent rapid observation and analysis of anatomical features on the cross section of the spine. Taking the target tissue or the target structure as a spinal cord body, referring to FIG. 6, a three-dimensional transverse curved surface reconstruction image corresponding to the spinal cord body center line and the spinal cross section is shown.

[0124] For example, taking the target tissue or the target structure as a spine, the spine can be curved surface reconstructed on the transverse position to facilitate subsequent rapid observation and analysis of anatomical features on the cross section of the spine. Taking the target tissue or the target structure as a spinal cord body, referring to FIG. 6, a three-dimensional transverse curved surface reconstruction image corresponding to the spinal cord body center line and the spinal cross section is shown. Figure 11 For example, taking the target tissue or the target structure as a spine, the spine can be curved surface reconstructed on the transverse position to facilitate subsequent rapid observation and analysis of anatomical features on the cross section of the spine. Taking the target tissue or the target structure as a spinal cord body, referring to FIG. 6, a three-dimensional transverse curved surface reconstruction image corresponding to the spinal cord body center line and the spinal cross section is shown.

[0125] For example, taking the target tissue or the target structure as a spine, the spine can be curved surface reconstructed on the transverse position to facilitate subsequent rapid observation and analysis of anatomical features on the cross section of the spine. Taking the target tissue or the target structure as a spinal cord body, referring to FIG. 6, a three-dimensional transverse curved surface reconstruction image corresponding to the spinal cord body center line and the spinal cross section is shown. Figure 12The image shown is a three-dimensional coronal plane reconstruction image along the central line of the spinal cord body in the coronal plane.

[0126] The following is a specific flowchart using the spinal cord as an example of the target tissue or structure. (See attached diagram.) Figure 13 As shown, the process involves first segmenting the spinal cord in the 3DCT image of the spine, then extracting the centerline, and simultaneously obtaining the projection curves of the centerline on the y=0 plane and the x=0 plane. Next, a function curve can be used to fit the centerline, and the fitted surface is resampled at pre-specified intervals according to the sampling size to obtain sampling points. Then, the tangent direction at each sampling point on the fitted curve can be calculated, and sampling surfaces with the tangent direction as the normal direction and passing through the current sampling point are found sequentially, and the images are stacked sequentially to reconstruct the images. Finally, a 3D CT reconstructed image free from the influence of scoliosis can be obtained through the projection curve on the y=0 plane, a 3D CT reconstructed image of the cross-section along the natural curvature of the spinal cord obtained through the spinal cord centerline, and a 3D CT reconstructed image free from the influence of spinal curvature can be obtained through the projection curve on the x=0 plane.

[0127] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0128] Based on the same inventive concept, this application also provides a surface reconstruction apparatus for implementing the surface reconstruction method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more surface reconstruction apparatus embodiments provided below can be found in the limitations of the surface reconstruction method described above, and will not be repeated here.

[0129] In one embodiment, such as Figure 14 As shown, a surface reconstruction device is provided, including: a segmentation module 11, a sampling point determination module 12, a sampling plane determination module 13, and a reconstruction module 14, wherein:

[0130] The segmentation module 11 is configured to perform segmentation processing on the acquired medical image of the to-be-tested object to determine a target segmentation image corresponding to the medical image; the target segmentation image includes a target tissue or a target structure, and the target segmentation image is a curved surface image;

[0131] The sampling point determination module 12 is configured to determine a plurality of target sampling points on the target tissue and positions of the target sampling points according to the target segmentation image;

[0132] The sampling plane determination module 13 is configured to determine a plurality of sampling planes perpendicular to tangent lines at the target sampling points according to the positions of the target sampling points; each sampling plane of the target sampling points passes through a corresponding target sampling point.

[0133] The reconstruction module 14 is configured to determine a plurality of plane images corresponding to the sampling planes in the medical image, and stack the plane images in sequence to determine a curved surface reconstruction image corresponding to the medical image.

[0134] Optionally, the curved surface reconstruction image includes at least one of a transverse curved surface reconstruction image, a sagittal curved surface reconstruction image, and a coronal curved surface reconstruction image.

[0135] In another embodiment, another curved surface reconstruction device is provided, and on the basis of the above-mentioned embodiment, the sampling plane determination module 13 can include:

[0136] The tangent line calculation unit is configured to calculate tangent lines at the target sampling points in a transverse direction, and / or a sagittal direction, and / or a coronal direction according to the positions of the target sampling points.

[0137] The sampling plane construction unit is configured to construct the sampling planes passing through the corresponding target sampling points with the tangent lines as normal directions to obtain the sampling planes.

[0138] In another embodiment, another curved surface reconstruction device is provided, and on the basis of the above-mentioned embodiment, the sampling point determination module 12 can include:

[0139] The center line extraction unit is configured to perform center line extraction processing on the target tissue according to the target segmentation image to determine a plurality of initial sampling points constituting a center line of the target tissue; distances between the initial sampling points are not all equal.

[0140] The resampling unit is configured to resample the plurality of initial sampling points to determine a plurality of target sampling points; distances between the target sampling points are all equal.

[0141] Optionally, the resampling unit can include:

[0142] The curve fitting subunit is configured to perform curve fitting processing on the plurality of initial sampling points to determine a reference center line corresponding to the target tissue.

[0143] a determination subunit, configured to determine a target centerline according to the reference centerline;

[0144] an equidistant resampling subunit, configured to perform equidistant resampling on the target centerline by using a preset sampling size to determine a plurality of target sampling points.

[0145] Optionally, the determination subunit is specifically configured to determine the reference centerline as the target centerline, or project the reference centerline onto a sagittal plane to obtain a sagittal centerline and determine the sagittal centerline as the target centerline, or project the reference centerline onto a coronal plane to obtain a coronal centerline and determine the coronal centerline as the target centerline.

[0146] In another embodiment, another curved surface reconstruction apparatus is provided, and on the basis of the above-mentioned embodiment, the apparatus further comprises the following before the reconstruction module 14 stacks the planar images in sequence:

[0147] a rotation module, configured to perform a rotation operation, the rotation operation comprising: rotating the planar image corresponding to each target sampling point along a first axis by a corresponding initial rotation angle to obtain a new planar image corresponding to each target sampling point;

[0148] a judgment module, configured to judge whether the new planar image meets an iteration stop condition, and when the new planar image does not meet the iteration stop condition, adjust the initial rotation angle according to a preset step to obtain a new initial rotation angle, and return to perform the rotation operation until the new planar image meets the iteration stop condition; wherein the iteration stop condition is that the new planar images are all distributed symmetrically along a second axis, and a plane formed by the first axis and the second axis is a transverse plane.

[0149] Correspondingly, the reconstruction module 14 is specifically configured to stack the new planar images in sequence.

[0150] The modules in the curved surface reconstruction apparatus can be all or partially realized by software, hardware and combinations thereof. The modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform operations corresponding to the modules.

[0151] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps:

[0152] Segmenting the acquired medical image of the object to be tested to determine a target segmentation image corresponding to the medical image; the target segmentation image includes a target tissue or a target structure, and the target segmentation image is a curved surface image; determining a plurality of target sampling points on the target tissue and positions of the target sampling points according to the target segmentation image; determining a plurality of sampling planes perpendicular to tangent lines at the target sampling points according to the positions of the target sampling points; the sampling planes of the target sampling points all pass through the corresponding target sampling points; determining a plurality of plane images corresponding to the sampling planes in the medical image, and stacking the plane images in sequence to determine a curved surface reconstruction image corresponding to the medical image.

[0153] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0154] According to the positions of the target sampling points, calculating tangent lines at the target sampling points in transverse, and / or, sagittal, and / or, coronal positions; constructing the sampling planes passing through the corresponding target sampling points with the tangent lines as the normal directions to obtain the sampling planes.

[0155] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0156] According to the target segmentation image, performing center line extraction processing on the target tissue to determine a plurality of initial sampling points constituting a center line of the target tissue; the distances between the initial sampling points are not all equal; resampling the plurality of initial sampling points to determine a plurality of target sampling points; the distances between the target sampling points are all equal.

[0157] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0158] Performing curve fitting processing on the plurality of initial sampling points to determine a reference center line corresponding to the target tissue, and determining a target center line according to the reference center line; resampling the target center line at equal distances with a preset sampling size to determine a plurality of target sampling points.

[0159] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0160] Determining the reference center line as the target center line; or, projecting the reference center line onto a sagittal plane to obtain a sagittal center line, and determining the sagittal center line as the target center line; or, projecting the reference center line onto a coronal plane to obtain a coronal center line, and determining the coronal center line as the target center line.

[0161] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0162] performing a rotating operation, the rotating operation comprising: rotating each target sampling point corresponding planar image along a first axis by a corresponding initial rotation angle to obtain a new planar image corresponding to each target sampling point; determining whether the new planar image satisfies an iteration stop condition, and when the new planar image does not satisfy the iteration stop condition, adjusting the initial rotation angle by a set step to obtain a new initial rotation angle, and returning to perform the rotating operation until the new planar image satisfies the iteration stop condition; wherein the iteration stop condition is that each new planar image is symmetrically distributed along a second axis, and a plane formed by the first axis and the second axis is a transverse plane.

[0163] In one embodiment, the processor further implements the following steps when executing the computer program:

[0164] stacking the new planar images in sequence.

[0165] In one embodiment, the curved reconstruction image comprises at least one of a transverse curved reconstruction image, a sagittal curved reconstruction image, and a coronal curved reconstruction image.

[0166] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0167] segmenting the obtained medical image of the object to be measured to determine a target segmentation image corresponding to the medical image; the target segmentation image includes a target tissue or a target structure, and the target segmentation image is a curved image; determining a plurality of target sampling points on the target tissue and positions of the target sampling points according to the target segmentation image; determining a sampling plane perpendicular to a tangent line at each target sampling point according to the positions of the target sampling points; each target sampling point passes through a corresponding sampling plane; determining a planar image corresponding to each sampling plane in the medical image, and stacking the planar images in sequence to determine a curved reconstruction image corresponding to the medical image.

[0168] In one embodiment, the processor further implements the following steps when executing the computer program:

[0169] calculating a tangent line at each target sampling point in a transverse plane, and / or a sagittal plane, and / or a coronal plane according to the positions of the target sampling points; constructing a sampling plane passing through a corresponding target sampling point with the tangent line as a normal direction to obtain each sampling plane.

[0170] In one embodiment, the processor further implements the following steps when executing the computer program:

[0171] According to the target segmentation image, a center line extraction process is performed on the target tissue to determine a plurality of initial sampling points constituting a center line of the target tissue; distances between the initial sampling points are not all equal; the plurality of initial sampling points are resampled to determine a plurality of target sampling points; distances between the target sampling points are all equal.

[0172] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0173] The plurality of initial sampling points are subjected to curve fitting processing to determine a reference center line corresponding to the target tissue, and the target center line is determined according to the reference center line; the target center line is subjected to equal-distance resampling with a preset sampling size to determine the plurality of target sampling points.

[0174] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0175] The reference center line is determined as the target center line; or the reference center line is projected onto a sagittal plane to obtain a sagittal center line, and the sagittal center line is determined as the target center line; or the reference center line is projected onto a coronal plane to obtain a coronal center line, and the coronal center line is determined as the target center line.

[0176] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0177] The rotation operation is performed, and the rotation operation includes: rotating each target sampling point corresponding planar image along a first axis by a corresponding initial rotation angle to obtain a new planar image corresponding to each target sampling point; determining whether the new planar image satisfies an iteration stop condition, and when the iteration stop condition is not satisfied, adjusting the initial rotation angle by a set step to obtain a new initial rotation angle, and returning to perform the rotation operation until the new planar image satisfies the iteration stop condition; wherein the iteration stop condition is that each new planar image is symmetrically distributed along a second axis, and a plane formed by the first axis and the second axis is a transverse plane.

[0178] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0179] Each new planar image is stacked in sequence.

[0180] In one embodiment, the curved surface reconstruction image includes at least one of a transverse curved surface reconstruction image, a sagittal curved surface reconstruction image, and a coronal curved surface reconstruction image.

[0181] In one embodiment, a computer program product is provided, including a computer program, which, when executed by the processor, implements the following steps:

[0182] Segmenting the acquired medical image of the object to be tested to determine a target segmentation image corresponding to the medical image; the target segmentation image includes a target tissue or a target structure, and the target segmentation image is a curved surface image; determining a plurality of target sampling points on the target tissue and positions of the target sampling points according to the target segmentation image; determining a plurality of sampling planes perpendicular to tangent lines at the target sampling points according to the positions of the target sampling points; the sampling planes of the target sampling points all pass through the corresponding target sampling points; determining a plurality of plane images corresponding to the sampling planes in the medical image, and stacking the plane images in sequence to determine a curved surface reconstruction image corresponding to the medical image.

[0183] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0184] According to the positions of the target sampling points, calculating tangent lines at the target sampling points in transverse, and / or, sagittal, and / or, coronal positions; constructing the sampling planes passing through the corresponding target sampling points with the tangent lines as the normal directions to obtain the sampling planes.

[0185] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0186] According to the target segmentation image, performing center line extraction processing on the target tissue to determine a plurality of initial sampling points constituting a center line of the target tissue; the distances between the initial sampling points are not all equal; resampling the plurality of initial sampling points to determine a plurality of target sampling points; the distances between the target sampling points are all equal.

[0187] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0188] Performing curve fitting processing on the plurality of initial sampling points to determine a reference center line corresponding to the target tissue, and determining a target center line according to the reference center line; resampling the target center line at equal distances with a preset sampling size to determine a plurality of target sampling points.

[0189] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0190] Determining the reference center line as the target center line; or, projecting the reference center line onto a sagittal plane to obtain a sagittal center line, and determining the sagittal center line as the target center line; or, projecting the reference center line onto a coronal plane to obtain a coronal center line, and determining the coronal center line as the target center line.

[0191] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0192] The rotation operation includes rotating each target sampling point corresponding planar image along a first axis by a corresponding initial rotation angle to obtain a new planar image corresponding to each target sampling point; determining whether the new planar image meets an iteration stop condition; when the new planar image does not meet the iteration stop condition, adjusting the initial rotation angle by a set step to obtain a new initial rotation angle, and returning to perform the rotation operation until the new planar image meets the iteration stop condition; wherein the iteration stop condition is that each new planar image is symmetrically distributed along a second axis, and a plane formed by the first axis and the second axis is a transverse plane.

[0193] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0194] Stacking each new planar image in sequence.

[0195] In one embodiment, the curved surface reconstruction image includes at least one of a transverse curved surface reconstruction image, a sagittal curved surface reconstruction image, and a coronal curved surface reconstruction image.

[0196] It should be noted that the data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties.

[0197] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0198] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0199] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be noted that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method of surface reconstruction, characterized by, The method comprises: segmenting an acquired medical image of a subject to be tested to determine a target segmentation image corresponding to the medical image; the target segmentation image comprises a target tissue or a target structure, and the target segmentation image is a curved surface image; determining a plurality of target sampling points corresponding to different anatomical positions on the target tissue and positions of the target sampling points according to the target segmentation image; determining a plurality of sampling planes perpendicular to tangent lines at the target sampling points according to the positions of the target sampling points at different anatomical positions; each of the target sampling points has a sampling plane passing through the corresponding target sampling point; determining a plane image corresponding to each of the sampling planes in the medical image; performing a rotation operation, which comprises rotating the plane image of each of the target sampling points at different anatomical positions by a corresponding initial rotation angle along a first axis to obtain a new plane image of each of the target sampling points at different anatomical positions; determining whether the new plane image meets an iterative stop condition; if not, adjusting the initial rotation angle by a set step to obtain a new initial rotation angle corresponding to each of the anatomical positions, and returning to perform the rotation operation until the new plane image meets the iterative stop condition; wherein the iterative stop condition is that each of the new plane images is symmetrically distributed along a second axis, and the plane formed by the first axis and the second axis is a transverse plane; stacking each of the plane images in sequence to determine a curved surface reconstruction image corresponding to the medical image.

2. The method of claim 1, wherein, The method comprises: calculating tangent lines at each of the target sampling points in a transverse plane, and / or a sagittal plane, and / or a coronal plane according to the positions of the target sampling points; constructing a sampling plane passing through the corresponding target sampling point with each of the tangent lines as a normal direction to obtain each of the sampling planes.

3. The method of claim 1, wherein, The method comprises: extracting a center line of the target tissue according to the target segmentation image to determine a plurality of initial sampling points constituting the center line of the target tissue; the distances between the initial sampling points are not all equal; re-sampling the plurality of initial sampling points to determine the plurality of target sampling points; the distances between the target sampling points are all equal.

4. The method of claim 3, wherein, The method comprises: performing curve fitting processing on the plurality of initial sampling points to determine a reference center line corresponding to the target tissue, and determining a target center line according to the reference center line; re-sampling the target center line at equal distances with a preset sampling size to determine the plurality of target sampling points.

5. The method of claim 4, wherein, The method comprises: determining the reference center line as the target center line; or, projecting the reference center line onto a sagittal plane to obtain a sagittal center line, and determining the sagittal center line as the target center line; or projecting the reference center line onto a coronal plane to obtain a coronal center line, and determining the coronal center line as the target center line.

6. The method according to any one of claims 1 to 5, characterized in that, The sequentially stacking each of the planar images comprises: sequentially stacking each of the new planar images.

7. The method according to any one of claims 1 to 5, characterized in that, The curved surface reconstruction image comprises at least one of a transverse curved surface reconstruction image, a sagittal curved surface reconstruction image, and a coronal curved surface reconstruction image.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor, when executing the computer program, implements the steps of the method of any one of claims 1 to 7.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 7.

Images