Medical image optimization method, system, electronic device and storage medium

Abstract

The present application provides a kind of medical image optimization method, system, electronic equipment and storage medium, wherein medical image optimization method includes the following steps: to be optimized medical image is extracted by contour, obtains first medical image;According to preset smoothing control target, the first medical image is carried out smoothing processing, obtains second medical image, and the second medical image is used as optimized medical image. Therefore, the medical image optimization method, system, electronic equipment and storage medium provided by the present application realize end-to-end processing flow, can make the result display of target organ tissue more accurate, can better assist doctor to improve diagnostic accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a medical image optimization method and system, an electronic device and a storage medium. BACKGROUND

[0002] With the development of medical imaging technology, medical imaging has become an important means for doctors to judge lesions. Reconstructing three-dimensional images of organ tissues from medical two-dimensional tomographic images and displaying them greatly improves the diagnosis rate of doctors. For example, doctors can use blood vessel imaging technology to assist in diagnosing various blood vessel diseases.

[0003] In the prior art, blood vessel imaging technology includes computed tomography angiography (CTA), magnetic resonance angiography (MRA), etc. However, the blood vessel imaging obtained is a three-dimensional image, which not only contains blood vessel tissue but also other tissues around the blood vessels (such as bone, fat, muscle, lung tissue, etc.), which will greatly affect the accurate diagnosis of doctors. Therefore, by using blood vessel segmentation technology, the entire blood vessel region is extracted from the three-dimensional image, and the morphology of the blood vessel is displayed using three-dimensional display technology, which can improve the accuracy of doctor's diagnosis.

[0004] Although there are many blood vessel segmentation technologies at present, the display problem after blood vessel segmentation is still a very challenging task. At present, blood vessel display optimization mainly focuses on images and graphics. The image post-processing optimization algorithm mainly uses morphological methods to post-process the blood vessel results, but the morphological method is not only time-consuming and inefficient, but also a big challenge to set appropriate morphological parameters to get satisfactory optimized blood vessel results.

[0005] Therefore, in view of the above defects in the prior art, how to provide an optimized display method for medical images so that the results of the target medical images (such as blood vessels) are displayed more smoothly and accurately has become one of the technical problems that the technical personnel in the field are eager to solve.

[0006] It should be noted that the information disclosed in the background section of the present application is only intended to deepen the understanding of the general background of the present application, and should not be regarded as acknowledging or implying in any form that the information constitutes prior art known to those skilled in the art. SUMMARY

[0007] The purpose of the present application is to provide a medical image optimization method and system, an electronic device and a storage medium, which can not only make the results of medical images more smooth and accurate, thereby better assisting doctors to improve the accuracy of diagnosis, but also realize an end-to-end processing flow.

[0008] To achieve the above object, the present application is implemented by the following technical solutions: a medical image optimization method, comprising:

[0009] Isosurface contour extraction is performed on the medical image to be optimized to obtain a first medical image;

[0010] According to a preset smoothing control target, the first medical image is smoothed to obtain a second medical image, and the second medical image is taken as an optimized medical image.

[0011] Optionally, the isosurface contour extraction on the medical image to be optimized to obtain a first medical image comprises:

[0012] According to the volume data of the medical image to be optimized, information of each first unit volume is extracted;

[0013] According to the position relationship between a preset isosurface and each first unit volume, a second unit volume intersecting with the preset isosurface is separated out;

[0014] An isosurface approximating the representation of the preset isosurface in each second unit volume is obtained;

[0015] All the isosurfaces are connected to obtain the first medical image.

[0016] Optionally, the smoothing of the first medical image according to a preset smoothing control target to obtain a second medical image comprises:

[0017] According to first preset smoothing control information, an anisotropic Laplacian operator is used to perform first smoothing on the first medical image to obtain a first smoothed medical image;

[0018] According to second preset smoothing control information, a taubin window function based on sigmod logistic regression is used to perform second smoothing on the first smoothed medical image to obtain a second smoothed medical image;

[0019] The second smoothed medical image is taken as the second medical image.

[0020] Optionally, the first preset smoothing control information comprises a first preset iteration number and a preset relaxation factor;

[0021] Before the first smoothed medical image is obtained, it further comprises:

[0022] According to the preset smoothing control target, the first preset iteration number and the preset relaxation factor are obtained;

[0023] Correspondingly, the first medical image is first smoothed according to first preset smoothing control information by using an anisotropic Laplacian operator, including:

[0024] The edge information of the first isosurface is enhanced and highlighted by using an anisotropic Laplacian operator, wherein the first isosurface is an isosurface of the first medical image.

[0025] The contour of the second isosurface is smoothed according to the first preset iteration number and the preset relaxation factor by iteratively using the anisotropic Laplacian operator, wherein the second isosurface is the first isosurface after the enhanced and highlighted processing.

[0026] Optionally, the second preset smoothing control information includes a second preset iteration number and a preset filter passband value.

[0027] Before obtaining the second smoothed medical image, further comprising:

[0028] According to the preset smoothing control target, the second preset iteration number and the preset filter passband value are obtained.

[0029] The first smoothed medical image is second smoothed according to second preset smoothing control information by using a taubin window function based on sigmod logistic regression, including:

[0030] The third isosurface is transformed by using a sigmod logistic regression function, wherein the third isosurface is an isosurface of the first smoothed medical image.

[0031] The contour of the fourth isosurface is smoothed according to the second preset iteration number and the preset filter passband value by iteratively using the taubin window function, wherein the fourth isosurface is the third isosurface after the transformation.

[0032] Optionally, before the second medical image is taken as an optimized medical image, further comprising:

[0033] The second medical image is isosurface contour compressed to obtain a third medical image.

[0034] Correspondingly, the second medical image is taken as an optimized medical image, including that the third medical image is taken as an optimized medical image.

[0035] Optionally, the isosurface of the second medical image includes a plurality of triangular patches.

[0036] The second medical image is isosurface contour compressed to obtain a third medical image, including:

[0037] For each of the triangular facet regions, the plane normal vector is calculated to obtain its corresponding normal vector angle;

[0038] The triangular facets are merged according to the normal vector angle and the preset merging rules to obtain the third medical image.

[0039] Optionally, the step of merging the triangular facets according to the normal vector angle and a preset merging rule to obtain the third medical image includes:

[0040] Determine whether the difference between the normal angles of the triangular facets to be merged is within a preset angle threshold range. If so, merge the triangular facets to be merged in the following manner:

[0041] The outer vertices of the triangular facets to be merged are retained, and the internal point connections of the triangular facets to be merged are removed to obtain the third medical image.

[0042] Optionally, the medical image to be optimized includes a mask image after CTA body data vessel segmentation;

[0043] Before extracting the contour of the isosurface from the medical image to be optimized to obtain the first medical image, the process further includes preprocessing the medical image to be optimized in the following manner:

[0044] The mask image is preprocessed according to the preset image preprocessing target to obtain the medical image to be optimized.

[0045] To achieve the above objectives, the present invention also provides a medical image acquisition system, the medical image acquisition system comprising:

[0046] A medical image acquisition device is configured to acquire a medical image to be optimized;

[0047] A medical image optimization device is configured to optimize the medical image to be optimized;

[0048] The medical image optimization device includes: an isosurface acquisition unit and a smoothing processing unit; wherein:

[0049] The isosurface acquisition unit is configured to extract isosurface contours from the medical image to be optimized, thereby obtaining a first medical image.

[0050] The smoothing processing unit is configured to smooth the first medical image according to a preset smoothing control target to obtain a second medical image, and use the second medical image as the optimized medical image.

[0051] Optionally, the medical image optimization apparatus further comprises an isosurface contour compression unit configured to perform isosurface contour compression on the second medical image to obtain a third medical image.

[0052] Correspondingly, the second medical image as the optimized medical image comprises the third medical image as the optimized medical image.

[0053] To achieve the above object, the present application further provides an electronic device comprising a processor and a memory, wherein the memory stores a computer program, and the computer program is executed by the processor to implement the medical image optimization method.

[0054] To achieve the above object, the present application further provides a computer readable storage medium, wherein the storage medium stores a computer program, and the computer program is executed by a processor to implement the medical image optimization method.

[0055] Compared with the prior art, the present application provides a medical image optimization method, system, electronic device and storage medium, which has the following beneficial effects:

[0056] The medical image optimization method comprises the following steps: performing isosurface contour extraction on a medical image to be optimized to obtain a first medical image; performing smoothing processing on the first medical image according to a preset smoothing control target to obtain a second medical image, and taking the second medical image as an optimized medical image. Thus, the medical image optimization method, system, electronic device and storage medium provided by the present application realize an end-to-end image segmentation processing flow, can make the result display of the target organ tissue more accurate, and can better assist doctors to improve the diagnostic accuracy. Especially for the blood vessel image after blood vessel segmentation, the blood vessel result display can be made more smooth.

[0057] Further, the medical image optimization method provided by the present application makes the transition of the steep convex and concave pits in the medical image more smooth through iteration of the Laplace operator; and makes the isosurface contour more stably smooth through iteration of the taubin window function based on sigmod logistic regression. Thus, the medical image optimization method provided by the present application is easy to implement, and can make the result display of the organ tissue of the medical image more smooth and accurate.

[0058] Still further, the medical image optimization method provided by the present application has strong universality, can be applied not only to the optimization of aortic blood vessels, but also to the optimization of coronary blood vessels and nerve blood vessels, realizes an end-to-end algorithm flow, and can better assist doctors to improve the diagnostic accuracy.

[0059] Further, the medical image optimization method provided by the present application further comprises isosurface contour compression on the second medical image to obtain a third medical image, and the third medical image is taken as the optimized medical image. In this way, the result display of the organ tissue in the medical image is more smooth and accurate, the storage space of the image data is saved, the efficiency of the subsequent image display is improved, the system resources are saved, and the system cost is reduced.

[0060] Since the medical image acquisition system, the electronic device and the storage medium provided by the present application belong to the same inventive concept as the medical image optimization method provided by the present application, at least have the same beneficial effects, here, will not be repeated. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 The medical image optimization method flowchart in an embodiment of the present application;

[0062] Figure 2 The isosurface schematic diagram of the approximation representation of the preset isosurface in one of the second units in an embodiment of the present application;

[0063] Figure 3 The display result schematic diagram of the first medical image and the local area amplification in an embodiment of the present application;

[0064] Figure 4 The display result schematic diagram of the medical image shown in the first smoothing processing; Figure 3

[0065] The display result schematic diagram of the medical image shown in the second smoothing processing; Figure 5 Figure 4 The display result schematic diagram of the medical image shown in the isosurface contour compression;

[0066] Figure 6 Figure 5 The display result schematic diagram of the medical image shown in the isosurface contour compression;

[0067] Figure 7 The schematic diagram of the triangle patch merging principle in an embodiment of the present application;

[0068] Figure 8 The structural block diagram of a medical image acquisition system provided by an embodiment of the present application;

[0069] Figure 9 The block structure schematic diagram of the electronic device in an embodiment of the present application;

[0070] Among them, the sign explanation is as follows:

[0071] ​​100 - medical image acquisition device, 200 - medical image optimization device, 210 - isosurface acquisition unit, 220 - smoothing processing unit, 230 - isosurface profile compression unit

[0072] 301 - processor, 302 - communication interface, 303 - memory, 304 - communication bus DETAILED DESCRIPTION

[0073] To make the purposes, advantages and features of the present application clearer, the medical image optimization method, system, electronic device and storage medium proposed by the present application are further described in detail below in combination with the drawings. It should be noted that the drawings are all very simplified and use non-precise proportions, and are only used to facilitate and clearly assist the purpose of explaining the embodiments of the present application. It should be understood that the drawings of the specification do not necessarily show the specific structure of the present application in proportion, and the illustrative features used to explain some principles of the present application in the drawings of the specification will also be slightly simplified. The specific design features of the present application disclosed herein include, for example, specific dimensions, directions, positions and shapes, which will be determined in part by the specific application and use environment to be applied and used. In addition, in the following described embodiments, the same reference signs are sometimes used between different drawings to represent the same parts or parts with the same function, and the repeated description is omitted. In this specification, similar reference signs and letters are used to represent similar items, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0074] In appropriate cases, these terms used in this way can be replaced. Similarly, if the method described herein includes a series of steps, and the order of the steps presented herein is not necessarily the only order in which the steps can be performed, and some of the described steps can be omitted and / or some other steps not described herein can be added to the method.

[0075] The core idea of the present application is to provide a medical image optimization method, system, electronic device and storage medium to realize an end-to-end processing flow, so that the result display of the organ tissue of the medical image is smoother and more accurate, thereby better assisting doctors to improve the diagnostic accuracy.

[0076] It should be noted that the electronic device of the embodiment of the present application can be a personal computer, a mobile terminal, etc., and the mobile terminal can be a mobile phone, a tablet computer, etc. hardware devices with various operating systems. In particular, although this paper mainly takes the image optimization of the aortic blood vessel as an example, more specifically, takes the CTA (Computed Tomography Angiography) aortic binary mask image (i.e. a binary image, in which the pixel value of the blood vessel region is 1, and the pixel value of the non-blood vessel region is 0) as an example, as can be understood by those skilled in the art, the present application can also be used for the blood vessel display optimization of other blood vessels, such as coronary blood vessels, neural blood vessels, radial artery blood vessels, etc. Of course, it is also applicable to medical images of other organ tissues, such as heart, lung, etc. will not be described one by one.

[0077] To achieve the above idea, the present application provides a medical image optimization method. In order to facilitate understanding and description, the overall process of the medical image optimization method provided by the present application is first described, and then each step is described.

[0078] Specifically, please refer to Figure 1 which schematically shows the flowchart of the medical image optimization method provided by the embodiment of the present application, which comprises:

[0079] S1: isosurface contour extraction is performed on the to-be-optimized medical image to obtain a first medical image;

[0080] S2: according to a preset smoothing control target, the first medical image is smoothed to obtain a second medical image, and the second medical image is taken as an optimized medical image.

[0081] The to-be-optimized medical image can be a mask image after CTA (Computed Tomography Angiography) body data blood vessel segmentation, or a mask image after MRA (Magnetic Resonance Angiography) body data blood vessel segmentation, or other medical images. The to-be-optimized medical image can be collected by an image acquisition device, such as a CT, MRI, etc. imaging equipment, or can be collected through the Internet, or can be collected by a scanning device. As mentioned before, in order to facilitate understanding, Figures 3 to 6 In the embodiment of the present application, the aortic blood vessel after blood vessel segmentation is taken as an example, which is not a limitation of the present application.

[0082] In this way, the medical image optimization method provided by the present application realizes an end-to-end processing flow, which can make the result display of the target organ tissue more accurate, and can better assist doctors to improve the diagnostic accuracy. Especially for the mask image after blood vessel segmentation, the blood vessel result display can be smoother.

[0083] Preferably, in one embodiment, before step S1, the method further comprises pre-processing the to-be-optimized medical image by:

[0084] Step S0: pre-processing the mask image according to a preset image pre-processing target to obtain the to-be-optimized medical image.

[0085] As can be understood by those skilled in the art, the pre-processing includes normalizing the size of the to-be-optimized medical image according to the preset image pre-processing target, such as normalizing the size of the to-be-optimized medical image to 512x512x130 pixels. Obviously, the size of the to-be-optimized medical image should be set according to the specific situation, and the present application does not limit this. Further, the pre-processing also includes normalizing the storage of the volume data. The volume data is composed of voxels, which are basic volume elements, and can also be understood as points or small areas with arrangement and color in a three-dimensional space. Usually, voxels (hexahedrons, usually cubes) belong to a fixed grid (grid unit). Therefore, in some embodiments, the volume data can also be stored as a table, which can be considered as a multi-dimensional array in this case. The volume data can be stored as a formatted file locally, such as a *.csv format. In other embodiments, the data set is divided into several slices, and each slice is stored as a bitmap image. Specifically, the mask image can be pre-processed according to the actual demand and the preset image pre-processing target, and the present application does not limit the pre-processing content to the above-mentioned exemplary embodiments.

[0086] In this way, the medical image optimization method provided by the present application can normalize the to-be-optimized medical image through pre-processing, thereby significantly reducing the complexity of steps S1 and S2, saving computing resources, and improving the efficiency of medical image optimization processing.

[0087] Preferably, in one preferred embodiment, in step S1, the isosurface contour extraction of the to-be-optimized medical image to obtain the first medical image comprises:

[0088] S11: extracting the information of each first unit volume according to the volume data of the to-be-optimized medical image;

[0089] S12: separating out the second unit volume intersecting with the preset isosurface according to the positional relationship between the preset isosurface and each first unit volume;

[0090] S13: obtaining the isosurface approximating the representation of the preset isosurface in each second unit volume.

[0091] Specifically, in one preferred embodiment, the first unit body / second unit body comprises a cube, and the information of the first unit body / second unit body comprises position information (such as coordinate information) of eight vertices of the cube. In one preferred embodiment, the method for obtaining the isosurface comprises:

[0092] S131: According to the position relationship between the position information of the vertices of the second unit body and the preset isosurface, an intersection point of the preset isosurface and the edge of the second unit body is obtained by using an interpolation calculation. The interpolation algorithm can be a linear interpolation algorithm, a nearest interpolation method, etc. In order to improve the quality of the isosurface, other higher-precision interpolation algorithms can also be used, and the present application does not make any limitation in this regard.

[0093] S132: According to the relative position of each vertex of the second unit body and the preset isosurface, the intersection point of the preset isosurface and the edge of the second unit body is connected according to a preset topological connection relationship, and an isosurface approximated to the representation of the preset isosurface in the second unit body is obtained.

[0094] Please refer to Figure 2 , Figure 2 The figure is a schematic diagram of an isosurface approximated to the representation of a preset isosurface in a second unit according to one embodiment of the present application. Assuming that among the eight vertices 1-8 of a cube, the value of vertex 3 is smaller than the value of a point on the preset isosurface, and the values of the other seven vertices 1-2 and vertices 4-8 are greater than the value of a point on the preset isosurface, the preset isosurface must pass through the cube. Among them, a1, a2 and a3 are the intersection points of the preset isosurface and the edge of the second unit, and the isosurface in the cube can be approximated by triangular facets (shown in the shaded area) as shown in Figure 2 . By analogy, after all the second unit bodies are processed, a plurality of triangular facets that are unified, correlated and continuous with each other are obtained, and these triangular facets form the first medical image.

[0095] The optimization method of the medical image provided by the present application can extract the isosurface by using an isosurface extraction algorithm (including but not limited to the Marching Cubes algorithm), and such configuration can not only reduce the complexity of the extraction process, but also be more conducive to the display of the medical image.

[0096] S14: Connecting all the isosurfaces, the first medical image is obtained. Please refer to Figure 3 , Figure 3 The figure is a schematic diagram of the display result of the first medical image and the enlarged display of the local area in one embodiment of the present application. Specifically, Figure 3The mask image after the vessel segmentation of the CTA (computed tomography angiography) volume data of the aortic blood vessel shown in the middle is the result after the isosurface extraction, and as can be seen from the local enlarged view, the medical image (isosurface contour) at this stage has a boundary protruding burr noise and obvious convex-concave regions in the aortic blood vessel region.

[0097] As can be understood by those skilled in the art, the isosurface is a curved surface in space, and the value of the function F(x, y, z) on the curved surface is equal to a given value. To be precise, it refers to a grid space, assuming that each node stores a three-variable function F(x, y, z), and the continuous sampling value of the grid cell in the x, y, z direction is F(x, y, z), and for a given value Fi, the isosurface is a curved surface composed of all points that satisfy S = {(x, y, z) | F(x, y, z) = Fi}. The information of the preset isosurface includes the value of the function F(x, y, z) of the isosurface determined according to the optimization target of the to-be-processed medical image. As described above, if the CTA (computed tomography angiography) aortic binary mask image is the to-be-optimized image, the value of the function F(x, y, z) of the isosurface is 1.

[0098] The medical image optimization method provided by the present application is based on the basic idea of the Marching Cubes algorithm: processing the cubes (voxels) in the volume data one by one, separating the cubes intersecting with the preset isosurface, and using interpolation to calculate the intersection points of the isosurface and the edges of the cube. According to the relative position of each vertex of the cube and the preset isosurface, the intersection points a1, a2, a3 (for example) of the preset isosurface and the edges of the cube are connected in a certain way to generate an isosurface, which is an approximate representation of the preset isosurface in the cube. In this way, the medical image optimization method provided by the present application lays a foundation for the smoothing processing of the to-be-processed medical image in step S2 by extracting the isosurface contour of the to-be-processed medical image. Figure 2

[0099] As can be understood by those skilled in the art, although the above-mentioned embodiments take the Marching Cubes method as an example to describe the specific process of the isosurface extraction provided by the present application in detail, other isosurface extraction methods such as the moving tetrahedron algorithm or the partial cube algorithm can also be used in other embodiments, which will not be described one by one.

[0100] ​Preferably, in one of the example embodiments, the step S2 of smoothing the first medical image according to the preset smoothing control target to obtain a second medical image comprises: a step S21 of performing first smoothing processing on the first medical image, a step S22 of performing second smoothing processing on the first medical image after the first smoothing processing, and taking the second medical image after the second smoothing processing as the second medical image.

[0101] Specifically, the contents of the steps S21 and S22 are described as follows respectively:

[0102] S21: performing first smoothing processing on the first medical image according to first preset smoothing control information by using an anisotropic Laplace operator to obtain a first medical image after the first smoothing processing.

[0103] Preferably, in one of the example embodiments, the first preset smoothing control information comprises a first preset iteration number and a preset relaxation factor. Before obtaining the first medical image after the first smoothing processing, the method further comprises: obtaining the first preset iteration number and the preset relaxation factor according to the preset smoothing control target. The relaxation factor is used to control the maximum offset value of one iteration of high frequency information, which is manifested as a boundary protruding burr-like noise in the profile of the isosurface. Specifically, the first preset iteration number should be set according to the actual working condition. For example, in order to obtain better optimization effect, the first preset iteration number used in coronary blood vessels and nerve blood vessels may be different. Taking the abdominal aortic blood vessel as an example, the first preset iteration number is 20-40 times, preferably 40 times. Similarly, the value of the preset relaxation factor should also be determined according to the actual working condition and the optimization target, preferably between 0.1 and 1, and the value is preferably 0.3. Obviously, this is only an example description of the preferred embodiment, not a limitation of the present application itself.

[0104] Correspondingly, the step S21 comprises the following steps S211 and S212:

[0105] S211: performing enhanced protruding processing on the edge information of the first isosurface by using an anisotropic Laplace operator; wherein the first isosurface is an isosurface of the first medical image;

[0106] S212: performing smoothing processing on the profile of the second isosurface by iteratively using the anisotropic Laplace operator according to the first preset iteration number and the preset relaxation factor; wherein the second isosurface is the first isosurface after the enhanced protruding processing.

[0107] Referring to Figure 4 , Figure 4 to the Figure 3The display result schematic diagram of the first smoothing processed medical image and the local region amplification is shown in the following figure. Figure 4 With Figure 3 By comparison (see the local amplification part), it is not difficult to find that, in this configuration, the optimization method of the medical image provided by the present application can suppress the high frequency information (noise) of the contour of the isosurface by using the anisotropic operator to enhance and highlight the edge information of the isosurface and then using the Laplace operator to perform smoothing processing on the contour of the isosurface, thereby reducing the influence of the noise, making the suppression of the burr-like noise more complete, and making the contour of the isosurface more stable and smooth.

[0108] S22: performing second smoothing processing on the first smoothed medical image according to second preset smoothing control information by using a taubin window function based on sigmod logistic regression to obtain a second smoothed medical image.

[0109] Preferably, in one preferred embodiment, the second preset smoothing control information includes a second preset iteration number and a preset filter passband value. Before obtaining the second smoothed medical image, it further includes: obtaining the second preset iteration number and the preset filter passband value according to the preset smoothing control target. The preset filter passband value is used for the passband value of the one-time interpolation processing of the grid vertex. Similar to the first preset iteration number and the preset relaxation factor, the second preset iteration number and the preset filter passband value should be set according to the actual working condition and the optimization target. For example, taking the abdominal aortic blood vessel as an example, the value of the second preset iteration number is 5-15 times, preferably 10 times, and the range of the preset filter passband value is 0.8-1.2, preferably 1.

[0110] Correspondingly, step S22 includes step S221 and step S222:

[0111] S221: performing transformation processing on a third isosurface by using a sigmod logistic regression function; wherein the third isosurface is the isosurface of the first smoothed medical image;

[0112] S222: iteratively using the taubin window function to perform smoothing processing on the contour of a fourth isosurface according to the second preset iteration number and the preset filter passband value; wherein the fourth isosurface is the third isosurface after the transformation processing.

[0113] Referring to Figure 5 , Figure 5 The display result schematic diagram of the second smoothed medical image and the local region amplification in an embodiment of the present application is shown in the following figure. Figure 5 With Figure 4 By comparison (see the local amplification part), it is not difficult to find that, in this configuration, the optimization method of the medical image provided by the present application can suppress the high frequency information (noise) of the contour of the isosurface by using the anisotropic operator to enhance and highlight the edge information of the isosurface and then using the Laplace operator to perform smoothing processing on the contour of the isosurface, thereby reducing the influence of the noise, making the suppression of the burr-like noise more complete, and making the contour of the isosurface more stable and smooth.Figure 4 The convex and concave pits of the diseased blood vessels in the medical image are very different and not smooth enough. Figure 5 It can be seen that the smoothed blood vessel result is more delicate and more accurate.

[0114] In this way, the medical image optimization method provided by the application can make the transition of the convex and concave pits smoother, so as to change the steeply changing blood vessel convex and concave region into a smooth transition region. Then, the isosurface profile is smoothed by iteratively using the taubin window function (which is essentially a low-pass filter), so that the isosurface shape has a better meshing result, and the mesh vertices have a better distribution.

[0115] Those skilled in the art can understand that the above is only a description of a preferred embodiment, and is not a limitation of the application. In other embodiments, burr removal can also be performed by using a curvature smoothing algorithm, a mean filter smoothing algorithm and / or a bidirectional filter smoothing algorithm, and the first medical image is smoothed, which is not described one by one.

[0116] Preferably, in one preferred embodiment, before the second medical image is taken as the optimized medical image, the method further comprises:

[0117] Step S3: performing isosurface profile compression on the second medical image to obtain a third medical image.

[0118] Correspondingly, the second medical image is taken as the optimized medical image, which comprises taking the third medical image as the optimized medical image.

[0119] Preferably, in one preferred embodiment, the isosurface of the second medical image comprises a plurality of triangular patches. As described above, the Marching Cubes algorithm is actually a divide-and-conquer method, which distributes the extraction of the isosurface in each unit body (voxel). For each processed voxel, the isosurface inside it is approximated by a triangular patch.

[0120] Specifically, the isosurface profile compression on the second medical image to obtain a third medical image comprises:

[0121] S31: performing plane normal vector calculation on each triangular patch region to obtain a corresponding normal vector angle;

[0122] S32: merging the triangular patches according to the normal vector angle and a preset merging rule to obtain the third medical image.

[0123] Preferably, in one exemplary embodiment, step S32 specifically includes:

[0124] S321: Determine whether the difference between the normal angles of the triangular facets to be merged is within a preset angle threshold range. If so, merge the triangular facets to be merged in the following manner:

[0125] S322: Retain the circumscribed vertices of the triangular facets to be merged and remove the internal point connections of the triangular facets to be merged to obtain the third medical image.

[0126] Specifically, in one embodiment, please refer to Figure 6 and Figure 7 ,in, Figure 6 To Figure 5 The image shown is a schematic diagram of the medical image after isosurface contour compression and a magnified view of a local area. Figure 7 This is a schematic diagram illustrating the principle of triangular facet merging in one embodiment of the present invention. For example, a value between 3° and 8° is arbitrarily chosen as the preset angle threshold. As mentioned earlier, for medical images of the abdominal aorta, the preset angle threshold is preferably 5°. Triangular facets with an angle between their normal vectors smaller than the preset angle threshold are merged. Figure 7 As shown, there are three connected triangular faces A, B, and C, originally with nine vertices: A1, A2, A3, B1, B2, B3, C1, C2, and C3. Because the angle between their normal vectors NA, NB, and NC is less than 5 degrees, after merging, only four circumscribed vertices remain: A1, A2 (or any one of B1), B2 (or any one of C2), C3, and C1 (or any one of B2 or A3). Those skilled in the art will understand that although three adjacent triangular faces are used as an example, this is not a limitation of the invention. As mentioned earlier, whether the triangular faces to be merged are merged is mainly based on whether the difference between their normal vector angles is within a preset angle threshold range. Specifically, please refer to [link to relevant documentation]. Figure 6 By comparison Figure 6 and Figure 5 It is easy to see that the medical image optimization method provided by the present invention can reduce the number of triangular facet structures without reducing display accuracy by compressing isosurface contours, thereby compressing the model size and improving display efficiency.

[0127] In this way, the medical image optimization method provided by the application can simplify the triangular facets generated in the isosurface contour extraction, and combine the triangular facets that are approximately coplanar into a large polygon according to a preset included angle threshold, so as to achieve the simplification purpose. Obviously, the large polygon can also be iterated and optimized to remain triangular facets, and the application does not limit this. Therefore, the medical image optimization method provided by the application can simplify the number of triangular facets on the premise of maximizing the retention of image details, improve the efficiency of subsequent image display (rendering) and transmission, and save storage space and processing time.

[0128] Based on the same inventive concept, another embodiment of the application also provides a medical image acquisition system, which is described below with reference to Figure 8 , Figure 8 The structure block diagram of a medical image acquisition system provided by an embodiment of the application is shown in FIG. 2. As can be seen from Figure 8 The medical image acquisition system includes a medical image acquisition device 100 and a medical image optimization device 200. The medical image acquisition device 100 is configured to acquire a medical image to be optimized. The medical image acquisition device 100 includes, but is not limited to, an imaging device such as a CT or MRI, an electronic device connected to the Internet and capable of acquiring the medical image to be optimized from the Internet, or a scanning device capable of acquiring the medical image to be optimized. The medical image acquisition device 100 includes the medical image optimization device 200, which is configured to optimize the medical image to be optimized.

[0129] Specifically, the medical image optimization device 200 includes an isosurface acquisition unit 210 and a smoothing processing unit 220. The isosurface acquisition unit 210 is configured to perform isosurface contour extraction on the medical image to be optimized to obtain a first medical image. The smoothing processing unit 220 is configured to perform smoothing processing on the first medical image according to a preset smoothing control target to obtain a second medical image, and the second medical image is taken as an optimized medical image.

[0130] Further, in a preferred embodiment, the medical image optimization device 200 further includes an isosurface contour compression unit 230, which is configured to perform isosurface contour compression on the second medical image to obtain a third medical image. Accordingly, the second medical image is taken as an optimized medical image includes taking the third medical image as an optimized medical image.

[0131] Thus configured, the medical image acquisition system provided by the present application realizes an end-to-end processing flow, can make the result display of the target organ tissue more accurate, and can better assist doctors in improving the diagnostic accuracy. Especially for the mask image after the blood vessel segmentation, the blood vessel result display can be made smoother.

[0132] It should be noted that the systems and methods disclosed in the embodiments herein can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the drawings show possible architectural, functional, and operational scenarios that can be implemented according to the embodiments herein. In this regard, each block in the flowcharts and block diagrams can represent a module, a segment, or a portion of code that comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession can in fact be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block and combination of blocks in the block diagrams and / or flowcharts can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or can be implemented by a combination of special purpose hardware and computer instructions.

[0133] In addition, the terms "first", "second", etc. are used only for the purpose of description and should not be understood as indicating or implying relative importance or an indicated number of technical features. Therefore, the features defined as "first", "second", etc. can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0134] In addition, each functional module in each embodiment herein can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0135] Based on the same inventive concept, the present application also provides an electronic device, please refer to Figure 9 , which schematically shows a block structure schematic diagram of the electronic device provided by an embodiment of the present application. As Figure 9 shown, the electronic device includes a processor 301 and a memory 303, the memory 303 stores a computer program, and the computer program is executed by the processor 301 to realize the medical image optimization method described above.

[0136] As shown in Figure 9 The electronic device further includes a communication interface 302 and a communication bus 304, wherein the processor 301, the communication interface 302 and the memory 303 communicate with each other through the communication bus 304. The communication bus 304 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 304 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is shown in the figure, but it does not mean that there is only one bus or only one type of bus. The communication interface 302 is used for communication between the electronic device and other devices.

[0137] The processor 301 in the present application can be a Central Processing Unit (CPU), and can also be other general-purpose processors, Digital Signal Processors (DSP), Application Specific Integrated Circuits (ASIC), Field-Programmable Gate Arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor 301 is the control center of the electronic device, and connects various parts of the electronic device through various interfaces and lines.

[0138] The memory 303 can be used to store the computer program, and the processor 301 realizes various functions of the electronic device by running or executing the computer program stored in the memory 303 and calling the data stored in the memory 303.

[0139] The memory 303 can include nonvolatile and / or volatile memory. Nonvolatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random-access memory (RAM), or external cache memory. By way of illustration, and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), Rambus DRAM (RDRAM), direct Rambus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0140] Still another embodiment of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the medical image optimization method described above.

[0141] The readable storage medium of the embodiments of the present application can employ any combination of one or more computer readable media. The computer readable media can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this context, a computer readable storage medium can be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0142] The computer readable signal medium can include a propagated data signal with computer readable program code embodied therein. The propagated data signal can take any of a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium can be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0143] It should be noted that the computer program code for carrying out operations of the present application can be written in one or more programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages such as C or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0144] To sum up, the medical image optimization method, system, electronic equipment and storage medium provided by the present application make the transition of the convex and concave pits in the medical image more smooth through the iteration of the Laplace operator; and make the isosurface profile more stably smooth through the iteration of the taubin window function based on the sigmod logistic regression, thereby realizing an end-to-end processing flow, enabling the result display of the target organ tissue to be more accurate, and better assisting doctors to improve the diagnostic accuracy.

[0145] Further, the medical image optimization method, system, electronic equipment and storage medium provided by the present application are highly versatile, and can be applied not only to the optimization of aortic blood vessels, but also to the optimization of coronary blood vessels and nerve blood vessels.

[0146] Still further, the medical image optimization method provided by the present application further performs isosurface profile compression on the medical image after the smoothing processing, so that the result display of the organ tissue in the medical image is more smooth and accurate, the storage space of the image data is saved, the efficiency of subsequent image display is improved, the system resources are saved, and the system cost is reduced.

[0147] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0148] In summary, the above embodiments describe the different configurations of the medical image optimization method, system, electronic device and storage medium proposed by the present application in detail. Of course, the above description is only a description of the preferred embodiments of the present application, and does not limit the scope of the present application in any way. The present application includes but is not limited to the configurations listed in the above embodiments. Those skilled in the art can easily deduce other embodiments from the above embodiments. Any modification or modification made by those skilled in the art according to the above disclosure is within the scope of the claims.

Claims

1. A method for optimizing medical images, characterized in that, include: The contour of the isosurface is extracted from the medical image to be optimized to obtain the first medical image; Based on the preset smoothing control target, first preset smoothing control information is obtained, wherein the first preset smoothing control information includes a first preset iteration number and a preset relaxation factor; An anisotropic Laplace operator is used to enhance and highlight the edge information of the first isosurface; wherein, the first isosurface is the isosurface of the first medical image; Based on the first preset number of iterations and the preset relaxation factor, the anisotropic Laplacian operator is used iteratively to smooth the contour of the second isosurface; wherein, the second isosurface is the first isosurface after the enhancement and protrusion processing, so as to obtain the medical image after the first smoothing processing; According to the second preset smoothing control information, the Taubin window function based on sigmoid logistic regression is used to perform a second smoothing process on the first smoothed medical image to obtain a second smoothed medical image, and the second smoothed medical image is used as the second medical image. The second medical image is used as the optimized medical image.

2. The medical image optimization method according to claim 1, characterized in that, The process of extracting contours from the medical image to be optimized to obtain a first medical image includes: Based on the volume data of the medical image to be optimized, extract information for each first unit volume; Based on the positional relationship between the preset isosurface and each of the first unit cells, the second unit cells intersecting with the preset isosurface are separated. Obtain the approximate representation of the preset isosurface within each of the second unit cells; Connect all the isosurfaces to obtain the first medical image.

3. The medical image optimization method according to claim 1, characterized in that, The second preset smoothing control information includes a second preset number of iterations and a preset filter passband value; Before obtaining the second smoothed medical image, the process also includes: Based on the preset smoothing control target, obtain the second preset iteration number and the preset filter passband value; The step of performing a second smoothing process on the first smoothed medical image based on the second preset smoothing control information and using a Taubin window function based on sigmoid logistic regression includes: The third isosurface is transformed using the sigmoid logistic regression function; wherein, the third isosurface is the isosurface of the medical image after the first smoothing process. Based on the second preset iteration count and the preset filter passband value, the Taubin window function is used iteratively to smooth the contour of the fourth isosurface; wherein, the fourth isosurface is the third isosurface after transformation.

4. The medical image optimization method according to claim 1, characterized in that, Before using the second medical image as the optimized medical image, the process also includes: The second medical image is subjected to isosurface contour compression to obtain the third medical image; Accordingly, using the second medical image as the optimized medical image includes using the third medical image as the optimized medical image.

5. The medical image optimization method according to claim 4, characterized in that, The isosurface of the second medical image comprises several triangular facets; The process of compressing the second medical image using isosurface contours to obtain the third medical image includes: For each of the triangular facet regions, the plane normal vector is calculated to obtain its corresponding normal vector angle; The triangular facets are merged according to the normal vector angle and the preset merging rules to obtain the third medical image.

6. The medical image optimization method according to claim 5, characterized in that, The process of merging the triangular facets according to the normal vector angle and a preset merging rule to obtain the third medical image includes: Determine whether the difference between the normal angles of the triangular facets to be merged is within a preset angle threshold range. If so, merge the triangular facets to be merged in the following manner: The outer vertices of the triangular facets to be merged are retained, and the internal point connections of the triangular facets to be merged are removed to obtain the third medical image.

7. The medical image optimization method according to any one of claims 1-6, characterized in that, The medical image to be optimized includes a mask image after CTA body data vessel segmentation; Before extracting the contour of the isosurface from the medical image to be optimized to obtain the first medical image, the process further includes preprocessing the medical image to be optimized in the following manner: The mask image is preprocessed according to the preset image preprocessing target to obtain the medical image to be optimized.

8. A medical image acquisition system, characterized in that, include: A medical image acquisition device is configured to acquire a medical image to be optimized; A medical image optimization device is configured to optimize the medical image to be optimized; The medical image optimization device includes: an isosurface acquisition unit and a smoothing processing unit; wherein: The isosurface acquisition unit is configured to extract isosurface contours from the medical image to be optimized, thereby obtaining a first medical image; The smoothing processing unit is configured to obtain first preset smoothing control information according to a preset smoothing control target, wherein the first preset smoothing control information includes a first preset number of iterations and a preset relaxation factor. An anisotropic Laplacian operator is used to enhance and highlight the edge information of the first isosurface; wherein, the first isosurface is the isosurface of the first medical image; according to the first preset number of iterations and the preset relaxation factor, the anisotropic Laplacian operator is iteratively used to smooth the contour of the second isosurface; wherein, the second isosurface is the first isosurface after the enhancement and highlighting process, to obtain the first smoothed medical image; according to the second preset smoothing control information, a Taubin window function based on sigmoid logistic regression is used to perform a second smoothing process on the first smoothed medical image, to obtain the second smoothed medical image, and the second smoothed medical image is used as the second medical image; the second medical image is used as the optimized medical image.

9. The medical image acquisition system according to claim 8, characterized in that, The medical image optimization device further includes an isosurface contour compression unit, which is configured to compress the second medical image using isosurface contours to obtain a third medical image. Accordingly, using the second medical image as the optimized medical image includes using the third medical image as the optimized medical image.

10. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, which, when executed by the processor, implements the medical image optimization method according to any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, implements the medical image optimization method according to any one of claims 1 to 7.

Images