CN115705638A - Medical image optimization method, system, electronic device and storage medium - Google Patents
Medical image optimization method, system, electronic device and storage medium Download PDFInfo
- Publication number
- CN115705638A CN115705638A CN202110919636.6A CN202110919636A CN115705638A CN 115705638 A CN115705638 A CN 115705638A CN 202110919636 A CN202110919636 A CN 202110919636A CN 115705638 A CN115705638 A CN 115705638A
- Authority
- CN
- China
- Prior art keywords
- medical image
- preset
- optimized
- smoothing
- isosurface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention provides a medical image optimization method, a system, electronic equipment and a storage medium, wherein the medical image optimization method comprises the following steps: extracting an isosurface contour of the medical image to be optimized to obtain a first medical image; and according to a preset smooth control target, carrying out smooth processing on the first medical image to obtain a second medical image, and taking the second medical image as an optimized medical image. Therefore, the medical image optimization method, the medical image optimization system, the electronic equipment and the storage medium provided by the invention realize an end-to-end processing flow, can enable the result display of the target organ tissues to be more accurate, and can better assist doctors to improve the diagnosis accuracy.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method and a system for optimizing a medical image, an electronic device, and a storage medium.
Background
With the development of medical imaging technology, medical imaging has become an important means for doctors to determine the focus. The medical two-dimensional tomographic image is used for reconstructing and displaying a three-dimensional image of an organ tissue, so that the diagnosis rate of a doctor on the condition of an illness is greatly improved. For example, physicians may assist in diagnosing various vascular diseases through vascular imaging techniques.
In the prior art, the vascular imaging techniques include Computed Tomography Angiography (CTA), magnetic Resonance Angiography (MRA), and the like. However, the blood vessel imaging is a three-dimensional image, which not only includes blood vessel tissue but also includes other tissues around the blood vessel (such as bone, fat, muscle, lung tissue, etc.), which may have a great adverse effect on accurate diagnosis by the doctor. Therefore, the whole blood vessel region is extracted from the three-dimensional image through the blood vessel segmentation technology, and the shape of the blood vessel is displayed through the three-dimensional display technology, so that the diagnosis accuracy of a doctor can be improved.
Although there are many techniques for vessel segmentation, the display problem after vessel segmentation is still a very challenging task. At present, the optimization of blood vessel display mainly takes images and graphs as main parts, the optimization algorithm of image post-processing mainly adopts a morphological method to carry out post-processing on blood vessel results, and the morphological method is not only time-consuming and low in efficiency, but also is a challenge of setting appropriate morphological parameters to obtain satisfactory optimized blood vessel results.
Therefore, in view of the above-mentioned drawbacks in the prior art, how to provide an optimized display method for medical images to make the result display of target medical images (such as blood vessels) smoother and more accurate is becoming one of the technical problems to be solved by those skilled in the art.
It is noted that the information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
The present invention aims to provide a method, a system, an electronic device and a storage medium for optimizing a medical image, which can not only make the result display of the medical image smoother and more accurate, but also better assist a doctor to improve the diagnosis accuracy; and end-to-end processing flow is realized.
In order to realize the purpose, the invention is realized by the following technical scheme: a medical image optimization method, comprising:
extracting an isosurface contour of the medical image to be optimized to obtain a first medical image;
and according to a preset smooth control target, carrying out smoothing treatment on the first medical image to obtain a second medical image, and taking the second medical image as an optimized medical image.
Optionally, performing isosurface contour extraction on the medical image to be optimized to obtain a first medical image, including:
extracting the information of each first unit body according to the volume data of the medical image to be optimized;
separating a second unit body intersected with the preset isosurface according to the position relation between the preset isosurface and each first unit body;
obtaining an isosurface of an approximate representation of the preset isosurface in each second unit body;
and connecting all the iso-surfaces to obtain the first medical image.
Optionally, the smoothing the first medical image according to a preset smoothing control target to obtain a second medical image includes:
according to first preset smoothing control information, performing first smoothing processing on the first medical image by adopting a Laplacian operator based on anisotropy to obtain a medical image after the first smoothing processing;
according to second preset smoothing control information, performing second smoothing processing on the medical image after the first smoothing by using a taubin window function based on sigmod logistic regression to obtain a medical image after the second smoothing processing;
and taking the second smoothed medical image as the second medical image.
Optionally, the first preset smoothing control information includes a first preset iteration number and a preset relaxation factor;
before obtaining the first smoothed medical image, the method further includes:
acquiring the first preset iteration number and the preset relaxation factor according to the preset smooth control target;
correspondingly, the performing, according to the first preset smoothing control information, the first smoothing process on the first medical image by using an anisotropy-based laplacian operator includes:
adopting an anisotropic Lass operator to perform enhancement highlighting processing on the edge information of the first equivalence surface; wherein the first iso-surface is an iso-surface of the first medical image;
according to the first preset iteration number and the preset relaxation factor, the anisotropic Laplacian is used iteratively to carry out smoothing processing on the outline of the second equator surface; wherein the second equivalence surface is the first equivalence surface after the enhancement highlighting process.
Optionally, the second preset smoothing control information includes a second preset iteration number and a preset filtering passband value;
before obtaining the second smoothed medical image, the method further comprises:
acquiring the second preset iteration times and the preset filtering passband value according to the preset smooth control target;
and performing second smoothing processing on the first smoothed medical image by using a taubin window function based on sigmod logistic regression according to second preset smoothing control information, wherein the second smoothing processing comprises the following steps:
carrying out transformation processing on the third equivalent surface by adopting a sigmod logistic regression function; wherein the third iso-surface is the iso-surface of the medical image after the first smoothing processing;
according to the second preset iteration times iteration and the preset filtering pass band value, the taubin window function is used in an iteration mode, and the contour of a fourth equivalent surface is subjected to smoothing processing; and the fourth isosurface is the third isosurface after conversion processing.
Optionally, before the second medical image is used as the optimized medical image, the method further includes:
performing contour compression on the second medical image to obtain a third medical image;
correspondingly, said taking the second medical image as the optimized medical image comprises: the third medical image is taken as an optimized medical image.
Optionally, the iso-surface of the second medical image comprises a number of triangular patches;
the iso-surface contour compression is performed on the second medical image to obtain a third medical image, and the method comprises the following steps:
performing plane normal vector calculation on each triangular patch area to obtain a corresponding normal vector angle;
and combining the triangular patches according to the normal vector angle and a preset combination rule to obtain the third medical image.
Optionally, the merging the triangular patch according to the normal vector angle and a preset merging rule to obtain the third medical image includes:
judging whether the difference value between the normal vector angles of the triangular surface patches to be combined is within a preset included angle threshold range, if so, combining the triangular surface patches to be combined in the following mode:
and reserving an external vertex of the triangular patch to be merged, and removing the internal point connection of the triangular patch to be merged to obtain the third medical image.
Optionally, the medical image to be optimized comprises a mask image after blood vessel segmentation of CTA volume data;
before extracting the contour of the isosurface of the medical image to be optimized to obtain the first medical image, preprocessing the medical image to be optimized in the following mode:
and preprocessing the mask image according to a preset image preprocessing target to obtain the medical image to be optimized.
In order to achieve the above object, the present invention also provides a medical image acquisition system including:
a medical image acquisition device configured to acquire a medical image to be optimized;
a medical image optimization device configured to optimize the medical image to be optimized;
the medical image optimization apparatus includes: an isosurface acquisition unit and a smoothing unit; wherein:
the isosurface acquisition unit is configured to perform isosurface contour extraction on the medical image to be optimized to obtain a first medical image;
the smoothing unit is configured to smooth the first medical image according to a preset smoothing control target to obtain a second medical image, and the second medical image is used as an optimized medical image.
Optionally, the medical image optimization apparatus further comprises an iso-surface contour compression unit, configured to perform iso-surface contour compression on the second medical image to obtain a third medical image;
correspondingly, said taking the second medical image as the optimized medical image comprises: the third medical image is taken as the optimized medical image.
In order to achieve the above object, the present invention further provides an electronic device, which includes a processor and a memory, the memory storing thereon a computer program, which when executed by the processor, implements the medical image optimization method of any one of the above.
In order to achieve the above object, the present invention further provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the medical image optimization method of any one of the above.
Compared with the prior art, the invention provides a medical image optimization method, a medical image optimization system, electronic equipment and a storage medium, and has the following beneficial effects:
the medical image optimization method comprises the following steps: extracting an isosurface contour of the medical image to be optimized to obtain a first medical image; and according to a preset smooth control target, carrying out smooth processing on the first medical image to obtain a second medical image, and taking the second medical image as an optimized medical image. Therefore, the medical image optimization method, the medical image optimization system, the electronic equipment and the storage medium provided by the invention realize the end-to-end image segmentation processing flow, can enable the result display of the target organ tissues to be more accurate, and can better assist doctors to improve the diagnosis accuracy. Especially, for the blood vessel image after the blood vessel segmentation, the blood vessel result display can be smoother.
Furthermore, the medical image optimization method provided by the invention enables abrupt concave-convex pit transition in the medical image to be smoother through iteration Laplace operator; through iteration of a taubin window function based on sigmod logistic regression, the contour of the isosurface is more stably and smoothly, so that the medical image optimization method provided by the invention is easy to implement, and the result display of the organ tissues of the medical image is smoother and more accurate.
Furthermore, the medical image optimization method provided by the invention has strong universality, not only can be suitable for the optimization of aorta blood vessels, but also can be suitable for the optimization of coronary artery blood vessels and nerve blood vessels, the end-to-end algorithm process is realized, and a doctor can be better assisted to improve the diagnosis accuracy.
Still further, the medical image optimization method provided by the invention further comprises the steps of performing contour compression on the second medical image to obtain a third medical image, and using the third medical image as the optimized medical image. By the configuration, the result display of organ tissues in the medical image is smoother and more accurate, the storage space of image data can be saved, the efficiency of subsequent image display is improved, system resources are saved, and the system cost is reduced.
Since the medical image acquisition system, the electronic device and the storage medium provided by the invention belong to the same inventive concept as the medical image optimization method provided by the invention, the medical image acquisition system, the electronic device and the storage medium have at least the same beneficial effects, and are not repeated.
Drawings
FIG. 1 is a flow chart of a medical image optimization method according to an embodiment of the present invention;
FIG. 2 is a schematic iso-surface representation of an approximation of a pre-defined iso-surface within one of the second cells in accordance with an embodiment of the present invention;
FIG. 3 is a diagram illustrating a first medical image and a display result of a local area enlargement according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating the overall and local enlarged display of the medical image after the first smoothing process is performed on the medical image shown in FIG. 3;
FIG. 5 is a diagram illustrating a medical image after the second smoothing process and a partially enlarged display result of the medical image shown in FIG. 4;
FIG. 6 is a diagram illustrating a medical image after iso-surface contour compression and a partially enlarged display result of the medical image shown in FIG. 5;
FIG. 7 is a schematic diagram of a triangular patch merging principle according to an embodiment of the present invention;
FIG. 8 is a block diagram of a medical image acquisition system according to an embodiment of the present invention;
fig. 9 is a schematic block diagram of an electronic device according to an embodiment of the present invention;
wherein the reference numerals are as follows:
100-a medical image acquisition device, 200-a medical image optimization device, 210-an isosurface acquisition unit, 220-a smoothing processing unit and 230-an isosurface contour compression unit;
301-processor, 302-communication interface, 303-memory, 304-communication bus.
Detailed Description
To make the objects, advantages and features of the present invention more apparent, a medical image optimization method, a medical image optimization system, an electronic device and a storage medium according to the present invention will be described in further detail with reference to the accompanying drawings. It is to be noted that the drawings are in a very simplified form and are not to precise scale, which is merely for the purpose of facilitating and distinctly claiming the embodiments of the present invention. It should be understood that the drawings are not necessarily to scale, showing the particular construction of the invention, and that the illustrative features in the drawings, which are used to illustrate certain principles of the invention, are also somewhat simplified. Specific design features of the invention disclosed herein, including, for example, specific dimensions, orientations, locations, and configurations, will be determined in part by the particular intended application and use environment. In the embodiments described below, the same reference numerals are used in common between different drawings to denote the same portions or portions having the same functions, and a repetitive description thereof will be omitted. In this specification, like reference numerals and letters are used to designate like items, and therefore, once an item is defined in one drawing, further discussion thereof is not required in subsequent drawings.
These terms, as used herein, are interchangeable where appropriate. Similarly, if a method described herein comprises a series of steps, the order in which these steps are presented herein is not necessarily the only order in which these steps can be performed, and some of the described steps may be omitted and/or some other steps not described herein may be added to the method.
The core idea of the invention is to provide a medical image optimization method, a system, an electronic device and a storage medium to realize an end-to-end processing flow, so that the result display of the organ tissues of the medical image is smoother and more accurate, thereby better assisting a doctor to improve the diagnosis accuracy.
The electronic device according to the embodiment of the present invention may be a personal computer, a mobile terminal, and the like, and the mobile terminal may be a hardware device having various operating systems, such as a mobile phone and a tablet computer. In particular, although the present disclosure mainly describes the optimization of the aorta blood vessel image as an example, and more specifically, the CTA (computed tomography angiography) aorta 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 will be understood by those skilled in the art, the present disclosure may also be applied to the blood vessel display optimization of other blood vessels, such as coronary vessels, nerve vessels, radial artery vessels, etc.; of course, the method is also applicable to medical images of other organ tissues, such as the heart, the lung and the like, which are not described in detail.
In order to realize the above idea, the present invention provides a medical image optimization method, and for convenience of understanding and description, an overall flow of the medical image optimization method provided by the present invention is described first, and then, a description is given for each step.
Specifically, please refer to fig. 1, which schematically shows a flowchart of a medical image optimization method according to an embodiment of the present invention, including:
s1: extracting an isosurface contour of the medical image to be optimized to obtain a first medical image;
s2: and according to a preset smooth control target, carrying out smooth processing on the first medical image to obtain a second medical image, and taking the second medical image as an optimized medical image.
The medical image to be optimized may be a mask image obtained by segmenting a blood vessel of CTA (computed tomography angiography) volume data, a mask image obtained by segmenting a blood vessel of MRA (magnetic resonance angiography) volume data, or other medical images. The medical image to be optimized can be acquired by an image acquisition device, such as imaging equipment such as CT, MRI and the like, can be collected through the Internet, and can also be obtained through scanning by scanning equipment. As described above, in fig. 3 to 6, for the sake of easy understanding, the embodiment of the present invention is described by taking an aortic blood vessel after blood vessel segmentation as an example, which is not intended to limit the present invention.
With the configuration, the medical image optimization method provided by the invention realizes an end-to-end processing flow, can enable the result display of the target organ tissue to be more accurate, and can better assist a doctor to improve the diagnosis accuracy. Especially for the mask image after the blood vessel segmentation, the blood vessel result display can be smoother.
Preferably, in one embodiment, before step S1, the method further includes, by:
step S0: and preprocessing the mask image according to a preset image preprocessing target to obtain the medical image to be optimized.
As will be understood by those skilled in the art, the preprocessing includes normalizing the size of the medical image to be optimized according to a preset image preprocessing target, such as normalizing the size of the medical image to be optimized to 512 × 512 × 130 pixels. Obviously, the size of the medical image to be optimized should be set according to specific situations, and the invention is not limited to this. Further, the preprocessing further comprises normalizing the storage of the volumetric data. The volume data is composed of voxels, which are basic volume elements and can also be understood as points or a small area with arrangement and color in a three-dimensional space, and the voxels (hexahedron, usually cube) belong to a fixed grid (grid unit). Thus, in some embodiments, the volumetric data may also be stored as a table, in which case it may be considered a multidimensional array, and the volumetric data may be treated as a locally stored formatted file, such as in the. In other embodiments, the data set is divided into several slices, and each slice is stored as a bitmap image. Specifically, the mask image may be preprocessed according to actual requirements and according to a preset image preprocessing target, and is not limited to the preprocessing content mentioned in the above exemplary embodiments, and the present invention is not limited thereto.
With the configuration, the medical image optimization method provided by the invention normalizes the medical image to be processed by preprocessing the medical image to be optimized, so that the complexity of the step S1 and the step S2 can be obviously reduced, the computational resources are saved, and the efficiency of the medical image optimization processing is improved.
Preferably, in one preferred embodiment, in step S1, the performing iso-surface contour extraction on the medical image to be optimized to obtain a first medical image includes:
s11: extracting the information of each first unit body according to the volume data of the medical image to be optimized;
s12: separating a second unit body intersected with a preset isosurface according to the position relation between the preset isosurface and each first unit body;
s13: and acquiring the isosurface of the approximate representation of the preset isosurface in each second unit body.
Specifically, in one preferred embodiment, the first unit body/the second unit body includes a cube, and the information of the first unit body/the second unit body includes position information (such as coordinate information) of eight vertices of the cube. In a preferred embodiment, the method of acquiring the iso-surface includes:
s131: and obtaining the intersection point of the preset isosurface and the second unit body side by adopting interpolation calculation according to the position relation between the position information of the vertex of the second unit body and the preset isosurface. The interpolation algorithm can adopt a linear interpolation algorithm, a nearest interpolation method and the like; in order to improve the quality of the iso-surface, other interpolation algorithms with higher precision can be adopted, and the method is not limited in any way.
S132: and connecting the intersection points of the preset isosurface and the second unit body side according to a preset topological connection relation according to the relative position of each vertex of the second unit body and the preset isosurface to obtain an isosurface which is approximately represented by the preset isosurface in the second unit body.
Referring to fig. 2, fig. 2 is a schematic diagram of isosurface represented by the approximation of the predetermined isosurface in the second unit according to an embodiment of the present invention, if the value of vertex 3 is smaller than that of the point on the predetermined isosurface among 8 vertices 1-8 of a cube, and the values of the other 7 vertices 1-2 and vertices 4-8 are larger than that of the point on the predetermined isosurface, the predetermined isosurface must pass through the cube, where a1, a2 and a3 are the intersection points of the predetermined isosurface and the second unit cube edge, and the isosurface in the cube can be approximated by a triangular patch (shown by the shaded area) as shown in fig. 2. And analogizing in sequence, after all the second unit bodies are processed, obtaining a plurality of mutually unified, mutually associated and continuous triangular surface patches, and forming the first medical image by the plurality of triangular surfaces.
According to the medical image optimization method provided by the invention, the isosurface is extracted through an isosurface extraction algorithm (including but not limited to a Marching cube algorithm), and the configuration can not only reduce the complexity of the extraction process, but also be more beneficial to the display of the medical image.
S14: and connecting all the iso-surfaces to obtain the first medical image. Referring to fig. 3, fig. 3 is a schematic diagram showing a first medical image and an enlarged display result of a local region according to an embodiment of the present invention, and specifically, fig. 3 shows a result of isosurface extraction of a mask image after blood vessel segmentation of CTA (computed tomography angiography) volume data of an aortic blood vessel, as can be seen from an enlarged partial view: the medical image (iso-surface contour) at this stage has a burr-like noise with protruding boundaries and a prominent convex-concave area in the aortic vessel region.
As will be understood by those skilled in the art, an iso-surface is a surface in space on which the value of the function F (x, y, z) is equal to some given value. Specifically, if each node holds a three-variable function F (x, y, z) and the continuous sampling values of the grid cells in the x, y, z directions are F (x, y, z), the iso-surface is a curved surface composed of all points satisfying S = { (x, y, z) | F (x, y, z) = Fi } for a given value Fi. The information of the preset iso-surface comprises the value of a function F (x, y, z) of the iso-surface determined according to the optimization target of the medical image to be processed. As described above, if a CTA (computed tomography angiography) aortic binary mask image is used as an image to be optimized, the value of the function F (x, y, z) of the iso-surface takes 1.
The method for optimizing the medical image provided by the invention is based on the basic idea of a Marking Cubes algorithm: and processing cubes (voxels) in the volume data one by one, separating out the cubes intersected with the preset isosurface, and calculating the intersection points of the isosurface and the cube edges by adopting interpolation. According to the relative position of each vertex of the cube and the preset isosurface, intersection points a1, a2 and a3 (taking fig. 2 as an example) of the preset isosurface and the side of the cube are connected in a certain mode to generate the isosurface which is used as an approximate representation of the preset isosurface in the cube. With the configuration, the medical image optimization method provided by the invention lays a foundation for the smoothing of the medical image to be processed in the step S2 by extracting the contour of the isosurface of the medical image to be processed.
It can be understood by those skilled in the art that although the specific process of isosurface extraction provided by the present invention is described in detail by taking the Marching Cubes method as an example in the foregoing embodiment, in other embodiments, other isosurface extraction methods, such as a moving tetrahedron algorithm or a partial cube algorithm, may also be used, and are not described in detail.
Preferably, in an exemplary embodiment, in step S2, the smoothing processing on the first medical image according to a preset smoothing control target to obtain a second medical image includes: step S21, performing first smoothing processing on the first medical image, step S22, performing second smoothing processing on the medical image after the first smoothing processing, and taking the medical image after the second smoothing processing as the second medical image.
Specifically, the following describes the contents of step S21 and step S22, respectively, as follows:
s21: and according to first preset smoothing control information, performing first smoothing processing on the first medical image by adopting an anisotropic-based Laplacian operator to obtain the medical image after the first smoothing processing.
Preferably, in one exemplary embodiment, the first preset smoothing control information includes a first preset number of iterations and a preset relaxation factor. Before obtaining the first smoothed medical image, the method further includes: and acquiring the first preset iteration number and the preset relaxation factor according to the preset smooth control target. Wherein the relaxation factor is used to control a maximum offset value for one iteration of high frequency information; the high-frequency information appears as a burr-like noise or the like with a protruding boundary in the contour of the iso-surface. Specifically, the first preset iteration number should be set according to an actual working condition, for example, in order to obtain a better optimization effect, values of the first preset iteration number adopted by the coronary artery and the neural blood vessel may be different. Taking the abdominal aorta blood vessel as an example, the value of the first preset iteration is 20 to 40 times, and preferably 40 times. Similarly, the value of the preset relaxation factor should also be determined preferably between 0.1 and 1 according to the actual working condition and the optimization target, and the preferred value is 0.3. It is to be understood that this is merely an illustrative of the preferred embodiments and is not to be construed as limiting the invention itself.
Accordingly, step S21 includes the following steps S211 and S212:
s211: adopting an anisotropic Lass operator to perform enhancement highlighting processing on the edge information of the first equivalence plane; wherein the first iso-surface is an iso-surface of the first medical image;
s212: according to the first preset iteration number and the preset relaxation factor, the anisotropic Laplacian is used iteratively to carry out smoothing processing on the outline of the second equator surface; wherein the second equivalence surface is the first equivalence surface after the enhancement highlighting process.
Referring to fig. 4, fig. 4 is a schematic diagram of a medical image and a display result of a local area enlargement after the first smoothing processing is performed on fig. 3. Comparing fig. 4 with fig. 3 (see the partial enlarged part), it is not difficult to find that, with such configuration, the medical image optimization method provided by the present invention performs enhancement and highlighting processing on the edge information by using an anisotropic operator on the iso-surface, and then iteratively performs smoothing processing on the contour of the iso-surface by using a laplacian operator, so that high-frequency information (noise) of the contour of the iso-surface can be suppressed, and the influence of the noise is reduced, so that the suppression of the burr-like noise is more complete, and the contour of the iso-surface is more stable and smooth.
S22: and according to second preset smoothing control information, performing second smoothing processing on the medical image after the first smoothing by using a taubin window function based on sigmod logistic regression to obtain the medical image after the second smoothing processing.
Preferably, in a preferred embodiment, the second preset smoothing control information includes a second preset number of iterations and a preset filtering pass band value. Before obtaining the second smoothed medical image, the method further comprises: and acquiring the second preset iteration number and the preset filtering passband value according to the preset smooth control target. And the preset filtering passband value is used for carrying out once interpolation processing on the grid vertex. Similar to the first preset iteration number and the preset relaxation factor, the second preset iteration number and the preset filter pass band value are set according to the actual working condition and the optimization target. For example, taking an abdominal aorta blood vessel as an example, the second preset iteration number takes a value of 5 to 15 times, preferably 10 times, and the preset filtering pass band value ranges from 0.8 to 1.2, preferably 1.
In accordance with this, step S22 includes step S221 and step S222:
s221: transforming the third equivalent surface by adopting a sigmod logistic regression function; wherein the third iso-surface is the iso-surface of the medical image after the first smoothing processing;
s222: according to the second preset iteration times iteration and the preset filtering pass band value, the taubin window function is used in an iteration mode, and the contour of a fourth equivalent surface is subjected to smoothing processing; and the fourth isosurface is the third isosurface after conversion processing.
Referring to fig. 5, fig. 5 is a schematic diagram showing the medical image after the second smoothing process and the enlarged display result of the local area according to the embodiment of the present invention, and comparing fig. 5 with fig. 4 (see the enlarged local area), it is easy to find that the blood vessel in fig. 4 has lesion pits with a large variation and is not smooth enough. As can be seen from fig. 5, the smoothed blood vessel results are more refined and accurate.
With the configuration, the medical image optimization method provided by the invention can enable the transition of concave-convex pits to be smoother by adopting the sigmod logistic regression function to carry out transformation processing on the third isosurface, so that a steep vessel concave-convex area is changed into a smooth transition area; smoothing the contour of the equivalent surface using a taubin window function (essentially a low-pass filter) in an iteration can make the contour shape of the equivalent surface have better gridding results and the grid vertices have better distribution.
It should be understood by those skilled in the art that the foregoing is only a description of the preferred embodiment, and is not a limitation of the present invention, and in other embodiments, a curvature smoothing algorithm, a mean filtering smoothing algorithm, and/or a bilateral filtering smoothing algorithm, etc. may also be used to remove burrs and perform a smoothing process on the first medical image, which is not described in detail herein.
Preferably, in a preferred embodiment, before the second medical image is used as the optimized medical image, the method further includes:
and step S3: and carrying out contour compression on the second medical image to obtain a third medical image.
Correspondingly, said taking the second medical image as the optimized medical image comprises: the third medical image is taken as an optimized medical image.
Preferably, in one preferred embodiment, the iso-surface of the second medical image comprises a plurality of triangular patches. As will be appreciated by those skilled in the art, as mentioned above, the Marching Cubes algorithm is actually a divide-and-conquer method that distributes the extraction of the iso-surface across each unit cell (voxel). For each voxel processed, the iso-surface inside it is approximated by a triangular patch.
Specifically, the iso-surface contour compression is performed on the second medical image to obtain a third medical image, and the method includes:
s31: performing plane normal vector calculation on each triangular patch area to obtain a corresponding normal vector angle;
s32: and combining the triangular patches according to the normal vector angle and a preset combination rule to obtain the third medical image.
Preferably, in one exemplary embodiment, step S32 specifically includes:
s321: judging whether the difference value between the normal vector angles of the triangular surface patches to be combined is within a preset included angle threshold range, if so, combining the triangular surface patches to be combined in the following mode:
s322: and reserving the external vertex of the triangular patch to be combined, and removing the internal point connection of the triangular patch to be combined to obtain the third medical image.
Specifically, please refer to fig. 6 and 7 in an embodiment, wherein fig. 6 is a schematic diagram of a medical image after iso-surface contour compression and a partially enlarged display result of the medical image shown in fig. 5, and fig. 7 is a schematic diagram of a principle of implementing four triangular patch merging according to an embodiment of the present invention. For example, any value between 3 ° and 8 ° is taken as the preset included angle threshold, as described above, for the medical image of the abdominal aorta blood vessel, the preset included angle threshold is preferably 5 °, and the triangular patches whose included angles between normal vector angles are smaller than the preset included angle threshold are merged. As shown in FIG. 7, there are three connected triangular patches A, B and C, originally having 9 vertices A1, A2, A3, B1, B2, B3, C1, C2 and C3; because the included angles between the normal vectors NA, NB and NC of the two vertex-contained optical fibers are less than 5 degrees, only external 4 vertexes are left after the vertexes are merged: a1, A2 (or one of B1), B2 (or one of C2), C3 and C1 (or one of B2 or A3). As will be understood by those skilled in the art, although three adjacent triangular patches are taken as an example, this is not a limitation of the present invention, and as mentioned above, whether the triangular patch to be merged is mainly based on whether the difference between the normal angles thereof is within the preset included angle threshold range. Specifically, referring to fig. 6, it can be easily found by comparing fig. 6 with fig. 5 that the method for optimizing a medical image provided by the present invention can reduce the number of triangular patch structures by iso-surface contour compression without reducing the display accuracy, thereby compressing the size of the model and improving the display efficiency.
With the configuration, the medical image optimization method provided by the invention can simplify the triangular surface patch generated during the contour extraction of the isosurface by compressing the isosurface contour, and combines the approximately coplanar triangular surface patches into a large polygon according to the preset included angle threshold; to achieve the purpose of simplification; obviously, iteration and optimization can also be continued, and a large polygon is still a triangular patch, which is not limited by the present invention. Therefore, the medical image optimization method provided by the invention simplifies the number of triangular plates, improves the display (drawing) and transmission efficiency of subsequent images, and saves the storage space and the processing time on the premise of maximally retaining the image details.
Based on the same inventive concept, a medical image acquisition system is further provided in another embodiment of the present invention, and referring to fig. 8, fig. 8 is a block diagram of a medical image acquisition system according to an embodiment of the present invention. As can be seen from fig. 8, the medical image acquisition system comprises: a medical image acquisition apparatus 100 and a medical image optimization apparatus 200. Wherein the medical image acquisition apparatus 100 is configured to acquire a medical image to be optimized; the medical image acquiring apparatus 100 includes, but is not limited to, imaging devices such as CT and MRI, electronic devices connected to the internet and capable of acquiring medical images to be optimized from the internet, or scanning devices capable of acquiring the medical images to be optimized; the medical image acquisition apparatus 100 comprises the medical image optimization apparatus 200 configured to optimize the medical image to be optimized.
Specifically, the medical image optimization apparatus 200 includes: an iso-surface acquisition unit 210 and a smoothing processing unit 220. The iso-surface obtaining unit 210 is configured to perform iso-surface contour extraction on the medical image to be optimized, so as to obtain a first medical image. The smoothing unit 220 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 an optimized medical image.
Further, in a preferred embodiment, the medical image optimization apparatus 200 further comprises an iso-surface contour compression unit 230, wherein the iso-surface contour compression unit 230 is configured to perform iso-surface contour compression on the second medical image to obtain a third medical image. Correspondingly, said taking the second medical image as the optimized medical image comprises: the third medical image is taken as an optimized medical image.
With the configuration, the medical image acquisition system provided by the invention realizes an end-to-end processing flow, can enable the result display of the target organ tissue to be more accurate, and can better assist a doctor to improve the diagnosis accuracy. Especially, the mask image after the blood vessel segmentation can enable the blood vessel result display to be smoother.
It should be noted that the systems and methods disclosed in the embodiments herein may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments herein. In this regard, each block in the flowchart or block diagrams may represent a module, a program, or a portion of code, which 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 block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In addition, the functional modules in the embodiments herein may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
Based on the same inventive concept, the present invention further provides an electronic device, and please refer to fig. 9, which schematically shows a block structure diagram of the electronic device according to an embodiment of the present invention. As shown in fig. 9, the electronic device comprises a processor 301 and a memory 303, the memory 303 having stored thereon a computer program, which when executed by the processor 301, implements the medical image optimization method described above.
As shown in fig. 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 complete communication with each other through the communication bus 304. The communication bus 304 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 304 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The communication interface 302 is used for communication between the electronic device and other devices.
The Processor 301 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and the processor 301 is the control center of the electronic device and is connected to various parts of the whole electronic device by various interfaces and lines.
The memory 303 may be used for storing the computer program, and the processor 301 implements various functions of the electronic device by running or executing the computer program stored in the memory 303 and calling data stored in the memory 303.
The memory 303 may include non-volatile and/or volatile memory. Non-volatile 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 a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct Rambus Dynamic RAM (DRDRAM), and Rambus Dynamic RAM (RDRAM), among others.
Yet another embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, may carry out the steps of the medical image optimization method described above.
The readable storage media of embodiments of the invention may take any combination of one or more computer-readable media. The readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer 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 foregoing. In this context, a computer readable storage medium may 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.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may 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.
It should be noted that computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may 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 case of a remote computer, the remote computer may 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 may be made to an external computer (for example, through the Internet using an Internet service provider).
In summary, the medical image optimization method, system, electronic device and storage medium provided by the present invention make abrupt concave-convex pit transition in the medical image smoother by iterating laplacian operator; through iteration of a taubin window function based on sigmod logistic regression, the contour of the isosurface is more stably and smoothly, so that an end-to-end processing flow is realized, the result display of the target organ tissue can be more accurate, and a doctor can be better assisted to improve the diagnosis accuracy.
Furthermore, the medical image optimization method, the medical image optimization system, the electronic device and the storage medium provided by the invention have strong universality, and are not only suitable for aortic blood vessels, but also suitable for optimizing coronary blood vessels and nerve blood vessels.
Still further, the medical image optimization method provided by the invention also performs iso-surface contour compression on the medical image after smoothing treatment, and the configuration can save the storage space of image data and improve the efficiency of subsequent image display while improving the smooth and accurate result display of organ tissues in the medical image, thereby saving system resources and reducing system cost.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
In summary, the above embodiments have described in detail different configurations of the medical image optimization method, system, electronic device and storage medium proposed by the present invention, and it is understood that the above description is only a description of the preferred embodiments of the present invention, and does not limit the scope of the present invention in any way.
Claims (13)
1. A method of medical image optimization, comprising:
extracting an isosurface contour of the medical image to be optimized to obtain a first medical image;
and according to a preset smooth control target, carrying out smooth processing on the first medical image to obtain a second medical image, and taking the second medical image as an optimized medical image.
2. The medical image optimization method according to claim 1, wherein the extracting the contour of the iso-surface of the medical image to be optimized to obtain the first medical image comprises:
extracting the information of each first unit body according to the volume data of the medical image to be optimized;
separating a second unit body intersected with a preset isosurface according to the position relation between the preset isosurface and each first unit body;
obtaining an isosurface of an approximate representation of the preset isosurface in each second unit body;
and connecting all the isosurfaces to obtain the first medical image.
3. The medical image optimization method according to claim 1, wherein the smoothing the first medical image according to a preset smoothing control target to obtain a second medical image comprises:
according to first preset smoothing control information, performing first smoothing processing on the first medical image by adopting an anisotropic-based Laplacian operator to obtain a first smoothed medical image;
according to second preset smoothing control information, performing second smoothing processing on the medical image subjected to the first smoothing by using a taubin window function based on sigmod logistic regression to obtain a medical image subjected to the second smoothing processing;
and taking the second smoothed medical image as the second medical image.
4. The medical image optimization method according to claim 3, wherein the first preset smoothing control information includes a first preset number of iterations and a preset relaxation factor;
before obtaining the first smoothed medical image, the method further includes:
acquiring the first preset iteration times and the preset relaxation factor according to the preset smooth control target;
correspondingly, the performing, according to the first preset smoothing control information, the first smoothing process on the first medical image by using an anisotropy-based laplacian operator includes:
adopting an anisotropic Lass operator to perform enhancement highlighting processing on the edge information of the first equivalence surface; wherein the first iso-surface is an iso-surface of the first medical image;
according to the first preset iteration number and the preset relaxation factor, the anisotropic Laplacian is used iteratively to carry out smoothing processing on the outline of the second equator surface; and the second equivalence surface is the first equivalence surface subjected to the enhancement and projection processing.
5. The medical image optimization method according to claim 3, wherein the second preset smoothing control information includes a second preset number of iterations and a preset filtering pass band value;
before obtaining the second smoothed medical image, the method further comprises:
acquiring the second preset iteration times and the preset filtering passband value according to the preset smooth control target;
and performing second smoothing processing on the first smoothed medical image by using a taubin window function based on sigmod logistic regression according to second preset smoothing control information, wherein the second smoothing processing comprises the following steps:
carrying out transformation processing on the third equivalent surface by adopting a sigmod logistic regression function; wherein the third iso-surface is the iso-surface of the medical image after the first smoothing processing;
iterating and using the tau window function according to the second preset iteration times and the preset filtering pass band value to carry out smoothing processing on the contour of a fourth equivalent surface; and the fourth isosurface is the third isosurface after conversion processing.
6. The medical image optimization method according to claim 1, further comprising, before the second medical image is taken as the optimized medical image:
performing contour compression on the contour of the isosurface of the second medical image to obtain a third medical image;
accordingly, the taking the second medical image as the optimized medical image comprises: the third medical image is taken as the optimized medical image.
7. A medical image optimization method according to claim 6, wherein the iso-surface of the second medical image comprises a number of triangular patches;
the iso-surface contour compression is performed on the second medical image to obtain a third medical image, and the method comprises the following steps:
performing plane normal vector calculation on each triangular patch area to obtain a corresponding normal vector angle;
and combining the triangular patches according to the normal vector angle and a preset combination rule to obtain the third medical image.
8. The medical image optimization method according to claim 7, wherein the merging the triangular patches according to the normal vector angle and a preset merging rule to obtain the third medical image comprises:
judging whether the difference value between the normal vector angles of the triangular surface patches to be combined is within a preset included angle threshold range, if so, combining the triangular surface patches to be combined in the following mode:
and reserving an external vertex of the triangular patch to be merged, and removing the internal point connection of the triangular patch to be merged to obtain the third medical image.
9. The medical image optimization method according to any one of claims 1 to 8, wherein the medical image to be optimized comprises a mask image after blood vessel segmentation of CTA volume data;
before extracting the contour of the isosurface of the medical image to be optimized to obtain the first medical image, preprocessing the medical image to be optimized in the following mode:
and preprocessing the mask image according to a preset image preprocessing target to obtain the medical image to be optimized.
10. A medical image acquisition system, comprising:
a medical image acquisition device configured to acquire a medical image to be optimized;
a medical image optimization device configured to optimize the medical image to be optimized;
the medical image optimization apparatus includes: an isosurface acquisition unit and a smoothing unit; wherein:
the isosurface acquisition unit is configured to extract an isosurface contour of the medical image to be optimized to obtain a first medical image;
the smoothing unit is configured to smooth the first medical image according to a preset smoothing control target to obtain a second medical image, and the second medical image is used as an optimized medical image.
11. The medical image acquisition system according to claim 10, wherein the medical image optimization apparatus further comprises an iso-surface contour compression unit configured to perform iso-surface contour compression on the second medical image, resulting in a third medical image;
correspondingly, said taking the second medical image as the optimized medical image comprises: the third medical image is taken as the optimized medical image.
12. An electronic device, characterized in that it comprises a processor and a memory, on which a computer program is stored which, when being executed by the processor, carries out the medical image optimization method of any one of claims 1 to 9.
13. A computer-readable storage medium, characterized in that a computer program is stored in the readable storage medium, which computer program, when being executed by a processor, carries out the medical image optimization method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110919636.6A CN115705638A (en) | 2021-08-11 | 2021-08-11 | Medical image optimization method, system, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110919636.6A CN115705638A (en) | 2021-08-11 | 2021-08-11 | Medical image optimization method, system, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115705638A true CN115705638A (en) | 2023-02-17 |
Family
ID=85180104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110919636.6A Pending CN115705638A (en) | 2021-08-11 | 2021-08-11 | Medical image optimization method, system, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115705638A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116152124A (en) * | 2023-04-23 | 2023-05-23 | 广东欧谱曼迪科技有限公司 | Vascular model smoothing method and device, electronic equipment and storage medium |
| CN116597111A (en) * | 2023-03-15 | 2023-08-15 | 磅客策(上海)智能医疗科技有限公司 | Processing method and processing device for three-dimensional image |
-
2021
- 2021-08-11 CN CN202110919636.6A patent/CN115705638A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116597111A (en) * | 2023-03-15 | 2023-08-15 | 磅客策(上海)智能医疗科技有限公司 | Processing method and processing device for three-dimensional image |
| CN116597111B (en) * | 2023-03-15 | 2024-04-26 | 磅客策(上海)智能医疗科技有限公司 | Processing method and processing device for three-dimensional image |
| CN116152124A (en) * | 2023-04-23 | 2023-05-23 | 广东欧谱曼迪科技有限公司 | Vascular model smoothing method and device, electronic equipment and storage medium |
| CN116152124B (en) * | 2023-04-23 | 2023-09-15 | 广东欧谱曼迪科技有限公司 | Vascular model smoothing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9968257B1 (en) | Volumetric quantification of cardiovascular structures from medical imaging | |
| Lebre et al. | Automatic segmentation methods for liver and hepatic vessels from CT and MRI volumes, applied to the Couinaud scheme | |
| US8761475B2 (en) | System and method for automatic recognition and labeling of anatomical structures and vessels in medical imaging scans | |
| US20230104173A1 (en) | Method and system for determining blood vessel information in an image | |
| WO2021136368A1 (en) | Method and apparatus for automatically detecting pectoralis major region in molybdenum target image | |
| CN113888555B (en) | Multi-mode brain tumor image segmentation system based on attention mechanism | |
| CN115705638A (en) | Medical image optimization method, system, electronic device and storage medium | |
| CN110570394B (en) | Medical image segmentation method, device, equipment and storage medium | |
| Wei et al. | Learning-based 3D surface optimization from medical image reconstruction | |
| CN113160189A (en) | Blood vessel center line extraction method, device, equipment and storage medium | |
| CN116503607B (en) | CT image segmentation method and system based on deep learning | |
| Han et al. | A fast seed detection using local geometrical feature for automatic tracking of coronary arteries in CTA | |
| Cui et al. | Automatic coronary centerline extraction using gradient vector flow field and fast marching method from CT images | |
| Jafari et al. | LMISA: A lightweight multi-modality image segmentation network via domain adaptation using gradient magnitude and shape constraint | |
| CN111223090A (en) | Identification system of tumor image in human lung CT image | |
| Cercos-Pita et al. | NASAL-Geom, a free upper respiratory tract 3D model reconstruction software | |
| CN117152173A (en) | Coronary artery segmentation method and system based on DUNetR model | |
| CN112116623A (en) | Image segmentation method and device | |
| Peiró et al. | Shape reconstruction from medical images and quality mesh generation via implicit surfaces | |
| CN116129184A (en) | Multi-phase focus classification method, device, equipment and readable storage medium | |
| JP2023548041A (en) | Method and system for segmentation and identification of at least one tubular structure in medical images | |
| CN113724264B (en) | Image segmentation method, system and readable storage medium | |
| Akkasaligar et al. | Analysis of polycystic kidney disease in medical ultrasound images | |
| Leonardi et al. | 3D reconstruction from CT-scan volume dataset application to kidney modeling | |
| O'Dell et al. | Traversing and labeling interconnected vascular tree structures from 3D medical images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |