Personalized coronary stent method and system based on 3D printing

Abstract

The method comprises the steps that the shape and size of a three-dimensional stent are matched with the three-dimensional structure of a coronary artery blood vessel, it is ensured that the stent is highly attached to the blood vessel, the situation that the stent moves or is unstable in the blood vessel is reduced, and the risk of thrombosis or restenosis is reduced; the surgical treatment effect is improved; the generative adversarial network and the image processing algorithm are combined, so that the structural features and lesion information of coronary artery blood vessels can be accurately extracted, the lesion type and position can be identified, and the accuracy and effectiveness of stent design can be improved; the three-dimensional model is reconstructed through a judgment mechanism, so that a personalized stent model can be automatically generated and optimized, manual intervention is reduced, and the intelligent degree of operation is improved; through geometric error minimization and maximum stress value optimization of hemodynamic force and blood vessel wall pressure, the stability and durability of the personalized coronary stent under the hemodynamic force and the blood vessel wall pressure are ensured, and the postoperative risk is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing and coronary stent customization, and in particular to a 3D printing-based personalized coronary stent method and system. Background Art

[0002] 3D printing technology: A type of rapid prototyping technology, it is a technology that uses digital model files as the basis, uses powdered metal or plastic and other bondable materials to construct objects by stacking and accumulating them layer by layer. 3D printing was originally designed to create prototypes quickly and more cost-effectively. Today, this technology has gradually been used for the direct manufacturing of some products and has been widely used in aerospace, medical and health, industrial production and other fields.

[0003] At present, 3D printing technology is widely used in the medical field. For example, 3D printing can customize personalized medical devices according to the specific conditions of patients, such as customized bone implants, dental braces, hearing aids, etc. However, there are still shortcomings for the current customization of coronary stents, which are specifically reflected in the following aspects: First, insufficient personalization: the existing coronary stents are mainly produced according to standard specifications, which cannot meet the unique coronary vascular shape and size requirements of each patient. Second, poor fit: due to the complex morphology of coronary vessels, traditional stents are difficult to fit completely, which may cause the stent to move or be unstable in the blood vessels, thereby increasing the risk of thrombosis or restenosis. Third, the diameter remains unchanged: the diameter of traditional stents in the length direction is usually fixed, while the diameter of the patient's coronary vessels may change, resulting in the inability of the stent to adapt to these changes, thereby affecting the treatment effect. Fourth, application problems: At present, almost all non-personalized coronary stents are customized for patients and hospitals, and personalized coronary stents are not yet popular enough. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a personalized coronary stent method based on 3D printing to solve the problems mentioned in the background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for personalized coronary stent based on 3D printing, comprising:

[0008] Acquire a patient's coronary artery image by using medical image generation technology, perform three-dimensional modeling on the coronary artery image using an image processing algorithm, and obtain the three-dimensional structure and vascular lesion information of the coronary artery;

[0009] Generate a personalized coronary stent model based on the three-dimensional structure and vascular lesion information of the coronary artery using a generative adversarial network, and obtain a three-dimensional stent shape and size by optimizing the personalized coronary stent model;

[0010] The three-dimensional stent shape and size are matched with the three-dimensional structure of the coronary artery. If the match is unsuccessful, the personalized coronary stent model is reconstructed. If successful, the current three-dimensional stent shape and size are used as input to output the coronary stent through 3D printing.

[0011] As a preferred solution of the 3D printing-based personalized coronary stent method of the present invention, wherein: obtaining a patient's coronary artery vascular image by medical image generation technology includes:

[0012] A CT or MRI device is used to acquire an image sequence of the coronary artery, and the image sequence is stored as a set of two-dimensional slice images.

[0013] As a preferred solution of the personalized coronary stent method based on 3D printing described in the present invention, wherein: using an image processing algorithm to perform three-dimensional modeling on the coronary artery vascular image to obtain the three-dimensional structure and vascular lesion information of the coronary artery vessel, including:

[0014] Segmenting the two-dimensional slice image and removing background noise and blood vessel noise in the two-dimensional slice image;

[0015] A grayscale threshold matrix of two-dimensional slice images is established, and image pyramids at different resolution angles are generated using the blood vessels after noise removal, where each layer of the image pyramid contains different levels of detail of blood vessels;

[0016] Among them, the detail levels are coarse scale and fine scale.

[0017] As a preferred solution of the 3D printing-based personalized coronary stent method of the present invention, the detail levels of different blood vessels include:

[0018] Calculate the coarse scale and fine scale of each layer of blood vessels to obtain the fuzzy local gradient value and clear local gradient value of the blood vessels in the coronary artery region;

[0019] Three-dimensional modeling is performed according to the gradient intervals of the fuzzy local gradient values ​​and the clear local gradient values ​​to obtain the three-dimensional structure of the coronary artery.

[0020] As a preferred solution of the 3D printing-based personalized coronary stent method of the present invention, it also includes:

[0021] The coronary artery surface is extracted from the three-dimensional structure of the coronary artery to obtain a three-dimensional gridded vascular structure model, and the texture features and geometric shape of the blood vessel are obtained using a local binary algorithm. The type of lesion is identified based on the texture features and geometric shape of the blood vessel, and the lesion position is marked using three-dimensional coordinates.

[0022] As a preferred embodiment of the 3D printing-based personalized coronary stent method of the present invention, a personalized coronary stent model is generated according to the three-dimensional structure and vascular lesion information of the coronary artery using a generative adversarial network, including:

[0023] The generative adversarial network uses a generator to generate different coronary stents according to the lesion type and lesion location, and at the same time introduces a large number of existing coronary stents. The discriminator compares the parameters of the generated coronary stents with the existing coronary stents, and repeats the process until the coronary stent generated by the generator matches the coronary stent, thus generating a personalized coronary stent model.

[0024] As a preferred embodiment of the method for personalized coronary stent based on 3D printing of the present invention, the three-dimensional stent shape and size are obtained by optimizing the personalized coronary stent model, including:

[0025] Selecting a number of stent control points on the personalized coronary stent model, defining a geometric error between the personalized coronary stent model and the three-dimensional structure of the coronary artery, and adjusting the stent control points according to the geometric error to minimize the geometric error;

[0026] Based on the minimization of geometric errors, the maximum stress value of the personalized coronary stent under hemodynamics and vascular wall pressure and the maximized stiffness of the personalized coronary stent are defined to obtain the three-dimensional stent shape and size.

[0027] In a second aspect, the present invention provides a personalized coronary stent system based on 3D printing, which comprises:

[0028] A coronary artery 3D modeling module is configured to obtain a patient's coronary artery vascular image through medical image generation technology, and perform 3D modeling on the coronary artery vascular image using an image processing algorithm to obtain the 3D structure and vascular lesion information of the coronary artery;

[0029] The personalized coronary stent model establishment and optimization module is configured to generate a personalized coronary stent model based on the three-dimensional structure and vascular lesion information of the coronary artery using a generative adversarial network, and obtain a three-dimensional stent shape and size by optimizing the personalized coronary stent model;

[0030] The three-dimensional model reconstruction and 3D printing module is configured to match the three-dimensional stent shape and size with the three-dimensional structure of the coronary artery. If the match is unsuccessful, the personalized coronary stent model is reconstructed. If successful, the current three-dimensional stent shape and size are used as input to output the coronary stent through 3D printing.

[0031] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: the processor implements any step of the above method when executing the computer program.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: the computer program implements any step of the above method when executed by a processor.

[0033] Compared with the prior art, the invention has the following beneficial effects:

[0034] 1. The present invention obtains the patient's coronary artery images through medical image generation technology, and uses image processing algorithms to perform three-dimensional modeling to generate the three-dimensional structure and lesion information of the coronary artery. The generative adversarial network is used to generate a personalized coronary stent model, and the three-dimensional stent shape and size suitable for the patient are obtained through optimization, thereby achieving personalized customization to meet the unique coronary artery shape and size requirements of each patient;

[0035] 2. By matching the shape and size of the three-dimensional stent with the three-dimensional structure of the coronary artery, the stent is ensured to fit the blood vessel closely, the movement or instability of the stent in the blood vessel is reduced, the risk of thrombosis or restenosis is reduced, and the surgical treatment effect is improved;

[0036] 3. The combination of generative adversarial networks and image processing algorithms can accurately extract the structural characteristics and lesion information of coronary arteries, accurately identify the type and location of lesions, and improve the accuracy and effectiveness of stent design;

[0037] 4. By reconstructing the three-dimensional model through the judgment mechanism, it is possible to automatically generate and optimize the personalized stent model, reduce manual intervention, improve the intelligence of the operation, and improve the efficiency of the entire process;

[0038] 5. By minimizing geometric errors and optimizing the maximum stress values ​​of hemodynamics and vascular wall pressure, the stability and durability of personalized coronary stents under hemodynamics and vascular wall pressure are ensured, reducing postoperative risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0040] Figure 1 This is an overall flow chart of a method for personalized coronary stent based on 3D printing according to an embodiment of the present invention;

[0041] Figure 2 A preoperative coronary artery lesion angiography image of a personalized coronary stent method based on 3D printing according to an embodiment of the present invention;

[0042] Figure 3 This is an angiogram of a coronary artery filled with a coronary stent after surgery based on a 3D-printed personalized coronary stent method according to an embodiment of the present invention;

[0043] Figure 4 This is a comparison chart of stent performance 1 to 12 months after surgery using a personalized coronary stent method based on 3D printing according to an embodiment of the present invention;

[0044] Figure 5 This is a time and error comparison diagram of three-dimensional model reconstruction based on a 3D printing-based personalized coronary stent method described in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0046] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0047] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0048] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0049] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0050] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0051] Example 1

[0052] Reference Figure 1 , which is the first embodiment of the present invention, and provides a method for personalized coronary stent based on 3D printing, comprising:

[0053] S1. Obtain the patient's coronary artery vascular image through medical image generation technology, use image processing algorithm to perform three-dimensional modeling on the coronary artery vascular image, and obtain the three-dimensional structure and vascular lesion information of the coronary artery;

[0054] Furthermore, the medical image generation technology uses a CT or MRI device to obtain an image sequence of the coronary artery blood vessels, and stores the image sequence of the coronary artery blood vessels as a set of two-dimensional slice images;

[0055] Specifically, assume that the set of two-dimensional slice images is represented as:

[0056]

[0057] Among them, I 2D represents a two-dimensional slice image sequence, represents the nth two-dimensional slice image;

[0058] It should be noted that after conversion into slice images, each slice represents the details of the blood vessels on a specific plane, so the details between blood vessels can be captured and the error of generating the image pyramid can be reduced;

[0059] Further, the two-dimensional slice image is segmented, and the background and blood vessel noise in the two-dimensional slice image are removed;

[0060] Specifically, segmenting and removing the background and blood vessel noise in the two-dimensional slice image is expressed as:

[0061]

[0062] in, represents the segmented two-dimensional slice image, represents the two-dimensional slice image after noise removal; S represents the segmentation operation, and D represents the denoising operation;

[0063] Furthermore, a grayscale threshold matrix of the two-dimensional slice image is established, and the image pyramids at different resolution angles are generated using the blood vessels after noise removal, where each layer of the image pyramid contains the detail levels of different blood vessels;

[0064] Specifically, a two-dimensional slice image grayscale threshold matrix is ​​established, which is expressed as:

[0065]

[0066] in, is the gray threshold matrix N of the nth image, is the grayscale threshold of each pixel (x, y);

[0067] Specifically,

[0068] Specifically,

[0069] Specifically,

[0070] Specifically, through The generated pyramid P is expressed as:

[0071]

[0072] in, represents the i-th level pyramid image;

[0073] Specifically, the levels of detail are coarse scale and fine scale;

[0074] It should be noted that classifying detail levels can more comprehensively display the details of blood vessels, improve the flexibility and adaptability of image processing, and help to more accurately identify and three-dimensionally model vascular lesions;

[0075] Furthermore, the coarse scale and fine scale of each layer of blood vessels are calculated to obtain the fuzzy local gradient value and clear local gradient value of the blood vessels in the coronary artery region;

[0076] Specifically, the blurred and clear local gradient values ​​of each layer of the blood vessel image are calculated, which are expressed as follows:

[0077]

[0078] in, Represented as a gradient operation, To sharpen the kernel, It is represented as the fuzzy gradient value of the pixel point (x, y) of the i-th layer of blood vessels; It is represented as the clear local gradient value of the pixel (x, y) of the i-th layer of blood vessels;

[0079] Furthermore, three-dimensional modeling is performed based on the gradient intervals of the fuzzy local gradient values ​​and the clear local gradient values ​​to obtain the three-dimensional structure of the coronary artery blood vessels;

[0080] It should be noted that calculating the fuzzy and clear local gradient values ​​can accurately extract the structural features of the blood vessels, making the morphology of the blood vessels clearer, thus fitting the design of the coronary stent;

[0081] Specifically, the three-dimensional structure of the coronary artery is represented as follows:

[0082]

[0083] in, is the three-dimensional modeling function, M 3D Represented as the three-dimensional structure of the coronary artery vessels;

[0084] Furthermore, the coronary artery surface is extracted from the three-dimensional structure of the coronary artery to obtain a three-dimensional gridded vascular structure model, and the texture features and geometric shapes of the blood vessels are obtained using a local binary algorithm. The lesion type is identified based on the texture features and geometric shapes of the blood vessels, and the lesion position is marked using three-dimensional coordinates.

[0085] Specifically, the local binary algorithm is processed as follows:

[0086]

[0087] in, represents the local binary threshold, Represents a binary image;

[0088] Specifically, the local geometric features of each pixel of the image processed by the local binary algorithm are extracted by gradient and curvature calculation; the geometric features include the three-dimensional blood vessel area, perimeter and centroid; the local geometric features are added to the three-dimensional gridded blood vessel structure model to obtain the texture features and geometric shape of the blood vessel;

[0089] Specifically, the texture features and geometric shapes of blood vessels are imported into the lesion type library, and the lesion type library classifies lesions by comparison. For example, the imported vascular texture features are F n , F n contains the three-dimensional coordinates corresponding to the features, then the lesion type library is from F n Start traversing the data under the entire vascular texture feature entry. If found, the current type is F n And display the current three-dimensional coordinates. If it cannot be found, F n Add to the end of the lesion type library and update the corresponding entry in the lesion type library; the search for vascular geometry is the same as the process;

[0090] It should be noted that, through the virus type library, not only can the texture features and geometric shapes of blood vessels be updated in real time, but also the processing flow and complexity of the generative adversarial network can be reduced, and the model processing efficiency can be improved;

[0091] S2. Generate a personalized coronary stent model based on the three-dimensional structure of the coronary artery and the vascular lesion information using a generative adversarial network, and obtain the three-dimensional stent shape and size by optimizing the personalized coronary stent model;

[0092] Furthermore, the generative adversarial network generates different coronary stents according to the lesion type and lesion location through the generator, and introduces a large number of existing coronary stents at the same time. The discriminator compares the parameters of the generated coronary stents with the existing coronary stents, and repeats the cycle until the coronary stent generated by the generator matches the coronary stent, thus generating a personalized coronary stent model.

[0093] It should be noted that by generating adversarial networks, personalized stents that meet the patient's specific conditions can be generated, which improves the accuracy of coronary stent customization and reduces surgical risks;

[0094] Furthermore, to optimize the personalized coronary stent model, it is necessary to select a number of stent control points on the personalized coronary stent model, define the geometric error between the personalized coronary stent model and the three-dimensional structure of the coronary artery, and adjust the stent control points by the geometric error to minimize the geometric error;

[0095] Specifically, several support control points are selected to obtain the control point set C:

[0096] C={C 1 ,C 2 ,C 3 ,…,C m}

[0097] Specifically, the geometric error E is calculated geo :

[0098]

[0099] Among them, S 3D represents a personalized coronary stent model;

[0100] Specifically, the geometric error is minimized as follows:

[0101] C * =argminCE geo

[0102] Among them, C * is the set of control points after minimizing the geometric error;

[0103] Furthermore, according to the minimization of geometric errors, the maximum stress value of the personalized coronary stent under hemodynamics and vascular wall pressure and the stiffness of the maximized personalized coronary stent are defined to obtain the three-dimensional stent shape and size;

[0104] Specifically, define the maximum stress value τ max :

[0105] τ max =max(τ flow ,τ wall )

[0106] Among them, τ flow and τ wall are the stress values ​​under hemodynamics and vascular wall pressure, respectively;

[0107] Specific, personalized coronary stent stiffness for:

[0108]

[0109] Among them, K stiff Expressed as stiffness coefficient;

[0110] It should be noted that the stability and durability of the coronary stent under actual conditions under hemodynamics and vessel wall pressure were taken into consideration, further improving the performance and safety of the stent;

[0111] S3, matching the shape and size of the three-dimensional stent with the three-dimensional structure of the coronary artery. If the matching is unsuccessful, the personalized coronary stent model is reconstructed. If the matching is successful, the current three-dimensional stent shape and size are used as input to output the coronary stent through 3D printing;

[0112] It should be noted that the matching mechanism ensures the optimal fit of the coronary stent in the patient's blood vessels, reduces the risk of stent displacement, twisting or adverse reactions, and improves the treatment effect; at the same time, when the matching is unsuccessful, the stent model can be automatically reconstructed and adjusted, reducing manual intervention and improving the level of intelligence.

[0113] Furthermore, this embodiment also provides a personalized coronary stent system based on 3D printing, including:

[0114] A coronary artery 3D modeling module is configured to obtain a patient's coronary artery vascular image through medical image generation technology, and perform 3D modeling on the coronary artery vascular image using an image processing algorithm to obtain the 3D structure and vascular lesion information of the coronary artery;

[0115] The personalized coronary stent model establishment and optimization module is configured to generate a personalized coronary stent model based on the three-dimensional structure and vascular lesion information of the coronary artery using a generative adversarial network, and obtain a three-dimensional stent shape and size by optimizing the personalized coronary stent model;

[0116] The three-dimensional model reconstruction and 3D printing module is configured to match the three-dimensional stent shape and size with the three-dimensional structure of the coronary artery. If the match is unsuccessful, the personalized coronary stent model is reconstructed. If successful, the current three-dimensional stent shape and size are used as input to output the coronary stent through 3D printing.

[0117] This embodiment further provides a computer device, which is applicable to the case of a personalized coronary stent method based on 3D printing, including:

[0118] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the personalized coronary stent method based on 3D printing as proposed in the above embodiment.

[0119] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0120] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the personalized coronary stent method based on 3D printing as proposed in the above embodiment is implemented.

[0121] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0122] Example 2

[0123] Reference Figures 2 to 5 , which is the second embodiment of the present invention, and provides a personalized coronary stent method based on 3D printing, comprising: In order to verify the superiority of the personalized coronary stent method of the present invention, the following experiment was conducted, in which 20 patients with coronary artery lesions of different ages were selected and divided into two groups: an experimental group and a control group; the experimental group used the personalized coronary stent method based on 3D printing of the present invention, and the control group used a coronary stent of traditional standard specifications;

[0124] Experimental preparation and process: First, 200 patients with coronary artery disease were selected and randomly divided into an experimental group and a control group, with 100 people in each group; the age, gender and degree of disease of the patients were evenly distributed to ensure the fairness and representativeness of the experiment; secondly, Revolution CT equipment or GE Discovery MR750, which is used in most hospitals, was used. 3.0T equipment was used to obtain coronary vascular images of all patients and store the image sequences as two-dimensional slice images; the coronary vascular images of patients were processed using OsiriX software to remove background and noise and establish a grayscale threshold matrix for two-dimensional slice images; the coarse scale and fine scale of each layer of blood vessels were calculated through the image pyramid to obtain the three-dimensional structure and lesion information of the coronary artery vessels; the generative adversarial network (GAN) training was performed using PyTorch to generate a personalized coronary stent model based on the three-dimensional structure and lesion information of the coronary artery vessels; the generated stent model was optimized, and the stent control points were adjusted through the geometric error minimization algorithm to ensure the height match between the stent and the coronary artery vessels, and the maximum stress value and stiffness of the stent under hemodynamics and vascular wall pressure were calculated; the optimized personalized coronary stent was printed using the ALPHA-CPT2 printer, and the printing material was the biocompatible material MED610;

[0125] Experimental results: All patients were followed up 1 month after stent implantation, and images were regenerated using Revolution CT equipment or GE Discovery MR750 3.0T equipment to check the stent fit, stent displacement, blood flow patency and in-stent restenosis indicators; the first 5 groups of control experimental data were taken, as shown in Table 1; the control group used EUROLIMUS standard stents; the experimental group used stents generated by the scheme of the present invention;

[0126] Table 1 Control experiments of the first five groups

[0127]

[0128] From Table 1, we can first see that the degree of fit of the experimental group patients after using personalized coronary stents was above 95%, while the degree of fit of the control group patients using standard coronary stents was about 80%, indicating that the personalized coronary stent can better match the patient's coronary artery vascular structure, reduce the gap between the stent and the blood vessel, and reduce the risk of stent displacement; secondly, the number of stent displacements in the experimental group patients was 0, while the number of stent displacements in the control group patients was 1 or more, further proving that the stability of the personalized coronary stent in the blood vessel is better than that of the standard coronary stent, reducing the risk of complications that may be caused by stent displacement; and the average blood flow patency of the experimental group patients was 83.2ml / s, and the average of the control group was 60ml / s; indicating that the personalized coronary stent can better maintain normal blood flow in the blood vessel and avoid blood flow obstruction caused by stent discomfort; finally, the in-stent restenosis rate of the experimental group patients was significantly lower than that of the control group, with an average restenosis rate of 1.94%, while that of the control group was 10.3%, which fully demonstrates that the personalized coronary stent can effectively reduce the incidence of postoperative in-stent restenosis and improve the long-term treatment effect; the above conclusions are Figure 2 and Figure 3 As displayed;

[0129] Combination Figure 4 It can be seen from the subsequent 195 experimental data that within 1 month to 12 months after surgery, the personalized coronary stent of the present invention is still superior to the traditional stent in terms of stent fit, stent displacement times, blood flow patency and in-stent restenosis rate. Figure 5 It can be seen that after 1000 iterations of training, the present invention has a high level of intelligence in 3D model reconstruction, reduces manual intervention, and improves model processing efficiency;

[0130] The above experimental process indicates that the solution of the present invention can better customize personalized coronary stents and has broad application prospects.

[0131] Those skilled in the art will appreciate that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program codes. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0132] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0135] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0136] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A personalized coronary stent method based on 3D printing, characterized in that: include: Acquiring a coronary artery image of the patient using medical imaging technology, and performing three-dimensional modeling on the coronary artery image using an image processing algorithm to obtain three-dimensional structure and vascular lesion information of the coronary artery; Using a generative adversarial network, a personalized coronary stent model is generated based on the three-dimensional structure and vascular lesion information of the coronary artery, and the three-dimensional stent shape and size are obtained by optimizing the personalized coronary stent model; The three-dimensional stent shape and size are matched with the three-dimensional structure of the coronary artery. If the match is unsuccessful, the personalized coronary stent model is reconstructed. If successful, the current three-dimensional stent shape and size are used as input to output the coronary stent through 3D printing.

2. The personalized coronary stent method based on 3D printing according to claim 1, characterized in that: The patient's coronary artery images are obtained through medical image generation technology, including: A CT or MRI device is used to acquire an image sequence of the coronary artery, and the image sequence is stored as a set of two-dimensional slice images.

3. The personalized coronary stent method based on 3D printing according to claim 2, characterized in that: Performing three-dimensional modeling on the coronary artery image using an image processing algorithm to obtain three-dimensional structure and vascular lesion information of the coronary artery, including: Segmenting the two-dimensional slice image and removing background noise and blood vessel noise in the two-dimensional slice image; A grayscale threshold matrix of two-dimensional slice images is established, and the image pyramids at different resolution angles are generated using the blood vessels after noise removal, where each layer of the image pyramid contains the details of different blood vessels; Among them, the detail levels are coarse scale and fine scale.

4. The personalized coronary stent method based on 3D printing according to claim 3, characterized in that: The different levels of detail of blood vessels include: Calculate the coarse scale and fine scale of each layer of blood vessels to obtain the fuzzy local gradient value and clear local gradient value of the blood vessels in the coronary artery area; Three-dimensional modeling is performed based on the gradient intervals of the fuzzy local gradient values ​​and the clear local gradient values ​​to obtain the three-dimensional structure of the coronary artery.

5. The personalized coronary stent method based on 3D printing according to claim 4, characterized in that: Also includes: The coronary artery surface is extracted from the three-dimensional structure of the coronary artery to obtain a three-dimensional gridded vascular structure model. The texture features and geometric shape of the blood vessel are obtained using a local binary algorithm. The type of lesion is identified based on the texture features and geometric shape of the blood vessel, and the lesion location is marked using three-dimensional coordinates.

6. The personalized coronary stent method based on 3D printing according to claim 5, characterized in that: A personalized coronary stent model is generated based on the three-dimensional structure and vascular lesion information of the coronary artery using a generative adversarial network, including: The generative adversarial network uses a generator to generate different coronary stents according to the lesion type and lesion location, and at the same time introduces a large number of existing coronary stents. The discriminator compares the parameters of the generated coronary stents with the existing coronary stents, and repeats the cycle until the coronary stent generated by the generator matches the coronary stent, thus generating a personalized coronary stent model.

7. The personalized coronary stent method based on 3D printing according to claim 6, characterized in that: By optimizing the personalized coronary stent model, a three-dimensional stent shape and size are obtained, including: Selecting a number of stent control points on the personalized coronary stent model, defining a geometric error between the personalized coronary stent model and the three-dimensional structure of the coronary artery, and adjusting the stent control points based on the geometric error to minimize the geometric error; Based on the minimization of geometric errors, the maximum stress value of the personalized coronary stent under hemodynamics and vascular wall pressure is defined and the stiffness of the personalized coronary stent is maximized to obtain the three-dimensional stent shape and size.

8. A personalized coronary stent system based on 3D printing, based on the personalized coronary stent method based on 3D printing according to any one of claims 1 to 7, characterized in that: include: a coronary artery 3D modeling module configured to acquire a patient's coronary artery image using medical imaging technology, and perform 3D modeling on the coronary artery image using an image processing algorithm to obtain 3D structure and vascular lesion information of the coronary artery; a personalized coronary stent model establishment and optimization module, configured to generate a personalized coronary stent model based on the three-dimensional structure and vascular lesion information of the coronary artery using a generative adversarial network, and obtain a three-dimensional stent shape and size by optimizing the personalized coronary stent model; The three-dimensional model reconstruction and 3D printing module is configured to match the three-dimensional stent shape and size with the three-dimensional structure of the coronary artery. If the match is unsuccessful, the personalized coronary stent model is reconstructed. If successful, the current three-dimensional stent shape and size are used as input to output the coronary stent through 3D printing.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images