A method for integrating angiography imaging and 3D printing based on the Internet

Abstract

The present invention discloses a method for integrating angiography imaging and 3D printing based on the Internet, including: generating angiography images by using OsiriX software, and increasing the image quality when extracting vascular lesion information through image enhancement and noise elimination algorithms of a cloud server, and improving the processing efficiency of a three-dimensional model; establishing a patient information database, angiography image database and a medical diagnosis platform, and through the connection relationship between the three, providing real-time feedback of lesion information, and providing a more accurate diagnosis effect; and using a multi-dimensional calcified plaque simulation algorithm to calculate the density, length, width and volume of the adjusted calcified plaque and the stenosis rate in the blood vessel, further ensuring the accuracy of the model.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an Internet-based angiography imaging and 3D printing fusion method. Background Art

[0002] With the rapid development of medical imaging technology, angiographic imaging technology has played a key role in the diagnosis and treatment of cardiovascular diseases. Traditional angiographic techniques mainly rely on X-ray imaging and digital subtraction angiography (DSA). Although these technologies perform well in diagnosing vascular stenosis and aneurysms, they have certain limitations in three-dimensional imaging and precise lesion localization. In recent years, emerging technologies such as computed tomography angiography (CTA) and magnetic resonance angiography (MRA) have gradually become popular. These technologies provide clinicians with more detailed vascular structure information through high-resolution three-dimensional imaging. However, even so, there is still significant room for improvement in existing technologies in terms of how to more effectively integrate patients' personalized data, especially in organically combining three-dimensional imaging data with specific treatment plans.

[0003] The shortcomings of existing angiography technology are mainly reflected in the following aspects. First, the traditional angiography image processing and analysis methods are relatively simple, and it is difficult to fully utilize the advantages of modern computing technology. For example, only using image enhancement and noise elimination algorithms is often inefficient when processing complex vascular structures, and it is easy to cause the loss of vascular segment details. Secondly, although some three-dimensional imaging technologies have made certain progress, there are still problems of inaccuracy and slow update in real-time updating and precise positioning of lesions. In addition, current medical diagnostic platforms often lack effective data integration capabilities, and are unable to efficiently integrate patients' angiography images, medical records and real-time monitoring data, making it difficult to provide patients with accurate treatment plans. 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 an Internet-based angiography imaging and 3D printing fusion method to solve the problems raised in the background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for integrating angiography imaging and 3D printing based on the Internet, comprising:

[0007] Obtaining the patient's vascular morphology data and hemodynamic data through coronary CTA examination, and using the vascular morphology data and hemodynamic data as input to generate angiography images using OsiriX software;

[0008] The generated angiography image is uploaded to a cloud server, and the cloud server processes the angiography image through an image enhancement and noise elimination algorithm, extracts the pathological information of the blood vessels in the angiography image, and establishes a three-dimensional blood vessel model;

[0009] Construct a patient information database, angiography image database, and a medical diagnosis platform, and consider the connection between angiography images, patient information, and the medical diagnosis platform;

[0010] The lesion information is fed back to the medical diagnosis platform in real time, and the three-dimensional blood vessel model is adjusted through the medical diagnosis platform, and the adjusted three-dimensional blood vessel model is printed.

[0011] As a preferred solution of the Internet-based angiography imaging and 3D printing fusion method of the present invention, the patient's vascular morphology data includes:

[0012] The length from the root of the main artery of the current vascular segment to the bifurcation point of the next vascular segment, the change in the inner diameter at different locations along the length of the vascular segment, the bifurcation position from the main flow of the vascular segment to the tributary of the vascular segment, and the distance from the intima to the adventitia from the root of the main artery of the current vascular segment to the bifurcation point of the next vascular segment.

[0013] As a preferred solution of the Internet-based angiography imaging and 3D printing fusion method of the present invention, the hemodynamic data includes:

[0014] The blood flow velocity in different vascular locations, the amount of blood passing through different vascular locations per unit time, and the shear stress borne by the adjacent areas of the vascular endothelium.

[0015] As a preferred solution of the Internet-based angiography imaging and 3D printing fusion method of the present invention, wherein: the vascular morphology data and hemodynamics data are used as input, and the angiography image is generated using OsiriX software, including:

[0016] The vascular morphology data and hemodynamic data are converted into DICOM format image data and imported into the library of OsiriX software. The vascular outline is automatically drawn or manually drawn through the built-in ROI tool or Brush tool of OsiriX software to obtain the angiography image.

[0017] As a preferred solution of the Internet-based angiography imaging and 3D printing fusion method of the present invention, the cloud server processes the angiography image by image enhancement and noise elimination algorithm, including:

[0018] The cloud server reads the angiography image, splits the angiography image into images of various blood vessel parts, and converts each blood vessel part image into an enhanced blood vessel part image and a non-enhanced blood vessel part image;

[0019] For the enhanced vascular part image and the non-enhanced vascular part image, the filter kernel size is set respectively, the clarity of the vascular part image is calculated, and the clarity of the enhanced vascular part image is compared with the clarity of the corresponding original vascular part image. If the clarity of the enhanced vascular part image is greater than or equal to the clarity of the original vascular part image, it is retained, otherwise the vascular part image is reconverted.

[0020] As a preferred solution of the Internet-based angiography imaging and 3D printing fusion method of the present invention, wherein: extracting the lesion information of the blood vessels in the angiography image and establishing a three-dimensional blood vessel model includes:

[0021] Through the CT value, the length, width and volume of the plaque in the enhanced vascular area are obtained;

[0022] The density of calcified plaques was evaluated by CT value;

[0023] By enhancing the minimum inner diameter and normal inner diameter of the blood vessel in the blood vessel part map, the stenosis rate in the blood vessel is obtained.

[0024] As a preferred solution of the Internet-based angiography imaging and 3D printing fusion method of the present invention, the connection relationship between the angiography image, the patient information and the medical diagnosis platform is considered, including:

[0025] Connecting the patient ID in the patient information with the image ID in the angiography image to establish a one-to-one relationship between the patient information database and the angiography image database;

[0026] The one-to-one relationship is taken as a whole, and a one-to-one relationship with the hospital ID in the medical diagnosis platform is established through nested association.

[0027] As a preferred solution of the Internet-based angiography imaging and 3D printing fusion method of the present invention, wherein: adjusting the three-dimensional blood vessel model through the medical diagnosis platform includes:

[0028] Through the connection relationship between the angiography image, the patient information and the medical diagnosis platform, the evaluation result of the medical diagnosis platform is obtained;

[0029] According to the evaluation results of the medical diagnosis platform, the density of the adjusted calcified plaque, the length, width and volume of the plaque, and the stenosis rate in the blood vessel are calculated using a multi-dimensional calcified plaque simulation algorithm, and returned to the three-dimensional blood vessel model. According to the evaluation results of the medical diagnosis platform, the density of the adjusted calcified plaque, the length, width and volume of the plaque, and the stenosis rate in the blood vessel are calculated using a multi-dimensional calcified plaque simulation algorithm, and returned to the three-dimensional blood vessel model to update the original three-dimensional blood vessel model.

[0030] As a preferred solution of the Internet-based angiography imaging and 3D printing fusion method of the present invention, the evaluation results of the medical diagnosis platform include:

[0031] According to the medical history in the patient information and the angiography images at different periods, the development trend and speed of the lesion information can be obtained.

[0032] As a preferred solution of the Internet-based angiography imaging and 3D printing fusion method of the present invention, a multi-dimensional calcified plaque simulation algorithm is used, including:

[0033] At least one of a finite element analysis method, an adversarial network method, a mining analysis method, and a multi-objective optimization method.

[0034] Compared with the prior art, the invention has the following beneficial effects: first, the present invention generates angiography images by using OsiriX software, and through the image enhancement and noise elimination algorithm of the cloud server, it can increase the quality of the image when extracting vascular lesion information, and improve the processing efficiency of the three-dimensional model; secondly, a patient information database, angiography image database and a medical diagnosis platform are established, and through the connection relationship between the three, the lesion information is fed back in real time, providing a more accurate diagnosis effect; finally, the density, length, width and volume of the adjusted calcified plaque and the stenosis rate in the blood vessel are calculated through a multi-dimensional calcified plaque simulation algorithm, which further ensures the accuracy of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] 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:

[0036] Figure 1 This is a general flow chart of an Internet-based angiography imaging and 3D printing fusion method according to an embodiment of the present invention;

[0037] Figure 2A noise process diagram of CT value in each lesion information of the Internet-based angiography imaging and 3D printing fusion method according to an embodiment of the present invention;

[0038] Figure 3 A decibel comparison diagram before and after noise of an Internet-based angiography imaging and 3D printing fusion method according to an embodiment of the present invention;

[0039] Figure 4 A comparison chart of processing efficiency and patient waiting time of an Internet-based angiography imaging and 3D printing fusion method according to an embodiment of the present invention;

[0040] Figure 5 This is a comparison chart of the diagnostic accuracy of the Internet-based angiography imaging and 3D printing fusion method described in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] Example 1

[0048] Reference Figure 1 , which is the first embodiment of the present invention, provides an Internet-based angiography imaging and 3D printing fusion method, including:

[0049] S1. Obtain the patient's vascular morphology data and hemodynamic data, use the vascular morphology data and hemodynamic data as input, and use OsiriX software to generate angiography images;

[0050] Furthermore, the vascular morphology data includes the length from the root of the main vein of the current vascular segment to the bifurcation point of the next vascular segment, the change of the inner diameter at different positions along the length of the vascular segment, the bifurcation position of the main flow of the vascular segment to the tributary of the vascular segment, and the distance from the intima to the adventitia between the root of the main vein of the current vascular segment and the bifurcation point of the next vascular segment;

[0051] Specifically, the main root of the vascular segment is the main starting point of the coronary artery, for example, the left main coronary artery starts at the first position of the aortic root, or the starting position of other vascular segments; the branch point to the next vascular segment is the end point or bifurcation point from the corresponding starting position to the next vascular segment, for example, the bifurcation point of the next vascular segment of the left main coronary artery at the first position, or the end of the vascular segment;

[0052] It should be noted that the change of inner diameter into stenosis, dilation or irregularity is helpful to extract the pathological information of blood vessels in angiographic images;

[0053] Specifically, the bifurcation position of the main flow of the blood vessel segment to the branch of the blood vessel segment refers to the position in the coronary artery, for example, the position where the left main trunk bifurcates into the left anterior descending branch and the left circumflex branch, or the starting position of the right coronary artery at the second position to the branch point of the next blood vessel segment;

[0054] Specifically, the distance from the intima to the adventitia between the root of the main artery of the current blood vessel segment and the bifurcation point of the next blood vessel segment refers to the wall thickness at different locations along the blood vessel segment, for example, at different locations of the blood vessel segment in the coronary artery;

[0055] Furthermore, the hemodynamic data include the blood flow velocity at different vascular sites, the blood volume passing through different vascular sites per unit time in milliliters per minute (ml / min), and the shear stress borne by the adjacent areas of the vascular endothelium;

[0056] Specifically, shear stress refers to the force exerted on the blood vessel wall by friction caused by the relative movement between blood layers when blood flows;

[0057] It should be noted that by obtaining the patient's vascular morphology data and hemodynamic data, it can not only be used to generate angiographic images, but also be used as analysis data for the medical diagnosis platform and for the storage of angiographic image databases. Compared with traditional software or machine direct angiography, it is more flexible and adjustable;

[0058] Furthermore, the vascular morphology data and hemodynamic data are converted into DICOM format image data and imported into the library of the OsiriX software, and the vascular contour is automatically drawn or manually drawn through the built-in ROI tool or Brush tool of the OsiriX software to obtain angiographic images;

[0059] It should be noted that although the software is convenient to generate, the angiography images generated by the software may contain noise or artifacts. The noise will seriously affect the clarity of the vascular contour. Manual drawing involves personal expertise and differences. Therefore, the obtained angiography images need to be enhanced and noise eliminated.

[0060] S2, uploading the generated angiography image to a cloud server, which processes the angiography image through an image enhancement and noise elimination algorithm, extracts the lesion information of the blood vessels in the angiography image, and establishes a three-dimensional blood vessel model;

[0061] Furthermore, the cloud server reads the angiography image, splits the angiography image into images of various vascular locations, and converts each vascular location image into an enhanced vascular location image and a non-enhanced vascular location image;

[0062] Specifically, the images of each vascular part need to be divided according to the location of the blood vessels (such as trunk and branches);

[0063] Furthermore, for the enhanced vascular part image and the non-enhanced vascular part image, the filter kernel size is set respectively, the clarity of the vascular part image is calculated, and the clarity of the enhanced vascular part image is compared with the clarity of the corresponding original vascular part image. If the clarity of the enhanced vascular part image is greater than or equal to the clarity of the original vascular part image, it is retained, otherwise the vascular part image is reconverted;

[0064] Specifically, for the enhanced blood vessel part map, a smaller filter kernel is used to retain a clear blood vessel contour, for example, (filter kernel = 1×1, 1×2, 1×3, ..., 5×5); for the non-enhanced blood vessel part map, a larger filter kernel is used to retain the actual blood vessel path, for example, (filter kernel = 5×5, 5×2, 5×3, ..., 15×15);

[0065] Specifically, let I enh (x, y) is the enhanced blood vessel location map, I orig (x, y) is the original blood vessel location map, and the formula for calculating the clarity of the blood vessel location map is expressed as:

[0066]

[0067] I orig_filtered (x, y) = I orig (x, y)

[0068] in, Indicates size K s Gaussian filter function, * represents the convolution operation; I enh_filtered (x, y) is the enhanced blood vessel part map after filtering, I orig_filtered (x, y) is the original blood vessel location map; K s Represented as a smaller filter kernel;

[0069] Furthermore, I enh_filtered (x, y) and I orig_filtered (x, y) is substituted into the Laplace operator In, we get:

[0070]

[0071] Among them, μ enh and μ orig They are and The mean of; M and N are the width and height of the blood vessel image respectively; C enh and C orig They are the clarity of the enhanced image and the original image respectively;

[0072] Furthermore, according to the clarity comparison and retention process, the following rules are obtained:

[0073] if C enh ≥C orig then retain I enh else retain I orig

[0074] It should be noted that by splitting the angiography image into vascular part maps and performing image enhancement and noise elimination processing, the computational complexity of image processing can be reduced, especially for angiography images at high resolution, compared with processing the angiography image as a whole. Moreover, by splitting the image, the pathological conditions of each vascular part can be analyzed separately, providing efficient processing for the established three-dimensional vascular model and medical diagnosis platform analysis.

[0075] Furthermore, the pathological information of the blood vessels in the angiography image is extracted, including obtaining the length, width and volume of the plaque in the enhanced blood vessel part map through the CT value; evaluating the density of the calcified plaque through the CT value; obtaining the stenosis rate in the blood vessel through the minimum inner diameter and normal inner diameter of the blood vessel in the enhanced blood vessel part map;

[0076] It should be noted that the CT value refers to the pixel value in the computed tomography (CT) image, which reflects the radiodensity of different tissues, and the CT value is expressed in Hounsfield units (HU), which are composed of air, adipose tissue, water, soft tissue and bone;

[0077] Specifically, the lesion information of the blood vessels in the angiography image is extracted, and a three-dimensional blood vessel model is established as follows:

[0078]

[0079] Among them, Ω is the lesion information of blood vessels in the angiography image, H(x i ,y i , z i ) represents the identity function, which is used to represent the coordinate x i ,y i , z i The lesion information inside, λ represents the density of plaque, V plaque Areas represented by plaques; CT plaque (u, v, w) represents the CT value at plaque length u, width v, and volume w; It is expressed as the average value of blood CT value. represents the average value of plaque CT value; κ represents the stenosis rate; d inner(x, y) represents the minimum inner diameter of the blood vessel, d normal (x, y) represents the normal inner diameter of the blood vessel, and min(d inner (x,y),d normal (x, y)) to obtain the degree of stenosis of the blood vessel;

[0080] S3, constructing a patient information database, angiography image database and a medical diagnosis platform, and considering the connection relationship between angiography images, patient information and the medical diagnosis platform;

[0081] Further, the patient ID in the patient information is connected with the image ID in the angiography image to establish a one-to-one relationship between the patient information database and the angiography image database;

[0082] Furthermore, the one-to-one relationship is taken as a whole, and a one-to-one relationship between the database and the medical diagnosis platform is established through nested association;

[0083] Specifically, the patient information database contains all the patient's information, such as the patient's age, past medical history, number of visits, and ID number, among which the patient ID refers to the patient's ID number, because the ID number is unique;

[0084] Specifically, the angiography graphic database includes vascular morphology data, hemodynamic data, and the original angiography image and the enhanced vascular location map corresponding to the original angiography image, wherein the image ID refers to the image number of the original angiography image and the image number is unique, and the enhanced and non-enhanced vascular location maps corresponding to the original angiography image are equivalent to each vascular location map having a unique association with the corresponding original angiography image, for example, the enhanced vascular location maps obtained from the angiography image A are A1, A2, A3, ..., AN; the non-enhanced vascular location maps obtained from the angiography image B are B1, B2, B3, ..., BN; and so on;

[0085] Specifically, the medical diagnosis platform includes hospitals, expert teams, three-dimensional vascular models, and evaluation results;

[0086] It should be noted that connection refers to binding the patient's ID number with the patient's original angiography image, so that the corresponding patient can be found no matter which vascular location map is called, so as to enhance the data integration capability of the medical diagnosis platform; nested association refers to establishing a relationship between the patient information database and the angiography image database and the medical diagnosis platform on the basis of a one-to-one relationship, and binding the hospital ID (hospital registration number) in the medical diagnosis platform, because a patient cannot be diagnosed in multiple hospitals on the medical diagnosis platform at the same time, and cannot be served by multiple expert teams at the same time, which enhances the rationality in actual application scenarios and increases the uniqueness and accuracy of the treatment plan provided by the medical diagnosis platform;

[0087] S4, feeding back the lesion information to the medical diagnosis platform in real time, adjusting the three-dimensional vascular model through the medical diagnosis platform, and printing the adjusted three-dimensional vascular model;

[0088] Furthermore, through the connection relationship between the angiography image, the patient information and the medical diagnosis platform, the evaluation result of the medical diagnosis platform is obtained;

[0089] Specifically, the medical diagnosis platform can display the patient's lesion information in real time through the established relationship. The patient can then choose a hospital, and the expert team of the corresponding hospital will analyze the generated 3D model, obtain the evaluation results, and adjust the 3D model accordingly;

[0090] Specifically, the evaluation result is embodied as an evaluation score, which is composed of the weights of the lesion information of the blood vessels in the angiography image, and is expressed as:

[0091] Score λ =λ×ω1

[0092] Score u =u×ω2

[0093] Score v =v×ω3

[0094] Score w =w×ω4

[0095] Score K =κ×ω5

[0096] Among them, ω1, ω2, ω3, ω4 and ω5 represent the weights of the corresponding lesion information respectively; Score λ Score is the evaluation score of plaque density; u Score is the evaluation score of plaque length; v Score is the evaluation score of plaque width; w Score is the evaluation score of plaque volume;κ It is a score for evaluating the stenosis rate within the blood vessel;

[0097] Specifically, adaptive adjustment refers to the state of the three-dimensional model that needs to be adjusted or does not need to be adjusted. If adjustment is required, a multi-dimensional calcified plaque simulation algorithm is used;

[0098] Furthermore, based on the evaluation results of the medical diagnosis platform, a multi-dimensional calcified plaque simulation algorithm is used to calculate the density of the adjusted calcified plaque, the length, width and volume of the plaque, and the stenosis rate in the blood vessel, and return them to the three-dimensional blood vessel model;

[0099] Specifically, the multi-dimensional calcified plaque simulation algorithm is expressed as:

[0100]

[0101] Among them, t represents the instantaneous value at a certain time point; λ(t) represents the instantaneous value of the plaque density; u(t) represents the instantaneous value of the plaque length; v(t) represents the instantaneous value of the plaque width;

[0102] Furthermore, at least one of a finite element analysis method, an adversarial network method, and a multi-objective optimization method may be introduced to reprocess the plaque;

[0103] Specifically, in the three-dimensional model, the density, length, width and volume of the calcified plaque and the stenosis rate within the blood vessel are dynamic parameters that change over time; the use of instantaneous values ​​can capture the state of these parameters at a specific time point, thereby combining the evaluation score to more accurately adjust the characteristics of the corresponding lesion information.

[0104] Example 2

[0105] Reference Figures 2 to 5 , which is the second embodiment of the present invention, and provides an Internet-based angiography imaging and 3D printing fusion method, including: verifying the beneficial effects involved in our invention scheme by means of simulation experiments;

[0106] Experimental preparation stage: OsiriX medical image processing software; high-performance cloud server; 3D printer (resolution reaches 0.1mm); CT and MRI scanning equipment; high-resolution display; medical image processing workstation; mold for angiography experiment;

[0107] Experimental process: Obtain the patient's vascular morphology data and hemodynamic data, and use traditional methods (X-ray imaging and digital subtraction angiography (DSA) technology), CTA (Computed Tomography Angiography), MRA (Magnetic Resonance Angiography) and the method of the present invention to generate angiography images; use OsiriX software to process the images and record the image resolution; upload the images to the cloud server for storage, and then record the image resolution after software processing and the time from data import to software processing completion, which are used to extract lesion information and establish a three-dimensional model, and print the final adjusted three-dimensional model through evaluation scores;

[0108] Experimental results: refer to Table 1 and Table 2;

[0109] Table 1

[0110]

[0111] Table 2

[0112]

[0113] First, it can be seen from Table 1 that the image resolution generated by the method of the present invention is as high as 1200dpi, which is four times that of traditional angiography and significantly higher than 600dpi of CTA and MRA; this shows that the images generated by the method of the present invention can better display the details of blood vessels and provide a more accurate diagnostic basis for the evaluation score of the medical diagnosis platform; in terms of image processing, through Figure 2 We simulated the noise of the CT value as time goes by to extract the lesion information. We found that the CT value after the noise fluctuates more than before the noise. Then we need to process the noise fluctuation. Through the image enhancement and noise elimination algorithm of the cloud server, Figure 3 It can be seen that before denoising, the noise level of each lesion information of the present invention is similar to that of the traditional method, CTA, and MRA. After denoising, the average noise level of the present invention is only 10dB, which is much lower than 25dB of the traditional method and 20dB and 18dB of CTA and MRA. This improvement greatly improves the clarity of the image and reduces the noise and artifacts of the image. The image processing time of the method of the present invention is 30 minutes, which is 50% faster than the traditional method, and is also significantly better than 45 minutes of CTA and 50 minutes of MRA. This shows that the present invention not only improves the processing efficiency of the three-dimensional model, but also can provide support for clinical decision-making more quickly. Figure 4It can also be seen that as the processing efficiency increases, the waiting time of patients is correspondingly reduced; in terms of three-dimensional printing, the printing accuracy of the method of the present invention reaches 0.1mm, which is five times the accuracy of the traditional method (0.5mm) and is 3 times higher than CTA and MRA on average, indicating that the high-precision three-dimensional model can reflect the patient's vascular condition and help to accurately deploy the treatment plan;

[0114] Combining the above data, Figure 5 It can be seen that the diagnostic accuracy of the three-dimensional model after adjusting the lesion information using the multi-dimensional calcified plaque simulation algorithm is 98%, which is significantly higher than the 85% of the traditional method, and is also better than the 90% of CTA and 92% of MRA; and it is 3% to 5% higher than the diagnostic accuracy of the three-dimensional model before adjustment, which fully demonstrates that the method of the present invention further guarantees the accuracy of the model.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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 The steps for the functions specified in one or more boxes.

[0119] 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.

[0120] 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 method for integrating angiography imaging and 3D printing based on the Internet, characterized in that: include: Acquiring vascular morphology data and hemodynamic data of the patient, and using the vascular morphology data and hemodynamic data as input to generate angiography images using OsiriX software; The patient's vascular morphology data includes: The length from the root of the main vein of the current segment to the bifurcation point of the next segment, the change in the inner diameter at different locations along the length of the segment, the bifurcation position of the main flow of the segment to the tributary of the segment, and the distance from the root of the main vein of the current segment to the bifurcation point of the next segment from the intima to the adventitia; The hemodynamic data include: The blood flow velocity in different blood vessel parts, the amount of blood passing through different blood vessel parts per unit time, and the shear stress borne by the adjacent areas of the vascular endothelium; The generated angiography image is uploaded to a cloud server, and the cloud server processes the angiography image through an image enhancement and noise elimination algorithm, extracts the pathological information of the blood vessels in the angiography image, and establishes a three-dimensional blood vessel model; The step of extracting the lesion information of blood vessels in the angiography image and establishing a three-dimensional blood vessel model comprises: Through the CT value, the length, width and volume of the plaque in the enhanced vascular area are obtained; The density of calcified plaques was evaluated by CT value; By enhancing the minimum inner diameter and normal inner diameter of the blood vessel in the blood vessel location map, the stenosis rate in the blood vessel is obtained; Construct a patient information database, angiography image database and a medical diagnosis platform, and establish a connection between angiography images, patient information and the medical diagnosis platform; Feeding back the lesion information to the medical diagnosis platform in real time, adjusting the three-dimensional blood vessel model through the medical diagnosis platform, and printing the adjusted three-dimensional blood vessel model; By means of the medical diagnosis platform, adjusting the three-dimensional blood vessel model includes: Through the connection relationship between the angiography image, the patient information and the medical diagnosis platform, the evaluation result of the medical diagnosis platform is obtained; According to the evaluation results of the medical diagnosis platform, a multi-dimensional calcified plaque simulation algorithm is used to calculate the density of the adjusted calcified plaque, the length, width and volume of the plaque, and the stenosis rate in the blood vessel, and return them to the three-dimensional blood vessel model.

2. The Internet-based angiography imaging and 3D printing fusion method according to claim 1, characterized in that: The vascular morphology data and hemodynamic data are used as input to generate angiography images using OsiriX software, including: The vascular morphology data and hemodynamic data are converted into DICOM format image data and imported into the library of OsiriX software. The vascular outline is automatically drawn or manually drawn through the built-in ROI tool or Brush tool of OsiriX software to obtain the angiography image.

3. The Internet-based angiography imaging and 3D printing fusion method according to claim 2, characterized in that: The cloud server processes the angiography image by using an image enhancement and noise elimination algorithm, including: The cloud server reads the angiography image, splits the angiography image into images of various blood vessel parts, and converts each blood vessel part image into an enhanced blood vessel part image and a non-enhanced blood vessel part image; For the enhanced vascular part image and the non-enhanced vascular part image, the filter kernel size is set respectively, the clarity of the vascular part image is calculated, and the clarity of the enhanced vascular part image is compared with the clarity of the corresponding original vascular part image. If the clarity of the enhanced vascular part image is greater than or equal to the clarity of the original vascular part image, it is retained, otherwise the vascular part image is reconverted.

4. The Internet-based angiography imaging and 3D printing fusion method according to claim 1, characterized in that: Establish connections between angiographic images, patient information, and medical diagnostic platforms, including: Connecting the patient ID in the patient information with the image ID in the angiography image to establish a one-to-one relationship between the patient information database and the angiography image database; The one-to-one relationship is taken as a whole, and a one-to-one relationship between the database and the medical diagnosis platform is established through nested association.

5. The Internet-based angiography imaging and 3D printing fusion method according to claim 1, characterized in that: The evaluation results of the medical diagnostic platform include: Based on the patient's medical history and angiography images at different times, the development trend and speed of the lesion information can be obtained.

6. The Internet-based angiography imaging and 3D printing fusion method according to claim 1, characterized in that: Utilizes multi-dimensional calcified plaque simulation algorithms, including: At least one of a finite element analysis method, an adversarial network method, and a multi-objective optimization method.

Images