A dynamic digital model of human blood vessels and an aging simulation system

Abstract

This invention discloses a dynamic digital model of human blood vessels and an aging simulation system. This system, which belongs to the fields of medical image processing and biomedical engineering, includes a medical image data processing module, a generative network module, a population data analysis module, an aging simulation module, and a dynamic rendering module. Using this dynamic digital model of human blood vessels and aging simulation system, the invention achieves dynamic, controllable, and precise simulation of human vascular structure and function, and simulates the aging process of blood vessels.

Description

Technical Field

[0001] The present invention belongs to the field of medical image processing and biomedical engineering technology, and in particular to a human blood vessel dynamic generation digital model and an aging simulation system. Background Art

[0002] With the continuous advancement of medical research and clinical applications, in-depth research and precise simulation of human blood vessels have become crucial. Currently, in the field of vascular research, traditional static models cannot accurately reflect the dynamic changes of blood vessels under different physiological states and the aging process. Furthermore, existing simulation technologies, when combined with medical imaging data to simulate vascular structure and function, suffer from low data utilization, poor model controllability, and difficulty in achieving personalized simulation.

[0003] Image labels obtained from medical images are an important foundation for constructing digital vascular models, but existing technologies struggle to fully utilize this label information to generate high-quality, dynamic digital vascular models that can simulate the aging process. For example, when dealing with complex vascular branching structures and vascular differences between individuals, traditional methods are unable to effectively integrate population data analysis results, resulting in a lack of versatility and accuracy in the model. Furthermore, in terms of dynamic rendering, existing vascular simulation systems cannot realistically display the dynamic changes and aging characteristics of blood vessels in real time, failing to meet the high-precision requirements for vascular simulation in fields such as medical education, clinical diagnosis, and drug development. Summary of the Invention

[0004] The purpose of the present invention is to provide a human blood vessel dynamic generation digital model and aging simulation system to achieve dynamic, controllable and accurate simulation of human blood vessel structure and function, and simulate the aging process of blood vessels.

[0005] To achieve the above-mentioned objectives, the present invention provides a human blood vessel dynamic generation digital model and aging simulation system, comprising a medical image data processing module, a generative network module, a crowd data analysis module, an aging simulation module, and a dynamic rendering module;

[0006] The medical image data processing module is used to acquire medical image data and perform preprocessing operations on it. The preprocessing includes image enhancement, image noise reduction and image segmentation;

[0007] The generative network module uses the generative adversarial network (GAN) generative network architecture, taking pre-processed medical imaging data and image labels as input to train and generate digital models of blood vessels.

[0008] The population data analysis module is used to establish a population vascular database. Statistical methods and machine learning algorithms are used to analyze the data in the database. The module extracts the patterns of vascular characteristics changing with age and the differences between individuals to obtain patterns of vascular aging. The analysis results are fed back to the generative network module to optimize the generated vascular digital model.

[0009] The aging simulation module simulates the vascular aging process based on the vascular digital model generated based on the vascular aging patterns obtained from population data analysis;

[0010] The dynamic rendering module uses computer graphics technology to render the generated vascular dynamic digital model and aging simulation model in real time.

[0011] Preferably, the specific operation process of preprocessing in the medical image data processing module is:

[0012] Image enhancement: The histogram equalization method is used to enhance the contrast of medical images. The calculation formula of histogram equalization is as follows:

[0013] ;

[0014] in, is the grayscale after equalization, The gray level in the original image is The number of pixels, is the total number of pixels in the image, is the grayscale level of the image;

[0015] Image denoising: Median filtering is used to reduce image noise. The filter window, the calculation formula of the median filter is as follows:

[0016] ;

[0017] in, The image after denoising is at coordinate The pixel value at The original image Central window The pixel values ​​within and is the offset;

[0018] Image segmentation: A segmentation algorithm based on region growing is used to extract the blood vessel region. The calculation formula for region growing is as follows:

[0019] ;

[0020] in, is the updated vascular area, is the blood vessel area in the previous step, is the pixel to be judged, Pixel The blood vessel area in the previous step The similarity measure of is the set similarity threshold.

[0021] Preferably, the calculation formula of the objective function of the generative adversarial network GAN in the generative network module is as follows:

[0022] ;

[0023] in, For the generator, is the discriminator, is the objective function, For real medical imaging data, is random noise, Generate data for the generator, For the discriminator The probability of discriminating against real data, For the discriminator The discriminant probability of the generated data, is the probability distribution of the real data, Probability distribution of the noise input to the generator.

[0024] Preferably, the population data analysis module uses principal component analysis to perform dimensionality reduction when analyzing population vascular data. The calculation formula is as follows:

[0025] ;

[0026] in, is the vascular feature after dimensionality reduction, is the original high-dimensional population vascular feature, is the projection matrix obtained in principal component analysis, is the projection matrix The transpose of

[0027] The linear regression model is used to analyze the law of vascular characteristics changing with age. and age The linear regression model is as follows:

[0028] ;

[0029] in, is the intercept, is the regression coefficient, reflecting the influence of age on vascular characteristics. is a random error term that follows a normal distribution with a mean of 0.

[0030] Preferably, the aging simulation module realizes dynamic simulation of vascular aging by changing the geometric morphology and mechanical properties of the blood vessels.

[0031] The geometric changes of blood vessels during vascular aging include changes in vascular wall thickness and lumen diameter. The calculation formula for vascular wall thickness changes is as follows:

[0032] ;

[0033] in, is the thickness of the vascular wall after aging, is the initial thickness, is the thickening rate parameter, For aging time;

[0034] The calculation formula for the change in lumen diameter is as follows:

[0035] ;

[0036] in, is the lumen diameter after aging, is the initial diameter, is the stenosis rate parameter;

[0037] The change in the mechanical properties of blood vessels during aging is a decrease in vascular elasticity. The formula for calculating the change in vascular elastic modulus is as follows:

[0038] ;

[0039] in, is the elastic modulus after aging, is the initial elastic modulus, is the elastic modulus reduction rate parameter.

[0040] Therefore, the present invention adopts the above-mentioned human blood vessel dynamic generation digital model and aging simulation system, which has the following beneficial effects:

[0041] 1) Combined with a generative adversarial network, it can fully utilize medical imaging data and image labels to generate a high-precision, dynamic digital model of human blood vessels that accurately reflects the actual structure and dynamic changes of blood vessels;

[0042] 2) Analyze the laws of vascular aging to make the generated vascular digital models and aging simulation models more versatile and personalized;

[0043] 3) Dynamic, controllable, and precise simulation of human vascular structure and function, and simulation of the aging process of blood vessels.

[0044] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a structural schematic diagram of a human blood vessel dynamic generation digital model and aging simulation system of the present invention. DETAILED DESCRIPTION

[0046] The technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

[0047] Unless otherwise defined, technical or scientific terms used in the present invention shall have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs.

[0048] Example 1

[0049] like Figure 1 As shown, the present invention provides a human blood vessel dynamic generation digital model and aging simulation system, including a medical image data processing module, a generative network module, a crowd data analysis module, an aging simulation module and a dynamic rendering module;

[0050] The medical image data processing module is used to acquire medical image data and perform preprocessing operations on it. The preprocessing includes image enhancement, image noise reduction and image segmentation. Image labels are obtained based on medical images. These labels contain information such as the location, morphology, and size of blood vessels, providing basic data for subsequent model generation.

[0051] The specific operation process of preprocessing is:

[0052] Image enhancement: The histogram equalization method is used to enhance the contrast of medical images. The calculation formula of histogram equalization is as follows:

[0053] ;

[0054] in, is the grayscale after equalization, The gray level in the original image is The number of pixels, is the total number of pixels in the image, is the grayscale level of the image;

[0055] Image denoising: Median filtering is used to reduce image noise. The filter window, the calculation formula of the median filter is as follows:

[0056] ;

[0057] in, The image after denoising is at coordinate The pixel value at The original image Central window The pixel values ​​within and is the offset;

[0058] Image segmentation: A segmentation algorithm based on region growing is used to extract the blood vessel region. The calculation formula for region growing is as follows:

[0059] ;

[0060] in, is the updated vascular area, is the blood vessel area in the previous step, is the pixel to be judged, Pixel The blood vessel area in the previous step The similarity measure of is the set similarity threshold.

[0061] The generative network module utilizes a generative adversarial network (GAN) architecture, taking preprocessed medical imaging data and image labels as input to train and generate digital models of blood vessels. During training, through an adversarial training mechanism, the generated digital models accurately reflect the structural characteristics of real blood vessels. This module can also generate digital models of blood vessels with different morphologies and structures by adjusting network parameters and input conditions to meet specific needs, achieving model controllability.

[0062] The calculation formula of the objective function of the generative adversarial network GAN is as follows:

[0063] ;

[0064] in, For the generator, is the discriminator, is the objective function, For real medical imaging data, is random noise, Generate data for the generator, For the discriminator The probability of discriminating against real data, For the discriminator The discriminant probability of the generated data, is the probability distribution of the real data, Probability distribution of the noise input to the generator.

[0065] The population data analysis module is used to collect a large amount of vascular medical imaging data and related clinical information from people of different ages, genders, and health conditions, establish a population vascular database, and use statistical methods and machine learning algorithms to analyze the data in the database. The module extracts the patterns of vascular characteristics changing with age and the differences between individuals to obtain patterns of vascular aging. The analysis results are fed back to the generative network module to optimize the generated vascular digital model.

[0066] When analyzing vascular data of a population, principal component analysis is used for dimensionality reduction. The calculation formula is as follows:

[0067] ;

[0068] in, is the vascular feature after dimensionality reduction, is the original high-dimensional population vascular feature, is the projection matrix obtained in principal component analysis, is the projection matrix The transpose of

[0069] The linear regression model is used to analyze the law of vascular characteristics changing with age. and age The linear regression model is as follows:

[0070] ;

[0071] in, is the intercept, is the regression coefficient, reflecting the influence of age on vascular characteristics. is a random error term that follows a normal distribution with a mean of 0.

[0072] The aging simulation module simulates the vascular aging process based on the vascular digital model generated based on the vascular aging patterns obtained from population data analysis; it achieves dynamic simulation of vascular aging by changing the geometric morphology and mechanical properties of the blood vessels. At the same time, the module can generate vascular aging models at different stages according to the aging degree and time process set by the user.

[0073] The geometric changes of blood vessels during vascular aging include changes in vascular wall thickness and lumen diameter. The calculation formula for vascular wall thickness changes is as follows:

[0074] ;

[0075] in, is the thickness of the vascular wall after aging, is the initial thickness, is the thickening rate parameter, For aging time;

[0076] The calculation formula for the change in lumen diameter is as follows:

[0077] ;

[0078] in, is the lumen diameter after aging, is the initial diameter, is the stenosis rate parameter;

[0079] The change in the mechanical properties of blood vessels during aging is a decrease in vascular elasticity. The formula for calculating the change in vascular elastic modulus is as follows:

[0080] ;

[0081] in, is the elastic modulus after aging, is the initial elastic modulus, is the elastic modulus reduction rate parameter.

[0082] The dynamic rendering module uses computer graphics technology to render the generated dynamic digital model of blood vessels and aging simulation model in real time. At the same time, it updates the rendering image in real time according to the dynamic changes and aging process of the blood vessels, realizing an intuitive display of the dynamic behavior and aging characteristics of the blood vessels.

[0083] Therefore, the present invention adopts the above-mentioned human blood vessel dynamic generation digital model and aging simulation system to achieve dynamic, controllable and accurate simulation of human blood vessel structure and function, and simulate the aging process of blood vessels.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A human blood vessel dynamic digital model generation and aging simulation system, characterized by: It includes medical image data processing module, generative network module, crowd data analysis module, aging simulation module and dynamic rendering module; The medical image data processing module is used to acquire medical image data and perform preprocessing operations on it. The preprocessing includes image enhancement, image noise reduction and image segmentation; The generative network module uses the generative adversarial network (GAN) generative network architecture, taking pre-processed medical imaging data and image labels as input to train and generate digital models of blood vessels. The population data analysis module is used to establish a population vascular database. Statistical methods and machine learning algorithms are used to analyze the data in the database. The module extracts the patterns of vascular characteristics changing with age and the differences between individuals to obtain patterns of vascular aging. The analysis results are fed back to the generative network module to optimize the generated vascular digital model. The population data analysis module uses principal component analysis to reduce dimensionality when analyzing population vascular data. The calculation formula is as follows: ； in, is the vascular feature after dimensionality reduction, is the original high-dimensional population vascular feature, is the projection matrix obtained in principal component analysis, is the projection matrix The transpose of The linear regression model is used to analyze the law of vascular characteristics changing with age. and age The linear regression model is as follows: ； in, is the intercept, is the regression coefficient, reflecting the influence of age on vascular characteristics. is a random error term, which obeys a normal distribution with a mean of 0; The aging simulation module simulates the vascular aging process based on the vascular digital model generated based on the vascular aging patterns obtained from population data analysis; The aging simulation module realizes dynamic simulation of vascular aging by changing the geometric shape and mechanical properties of blood vessels. The geometric changes of blood vessels during vascular aging include changes in vascular wall thickness and lumen diameter. The calculation formula for vascular wall thickness changes is as follows: ； in, is the thickness of the vascular wall after aging, is the initial thickness, is the thickening rate parameter, For aging time; The calculation formula for the change in lumen diameter is as follows: ； in, is the lumen diameter after aging, is the initial diameter, is the stenosis rate parameter; The change in the mechanical properties of blood vessels during aging is a decrease in vascular elasticity. The formula for calculating the change in vascular elastic modulus is as follows: ； in, is the elastic modulus after aging, is the initial elastic modulus, is the elastic modulus reduction rate parameter; The dynamic rendering module uses computer graphics technology to render the generated vascular dynamic digital model and aging simulation model in real time.

2. The human blood vessel dynamic digital model generation and aging simulation system according to claim 1, characterized in that: The specific operation process of preprocessing in the medical image data processing module is as follows: Image enhancement: The histogram equalization method is used to enhance the contrast of medical images. The calculation formula of histogram equalization is as follows: ； in, is the grayscale after equalization, The gray level in the original image is The number of pixels, is the total number of pixels in the image, is the grayscale level of the image; Image denoising: Median filtering is used to reduce image noise. The filter window, the calculation formula of the median filter is as follows: ； in, The image after denoising is at coordinate The pixel value at The original image Central window The pixel values ​​within and is the offset; Image segmentation: A segmentation algorithm based on region growing is used to extract the blood vessel region. The calculation formula for region growing is as follows: ； in, is the updated vascular area, is the blood vessel area in the previous step, is the pixel to be judged, Pixel The blood vessel area in the previous step The similarity measure of is the set similarity threshold.

3. The human blood vessel dynamic digital model generation and aging simulation system according to claim 1, characterized in that: The calculation formula of the objective function of the generative adversarial network GAN in the generative network module is as follows: ； in, For the generator, is the discriminator, is the objective function, For real medical imaging data, is random noise, Generate data for the generator, For the discriminator The probability of discriminating against real data, For the discriminator The discriminant probability of the generated data, is the probability distribution of the real data, Probability distribution of the noise input to the generator.

Images