CN111583385A - A personalized deformation method and system for a deformable digital human anatomy model - Google Patents

Abstract

The invention belongs to the technical field of digital human anatomy models, and discloses a personalized deformation method and system for a deformable digital human anatomy model. The personalized deformation system for the deformable digital human anatomy model includes: acquiring original image data Module, image data processing module, image data integration module, main control module, anatomical model establishment module, personalized deformation module, data storage module, display module. Through these external and internal anatomical morphological features, the present invention can guide the digital human body model to deform, so that the external and internal anatomical structures of the model become similar to the subjects, thereby constructing a personalized anatomical structure model. The invention can display the anatomical position relationship between the pipeline structure and the peripheral tissue, and realize the personalized deformation of the model; it can be applied to medical information management related to the individual user, human modeling simulation, personalized anatomical structure display, patient communication, anatomy education and many other fields.

Description

A personalized deformation method and system for a deformable digital human anatomy model

technical field

The invention belongs to the technical field of digital human anatomy models, and in particular relates to a personalized deformation method and system for a deformable digital human anatomy model.

Background technique

At present, with the advent of the era of big data, 3D digital human models are used in medical treatment, human modeling and simulation, clothing design, sports and other fields. information on individual anatomical morphological differences. If a deformable human anatomical model is established to realize the deformation registration of the digital human model and the individual patient, a personalized digital human similar to the anatomical shape of the patient can be generated through the deformation of the digital human, as the virtual digital representative of the patient itself. Provide personalized human anatomical models for doctor-patient communication, simulation, and clinical diagnosis and treatment.

On February 2, 2011, Chinese invention patent CN101964155A disclosed "a method for making a human anatomy casting mold specimen model". The technical solution disclosed in the patent uses the three-dimensional reconstruction technology of medical images to extract and analyze various human body pipeline structures. And use rapid prototyping equipment to 3D print out the mold specimen model. The model produced by this scheme is not wrapped by peripheral tissue, so it cannot show the anatomical positional relationship between the pipeline structure and the peripheral tissue; it cannot realize the personalized deformation of the model.

At the same time, most of the existing digital anatomical models are aimed at a standard human body and fail to cover the anatomical morphological differences between different human individuals. Therefore, a new method for establishing a deformable digital human anatomy model is urgently needed to solve the problems existing in the prior art solutions.

Through the above analysis, the existing problems and defects in the prior art are:

(1) The existing technical solution cannot display the anatomical positional relationship between the pipeline structure and the peripheral tissue, and cannot realize the personalized deformation of the model.

(2) Most of the existing digital anatomical models are aimed at a standard human body and fail to cover the anatomical morphological differences between different human individuals.

SUMMARY OF THE INVENTION

Aiming at the problems existing in the prior art, the present invention provides a personalized deformation method and system for a deformable digital human anatomy model.

The present invention is realized in this way, a personalized deformation method of a deformable digital human anatomy model, the personalized deformation method of the deformable digital human anatomy model comprises the following steps:

Step 1: Collect raw digital image data of different tissues or organs of individuals diagnosed as asymptomatic through CT scanning, MRI equipment, X-ray machine or 3D laser scanning equipment;

Step 2, analyze and process the acquired original image data through an image processing program; integrate the analyzed and processed image data through a data integration program;

Step 3: Control the normal operation of the model personalized deformation system through the single-chip microcomputer; establish a three-dimensional digital human anatomy model according to the integrated image data through a model establishment program;

Step 4, realize the personalized deformation of the three-dimensional digital human anatomy model by manual adjustment or automatic registration of the deformation program;

Step 5, storing the acquired original image data, the data after analysis and integration processing, the three-dimensional digital human anatomy model and the personalized deformation data of the model through the memory;

In step 6, the acquired original image data, the data after analysis and integration processing, the three-dimensional digital human anatomy model and the personalized deformation data of the model are displayed on the display.

Further, in step 1, the original digital image data of the individual includes the shape, size, external structure, internal pipeline digital image data of different tissues or organs of the human body, as well as vital anatomy information and Chinese population sample information;

The internal pipeline includes one or more of arteries, veins, trachea, bronchi, lymphatic vessels, hepatic ducts or pancreatic ducts; the Chinese population sample information includes human-to-human differences in all organs or tissues of the human body, Health and pathological differential changes in all organs or tissues.

Further, in step 2, the method for analyzing and processing the acquired original image data through an image processing program is as follows:

(1) the organ image in the acquired original image data is segmented, obtains the three-dimensional area division of all organs and tissues, and the segmentation result is presented with a three-dimensional curved surface;

The organ image segmentation method includes:

First, smooth the original image data; use Sobel and LOG for edge detection; use image expansion technology to expand the image boundary to the outside, perform image expansion, and remove noise in the image;

Secondly, carry out preliminary separation and labeling of each tissue and organ: traverse all the pixel points of the image, and find the point whose gray value is not 0. If the point is in the same area as the previous marked point, the same label is marked, otherwise, a new one is marked. Labels; sort out the labels, if a pixel and the pixel below it are marked with different label numbers and are connected, then combine the two pixels into one label, and re-adjust the labels of all labels at the same time;

Furthermore, the threshold difference segmentation algorithm is used to extract and divide each organ region to obtain the divided images of all organs and tissues;

Finally, the obtained organ and tissue division images are divided into multiple sub-images, and each sub-image is subjected to wavelet analysis to obtain the wavelet coefficients and average high-frequency coefficients of each sub-image; the seed nodes are obtained, the region is grown, and the position and the position of the object are obtained. Contour; according to the size of the obtained contour, the surrounding of the object in the sub-image is processed; the organ and tissue division image is smoothed and filtered to generate a depth image; the depth image is obtained by combining the depth image and the organ and tissue division image using the principle of depth image rendering. 3D region segmentation images of all organs and tissues;

(II) Using a point cloud registration algorithm, the standard three-dimensional model of the human body is registered with the three-dimensional regions obtained by image segmentation, and the anatomical position correspondence of the surface point clouds of the organs between individuals is obtained in turn;

(III) Based on the registration results of all individuals, the deformation model and the deformation component data are obtained through the statistical shape model algorithm.

Further, in step 2, the integration of the analyzed and processed image data through the data integration program includes:

First, based on the features of the analyzed image data, variables that can describe the image features are selected to form a multi-dimensional vector;

Secondly, project the feature vector into a low-dimensional space that distinguishes the image; cluster the feature points projected into the low-dimensional space; and use the label of the image and the clustering result to build the image feature distribution map;

Then, calculate the feature weights of all the images to be fused;

Finally, the analyzed images are fused based on the calculated feature weights.

Further, in step 3, the establishment process of the three-dimensional digital human anatomy model is as follows:

(1) Using a statistical shape training algorithm, the deformation components of the three-dimensional anatomical differences of the human body are obtained by training from a large amount of integrated medical image data;

(2) establishing a three-dimensional digital human anatomy model according to the deformation component of the three-dimensional anatomical difference of the human body obtained by training through the model building program;

(3) By adjusting many anatomical characteristic parameters to control the anatomical shape change of the human body model from the inside to the outside, so that the appearance of the human body model and the shape of the internal organs become similar to the individual human.

Further, the three-dimensional digital human anatomy model is:

表示解剖学平均模型，由模型曲面的顶点坐标构成；

为形变分量，是通过统计形状模型算法由训练数据集中学习得到；b＝[b₁,b₂,...,b_c]为形状系数；每个形变分量b_m取值为

λ_m为主成份分析特征值。Among them, X is a three-dimensional digital human anatomy model, and when the deformation component is known, the shape of X is controlled to change by adjusting the shape coefficient;

Represents the anatomical average model, which consists of the vertex coordinates of the model surface;

is the deformation component, which is learned from the training data set through the statistical shape model algorithm; b=[b ₁ , b ₂ ,...,b _c ] is the shape coefficient; each deformation component b _m takes the value of

λ _m is the principal component analysis eigenvalue.

Further, in step 4, the personalized deformation of the digital human anatomy model is realized by manual adjustment or automatic registration;

The manual adjustment method refers to artificially inputting the appearance and morphological parameters of the internal organs of the individual subject, and the model is deformed according to the input parameters and becomes similar to the individual patient's morphology.

Another object of the present invention is to provide a personalized deformation system of the deformable digital human anatomy model using the personalized deformation method of the deformable digital human anatomy model. Personalized deformation systems include:

Original image data acquisition module, image data processing module, image data integration module, main control module, anatomical model building module, personalized deformation module, data storage module, display module;

The original image data acquisition module, connected with the main control module, is used to acquire the original image data of different tissues or organs of the human body through the data acquisition device;

The image data processing module is connected with the main control module, and is used for analyzing and processing the acquired original image data through the image processing program;

The image data integration module, connected with the main control module, is used to integrate the analyzed and processed image data through the data integration program;

The main control module is connected with the original image data acquisition module, the image data processing module, the image data integration module, the anatomical model building module, the personalized deformation module, the data storage module and the display module, and is used to control the normal operation of each module of the system through the single chip microcomputer. run;

The anatomical model establishment module is connected with the main control module, and is used to establish a three-dimensional digital human anatomy model according to the integrated image data through the model establishment program;

The personalized deformation module, connected with the main control module, is used to realize the personalized deformation of the three-dimensional digital human anatomy model through manual adjustment or automatic registration of the deformation program;

A data storage module, connected with the main control module, is used for storing the acquired original image data, the data after analysis and integration processing, the three-dimensional digital human anatomy model and the personalized deformation data of the model through the memory;

The display module is connected with the main control module, and is used for displaying the acquired original image data, the data after analysis and integration, the three-dimensional digital human anatomy model and the personalized deformation data of the model through the display.

Another object of the present invention is to provide a computer program product stored on a computer-readable medium, including a computer-readable program that, when executed on an electronic device, provides a user input interface to implement the deformable digital human anatomy Personalized deformation methods for learning models.

Another object of the present invention is to provide a computer-readable storage medium storing instructions, which, when the instructions are executed on a computer, cause the computer to execute the personalized deformation method of the deformable digital human anatomy model.

Combined with all the above technical solutions, the advantages and positive effects of the present invention are as follows: the present invention realizes the deformable digital human model and the patient individual deformation registration through the original image data of different tissues or organs of the human body, and generates data for individual subjects. The anatomical structure model of the user can achieve the purpose of personalized whole-body anatomical structure modeling. Through these external and internal anatomical morphological features, the present invention can guide the digital human body model to deform, so that the external and internal anatomical structures of the model become similar to the subjects, thereby constructing a personalized anatomical structure model.

The invention can display the anatomical position relationship between the pipeline structure and the peripheral tissue, and realize the personalized deformation of the model; it can be applied to medical information management related to the individual user, human modeling simulation, personalized anatomical structure display, patient communication, anatomy education and many other fields.

Description of drawings

FIG. 1 is a flowchart of a method for personalized deformation of a deformable digital human anatomy model provided by an embodiment of the present invention.

2 is a structural block diagram of a personalized deformation system of a deformable digital human anatomy model provided by an embodiment of the present invention;

In the figure: 1. Original image data acquisition module; 2. Image data processing module; 3. Image data integration module; 4. Main control module; 5. Anatomy model building module; 6. Personalized deformation module; 7. Data storage module; 8. Display module.

FIG. 3 is a flowchart of a method for analyzing and processing raw image data provided by an embodiment of the present invention.

FIG. 4 is a flowchart of an image data integration method provided by an embodiment of the present invention.

FIG. 5 is a flowchart of a method for establishing a three-dimensional digital human anatomy model provided by an embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

In view of the problems existing in the prior art, the present invention provides a method and system for personalized deformation of a deformable digital human anatomy model. The present invention is described in detail below with reference to the accompanying drawings.

As shown in FIG. 1, the personalized deformation method of the deformable digital human anatomy model provided by the embodiment of the present invention includes the following steps:

S101 , acquire raw digital image data of different tissues or organs of individuals diagnosed as asymptomatic through CT scanning, MRI equipment, X-ray machine or three-dimensional laser scanning equipment.

S102, analyze and process the acquired original image data through an image processing program; integrate the analyzed and processed image data through a data integration program.

S103, the normal operation of the model personalized deformation system is controlled by the single chip computer; the three-dimensional digital human anatomy model is established according to the integrated image data through the model establishment program.

S104, the personalized deformation of the three-dimensional digital human anatomy model is realized by manual adjustment or automatic registration of the deformation program.

S105, store the acquired original image data, the data after analysis and integration processing, the three-dimensional digital human anatomy model and the personalized deformation data of the model through the memory.

S106, the acquired original image data, the data after analysis and integration processing, the three-dimensional digital human anatomy model and the model personalized deformation data are displayed on the display.

The original digital image data of the individual provided by the embodiment of the present invention includes the shapes, sizes, external structures of different tissues or organs of the human body, digital image data of internal pipelines, as well as bioanatomy information and Chinese population sample information; the internal pipelines include arteries, One or more of veins, trachea, bronchi, lymphatic vessels, hepatic ducts or pancreatic ducts; the Chinese population sample information includes human-to-human differences in all organs or tissues of the human body, the health and Morbid differential change.

The personalized deformation of the digital human anatomy model provided by the embodiment of the present invention is realized by manual adjustment or automatic registration; the manual adjustment method refers to the artificial input of the appearance and morphological parameters of the internal organs of the individual subject, and the model is based on the input. The parameters of the deformation are realized and become similar to the individual shape of the patient.

As shown in FIG. 2, the personalized deformation system of the deformable digital human anatomy model provided by the embodiment of the present invention includes: an original image data acquisition module 1, an image data processing module 2, an image data integration module 3, a main control module 4, Anatomical model building module 5 , personalized deformation module 6 , data storage module 7 , display module 8 .

The original image data acquisition module 1, connected with the main control module 4, is used to acquire the original image data of different tissues or organs of the human body through the data acquisition device;

The image data processing module 2 is connected with the main control module 4, and is used for analyzing and processing the acquired original image data through an image processing program;

The image data integration module 3 is connected with the main control module 4, and is used for integrating the analyzed and processed image data through the data integration program;

The main control module 4 is connected with the original image data acquisition module 1, the image data processing module 2, the image data integration module 3, the anatomical model establishment module 5, the personalized deformation module 6, the data storage module 7, and the display module 8, and is used for The normal operation of each module of the system is controlled by the single-chip microcomputer;

The anatomical model establishment module 5 is connected with the main control module 4, and is used for establishing a three-dimensional digital human anatomy model according to the integrated image data through the model establishment program;

The personalized deformation module 6, connected with the main control module 4, is used to realize the personalized deformation of the three-dimensional digital human anatomy model by manual adjustment or automatic registration of the deformation program;

The data storage module 7 is connected with the main control module 4, and is used for storing the obtained original image data, the data after analysis and integration processing, the three-dimensional digital human anatomy model and the personalized deformation data of the model through the memory;

The display module 8, connected with the main control module 4, is used to display the acquired original image data, the data after analysis and integration, the three-dimensional digital human anatomy model and the model personalized deformation data through the display.

The present invention will be further described below in conjunction with specific embodiments.

Example 1:

The personalized deformation method of the deformable digital human anatomy model provided by the embodiment of the present invention is shown in FIG. 1 . As a preferred embodiment, as shown in FIG. 3 , the original image obtained by the image processing program provided by the embodiment of the present invention is The methods of data analysis and processing are as follows:

S201 , segment the organ images in the acquired original image data to obtain three-dimensional region divisions of all organs and tissues, and the segmentation results are presented in a three-dimensional curved surface.

S202 , using a point cloud registration algorithm, the standard three-dimensional model of the human body is registered with the three-dimensional regions obtained by image segmentation, and the corresponding relationship between the anatomical positions of the surface point clouds of the organs between individuals is obtained in turn.

S203, based on the registration results of all individuals, obtain deformation model and deformation component data through a statistical shape model algorithm.

In step S201, the organ image segmentation method provided by the embodiment of the present invention includes:

First, smooth the original image data; use Sobel and LOG for edge detection; use image expansion technology to expand the image boundary to the outside, perform image expansion, and remove noise in the image;

Secondly, carry out preliminary separation and labeling of each tissue and organ: traverse all the pixel points of the image, and find the point whose gray value is not 0. If the point is in the same area as the previous marked point, the same label is marked, otherwise, a new one is marked. Labels; sort out the labels, if a pixel and the pixel below it are marked with different label numbers and are connected, then combine the two pixels into one label, and re-adjust the labels of all labels at the same time;

Furthermore, the threshold difference segmentation algorithm is used to extract and divide each organ region to obtain the divided images of all organs and tissues;

Finally, the obtained organ and tissue division images are divided into multiple sub-images, and each sub-image is subjected to wavelet analysis to obtain the wavelet coefficients and average high-frequency coefficients of each sub-image; the seed nodes are obtained, the region is grown, and the position and the position of the object are obtained. Contour; according to the size of the obtained contour, the surrounding of the object in the sub-image is processed; the organ and tissue division image is smoothed and filtered to generate a depth image; the depth image is obtained by combining the depth image and the organ and tissue division image using the principle of depth image rendering. 3D region segmentation images of all organs and tissues.

Example 2:

The personalized deformation method of the deformable digital human anatomy model provided by the embodiment of the present invention is shown in FIG. 1 . As a preferred embodiment, as shown in FIG. 4 , the data integration program provided by the embodiment of the present invention analyzes and processes the Image data integration methods include:

S301, select variables that can describe the image features based on the features of the analyzed and processed image data to form a multi-dimensional vector;

S302, project the feature vector to a low-dimensional space that distinguishes the image; cluster the feature points projected into the low-dimensional space; and use the label of the image and the clustering result to establish an image feature distribution map;

S303, calculate the feature weights of all the images to be fused;

S304 , fuse the analyzed and processed images based on the calculated feature weights.

Example 3:

The personalized deformation method of the deformable digital human anatomy model provided by the embodiment of the present invention is shown in FIG. 1 . As a preferred embodiment, as shown in FIG. 5 , the establishment process of the three-dimensional digital human anatomy model provided by the embodiment of the present invention is shown in FIG. as follows:

S401 , using a statistical shape training algorithm to train a deformation component of a three-dimensional anatomical difference of a human body from a large amount of integrated medical image data.

S402 , establishing a three-dimensional digital human anatomy model according to the deformation components of the three-dimensional anatomical differences of the human body obtained through training through a model building program.

S403, controlling the anatomical shape change of the human body model from the inside to the outside by adjusting many anatomical characteristic parameters, so that the appearance and the shape of the internal organs of the human body model become similar to an individual human.

The three-dimensional digital human anatomy model provided by the embodiment of the present invention is:

表示解剖学平均模型，由模型曲面的顶点坐标构成；

为形变分量，是通过统计形状模型算法由训练数据集中学习得到；b＝[b₁,b₂,...,b_c]为形状系数；每个形变分量b_m取值为

λ_m为主成份分析特征值。Among them, X is a three-dimensional digital human anatomy model, and when the deformation component is known, the shape of X is controlled to change by adjusting the shape coefficient;

Represents the anatomical average model, which consists of the vertex coordinates of the model surface;

is the deformation component, which is learned from the training data set through the statistical shape model algorithm; b=[b ₁ , b ₂ ,...,b _c ] is the shape coefficient; each deformation component b _m takes the value of

λ _m is the principal component analysis eigenvalue.

In the above-mentioned embodiments, it may be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented in whole or in part in the form of a computer program product, the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer may be a general purpose computer, special purpose computer, computer network, or other programmable device. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server, or data center Transmission to another website site, computer, server, or data center by wireline (eg, coaxial cable, fiber optic, digital subscriber line (DSL), or wireless (eg, infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, etc. that includes one or more available mediums integrated. The usable media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVD), or semiconductor media (eg, Solid State Disk (SSD)), and the like.

The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited to this. Any person skilled in the art is within the technical scope disclosed by the present invention, and all within the spirit and principle of the present invention Any modifications, equivalent replacements and improvements made within the scope of the present invention should be included within the protection scope of the present invention.

Claims (10)

1. A method for personalized deformation of a deformable digital human anatomical model, characterized in that it comprises the following steps:

acquiring original digital image data of different tissues or organs of an individual diagnosed as being free of clinical symptoms through CT machine scanning, MRI equipment, an X-ray machine or three-dimensional laser scanning equipment;

analyzing and processing the acquired original image data through an image processing program; integrating the analyzed and processed image data through a data integration program;

thirdly, controlling the normal operation of the model personalized deformation system through the single chip microcomputer; establishing a three-dimensional digital human anatomy model according to the integrated image data through a model establishing program;

step four, realizing the personalized deformation of the three-dimensional digital human anatomy model by manual adjustment or automatic registration of a deformation program;

storing the acquired original image data, the analyzed and integrated data, the three-dimensional digital human anatomy model and the model personalized deformation data through a memory;

and sixthly, displaying the acquired original image data, the analyzed and integrated data, the three-dimensional digital human anatomy model and the model personalized deformation data through a display.

2. The method for personalized deformation of a deformable digital human anatomical model according to claim 1, wherein in step one, the original digital image data of the individual includes digital image data of different tissues or organs of the human body in shape, size, external structure, internal conduit, and biopsy information and Chinese population sample information;

the internal conduit comprises one or more of an artery, vein, trachea, bronchus, lymphatic vessel, hepatic vessel, or pancreatic vessel; the Chinese population sample information comprises the human-to-human difference change of all organs or tissues of a human body and the health and pathological difference change of all organs or tissues.

3. The method for personalized deformation of a deformable digital human anatomical model according to claim 1, wherein in step two, the method for analyzing and processing the acquired raw image data by the image processing program comprises:

(I) segmenting an organ image in the acquired original image data to obtain three-dimensional region partitions of all organs and tissues, wherein segmentation results are presented by three-dimensional curved surfaces;

the organ image segmentation method comprises the following steps:

firstly, smoothing original image data; and performing edge detection by using Sobel and LOG; expanding the image boundary to the outside by adopting an image expansion technology, performing image expansion, and deleting miscellaneous points in the image;

secondly, the preliminary separation marking is carried out on each tissue organ: traversing all pixel points of the image, searching a gray value non-0 point, if the point and the last labeled point are in the same area, labeling the same label, and otherwise labeling a new label; sorting the printed labels, if a certain pixel point and a pixel point below the certain pixel point are marked with different label numbers and connected, combining the two pixel points into one label, and simultaneously readjusting the labels of all the labels;

thirdly, extracting and dividing each organ region by adopting a threshold difference segmentation algorithm to obtain divided images of all organs and tissues;

finally, dividing the obtained organ and tissue division image into a plurality of sub-images, and respectively performing wavelet analysis on each sub-image to obtain a wavelet coefficient and an average high-frequency coefficient of each sub-image; obtaining seed nodes, performing region growth, and obtaining the position and the outline of an object; processing the periphery of the object in the sub-image according to the size of the obtained contour; performing smooth filtering on the organ and tissue division image to generate a depth image; obtaining three-dimensional region division images of all organs and tissues by combining the depth image and the organ and tissue division images based on a depth image drawing principle;

(II) registering a standard human body three-dimensional model and a three-dimensional region obtained by image segmentation by adopting a point cloud registration algorithm, and sequentially obtaining the corresponding relation of anatomical positions of the point clouds on the surfaces of the organs among individuals;

and (III) based on the registration results of all individuals, obtaining a deformation model and deformation component data through a statistical shape model algorithm.

4. The method for personalized deformation of a deformable digital human anatomical model according to claim 1, wherein in step two, the integrating the image data after the analysis process by the data integration program comprises:

firstly, selecting variables capable of describing image characteristics based on the characteristics of image data after analysis processing to form a multi-dimensional vector;

secondly, projecting the characteristic vector to a low-dimensional space with discrimination for image identification; clustering the feature points projected into the low-dimensional space; establishing an image characteristic distribution map by using the label and the clustering result of the image;

then, calculating the feature weights of all the images to be fused;

finally, the analysis-processed image is fused based on the calculated feature weights.

5. The method for personalized deformation of a deformable digital human anatomical model according to claim 1, wherein in step three, the three-dimensional digital human anatomical model is built by:

(1) training a large amount of integrated medical image data by adopting a statistical shape training algorithm to obtain a deformation component of human three-dimensional anatomical difference;

(2) establishing a three-dimensional digital human anatomy model according to the deformation component of the human three-dimensional anatomy difference obtained by training through a model establishing program;

(3) the human body model is controlled to have anatomical form change from inside to outside by adjusting a plurality of anatomical characteristic parameters, so that the appearance and the internal organ form of the human body model become similar to those of an individual human.

6. The method for personalized deformation of a deformable digital human anatomical model according to claim 5, characterized in that said three-dimensional digital human anatomical model is:

wherein, X is a three-dimensional digital human anatomy model, and under the condition that the deformation component is known, the shape of X is controlled to change by adjusting the shape coefficient;

representing an anatomical mean model, consisting of the vertex coordinates of the model surface;

the deformation component is obtained by centralized learning of training data through a statistical shape model algorithm; b ═ b₁,b₂,...,b_c]Is a shape factor; each deformation component b_mTake a value of

λ_mThe characteristic value is analyzed as the principal component.

7. The method for personalized deformation of a deformable digital human anatomical model according to claim 1, wherein in step four, the personalized deformation of the digital human anatomical model is achieved by means of manual adjustment or automatic registration;

the manual adjustment method means that the appearance and internal organ morphological parameters of the individual subject are manually input, and the model realizes deformation according to the input parameters and becomes similar to the individual shape of the patient.

8. An individualized deformation system of a deformable digital human anatomical model applying the individualized deformation method of a deformable digital human anatomical model according to any one of claims 1 to 7, characterized in that the individualized deformation system of a deformable digital human anatomical model comprises:

the system comprises an original image data acquisition module, an image data processing module, an image data integration module, a main control module, an anatomical model establishing module, a personalized deformation module, a data storage module and a display module;

the original image data acquisition module is connected with the main control module and is used for acquiring original image data of different tissues or organs of a human body through data acquisition equipment;

the image data processing module is connected with the main control module and used for analyzing and processing the acquired original image data through an image processing program;

the image data integration module is connected with the main control module and is used for integrating the analyzed and processed image data through a data integration program;

the main control module is connected with the original image data acquisition module, the image data processing module, the image data integration module, the anatomical model establishing module, the personalized deformation module, the data storage module and the display module and is used for controlling the normal operation of each module of the system through the single chip microcomputer;

the anatomical model building module is connected with the main control module and used for building a three-dimensional digital human anatomical model according to the integrated image data through a model building program;

the personalized deformation module is connected with the main control module and is used for realizing personalized deformation of the three-dimensional digital human anatomy model in a manual adjustment or automatic registration mode of a deformation program;

the data storage module is connected with the main control module and used for storing the acquired original image data, the analyzed and integrated data, the three-dimensional digital human anatomy model and the model personalized deformation data through the memory;

and the display module is connected with the main control module and used for displaying the acquired original image data, the analyzed and integrated data, the three-dimensional digital human anatomy model and the model personalized deformation data through the display.

9. A computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface for implementing a method of personalized deformation of a deformable digital human anatomical model as claimed in any one of claims 1 to 7 when executed on an electronic device.

10. A computer-readable storage medium storing instructions which, when executed on a computer, cause the computer to perform a method of personalized deformation of a deformable digital human anatomical model as claimed in any one of claims 1 to 7.

Images