CN116645389A - A personalized vascular thrombus three-dimensional structure modeling method and system - Google Patents

Abstract

The present invention provides a personalized three-dimensional structure modeling method of blood vessel thrombus, including acquiring digital medical image data with target blood vessel segment and thrombus, and preprocessing the digital medical image data; importing the preprocessed digital medical image data into a The three-dimensional reverse automatic modeling platform constructed by the blood vessel segmentation algorithm, the thrombus automatic recognition algorithm and the surface reconstruction algorithm performs three-dimensional reconstruction to obtain a personalized three-dimensional visualization model of blood vessel thrombus. The invention also provides a personalized vascular thrombus three-dimensional structure modeling system. The implementation of the present invention can solve the problems of time-consuming, labor-intensive modeling, inaccurate modeling results and lack of differentiation existing in the existing modeling methods, and is helpful for accurate positioning and quantitative analysis of blood vessel thrombus.

Description

A personalized vascular thrombus three-dimensional structure modeling method and system

technical field

The invention relates to the technical field of computer image simulation, in particular to a method and system for modeling a three-dimensional structure of a personalized blood vessel thrombus.

Background technique

Vascular thrombosis is a common vascular disease, which may lead to serious diseases such as heart disease and stroke, and even endanger life. With the advancement of medical technology, computer simulation modeling technology is playing an increasingly important role in clinical diagnosis and treatment, especially for the evaluation of vascular thrombus.

Currently, three-dimensional structural modeling methods of vascular thrombus can help doctors better understand the shape, size and location of thrombus. However, the existing three-dimensional modeling methods of vascular thrombus have the following problems: (1) The modeling process is cumbersome and requires a lot of time and effort; (2) The modeling results are not accurate enough; (3) The modeling methods are not targeted and cannot Meet the needs of individual differences.

Therefore, in order to solve the above problems, the present invention proposes a personalized three-dimensional structure modeling method of vascular thrombus based on digital medical images, which is helpful for accurate positioning and quantitative analysis of vascular thrombus.

Contents of the invention

The technical problem to be solved by the embodiments of the present invention is to provide a personalized vascular thrombus three-dimensional structure modeling method and system, which can solve the problems of time-consuming, inaccurate modeling results and lack of differentiation existing in existing modeling methods , which is helpful for accurate location and quantitative analysis of vascular thrombus.

In order to solve the above technical problems, an embodiment of the present invention provides a personalized three-dimensional structure modeling method of vascular thrombus, the method includes the following steps:

Acquiring digital medical image data with the target blood vessel segment and thrombus, and performing preprocessing on the digital medical image data;

The preprocessed digital medical image data is imported into the 3D reverse automatic modeling platform constructed by the blood vessel segmentation algorithm, thrombus automatic recognition algorithm and surface reconstruction algorithm for 3D reconstruction, and a personalized 3D visualization model of vascular thrombus is obtained.

Wherein, the digital medical image data is two-dimensional CT computed tomography image data or MRI magnetic resonance imaging image data.

Wherein, the preprocessing includes image noise reduction processing, image enhancement processing, image smoothing processing and image standardization processing.

Wherein, the blood vessel segmentation algorithm is composed of one or more of a threshold-based algorithm, an edge detection-based algorithm, and a region growing-based algorithm, and is used to extract features of target blood vessel segments.

Wherein, the thrombus automatic recognition algorithm is composed of one or more of algorithms based on morphological features, algorithms based on grayscale features, and algorithms based on machine learning, and are used to identify the position area and contour shape of thrombus.

Wherein, the surface reconstruction algorithm is composed of one or more of an algorithm based on voxel surface reconstruction, an algorithm based on grid surface reconstruction, and an algorithm based on interpolation surface reconstruction, to identify the thrombus location area and The contour shape is used to establish a personalized three-dimensional visualization model of blood vessel thrombus according to the extracted characteristics of the target blood vessel segment and the identified location area and contour shape of the thrombus.

Wherein, the method further includes:

According to the personalized three-dimensional visualization model of blood vessel thrombus, the specific distribution position of the thrombus in the target blood vessel segment is determined.

The embodiment of the present invention also provides a personalized vascular thrombus three-dimensional structure modeling system, including:

An image acquisition and processing unit, configured to acquire digital medical image data with target blood vessel segments and thrombus, and preprocess the digital medical image data;

The 3D reverse modeling unit is used to import the preprocessed digital medical image data into the 3D reverse automatic modeling platform constructed by the blood vessel segmentation algorithm, thrombus automatic recognition algorithm and surface reconstruction algorithm for 3D reconstruction, and obtain personalized vascular thrombus 3D visualization model.

Wherein, the preprocessing includes image noise reduction processing, image enhancement processing, image smoothing processing and image standardization processing.

Wherein, the blood vessel segmentation algorithm is composed of one or more of a threshold-based algorithm, an edge detection-based algorithm, and a region-growing algorithm, and is used to extract features of target blood vessel segments;

The thrombus automatic identification algorithm is composed of one or more of an algorithm based on morphological features, an algorithm based on grayscale features, and an algorithm based on machine learning, and is used to identify the location area and contour shape of thrombus;

The surface reconstruction algorithm is composed of one or more of an algorithm based on voxel surface reconstruction, an algorithm based on grid surface reconstruction and an algorithm based on interpolation surface reconstruction, and is used to identify the location area and contour shape of thrombus , to establish a personalized three-dimensional visualization model of blood vessel thrombus according to the extracted features of the target blood vessel segment and the identified position area and contour shape of the thrombus.

Implementing the embodiment of the present invention has the following beneficial effects:

In the present invention, after preprocessing digital medical image data with target blood vessel segments and thrombus, the three-dimensional reverse automatic modeling platform constructed by blood vessel segmentation algorithm, thrombus automatic recognition algorithm and surface reconstruction algorithm is imported to carry out three-dimensional reconstruction, and quickly obtain The personalized three-dimensional visualization model of vascular thrombus solves the problems of time-consuming, laborious modeling, inaccurate modeling results, and lack of differentiation existing in existing modeling methods, and is helpful for accurate positioning and quantitative analysis of vascular thrombus.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, obtaining other drawings based on these drawings still belongs to the scope of the present invention without any creative effort.

FIG. 1 is a flow chart of a method for modeling a personalized vascular thrombus three-dimensional structure provided by an embodiment of the present invention;

FIG. 2 is a preparation state diagram for acquiring digital medical images and preprocessing digital medical images in a personalized vascular thrombus three-dimensional structure modeling method provided by an embodiment of the present invention;

3 is an algorithm structure diagram of a three-dimensional reverse automatic modeling platform in a personalized vascular thrombus three-dimensional structure modeling method provided by an embodiment of the present invention;

Fig. 4 is a three-dimensional reverse automatic modeling diagram in a personalized vascular thrombus three-dimensional structure modeling method provided by an embodiment of the present invention;

5 is a schematic diagram of the visualized results after three-dimensional reverse automatic modeling in a personalized vascular thrombus three-dimensional structure modeling method provided by an embodiment of the present invention;

FIG. 6 is a schematic structural diagram of a personalized vascular thrombus three-dimensional structure modeling system provided by an embodiment of the present invention.

Detailed ways

In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings.

As shown in Figure 1, in the embodiment of the present invention, a personalized three-dimensional structure modeling method of vascular thrombus is provided, including the following steps:

Step S1, acquiring digital medical image data with the target blood vessel segment and thrombus, and performing preprocessing on the digital medical image data;

Step S2. Import the preprocessed digital medical image data into the 3D reverse automatic modeling platform constructed by the blood vessel segmentation algorithm, thrombus automatic recognition algorithm and surface reconstruction algorithm for 3D reconstruction to obtain a personalized 3D visualization model of vascular thrombus.

The specific process is that in step S1, as shown in FIG. 2, image data preparation is performed in two steps, including acquiring digital medical image data and preprocessing digital medical image data. Wherein, the digital medical image data is two-dimensional CT computed tomography image data or MRI magnetic resonance imaging image data, and is saved in DICOM format. The preprocessing of digital medical image data includes but not limited to image noise reduction processing, image enhancement processing, image smoothing processing and image standardization processing.

In step S2, firstly, a three-dimensional reverse automatic modeling platform is constructed, which is constructed by a blood vessel segmentation algorithm, an automatic thrombus identification algorithm and a surface reconstruction algorithm, and the specific algorithm is shown in Figure 3 . Wherein, the blood vessel segmentation algorithm is composed of one or more of a threshold-based algorithm, an edge detection-based algorithm, and a region growing-based algorithm, and is used to extract features of target blood vessel segments. The thrombus automatic recognition algorithm is composed of one or more of algorithms based on morphological features, algorithms based on grayscale features, and algorithms based on machine learning, and is used to identify the location area and contour shape of thrombus. The surface reconstruction algorithm is composed of one or more of the algorithm based on voxel surface reconstruction, the algorithm based on grid surface reconstruction and the algorithm based on interpolation surface reconstruction, which is used to identify the location area and contour shape of thrombus. A three-dimensional visualization model of blood vessel thrombus is established according to the extracted features of the target blood vessel segment and the identified position area and contour shape of the thrombus.

Secondly, the preprocessed digital medical image data is imported into the 3D reverse automatic modeling platform for 3D reconstruction, and a personalized 3D visualization model of vascular thrombus can be quickly obtained.

In the embodiment of the present invention, as shown in Fig. 4, the 3D vascular geometric model and the 3D thrombus geometric model can be directly fused, and combined with visualization commands to generate a personalized 3D visualization model of blood vessels and thrombus, that is, according to the personalized vascular thrombus 3D Visualize the model to determine the specific distribution position of the thrombus in the target blood vessel segment, as shown in the results of three-dimensional reverse modeling in Figure 5.

As shown in Figure 6, it is a personalized vascular thrombus three-dimensional structure modeling system provided in the embodiment of the present invention, including:

An image acquisition and processing unit 110, configured to acquire digital medical image data with target blood vessel segments and thrombus, and preprocess the digital medical image data;

The 3D reverse modeling unit 120 is used to import the preprocessed digital medical image data into the 3D reverse automatic modeling platform constructed by the blood vessel segmentation algorithm, thrombus automatic recognition algorithm and surface reconstruction algorithm for 3D reconstruction to obtain personalized blood vessels 3D visualization model of thrombus.

Wherein, the preprocessing includes image noise reduction processing, image enhancement processing, image smoothing processing and image standardization processing.

Wherein, the blood vessel segmentation algorithm is composed of one or more of a threshold-based algorithm, an edge detection-based algorithm, and a region-growing algorithm, and is used to extract features of target blood vessel segments;

The thrombus automatic identification algorithm is composed of one or more of an algorithm based on morphological features, an algorithm based on grayscale features, and an algorithm based on machine learning, and is used to identify the location area and contour shape of thrombus;

The surface reconstruction algorithm is composed of one or more of an algorithm based on voxel surface reconstruction, an algorithm based on grid surface reconstruction and an algorithm based on interpolation surface reconstruction, and is used to identify the location area and contour shape of thrombus , to establish a personalized three-dimensional visualization model of blood vessel thrombus according to the extracted features of the target blood vessel segment and the identified position area and contour shape of the thrombus.

Implementing the embodiment of the present invention has the following beneficial effects:

In the present invention, after preprocessing digital medical image data with target blood vessel segments and thrombus, the three-dimensional reverse automatic modeling platform constructed by blood vessel segmentation algorithm, thrombus automatic recognition algorithm and surface reconstruction algorithm is imported to carry out three-dimensional reconstruction, and quickly obtain The personalized three-dimensional visualization model of vascular thrombus solves the problems of time-consuming, laborious modeling, inaccurate modeling results, and lack of differentiation existing in existing modeling methods, and is helpful for accurate positioning and quantitative analysis of vascular thrombus.

It is worth noting that in the above system embodiments, the units included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit It is only for the convenience of distinguishing each other, and is not used to limit the protection scope of the present invention.

Those of ordinary skill in the art can understand that all or part of the steps in the method of the above-mentioned embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage Media such as ROM/RAM, magnetic disk, optical disk, etc.

The above disclosures are only preferred embodiments of the present invention, and certainly cannot limit the scope of rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope of the present invention.

Claims (10)

1. A method for modeling a three-dimensional structure of a personalized vessel thrombus, the method comprising the steps of:

acquiring digital medical image data having a target vessel segment and thrombus, and preprocessing the digital medical image data;

and importing the preprocessed digital medical image data into a three-dimensional reverse automatic modeling platform constructed by a blood vessel segmentation algorithm, a thrombus automatic identification algorithm and a surface reconstruction algorithm to carry out three-dimensional reconstruction, so as to obtain a personalized blood vessel thrombus three-dimensional visualization model.

2. The personalized vessel thrombosis three dimensional structure modeling method of claim 1, wherein the digital medical image data is two dimensional CT computed tomography image data or MRI magnetic resonance imaging image data.

3. The personalized vessel thrombosis three-dimensional structure modeling method of claim 1, wherein the preprocessing comprises an image noise reduction process, an image enhancement process, an image smoothing process, and an image normalization process.

4. The method of claim 1, wherein the vessel segmentation algorithm is comprised of one or more of a threshold-based algorithm, an edge detection-based algorithm, and a region growing-based algorithm to extract the target vessel segment features.

5. The method of claim 4, wherein the automatic thrombus recognition algorithm is one or more of a morphology feature-based algorithm, a gray feature-based algorithm, and a machine learning-based algorithm for recognizing a location area and a contour morphology of the thrombus.

6. The method of claim 5, wherein the surface reconstruction algorithm is one or more of a voxel-based surface reconstruction algorithm, a mesh-based surface reconstruction algorithm, and an interpolation-based surface reconstruction algorithm, and is configured to identify a location area and a contour morphology of the thrombus, and to create a three-dimensional visualization model of the personalized vessel thrombus based on the extracted target vessel segment features and the identified location area and contour morphology of the thrombus.

7. The personalized vessel thrombosis three-dimensional structure modeling method of claim 1, further comprising:

and determining the specific distribution position of the thrombus in the target vessel segment according to the personalized vessel thrombus three-dimensional visualization model.

8. A personalized vascular thrombus three-dimensional structure modeling system, comprising:

an image acquisition and processing unit for acquiring digital medical image data having a target vessel segment and thrombus and preprocessing the digital medical image data;

the three-dimensional reverse modeling unit is used for importing the preprocessed digital medical image data into a three-dimensional reverse automatic modeling platform constructed by a blood vessel segmentation algorithm, a thrombus automatic identification algorithm and a surface reconstruction algorithm to carry out three-dimensional reconstruction, so as to obtain a personalized blood vessel thrombus three-dimensional visual model.

9. The personalized vessel thrombosis three dimensional structure modeling system of claim 8, wherein the preprocessing comprises an image noise reduction process, an image enhancement process, an image smoothing process, and an image normalization process.

10. The personalized vessel thrombosis three dimensional structure modeling system of claim 8, wherein the vessel segmentation algorithm is comprised of one or more of a threshold-based algorithm, an edge detection-based algorithm, and a region growing-based algorithm to extract a target vessel segment feature;

the automatic thrombus recognition algorithm is composed of one or more of a morphological feature-based algorithm, a gray feature-based algorithm and a machine learning-based algorithm and is used for recognizing the position area and the contour morphology of the thrombus;

the surface reconstruction algorithm is composed of one or more of a voxel-based surface reconstruction algorithm, a grid-based surface reconstruction algorithm and an interpolation-based surface reconstruction algorithm, is used for identifying the position area and the contour form of thrombus, and is used for establishing a personalized vessel thrombus three-dimensional visualization model according to the extracted target vessel segment characteristics and the identified position area and the contour form of thrombus.