WO2020253510A1

WO2020253510A1 - Big data blood vessel image identification-based disease prediction system and method

Info

Publication number: WO2020253510A1
Application number: PCT/CN2020/093613
Authority: WO
Inventors: 王红伟
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-06-21
Filing date: 2020-05-30
Publication date: 2020-12-24
Also published as: CN110364256A

Abstract

A big data blood vessel image identification-based disease prediction method and apparatus. The method may comprise steps such as: by means of an acquisition unit, acquiring blood vessel image data corresponding to a target user; processing the blood vessel image data by means of an image preprocessing unit according to a preset image processing rule, and generating a blood vessel identification report which corresponds to the target user; by means of an image analysis unit, comparing a value with a standard value which corresponds to at least one blood vessel physiological index; and determining a value range which corresponds to the difference between the value and the standard value. Disease prediction may be performed on a patient by means of big data technology, and medical personnel may further determine the disease of the patient on the basis of a prediction result, thereby improving the disease diagnosis efficiency of the medical personnel.

Description

Disease prediction system and method based on image recognition of large numbers of blood vessels

This application is based on the Paris Convention declaration to enjoy the priority of the Chinese patent application filed on June 21, 2019, with the application number CN201910542132.X and the name "A disease prediction system and method based on image recognition of large numbers of blood vessels". The entire content of the patent application is incorporated into this application by reference.

Technical field

This application relates to the field of Internet technology, in particular to the field of image recognition of artificial intelligence, and specifically to a disease prediction system based on image recognition of large numbers of blood vessels and a disease prediction method based on image recognition of large numbers of blood vessels applied to the system.

Background technique

With the development of economy, users pay more and more attention to their health. In particular, people hope to know their potential risk of illness in advance, and then prevent and treat the potential disease in advance. For example, since the beginning of this year, the number of casualties caused by cervical cancer has increased. Usually, patients with cervical cancer are not aware of their own lesions until the middle and late stages of cervical cancer. This shortens the treatment time of patients and reduces the incidence of illness. The possibility of a person's cure, therefore, is particularly important to their potential risk of illness. The inventor realizes that in the prior art, the prediction of the potential risk of a person’s disease is usually made by the doctor based on his personal experience and the person’s internal and external physiological characteristics. The prediction result formed in this way is very dependent on the doctor’s own ability. And this method requires a lot of energy from doctors, which in turn leads to low efficiency of disease analysis and prediction.

technical problem

The technical problem to be solved by the embodiments of the present application is to provide a disease prediction method and device based on image recognition of large numbers of blood vessels to solve the problem of unstable accuracy of medical personnel in predicting potential disease risks.

Technical solutions

In order to solve the above technical problems, the first aspect of the present application discloses a disease prediction method based on image recognition of large numbers of blood vessels, which is applied to an electronic device, wherein the electronic device includes an acquisition unit, an image preprocessing unit, and an image analysis unit, Correspondingly, disease prediction methods based on image recognition of large numbers of blood vessels include:

Collect blood vessel image data corresponding to the target user through the acquisition unit;

The image preprocessing unit processes the blood vessel image data according to preset image processing rules and generates a blood vessel recognition report corresponding to the target user, wherein the blood vessel recognition report includes at least one blood vessel physiological index and the at least one blood vessel The value corresponding to the physiological index;

Comparing the numerical value with the standard numerical value corresponding to the at least one vascular physiological index by the image analysis unit, and determining the value range corresponding to the difference between the numerical value and the standard numerical value;

The image analysis unit determines whether the value range is a reasonable value range according to a preset rule. If not, the image analysis unit determines at least one potential disease item corresponding to the target user according to the disease set of the value range.

The second aspect of the application discloses a disease prediction system, wherein the system includes:

A memory storing executable program codes;

A processor coupled with the memory;

The processor calls the executable program code stored in the memory to execute the disease prediction method based on image recognition of large numbers of blood vessels as described in the first aspect of the present application.

A third aspect of the present application provides a computer-readable storage medium in which a blood vessel image recognition program is stored. When the blood vessel image recognition program is executed by a processor, the following steps are performed:

Beneficial effect

Compared with the prior art, this application has the following technical effects:

This application can collect the user's blood vessel image data, and then use a preset analysis method to analyze the blood vessel image data, and then predict the user's potential risk of illness based on the analysis result. In this application, because the instrument is used to process and analyze the blood vessel image data, the potential risk of the user can be predicted, thereby reducing the workload of the medical staff and improving the diagnosis speed of the medical staff.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative work, other drawings can be obtained based on these drawings.

1 is a schematic flowchart of a disease prediction method based on image recognition of large numbers of blood vessels disclosed in Embodiment 1 of the present application;

2 is a schematic structural diagram of a disease prediction system based on image recognition of large numbers of blood vessels disclosed in Embodiment 2 of the present application;

3 is a schematic structural diagram of a disease prediction system based on image recognition of large numbers of blood vessels disclosed in Embodiment 3 of the present application.

Embodiments of the invention

For a better understanding and implementation, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application. Not all examples. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

Example one

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of a disease prediction method based on image recognition of large numbers of blood vessels according to an embodiment of the present application, wherein the method of disease prediction based on image recognition of large numbers of blood vessels is applied to the disease prediction system of blood vessel image recognition in. As shown in Fig. 1, the disease prediction method based on image recognition of large numbers of blood vessels may include the following steps:

101. Collect blood vessel image data corresponding to the target user through the acquisition unit.

102. Process the blood vessel image data according to preset image processing rules by the image preprocessing unit and generate a blood vessel recognition report corresponding to the target user, wherein the blood vessel recognition report includes at least one physiological index of a blood vessel and the at least one The value corresponding to the physiological index of blood vessel.

103. Compare the value with a standard value corresponding to the at least one vascular physiological index by the image analysis unit, and determine a value range corresponding to the difference between the value and the standard value.

104. Determine, by the image analysis unit, whether the value range is a reasonable value range according to preset rules, if not, the image analysis unit determines at least one potential disease corresponding to the target user according to the disease set of the value range item.

In some optional implementation manners, processing the blood vessel image data according to preset image processing rules by the image preprocessing unit and generating a blood vessel identification report corresponding to the target user includes:

Dividing the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index according to the correspondence between the blood vessel physiological index and the data area;

Analyze the target analysis data according to preset data analysis rules, where the preset data analysis rules include data discrete analysis and data linear analysis;

Determine the numerical value corresponding to the at least one vascular physiological index according to the analysis result of the target analysis data;

The blood vessel identification report corresponding to the target user is output according to a preset generation format.

In some optional implementation manners, the segmenting the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index according to the corresponding relationship between the blood vessel physiological index and the data area includes:

Forming a segmentation model based on the correspondence between historical vascular physiological indicators and data regions, wherein the segmentation model includes at least one vascular physiological reference index and a data region corresponding to the at least one vascular physiological reference index;

According to the corresponding relationship between the at least one vascular physiological reference index and the data area corresponding to the at least one vascular physiological reference index in the segmentation model, the blood vessel image data is divided into the at least one vascular physiological reference index. Target analysis data corresponding to the indicator.

In some optional implementations, after the segmentation model is formed based on the correspondence between historical vascular physiological indicators and data regions, the at least one vascular physiological reference index in the segmentation model and the Before dividing the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index by the correspondence between the data regions corresponding to the at least one blood vessel physiological reference index, the method further includes:

A correction instruction is received, wherein the correction instruction is used to correct the segmentation model, and the correction instruction includes at least one correction for correcting the correspondence between the data regions corresponding to the at least one vascular physiological reference index parameter;

Modify the segmentation model based on the modified parameter.

In some optional embodiments, the blood vessel image data includes first blood vessel image data, and/or second blood vessel image data.

In some optional implementation manners, the collecting blood vessel image data corresponding to the target user by the collecting unit includes:

Collecting the first blood vessel image data corresponding to the day, and/or collecting the second blood vessel image data corresponding to the night;

And, after the blood vessel image data corresponding to the target user is collected, before the blood vessel image data is processed according to a preset image processing rule and the blood vessel recognition report corresponding to the target user is generated, the method further includes:

A photoplethysmogram data set is generated according to the first blood vessel image data and/or the second blood vessel image data.

In some optional embodiments, before generating a photoplethysmogram data set according to the first blood vessel image data and/or the second blood vessel image data, the method further includes:

A filter is used to filter the first blood vessel image data and/or the second blood vessel image data to filter out noise in the first blood vessel image data and/or the second blood vessel image data.

In some optional embodiments, the at least one vascular physiological index includes blood flow speed, blood pressure, platelet content, blood oxygen content, red blood cell color, and hemoglobin content.

Example two

Please refer to FIG. 3, which is a schematic structural diagram of a disease prediction system based on image recognition of large numbers of blood vessels according to an embodiment of the present application. As shown in FIG. 3, the system includes an acquisition unit 201, an image preprocessing unit 202, and an image analysis. Unit 203, where

The collecting unit 201 is used for collecting blood vessel image data corresponding to the target user by the collecting unit;

The image preprocessing unit 202 is configured to process the blood vessel image data according to preset image processing rules and generate a blood vessel recognition report corresponding to the target user, wherein the blood vessel recognition report includes at least one physiological index of a blood vessel and the at least The value corresponding to a vascular physiological index;

The image analysis unit 203 is configured to compare the value with a standard value corresponding to the at least one vascular physiological index, and determine the value range corresponding to the difference between the value and the standard value;

The image analysis unit 203 is further configured to determine whether the value range is a reasonable value range according to preset rules, if not, the image analysis unit determines at least one potential disease corresponding to the target user according to the disease set of the value range item.

In some optional implementation manners, the image preprocessing unit 202 processing the blood vessel image data according to preset image processing rules and generating the blood vessel recognition report corresponding to the target user includes sub-steps:

In some optional implementation manners, the image preprocessing unit 202 divides the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index according to the corresponding relationship between the blood vessel physiological index and the data area, including: step:

In some optional implementation manners, after the image preprocessing unit 202 forms a segmentation model based on the correspondence between historical blood vessel physiological indicators and the data area, the image preprocessing unit follows all the segments in the segmentation model. Before dividing the blood vessel image data into target analysis data corresponding to the at least one vascular physiological index, the correspondence between the at least one vascular physiological reference index and the data area corresponding to the at least one vascular physiological reference index, The image preprocessing is also used for:

Modify the segmentation model based on the modified parameter.

In some optional implementation manners, the collecting unit 201 collecting blood vessel image data corresponding to the target user includes sub-steps:

And, after the blood vessel image data corresponding to the target user is collected, before the blood vessel image data is processed according to preset image processing rules and the blood vessel recognition report corresponding to the target user is generated, the image preprocessing unit 202 also uses in:

In some optional implementation manners, before generating a photoplethysmogram data set according to the first blood vessel image data and/or the second blood vessel image data, the image preprocessing unit 202 is further configured to:

The system of the present application can collect the user's blood vessel image data, and then analyze the blood vessel image data using a preset analysis method, and then predict the user's potential risk of illness based on the analysis result. In this application, because the instrument is used to process and analyze the blood vessel image data, the potential risk of the user can be predicted, thereby reducing the workload of the medical staff and improving the diagnosis speed of the medical staff.

Example three

Please refer to FIG. 3, which is a schematic structural diagram of another disease prediction system disclosed in an embodiment of the present application. As shown in Figure 3, the disease prediction system may include:

A memory 301 storing executable program codes;

A processor 302 coupled with the memory 301;

The processor 302 calls the executable program code stored in the memory 301, and executes the steps:

In some implementation manners, the processor 302 calls the executable program code stored in the memory 301, and further executes the steps:

In some optional embodiments, after forming a segmentation model based on the correspondence between historical vascular physiological indicators and data regions, the at least one vascular physiological reference index and the Before dividing the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index, the method further includes:

Modify the segmentation model based on the modified parameter.

Example four

The fourth embodiment of the present application discloses a computer-readable storage medium. The computer-readable storage medium may be non-volatile or volatile. It stores a computer program for electronic data exchange, wherein the computer The program causes the computer to perform the steps:

In some embodiments, the computer-readable storage medium further executes the steps:

Modify the segmentation model based on the modified parameter.

The computer-readable storage medium of the present application can collect the user's blood vessel image data by executing the steps in the disease prediction method based on the recognition of most blood vessel images, and then analyze the blood vessel image data using a preset analysis method, and then predict the user based on the analysis result Potential risk of illness. In this application, because the instrument is used to process and analyze the blood vessel image data, the potential risk of the user can be predicted, thereby reducing the workload of the medical staff and improving the diagnosis speed of the medical staff.

Example five

The embodiment of the present application discloses a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the computer-based computer program described in the first embodiment. Steps in the disease prediction method based on blood vessel image recognition.

The computer program product of the present application can collect the user’s blood vessel image data by executing the steps in the disease prediction method based on the recognition of most blood vessel images, and then analyze the blood vessel image data using a preset analysis method, and then predict the user’s potential Risk of illness. In this application, because the instrument is used to process and analyze the blood vessel image data, the potential risk of the user can be predicted, thereby reducing the workload of the medical staff and improving the diagnosis speed of the medical staff.

The device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement without creative work.

Through the specific description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution essentially or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory. (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), Programmable Read-Only Memory (Programmable Read-only Memory, PROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electronically Erasable Read-Only Memory (Electrically-Erasable) Programmable Read-Only Memory (EEPROM), CD-ROM (Compact Disc Read-Only Memory, CD-ROM) or other optical disk storage, magnetic disk storage, tape storage, or any other computer readable that can be used to carry or store data medium.

Finally, it should be noted that the method and device for disease prediction based on image recognition of large numbers of blood vessels disclosed in the embodiments of this application are only the preferred embodiments of this application, and are only used to illustrate the technical solutions of this application. It is not a limitation; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that; they can still modify the technical solutions described in the foregoing embodiments, or modify some of the technical features Perform equivalent replacements; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments.

Claims

A disease prediction method based on big data-based blood vessel image recognition is applied to an electronic device, the electronic device includes an acquisition unit, an image preprocessing unit, and an image analysis unit, wherein the method includes:

Collect blood vessel image data corresponding to the target user through the acquisition unit;

The image preprocessing unit processes the blood vessel image data according to preset image processing rules and generates a blood vessel recognition report corresponding to the target user, wherein the blood vessel recognition report includes at least one blood vessel physiological index and the at least one blood vessel The value corresponding to the physiological index;

Comparing the numerical value with the standard numerical value corresponding to the at least one vascular physiological index by the image analysis unit, and determining the value range corresponding to the difference between the numerical value and the standard numerical value;

The image analysis unit determines whether the value range is a reasonable value range according to a preset rule. If not, the image analysis unit determines at least one potential disease item corresponding to the target user according to the disease set of the value range.
The method according to claim 1, wherein the processing the blood vessel image data according to a preset image processing rule by the image preprocessing unit and generating the blood vessel identification report corresponding to the target user comprises:

Dividing the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index according to the correspondence between the blood vessel physiological index and the data area;

Analyze the target analysis data according to preset data analysis rules, where the preset data analysis rules include data discrete analysis and data linear analysis;

Determine the numerical value corresponding to the at least one vascular physiological index according to the analysis result of the target analysis data;

The blood vessel identification report corresponding to the target user is output according to a preset generation format.
The method according to claim 2, wherein the segmenting the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index according to the corresponding relationship between the blood vessel physiological index and the data area comprises:

Forming a segmentation model based on the correspondence between historical vascular physiological indicators and data regions, wherein the segmentation model includes at least one vascular physiological reference index and a data region corresponding to the at least one vascular physiological reference index;

According to the corresponding relationship between the at least one vascular physiological reference index and the data area corresponding to the at least one vascular physiological reference index in the segmentation model, the blood vessel image data is divided into the at least one vascular physiological reference index. Target analysis data corresponding to the indicator.
The method according to claim 3, wherein the corresponding relationship between the at least one vascular physiological reference index and the data region corresponding to the at least one vascular physiological reference index in the segmentation model is determined by Before segmenting the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index, the method further includes:

A correction instruction is received, wherein the correction instruction is used to correct the segmentation model, and the correction instruction includes at least one correction for correcting the correspondence between the data regions corresponding to the at least one vascular physiological reference index parameter;

Modify the segmentation model based on the modified parameter.
The method according to claim 1, wherein the blood vessel image data includes first blood vessel image data, and/or second blood vessel image data.
The method according to claim 1, wherein the collecting blood vessel image data corresponding to the target user by the collecting unit comprises:

Collecting first blood vessel image data corresponding to daytime, and/or collecting second blood vessel image data corresponding to night time;

And, after the blood vessel image data corresponding to the target user is collected, before the blood vessel image data is processed according to a preset image processing rule and the blood vessel recognition report corresponding to the target user is generated, the method further includes:

A photoplethysmogram data set is generated according to the first blood vessel image data and/or the second blood vessel image data.
The method according to claim 6, wherein before generating a photoplethysmogram data set according to the first blood vessel image data and/or the second blood vessel image data, the method further comprises:

A filter is used to filter the first blood vessel image data and/or the second blood vessel image data to filter out noise in the first blood vessel image data and/or the second blood vessel image data.
The method according to any one of claims 1-7, wherein the at least one vascular physiological index includes blood flow speed, blood pressure, platelet content, blood oxygen content, red blood cell color, hemoglobin content
An electronic device, the electronic device includes an acquisition unit, an image preprocessing unit, and an image analysis unit, wherein the electronic device further includes:

A memory storing executable program codes;

A processor coupled with the memory;

The processor calls the executable program code stored in the memory, and executes the following steps:

Collect blood vessel image data corresponding to the target user through the acquisition unit;

The image preprocessing unit processes the blood vessel image data according to preset image processing rules and generates a blood vessel recognition report corresponding to the target user, wherein the blood vessel recognition report includes at least one blood vessel physiological index and the at least one blood vessel The value corresponding to the physiological index;

Comparing the numerical value with the standard numerical value corresponding to the at least one vascular physiological index by the image analysis unit, and determining the value range corresponding to the difference between the numerical value and the standard numerical value;

The image analysis unit determines whether the value range is a reasonable value range according to a preset rule. If not, the image analysis unit determines at least one potential disease item corresponding to the target user according to the disease set of the value range.
9. The electronic device of claim 9, wherein the image preprocessing unit processes the blood vessel image data according to preset image processing rules and generates a blood vessel identification report corresponding to the target user, comprising:

Dividing the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index according to the correspondence between the blood vessel physiological index and the data area;

Analyze the target analysis data according to preset data analysis rules, where the preset data analysis rules include data discrete analysis and data linear analysis;

Determine the numerical value corresponding to the at least one vascular physiological index according to the analysis result of the target analysis data;

The blood vessel identification report corresponding to the target user is output according to a preset generation format.
10. The electronic device of claim 10, wherein the segmenting the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index according to the corresponding relationship between the blood vessel physiological index and the data area comprises:

Forming a segmentation model based on the correspondence between historical vascular physiological indicators and data regions, wherein the segmentation model includes at least one vascular physiological reference index and a data region corresponding to the at least one vascular physiological reference index;

According to the corresponding relationship between the at least one vascular physiological reference index and the data area corresponding to the at least one vascular physiological reference index in the segmentation model, the blood vessel image data is divided into the at least one vascular physiological reference index. Target analysis data corresponding to the indicator.
The electronic device according to claim 11, wherein the corresponding relationship between the at least one vascular physiological reference index and the data area corresponding to the at least one vascular physiological reference index in the segmentation model is Before segmenting the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index, the processor calls the executable program code stored in the memory, and further performs the following steps:

A correction instruction is received, wherein the correction instruction is used to correct the segmentation model, and the correction instruction includes at least one correction for correcting the correspondence between the data regions corresponding to the at least one vascular physiological reference index parameter;

Modify the segmentation model based on the modified parameter.
The electronic device according to claim 9, wherein the blood vessel image data includes first blood vessel image data, and/or second blood vessel image data.
9. The electronic device according to claim 9, wherein the collecting blood vessel image data corresponding to the target user by the collecting unit comprises:

Collecting first blood vessel image data corresponding to daytime, and/or collecting second blood vessel image data corresponding to night time;

And, after the blood vessel image data corresponding to the target user is collected, before the blood vessel image data is processed according to a preset image processing rule and the blood vessel recognition report corresponding to the target user is generated, the processor calls the memory The executable program code stored in, further executes the following steps:

A photoplethysmogram data set is generated according to the first blood vessel image data and/or the second blood vessel image data.
The electronic device according to any one of claims 9 to 14, wherein the at least one vascular physiological index includes blood flow speed, blood pressure, platelet content, blood oxygen content, red blood cell color, and hemoglobin content.
A computer-readable storage medium, wherein a blood vessel image recognition program is stored in the computer-readable storage medium, and when the blood vessel image recognition program is executed by a processor, the following steps are performed:

Collect blood vessel image data corresponding to the target user through the acquisition unit;

The image preprocessing unit processes the blood vessel image data according to preset image processing rules and generates a blood vessel recognition report corresponding to the target user, wherein the blood vessel recognition report includes at least one blood vessel physiological index and the at least one blood vessel The value corresponding to the physiological index;

Comparing the numerical value with the standard numerical value corresponding to the at least one vascular physiological index by the image analysis unit, and determining the value range corresponding to the difference between the numerical value and the standard numerical value;

The image analysis unit determines whether the value range is a reasonable value range according to a preset rule. If not, the image analysis unit determines at least one potential disease item corresponding to the target user according to the disease set of the value range.
15. The computer-readable storage medium according to claim 16, wherein the image preprocessing unit processes the blood vessel image data according to preset image processing rules and generates a blood vessel recognition report corresponding to the target user, comprising:

Dividing the blood vessel image data into target analysis data corresponding to the at least one blood vessel physiological index according to the correspondence between the blood vessel physiological index and the data area;

Analyze the target analysis data according to preset data analysis rules, where the preset data analysis rules include data discrete analysis and data linear analysis;

Determine the numerical value corresponding to the at least one vascular physiological index according to the analysis result of the target analysis data;

The blood vessel identification report corresponding to the target user is output according to a preset generation format.
17. The computer-readable storage medium according to claim 17, wherein said dividing said blood vessel image data into target analysis data corresponding to said at least one blood vessel physiological index according to the corresponding relationship between blood vessel physiological index and data area, include:

Forming a segmentation model based on the correspondence between historical vascular physiological indicators and data regions, wherein the segmentation model includes at least one vascular physiological reference index and a data region corresponding to the at least one vascular physiological reference index;

According to the corresponding relationship between the at least one vascular physiological reference index and the data area corresponding to the at least one vascular physiological reference index in the segmentation model, the blood vessel image data is divided into the at least one vascular physiological reference index. Target analysis data corresponding to the indicator.
16. The computer-readable storage medium of claim 16, wherein the blood vessel image data includes first blood vessel image data, and/or second blood vessel image data.
The computer-readable storage medium of claim 16, wherein the at least one vascular physiological index includes blood flow speed, blood pressure, platelet content, blood oxygen content, red blood cell color, and hemoglobin content.