CN112150376B

CN112150376B - Vascular medical image analysis method, vascular medical image analysis device, vascular medical image analysis computer equipment and vascular medical image storage medium

Info

Publication number: CN112150376B
Application number: CN202010846877.8A
Authority: CN
Inventors: 卿龙军; 郑凌霄; 兰宏志; 马骏
Original assignee: Shenzhen Raysight Intelligent Medical Technology Co Ltd
Current assignee: Shenzhen Raysight Intelligent Medical Technology Co Ltd
Priority date: 2020-08-21
Filing date: 2020-08-21
Publication date: 2023-08-15
Anticipated expiration: 2040-08-21
Also published as: CN112150376A

Abstract

The application relates to a vascular medical image analysis processing method, a vascular medical image analysis processing device, computer equipment and a storage medium. The method comprises the following steps: receiving a vascular medical image sent by a medical data system or imported by a doctor through a terminal; after the quality detection is passed, performing image processing to generate a central line and a contour of a blood vessel in the blood vessel medical image; when receiving a result of the data correction user which is returned by the terminal and is used for adjusting the center line and the outline, modeling is carried out according to the adjusted result; carrying out hydrodynamic simulation processing according to the three-dimensional grid obtained by modeling through cloud computing service to obtain a simulation result file comprising blood flow characteristic values of each point; generating a functional color code diagram according to the simulation result file and the three-dimensional grid, determining a blood flow characteristic value at a blood vessel stenosis position in the three-dimensional grid, generating an image analysis report according to the blood flow characteristic value and the functional color code diagram, and sending the image analysis report to a terminal used by a doctor. By adopting the method, the accuracy can be improved.

Description

Vascular medical image analysis method, vascular medical image analysis device, vascular medical image analysis computer equipment and vascular medical image storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a vascular medical image analysis method, apparatus, computer device, and storage medium.

Background

Along with the development of science and technology, people pay more attention to physical health, more and more technologies for processing and analyzing medical images are presented, and the analysis and the treatment of blood vessel images are one of them, and the deep analysis of blood vessel images is very important to know the specific condition of blood vessels.

In the conventional technology, a single machine is generally used to perform a limited analysis process on a blood vessel image. However, performing the limited analysis processing may result in insufficient accuracy of the analysis processing of the blood vessel image, and thus, how to improve the accuracy of the analysis processing of the blood vessel medical image is a problem to be solved.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a vascular medical image analysis processing method, apparatus, computer device, and storage medium that can improve accuracy.

A vascular medical image analysis processing method, the method comprising:

receiving a vascular medical image sent by a medical data system or imported by a doctor through a terminal;

Performing image quality detection on the vascular medical image, and performing image processing on the vascular medical image after the quality detection is passed so as to generate a central line and a contour of a blood vessel in the vascular medical image;

loading the centerline and profile of the vessel by data correction of the terminal used by the user;

when receiving a result of the data correction user which is returned by the terminal and is used for adjusting the center line and the profile, modeling is carried out according to the adjusted result, and a three-dimensional grid of the blood vessel is generated;

performing hydrodynamic simulation processing according to the three-dimensional grid through cloud computing service, and performing simulation prediction to obtain a simulation result file comprising blood flow characteristic values of each point in the three-dimensional grid;

generating a three-dimensional functional color code diagram according to the simulation result file and the three-dimensional grid;

and determining a blood flow characteristic value at a blood vessel stenosis position in the three-dimensional grid according to the simulation result file, generating an image analysis report according to the determined blood flow characteristic value and the functional color code diagram, and sending the image analysis report to a terminal used by a doctor.

In one embodiment, after loading the centerline and profile of the vessel with the data correction user used terminal, the method further comprises:

When receiving the message returned by the data correction user through the terminal and passing through the inspection of the central line and the outline, generating a three-dimensional grid of the blood vessel according to the central line and the outline of the blood vessel, executing the cloud computing service, and carrying out hydrodynamic simulation processing and subsequent steps according to the three-dimensional grid.

In one embodiment, after the modeling based on the adjusted results, the method further comprises:

loading the three-dimensional grid through a terminal used by an auditor;

when receiving a message returned by the auditor through a terminal and aiming at the passing of the audit of the three-dimensional grid, executing the passing cloud computing service, performing hydrodynamic simulation processing according to the three-dimensional grid, and performing simulation prediction to obtain a simulation result file comprising blood flow characteristic values of each point in the three-dimensional grid and subsequent steps;

and when receiving a message returned by the auditor through the terminal that the audit on the three-dimensional grid fails, returning to execute the steps of loading the central line and the outline of the blood vessel and the follow-up steps of the terminal used by the pass data correction user until the audit passes.

In one embodiment, generating an image analysis report according to the determined blood flow characteristic value and the functional color code diagram and sending the image analysis report to a terminal used by a doctor comprises:

loading the functional color code diagram through a terminal used by the data correction user;

when a screenshot instruction which is sent by the data correction user through the terminal and aims at the functional color code image is received, a two-dimensional image of the functional color code image is intercepted according to the screenshot instruction, and an image analysis report is generated according to the blood flow characteristic value and the two-dimensional image of the functional color code image and is sent to the terminal used by the doctor.

In one embodiment, the generating and sending the image analysis report to the terminal used by the doctor includes:

generating an image analysis report;

loading the generated image analysis report through a terminal used by an auditor;

when receiving a message returned by the auditor through a terminal and passing the audit of the image analysis report, sending the image analysis report to a terminal used by a doctor;

and when receiving a message which is returned by the auditor through the terminal and is not passed by the audit of the image analysis report, returning to execute the terminal used by the data correction user to load the functional color code diagram and the subsequent steps until the audit is passed.

In one embodiment, the performing, by the cloud computing service, the hydrodynamic simulation processing according to the three-dimensional grid, and the obtaining, by simulation prediction, a simulation result file including a blood flow characteristic value of each point in the three-dimensional grid includes:

obtaining a simulation parameter file;

iteratively performing hydrodynamic simulation processing on the blood vessel according to the simulation parameter file and the three-dimensional grid through cloud computing service to generate a blood flow characteristic value on each grid unit in the three-dimensional grid on each time node;

and merging the blood flow characteristic values on each grid unit in the three-dimensional grid in each time node in the last time period to generate a simulation result file.

In one embodiment, the method further comprises:

taking blood flow characteristic values along the central line of the blood vessel according to the simulation result file, and generating a blood flow characteristic result curve according to the taken blood flow characteristic values;

generating an image analysis report according to the determined blood flow characteristic value and the functional color code diagram and sending the image analysis report to a terminal used by a doctor comprises the following steps:

adjusting the current space coordinates of each point on the central line to the target space coordinates of each point on the central line in the functional color code diagram by adjusting the angle of the functional color code diagram;

Screenshot is carried out on the adjusted functional color code diagram to obtain a two-dimensional image of the functional color code diagram;

and generating an image analysis report according to the blood flow characteristic value, the two-dimensional image of the functional color code diagram and the blood flow characteristic result curve, and sending the image analysis report to a terminal used by a doctor.

In one embodiment, after the generating an image analysis report according to the determined blood flow characteristic value and the functional color code diagram and sending the image analysis report to a terminal used by a doctor, the method further includes:

displaying a functional color code diagram through a terminal used by the doctor to check an inlet and a center line modification inlet;

when receiving triggering operation of the doctor for checking the entrance to the functional color code diagram, displaying the functional color code diagram;

when a trigger operation of modifying an entry by the doctor for the center line is received, the center line and the outline are displayed;

when receiving the adjustment instruction for the displayed central line and the profile sent by the doctor through the terminal, correspondingly adjusting the central line and the profile, and returning to execute the modeling according to the adjusted result to generate the three-dimensional grid of the blood vessel and the subsequent steps.

In one embodiment, the data correction user comprises a doctor;

when receiving the result of the data correction user after the center line and the contour are adjusted through the terminal, modeling according to the adjusted result, and generating the three-dimensional grid of the blood vessel comprises the following steps:

when a result of the doctor after adjusting the center line and the contour is received, modeling is carried out according to the adjusted result, and a three-dimensional grid of the blood vessel is generated;

after the image analysis report is generated according to the determined blood flow characteristic value and the functional color code diagram and sent to a terminal used by a doctor, the method further comprises:

displaying an image analysis report viewing inlet through a terminal used by the doctor;

the visual analysis report is presented upon receipt of a trigger operation by the physician for the visual analysis report viewing portal.

A vascular medical image analysis processing device, the device comprising:

the image acquisition module is used for receiving the vascular medical image sent by the medical data system or imported by a doctor through a terminal;

the central line generation module is used for carrying out image quality detection on the vascular medical image, and carrying out image processing on the vascular medical image after the quality detection is passed so as to generate the central line and the outline of the blood vessel in the vascular medical image;

The correction module is used for loading the central line and the outline of the blood vessel through the terminal used by the data correction user;

the model generation module is used for modeling according to the adjusted result when receiving the result of the data correction user which is returned by the terminal and is used for adjusting the center line and the contour, so as to generate a three-dimensional grid of the blood vessel;

the simulation module is used for carrying out hydrodynamic simulation processing according to the three-dimensional grid through cloud computing service, and obtaining a simulation result file comprising blood flow characteristic values of each point in the three-dimensional grid through simulation prediction;

the simulation result processing module is used for generating a three-dimensional functional color code diagram according to the simulation result file and the three-dimensional grid;

and the report generation module is used for determining a blood flow characteristic value at the position of the vascular stenosis in the three-dimensional grid according to the simulation result file, generating an image analysis report according to the determined blood flow characteristic value and the functional color code diagram, and sending the image analysis report to a terminal used by a doctor.

A computer device comprising a memory and a processor, wherein the memory stores a computer program which, when executed by the processor, causes the processor to perform the steps of the vascular medical image analysis processing method according to the embodiments of the present application.

A computer readable storage medium having a computer program stored thereon, which when executed by a processor causes the processor to perform the steps of the vascular medical image analysis processing method according to the embodiments of the present application.

The vascular medical image analysis processing method, the vascular medical image analysis processing device, the computer equipment and the storage medium are used for receiving the vascular medical image transmitted by the medical data system or imported by a doctor through a terminal, and generating the central line and the outline of the blood vessel in the vascular medical image after the image quality of the vascular medical image is detected. After the image quality detection is passed, the subsequent image processing is performed, so that the accuracy and efficiency of the image processing and the accuracy of the subsequent image analysis result can be improved. And then receiving a result of the data correction user, which is returned by the terminal and is used for adjusting the center line and the contour, so that the accuracy of the center line and the contour is improved through the interactive operation of the data correction user for adjusting the center line and the contour, modeling according to the adjusted result to generate a three-dimensional grid of the blood vessel, and carrying out hydrodynamic simulation according to the three-dimensional grid through a cloud computing service, thereby obtaining a more accurate simulation result file. And generating an accurate three-dimensional functional color code diagram according to the simulation result file and the three-dimensional grid, accurately determining a blood flow characteristic value at a blood vessel stenosis position in the three-dimensional grid according to the accurate simulation result file, generating an accurate image analysis report according to the determined blood flow characteristic value and the functional color code diagram, and sending the accurate image analysis report to a terminal used by a doctor. The accuracy of analysis and processing of vascular medical images is improved through a complete scheme combining an AI algorithm, a hydrodynamic method and a cloud computing technology and a multi-terminal interaction and remote assistance process among doctors, data correction users and an automatic program.

Drawings

FIG. 1 is a diagram of an application environment of a vascular medical image analysis processing method in one embodiment;

FIG. 2 is a flow chart of a method for analyzing and processing vascular medical images according to an embodiment;

FIG. 3 is an interface diagram of a vascular medical image analysis processing method according to one embodiment;

FIG. 4 is a schematic diagram of a three-dimensional grid in one embodiment;

FIG. 5 is an interface diagram of a vascular medical image analysis processing method according to one embodiment;

FIG. 6 is a flowchart illustrating a method for analyzing and processing vascular medical images in an automatic mode according to an embodiment;

FIG. 7 is a schematic overall flow chart of a vascular medical image analysis processing method in an interactive mode in one embodiment;

FIG. 8 is a system architecture diagram for implementing a vascular medical image analysis processing method in one embodiment;

FIG. 9 is a block diagram of a vascular medical image analysis processing device according to an embodiment;

FIG. 10 is a block diagram illustrating a vascular medical image analysis device according to another embodiment;

FIG. 11 is an internal block diagram of a computer device in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

The vascular medical image analysis processing method provided by the application can be applied to an application environment shown in figure 1. Wherein communication is performed between the server 102, the terminal 104 used by the doctor, and the terminal 106 used by the data correction user via a network. The server 102 may receive the vascular medical image sent by the medical data system or imported by the physician using the terminal 104, and generate a centerline and a contour of a blood vessel in the vascular medical image. The terminal 106 used by the data correction user may load the centerline and profile of the vessel and send the results of the data correction user's adjustments to the centerline and profile to the server 102. The server 102 may perform modeling according to the adjusted result to generate a three-dimensional grid of the blood vessel, perform hydrodynamic simulation processing according to the three-dimensional grid through a cloud computing service, perform simulation prediction to obtain a simulation result file including blood flow characteristic values of points in the three-dimensional grid, generate a three-dimensional functional color code map according to the simulation result file and the three-dimensional grid, determine the blood flow characteristic values at the stenosis position of the blood vessel in the three-dimensional grid according to the simulation result file, generate an image analysis report according to the determined blood flow characteristic values and the functional color code map, and send the image analysis report to the terminal 104 used by the doctor.

Among them, the terminal 104 used by the doctor and the terminal 106 used by the data correction user may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. It should be noted that, in some embodiments, the data correction user may be a doctor, and in this case, the terminal used by the data correction user may be a terminal used by the doctor.

The server 102 may be implemented as a stand-alone server or as a server cluster of multiple servers. It is understood that the server 102 may include a plurality of servers having different functions (or performing different tasks), such as a WEB server, a GPU server, a database, and a NAS file system. The servers cooperate together to realize the vascular medical image analysis processing method in each embodiment of the application.

In one embodiment, as shown in fig. 2, a vascular medical image analysis processing method is provided, and the method is applied to the server in fig. 1 for illustration, and includes the following steps:

s202, receiving a vascular medical image sent by a medical data system or imported by a doctor by using a terminal.

The medical data system is a system for managing medical data such as medical images in hospitals.

In one embodiment, the medical data system may be any of a PACS system (Picture Archiving and Communication Systems, image archiving and communication system), a RIS system (Radioiogy information system, radiology information management system), a HIS system (Hospital Information System ), a system directly connected to a medical imaging (CT or nuclear magnetic resonance, etc.) system, and the like.

The vascular medical image is a three-dimensional medical image taken to contain a blood vessel. In one embodiment, the vascular medical image may include at least one of a CT (Computed Tomography, electronic computed tomography) image, an MRI (Magnetic Resonance Imaging ) image, an ultrasound image, a coronary angiography, a nuclear species imaging (SPECT or PET), an X-ray image, and the like. In one embodiment, the vascular medical image may be a file in DICOM format (Digital Imaging and Communications in Medicine, defining a medical image format that can be used for data exchange with quality meeting clinical needs).

In one embodiment, the server may receive a vascular medical image sent to the medical data system of the hospital.

In one embodiment, the server may receive a vascular medical image imported by a doctor in a page loaded by the terminal used. As shown in fig. 3, which is a schematic diagram of a page loaded by a doctor at a terminal used, the doctor can import a vascular medical image through an "import DICOM file" portal in the page shown in fig. 3. After the image is imported, the processing state in the system is displayed as "in process" as shown in fig. 3.

In one embodiment, a clinician of a clinical department may use a terminal of the clinical department to send a message to a terminal used by the radiologist. After the radiologist sees the message received by the terminal, the radiologist can import the vascular medical image to the server through the page loaded by the terminal used by the radiologist.

S204, performing image quality detection on the vascular medical image, and performing image processing on the vascular medical image after the quality detection is passed so as to generate the central line and the outline of the blood vessel in the vascular medical image.

In one embodiment, the server may perform image quality detection on the received vascular medical image, and when the image quality detection passes, the server may perform image processing on the vascular medical image to generate a centerline and a contour of a blood vessel in the vascular medical image and subsequent steps; when the image detection fails, the server may send a message indicating that the image quality is not acceptable to a terminal used by the doctor to inform the doctor that the quality of the vascular medical image is not acceptable.

In one embodiment, the server may perform an image segmentation process (i.e., an initial segmentation) on the blood vessel medical image after the image quality detection is passed to obtain a blood vessel segmented image, then perform a process of extracting a center line on the blood vessel segmented image, extract a center line of the blood vessel, and then generate a contour of the blood vessel based on the center line and the blood vessel segmented image.

S206, correcting the central line and the outline of the terminal loading blood vessel used by the user through data.

In one embodiment, the server, after generating the centerline and profile of the vessel, may send a message to the terminal used by the data correction user. The data correction user can load the center line and the contour of the blood vessel through the data correction user using the terminal after seeing the message received by the used terminal.

The data correction user can judge whether the center line and the outline of the loaded blood vessel need to be adjusted or not through the professionality, and when the adjustment is needed, the data correction user can adjust the center line and the outline of the blood vessel loaded by the terminal so as to improve the accuracy of the center line and the outline, and the adjusted result is sent to the server through the terminal. It will be appreciated that the data correction user may not perform the adjustment process when no adjustment is required.

In one embodiment, the data correction user may calibrate the centerline and check and correct the contour near the coronary lesion area to ensure that it reflects the true lumen of the blood vessel.

In one embodiment, the data correction user may be a data analyst or doctor who is responsible for data correction.

And S208, when receiving a result of the data correction user which is returned by the terminal and is used for adjusting the center line and the contour, modeling is carried out according to the adjusted result, and a three-dimensional grid of the blood vessel is generated.

Wherein the three-dimensional mesh is a vascular solid mesh represented by a solid polyhedron.

In one embodiment, the solid polyhedron may be a solid tetrahedron. As shown in fig. 4, is a schematic representation of a three-dimensional grid of blood vessels.

Specifically, when receiving the result of the data correction user returned by the terminal after the center line and the contour are adjusted, the server can model according to the adjusted center line and contour to generate a three-dimensional grid of the blood vessel.

In one embodiment, the step of modeling based on the adjusted results to generate a three-dimensional grid of blood vessels comprises: the server can firstly establish a blood vessel surface model according to the adjusted contour, then carry out smoothing treatment on the wall of the blood vessel surface model, and then carry out three-dimensional mesh subdivision based on the smooth blood vessel surface model to obtain a final three-dimensional mesh.

It will be understood that when the result of the adjustment of the center line and the contour returned by the data correction user through the terminal is not received, or the message of passing the inspection returned by the data correction user through the terminal is received, the adjustment is not required, and then the modeling can be automatically performed according to the contour generated in step S204, so as to generate the three-dimensional grid of the blood vessel.

S210, performing hydrodynamic simulation processing according to the three-dimensional grid through cloud computing service, and performing simulation prediction to obtain a simulation result file comprising blood flow characteristic values of each point in the three-dimensional grid.

Wherein, the blood flow characteristic value is the value of an important physiological index for a doctor to evaluate the health condition of the blood vessel. Hydrodynamic simulation processing involves computational fluid dynamics (Computational Fluid Dynamics, CFD for short). Computational fluid dynamics is an emerging interdisciplinary discipline of fluid mechanics and computer science, and is based on a calculation method, and an approximate solution of a fluid control equation is obtained by using the rapid calculation capability of a computer.

In one embodiment, the blood flow characteristic value may include a value of at least one of Fractional Flow Reserve (FFR), wall Shear Stress (WSS), axial Plaque Stress (APS), and oscillation coefficient (OSI), among others.

In one embodiment, the server may first obtain a simulation parameter file of a blood vessel, and then perform hydrodynamic simulation processing according to the simulation parameter file and the three-dimensional grid by using a cloud computing service provided by the supercomputer center, so as to generate a simulation result file, where the generated simulation result file includes blood flow characteristic values of points in the three-dimensional grid. The simulation parameter file is a file containing parameters required for hydrodynamic simulation of a blood vessel. In one embodiment, the simulation parameter file may include simulation parameters of the blood vessel, and initial conditions and boundary conditions corresponding to the three-dimensional grid generated according to the simulation parameters.

S212, generating a three-dimensional functional color code diagram according to the simulation result file and the three-dimensional grid.

The functional color code diagram is a color three-dimensional image used for representing blood flow characteristic values of points in the three-dimensional grid. In the functional color code diagram, different blood flow characteristic values are represented by different colors.

In one embodiment, the server may represent the blood flow characteristic values of each point in the three-dimensional grid in the simulation result file in the form of a color, and different blood flow characteristic values are distinguished by different colors, so as to generate a functional color code diagram.

S214, determining a blood flow characteristic value at a blood vessel stenosis position in the three-dimensional grid according to the simulation result file, generating an image analysis report according to the determined blood flow characteristic value and the functional color code diagram, and sending the image analysis report to a terminal used by a doctor.

It will be appreciated that there may be lesions at the site of the stenosis of the vessel, and therefore, it is necessary to determine data of the characteristic value of the blood flow at the site of the stenosis of the vessel and feed back to the doctor as reference data for the doctor to determine whether the lesion exists in the vessel. It should be noted that, the blood flow characteristic value at the position of the vascular stenosis does not directly represent whether a lesion exists, but needs a doctor or a professional to further judge whether a lesion exists according to the blood flow characteristic value through professional medical knowledge, and therefore, the blood flow characteristic value does not belong to a diagnosis result of a disease.

In one embodiment, the server may automatically determine a blood flow characteristic value at a blood vessel stenosis position in the three-dimensional grid according to the blood flow characteristic value of each point in the three-dimensional grid in the simulation result file, and generate an image analysis report according to the determined blood flow characteristic value at the blood vessel stenosis position and the generated functional color code diagram. That is, the image analysis report includes the blood flow characteristic value at the blood vessel stenosis position and the functional color code map of the blood vessel.

In one embodiment, the server may generate an image analysis report based on the blood flow characteristic value at the stenosis location of the blood vessel and a two-dimensional image obtained by capturing a functional color code map. In one embodiment, the two-dimensional image obtained by capturing the functional color code diagram may be obtained by automatically capturing the functional color code diagram by a server or may be obtained by capturing the functional color code diagram by a data correction user.

It can be understood that the image analysis report includes data obtained by performing image processing analysis on the vascular medical image, which is not a direct result of whether a lesion is present, but is used for providing reference data for analysis and judgment of the vascular condition by a doctor, and requires the doctor or a professional to further perform professional analysis and judgment on the image analysis report through professional medical knowledge, so that the image analysis report does not belong to a diagnosis result of a disease.

In one embodiment, after the image analysis report is generated, the server may send a message to the terminal used by the doctor. After seeing the message received by the terminal, the doctor can load the image analysis report through the terminal.

In one embodiment, after the image analysis report is generated, the server may send the image analysis report to a terminal used by a doctor and to a medical data system of a hospital.

In one embodiment, the image analysis report may include, without limitation, other data such as a blood flow characteristic value curve in addition to the blood flow characteristic value at the blood vessel stenosis position and the two-dimensional image of the functional color code map.

In the vascular medical image analysis processing method, the vascular medical image sent by the medical data system or imported by a doctor through a terminal is received, and after the image quality of the vascular medical image is detected, the central line and the outline of the blood vessel in the vascular medical image are generated. After the image quality detection is passed, the subsequent image processing is performed, so that the accuracy and efficiency of the image processing and the accuracy of the subsequent image analysis result can be improved. And then receiving a result of the data correction user, which is returned by the terminal and is used for adjusting the center line and the contour, so that the accuracy of the center line and the contour is improved through the interactive operation of the data correction user for adjusting the center line and the contour, modeling according to the adjusted result to generate a three-dimensional grid of the blood vessel, carrying out hydrodynamic simulation processing according to the three-dimensional grid through a cloud computing service to obtain a more accurate simulation result file, generating an accurate three-dimensional functional color code diagram according to the simulation result file and the three-dimensional grid, accurately determining a blood flow characteristic value at a narrow position of the blood vessel in the three-dimensional grid according to the accurate simulation result file, generating an accurate image analysis report according to the determined blood flow characteristic value and the functional color code diagram, and sending the accurate image analysis report to the terminal used by a doctor. The accuracy of analysis and processing of the vascular medical images is improved through a complete scheme of combining an AI algorithm, a hydrodynamic method and a cloud computing technology and a multi-terminal interaction (multi-person cooperation) and remote assistance process among doctors, data correction users and an automatic program. In addition, through cloud computing service, the large-scale batch processing of the system can be improved, and the processing efficiency is improved.

In one embodiment, after the step of loading the centerline and profile of the vessel with data to correct the terminal used by the user, the method further comprises: when receiving a message returned by the data correction user through the terminal and passing the inspection of the central line and the outline, generating a three-dimensional grid of the blood vessel according to the central line and the outline of the blood vessel, executing a cloud computing service, and carrying out hydrodynamic simulation processing and subsequent steps according to the three-dimensional grid.

Specifically, the terminal used by the data correction user may load the centerline and profile of the vessel, and the data correction user may examine the centerline and profile loaded by the terminal. When the inspection passes (i.e., no adjustment is required to be made to the center line and the contour), the data correction user can return a message that the inspection of the center line and the contour passes to the server through the terminal, and after receiving the message, the server can model according to the center line and the contour of the blood vessel automatically generated through the image processing (i.e., the center line and the contour which are not adjusted), generate a three-dimensional grid of the blood vessel, execute the through-cloud computing service, perform the hydrodynamic simulation processing according to the three-dimensional grid, and subsequent steps. When the inspection fails (i.e., the center line and the contour need to be adjusted), the data correction user can adjust the center line and the contour through the terminal, and return the adjusted center line and contour to the server through the terminal, and when the server receives the adjusted result, the server performs modeling according to the adjusted result, and generates a three-dimensional grid of the blood vessel and subsequent steps.

In this embodiment, the data correction user may examine the centerline and contour, and upon passing the examination, the server may model directly from the centerline and contour of the blood vessel generated by the image processing (i.e., the centerline and contour that have not been adjusted). The accuracy of the center line and the contour is ensured through the adjustment operation of the data correction user, and the accuracy of the blood vessel image analysis processing can be further improved.

In one embodiment, after the step of modeling based on the adjusted results to generate a three-dimensional grid of blood vessels, the method further comprises: loading a three-dimensional grid through a terminal used by an auditor; when a message of passing the auditing of the three-dimensional grid returned by the auditor through the terminal is received, executing a cloud computing service, performing hydrodynamic simulation processing according to the three-dimensional grid, and obtaining a simulation result file comprising blood flow characteristic values of each point in the three-dimensional grid through simulation prediction and subsequent steps; and when receiving a message returned by the auditor through the terminal and aiming at the failed audit of the three-dimensional grid, returning to execute the central line and the outline of the terminal loading blood vessel used by the user through data correction and the subsequent steps until the audit passes.

Specifically, after the step of modeling based on the adjusted results to generate a three-dimensional grid of blood vessels, the server may send a message to a terminal used by an auditor. After seeing the message received by the terminal, the auditor can load the generated three-dimensional grid through the terminal and audit the three-dimensional grid.

In one embodiment, when the auditor passes the audit (i.e. the generated three-dimensional grid is audited to be qualified), the auditor can send an audit passing message to the server through the terminal, and when the server receives the audit passing message, the server can execute the cloud computing service, perform hydrodynamic simulation processing according to the three-dimensional grid, and obtain a simulation result file comprising blood flow characteristic values of each point in the three-dimensional grid through simulation prediction and subsequent steps.

In one embodiment, when the auditor fails the audit (i.e., the generated three-dimensional grid fails the audit, the centerline and profile still need to be readjusted and the three-dimensional grid regenerated), the auditor may send a message to the server via the terminal that the audit failed. When the server receives the message which is not passed by the verification, the step of sending the message to the terminal used by the data correction user can be carried out in a return mode, so that the data correction user loads the central line and the outline of the blood vessel through the terminal after seeing the message received by the used terminal, and adjusts the central line and the outline of the blood vessel loaded by the terminal until the three-dimensional grid generated by modeling according to the adjusted central line and outline is verified by the server.

In one embodiment, both an automatic mode and an interactive mode are provided. In the automatic mode, the data correction user is a doctor, and can be performed according to steps S202 to S214. In the interaction mode, the data correction user can increase the steps of auditing the three-dimensional grid generated according to the adjusted result of the data analyst on the basis of the steps S202 to S214, so as to further improve the accuracy of the blood vessel image analysis processing result. The mode may be set in advance, or may be selected by the user himself.

In this embodiment, after the server generates the three-dimensional grid, the auditor audits the three-dimensional grid through the used terminal, and when the audit fails, the data correction user can readjust the center line and the profile until the audit passes, so that on the basis that the data correction user adjusts the center line and the profile, the auditing operation of the auditor further ensures the accuracy of the generated three-dimensional grid, and further improves the accuracy of the analysis processing of the vascular medical image.

In one embodiment, the step of generating an image analysis report based on the determined blood flow characteristic values and the functional color code pattern and transmitting the image analysis report to a terminal used by a doctor comprises: loading a functional color code diagram through a terminal used by a data correction user; when a screenshot instruction for the functional color code image sent by the data correction user through the terminal is received, a two-dimensional image of the functional color code image is intercepted according to the screenshot instruction, and an image analysis report is generated according to the blood flow characteristic value and the two-dimensional image of the functional color code image and is sent to the terminal used by the doctor.

In one embodiment, the data correction user may be a doctor or a data analyst who is responsible for performing the screenshot operations and generating the image analysis report.

Specifically, after the server determines the blood flow characteristic value at the stenosis position of the blood vessel in the three-dimensional grid and generates the three-dimensional functional color code map, the server may send a message to the terminal used by the data correction user. After the data correction user sees the message received by the terminal, the terminal can load the functional color code diagram generated by the server. The data correction user can perform screenshot operation through the terminal, and the terminal can generate screenshot instructions after receiving the screenshot operation. The terminal can intercept the two-dimensional image of the functional color code diagram on the currently displayed angle according to the screenshot instruction, and send the intercepted two-dimensional image to the server. The server can generate an image analysis report according to the intercepted two-dimensional image and the determined blood flow characteristic value at the position of the vascular stenosis in the three-dimensional grid, and send a message to a terminal used by a doctor. After seeing the message received by the terminal, the doctor can load the image analysis report through the terminal.

In one embodiment, the data correction user may adjust the angle of the functional color code pattern through the terminal, then perform the screenshot operation, the terminal may generate a screenshot instruction according to the screenshot operation, then intercept a two-dimensional image of the functional color code pattern at the adjusted angle according to the screenshot instruction, and perform sending the intercepted two-dimensional image to the server and subsequent steps.

In one embodiment, after the data correction user performs the screenshot operation, the used terminal can send an instruction for generating an image analysis report, the terminal can send the instruction for generating the image analysis report to the server, and the server can respond to the instruction for generating the image analysis report after receiving the instruction and generate the image analysis report according to the intercepted two-dimensional image and the determined blood flow characteristic value at the position of the vascular stenosis in the three-dimensional grid.

In this embodiment, the data correction user may perform screenshot processing on the functional color code map through the terminal to obtain a two-dimensional image of the functional color code map, and the server may generate an image analysis report according to the two-dimensional image of the functional color code map and a blood flow characteristic value at a blood vessel stenosis position in the three-dimensional grid and send the image analysis report to the terminal used by the doctor, so that the data correction user performs screenshot processing on the functional color code map through the terminal, thereby ensuring the accuracy of the two-dimensional image of the functional color code map in the image analysis report, and improving the accuracy of the blood vessel image analysis processing.

In one embodiment, the step of generating and transmitting the image analysis report to a terminal used by a doctor comprises: generating an image analysis report; loading the generated image analysis report through a terminal used by an auditor; when receiving a message returned by an auditor through a terminal and passing the audit of the image analysis report, sending the image analysis report to a terminal used by a doctor; and when receiving a message which is returned by the auditor through the terminal and is not passed by the audit of the image analysis report, returning to execute the terminal loading function color code diagram used by the user through data correction and the subsequent steps until the audit is passed.

Specifically, after the image analysis report is generated, the server can send a message to a terminal used by an auditor, and after the auditor sees the message received by the terminal, the auditor can load the image analysis report through the terminal and audit the loaded image analysis report.

In one embodiment, when an auditor audits an image analysis report (i.e., the image analysis report is acceptable, the image analysis report may be sent to a doctor), the auditor may send an audit-passed message to a server through a terminal used, and the server may send the image analysis report to the terminal used by the doctor after receiving the audit-passed message.

In one embodiment, when the auditor fails to audit the image analysis report (i.e., the image analysis report is not qualified and the image analysis report needs to be regenerated), the auditor can send a message that the audit fails to pass to the server through the used terminal, and after receiving the message that the audit fails, the server can execute the terminal loading function color code diagram used by the user through data correction and the subsequent steps, so that the user through data correction can perform screenshot operation on the function color code diagram again, and generate a new image analysis report according to the two-dimensional image after the screenshot and the blood flow characteristic value at the blood vessel stenosis position until the image analysis report passes the audit.

In one embodiment, the image analysis report audited by the auditor can be automatically generated by the server, when the auditor is not audited, the data correction user performs screenshot operation on the functional color code chart through the terminal, and the server regenerates the image analysis report according to the blood flow characteristic value at the blood vessel stenosis position and the two-dimensional image of the functional color code chart obtained by the screenshot operation of the data correction user. In another embodiment, the image analysis report audited by the auditor may be a two-dimensional image of a functional color code chart obtained by the server according to the blood flow characteristic value at the blood vessel stenosis position and the screenshot operation of the data correction user.

In this embodiment, an auditor may audit the generated image analysis report through the used terminal, and when the audit fails, the data correction user may perform the screenshot operation again, so that the server regenerates the image analysis report until the generated image analysis report passes the audit, and through the interaction between the auditor and the data analyst, the accuracy of the two-dimensional image of the functional color code chart in the generated image analysis report is ensured, so as to improve the accuracy of the blood vessel image analysis processing.

In one embodiment, the step of performing hydrodynamic simulation processing according to the three-dimensional grid through the cloud computing service to obtain a simulation result file including blood flow characteristic values of points in the three-dimensional grid through simulation prediction includes: obtaining a simulation parameter file; iteratively performing hydrodynamic simulation processing on the blood vessel according to the simulation parameter file and the three-dimensional grid through cloud computing service to generate a blood flow characteristic value on each grid unit in the three-dimensional grid on each time node; and merging the blood flow characteristic values on each grid unit in the three-dimensional grids on each time node in the last time period to generate a simulation result file.

Specifically, the server can iteratively perform hydrodynamic simulation processing on the blood vessel according to the simulation parameter file and the three-dimensional grid through cloud computing service provided by the supercomputer center to generate a blood flow characteristic value on each grid cell in the three-dimensional grid on each time node, and then combine the blood flow characteristic values on each grid cell in the three-dimensional grid on each time node in the last time period to generate a simulation result file. It will be appreciated that the simulation procedure is a procedure that progresses from an unstable state to a steady state, with the various hemodynamic parameters tending to stabilize over time, so that the result of the last cardiac cycle may be selected as the final simulation result.

In this embodiment, the server may perform hydrodynamic simulation on the blood vessel through the cloud computing service, so as to generate the simulation result file more quickly and accurately, thereby improving accuracy and efficiency of analysis processing of the blood vessel image.

In one embodiment, the method further comprises: and taking blood flow characteristic values along the central line of the blood vessel according to the simulation result file, and generating a blood flow characteristic result curve according to the taken blood flow characteristic values. The step of generating an image analysis report according to the determined blood flow characteristic value and the functional color code diagram and sending the image analysis report to a terminal used by a doctor comprises the following steps: the current space coordinates of each point on the central line are adjusted to the target space coordinates of each point on the central line in the functional color code diagram by adjusting the angle of the functional color code diagram; screenshot is carried out on the adjusted functional color code diagram to obtain a two-dimensional image of the functional color code diagram; and generating an image analysis report according to the blood flow characteristic value, the two-dimensional image of the functional color code diagram and the blood flow characteristic result curve, and sending the image analysis report to a terminal used by a doctor.

The blood flow characteristic result curve is a curve for representing blood flow characteristic values of points on a central line of a blood vessel.

In one embodiment, the server may select points in the simulation result file at equal intervals along the centerline of the blood vessel according to a preset interval, determine the blood flow characteristic value of each point, and generate a blood flow characteristic result curve according to the blood flow characteristic value of each point.

In one embodiment, the server may determine the target space coordinates of points on the centerline of the functional color code map, and then adjust the angles of the functional color code map to adjust points on the centerline of the functional color code map to the target space coordinates. The server can perform screenshot processing on the adjusted functional color code image to obtain a two-dimensional image of the functional color code image. The server can generate an image analysis report according to the blood flow characteristic value at the blood vessel stenosis position, the two-dimensional image of the functional color code diagram and the blood flow characteristic result curve, and send the image analysis report to a terminal used by a doctor.

In this embodiment, the server may generate a blood flow characteristic result curve, thereby improving the information content of the image analysis report. The server can also automatically perform screenshot to generate a two-dimensional image of the functional color code diagram, so that the automatic processing capacity of the system is improved, and the efficiency is improved.

In one embodiment, after the step of generating an image analysis report based on the determined blood flow characteristic values and the functional color code pattern and transmitting the image analysis report to a terminal used by a doctor, the method further includes: displaying a functional color code diagram through a terminal used by a doctor to check an inlet and a center line modification inlet; when receiving triggering operation of a doctor for checking an entry aiming at the functional color code diagram, displaying the functional color code diagram; when receiving triggering operation of modifying the entrance by a doctor aiming at the central line, displaying the central line and the outline; when receiving an adjustment instruction for the displayed central line and outline sent by a doctor through the terminal, correspondingly adjusting the central line and outline, and returning to execute modeling according to the adjusted result to generate a three-dimensional grid of the blood vessel and subsequent steps.

In one embodiment, as shown in fig. 5, a schematic diagram of a page loaded by a terminal used by a doctor is shown, where a "three-dimensional color chart" option in the diagram is a functional color chart viewing entry, and a "modify centerline" option in the diagram is a centerline modifying entry.

In one embodiment, when the terminal used by the doctor receives the trigger operation of the doctor to view the portal for the functional color code pattern, the terminal used by the doctor may display the functional color code pattern generated by the server.

In one embodiment, the visual analysis report viewing portal (i.e., the "download report" option in FIG. 5) may also be presented through a terminal used by the physician. When the terminal used by the doctor receives the triggering operation of the doctor for the image analysis report viewing portal, the terminal can display the image analysis report sent by the server. The doctor can trigger the terminal to download the image analysis report to the local of the terminal based on the download entrance in the display interface of the image analysis report.

It will be appreciated that the physician may generate the image analysis report by looking at least one of the functional color code map and the image analysis report, determining if an adjustment of the centerline and the contour is required, and causing the server to re-perform the vascular medical image analysis process based on the adjusted centerline and contour. When the physician determines that the center line and profile need to be adjusted, the physician may trigger the center line modification entry.

In one embodiment, when the terminal used by the doctor receives a trigger operation from the doctor to modify the portal for the centerline, the terminal used by the doctor may present the centerline and profile of the blood vessel generated by the server. The doctor can send out an adjustment instruction aiming at the displayed central line and outline through the terminal, the server can correspondingly adjust the central line and outline according to the adjustment instruction, then the server returns to execute modeling according to the adjusted result to generate a three-dimensional grid of the blood vessel and subsequent steps, so that vascular medical image analysis processing is carried out again according to the central line and outline adjusted by the doctor until an image analysis report is generated and sent to the terminal used by the doctor, and the doctor does not adjust the central line and outline any more.

In this embodiment, a doctor can view the portal through the functional color chart and view the functional color chart, and the doctor can also adjust the center line and the contour through the center line modification portal, so that the server can re-perform vascular medical image analysis processing according to the adjusted center line and contour to generate a new image analysis report, and thus after the image analysis report is generated, the accuracy of the finally generated image analysis report can be ensured through the adjustment of the center line and contour by the doctor.

In one embodiment, the data correction user comprises a doctor. When receiving a result of the data correction user which is returned by the terminal and is used for adjusting the center line and the outline, modeling is carried out according to the adjusted result, and the step of generating the three-dimensional grid of the blood vessel comprises the following steps: when receiving the result of the central line and the contour which are returned by the doctor through the terminal and are adjusted, modeling is carried out according to the adjusted result, and a three-dimensional grid of the blood vessel is generated. After the step of generating an image analysis report based on the determined blood flow characteristic values and the functional color code pattern and transmitting the image analysis report to a terminal used by a doctor, the method further comprises: displaying an image analysis report viewing inlet through a terminal used by a doctor; when a trigger operation of a doctor for the image analysis report viewing portal is received, the image analysis report is displayed.

Specifically, after the center line and the outline are generated, the server can send a message to the terminal used by the doctor, the doctor can load the center line and the outline through the terminal after seeing the message received by the terminal, adjust the center line and the outline through the terminal, and feed back the adjusted center line and outline to the server. After receiving the adjusted central line and contour, the server can model according to the adjusted central line and contour to generate a three-dimensional grid of the blood vessel.

In one embodiment, after the server generates and sends the visual analysis report to the terminal used by the doctor, the visual analysis report review portal (i.e., the "download report" option in FIG. 5) may be presented through the terminal used by the doctor. When the terminal used by the doctor receives the triggering operation of the doctor for the image analysis report viewing portal, the terminal can display the image analysis report sent by the server. The doctor can trigger the terminal to download the image analysis report to the local of the terminal based on the download entrance in the display interface of the image analysis report.

In this embodiment, a doctor may adjust the center line and the contour during the vascular medical image analysis processing, so as to improve the accuracy of the finally generated image analysis report. The doctor can also check the image analysis report through the image analysis report checking entrance of the used terminal, so that the convenience of operation is improved.

In one embodiment, as shown in fig. 6, an overall flow chart of a vascular medical image analysis processing method in an automatic mode according to the embodiments of the present application is shown. Firstly, an original vascular medical image (which can be a DICOM file) is sent from a medical data system to a server for analyzing and processing the vascular medical image, and the server can detect the image quality after receiving the vascular medical image. When the image quality detection is not passed, the server may send a notification of the image quality failure to the terminal used by the doctor. When the image quality detection is passed, the server can perform primary segmentation on the received vascular medical image, then extract the central line of the blood vessel and generate the contour of the blood vessel. After the center line and the profile are generated, the server can send a message to the terminal used by the doctor, after the doctor sees the message received by the terminal, the doctor can load the center line and the profile by triggering the modification center line entry displayed by the terminal, and after the doctor can check the center line and the profile loaded by the terminal, the doctor can determine whether the center line and the profile need to be manually adjusted. When the doctor determines that manual adjustment is not needed, the server can directly model according to the center line and the outline which are not adjusted, and a three-dimensional grid is generated. When the doctor determines that the center line and the contour need to be adjusted, the doctor can adjust the center line and the contour through the used terminal, and the server can model according to the adjusted center line and contour returned by the terminal used by the doctor, so that the three-dimensional grid is generated. After generating the three-dimensional grid, the server may perform a pre-simulation process (i.e., obtain a simulation parameter file), then perform a hydrodynamic simulation process according to the simulation parameter file and the three-dimensional grid through a cloud computing service provided by the supercomputer, then perform a file conversion process according to a simulation result (i.e., combine blood flow feature values on each grid unit in the three-dimensional grid at each time node in a last time period) to generate a simulation result file, and finally, perform a post-simulation process (including at least one of determining a blood flow feature value at a stenosis position of a blood vessel according to the simulation result file, generating a functional color code map according to the simulation result file, and generating a blood flow feature result curve according to the simulation result). The server can generate an image analysis report according to the result of the simulation post-processing. The doctor can load the image analysis report through the used terminal and view the report. The server may also send the image analysis report to the medical data system for storage.

In one embodiment, as shown in fig. 7, an overall flow chart of a vascular medical image analysis processing method in an interactive mode in each embodiment of the application is shown. The clinical department doctor sends a vascular medical image analysis application to the terminal used by the radiologist through the used terminal, the radiologist can import an original vascular medical image (can be a DICOM-format file) through the used terminal, the imported vascular medical image is desensitized and then sent to a server for vascular medical image analysis processing, a CT record of a patient is generated, and the server can detect the image quality of the received vascular medical image. When the image quality detection is not passed, the server may send a notification of the image quality failure to a terminal used by a clinical department doctor. When the image quality detection is passed, the server can perform primary segmentation on the received vascular medical image, then extract the central line of the blood vessel and generate the contour of the blood vessel. After generating the centerline and the profile, the data analyst may check the centerline and the profile through the terminals used to determine if adjustments to the centerline and the profile are needed. When the data analyst determines that no adjustment of the centerlines and contours is required, the server may model according to the unadjusted centerlines and contours to generate a three-dimensional grid file. When the data analyst determines that the center line and the contour need to be adjusted, the data analyst can adjust the center line and the contour through the used terminal, and the server can model according to the adjusted center line and contour to generate the three-dimensional grid file. After the three-dimensional grid file is generated, an auditor can audit the three-dimensional grid file through the used terminal. When the auditor passes the audit, the server can perform simulation processing according to the three-dimensional grid file. When the auditor passes the audit, the data analyst can adjust the central line and the outline again through the used terminal, and the server can generate a three-dimensional grid file according to the adjusted central line and outline until the auditor passes the audit on the generated three-dimensional grid file. After the verification is passed, the server may perform a pre-simulation process (i.e., obtain a simulation parameter file), then perform a hydrodynamic simulation process according to the simulation parameter file and the three-dimensional grid through a cloud computing service provided by the supercomputer, then perform a file conversion process according to a simulation result (i.e., combine blood flow feature values on each grid unit in the three-dimensional grid on each time node in a last time period) to generate a simulation result file, and finally perform a post-simulation process (including at least one of determining a blood flow feature value at a stenosis position of a blood vessel according to the simulation result file, generating a functional color code map according to the simulation result file, and generating a blood flow feature result curve according to the simulation result). The data analyst can perform corresponding processing (including screenshot of the functional color code diagram) according to the data obtained by the post-simulation processing through the used terminal to generate an image analysis report. And the auditor can audit the generated image analysis report through the used terminal. When the auditor passes the audit, the doctor can check the image analysis report through the used terminal. When the auditor passes the audit, the data analyst can process the data obtained by the post-simulation processing through the used terminal again (including screenshot of the functional color code diagram) to generate an image analysis report, and the doctor can check the image analysis report through the used terminal until the generated image analysis report passes the audit of the auditor.

In one embodiment, in the interaction mode, in the process of adjusting by the data analyst and auditing by the auditor, the server can directly and automatically execute the subsequent flow, after receiving the adjustment result of the data analyst, the server can return to execute the flow step according to the adjusted result, and when the data analyst does not make adjustment, the server directly carries out the subsequent processing of generating the image analysis report according to the automatically completed result, so that the processing efficiency can be improved. In another embodiment, in the interaction mode, the server may wait during the adjustment by the data analyst and the auditing by the auditor, and execute the subsequent steps after receiving the adjustment result or the auditing result, so that the waste of system resources may be avoided.

In one embodiment, the vascular medical image analysis processing method in the embodiments of the present application may be implemented by a system as shown in fig. 8. Wherein the WEB server is responsible for managing and scheduling all data, users such as doctors, data analyzers, auditors and the like can acquire and load the data in the WEB server through the used terminal so as to view the data in a browser of the terminal, the GPU server is responsible for executing all AI programs for executing the vascular medical image analysis processing method, the computer cluster is responsible for carrying out hydrodynamic simulation calculation, the database (master library and slave library) is responsible for storing and backing up service data (the service data comprises system user information, patient CT record information, audit record, operation log and the like), and the NAS file system is responsible for storing and managing medical image files.

It should be understood that, although the steps in the flowchart of fig. 2 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps in fig. 2 may include a plurality of steps or stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily sequential, but may be performed in rotation or alternatively with at least a portion of the steps or stages in other steps or other steps.

In one embodiment, as shown in fig. 9, there is provided a vascular medical image analysis processing apparatus 900, including: an image acquisition module 902, a centerline generation module 904, a correction module 906, a model generation module 908, a simulation module 910, a simulation result processing module 912, and a report generation module 914, wherein:

the image acquisition module 902 is configured to receive a vascular medical image sent by a medical data system or imported by a doctor using a terminal.

The central line generating module 904 is configured to perform image quality detection on the vascular medical image, and perform image processing on the vascular medical image after the quality detection is passed, so as to generate a central line and a contour of a blood vessel in the vascular medical image.

A correction module 906 for correcting the centerline and profile of the end-loaded vessel used by the user with the data.

The model generating module 908 is configured to, when receiving a result of the data correction user that adjusts the center line and the contour through the terminal, perform modeling according to the adjusted result, and generate a three-dimensional grid of the blood vessel.

The simulation module 910 is configured to perform a hydrodynamic simulation process according to the three-dimensional grid through the cloud computing service, and perform a simulation prediction to obtain a simulation result file including the blood flow characteristic values of each point in the three-dimensional grid.

The simulation result processing module 912 is configured to generate a three-dimensional functional color code map according to the simulation result file and the three-dimensional grid.

The report generating module 914 is configured to determine a blood flow characteristic value at a blood vessel stenosis position in the three-dimensional grid according to the simulation result file, generate an image analysis report according to the determined blood flow characteristic value and the functional color code diagram, and send the image analysis report to a terminal used by a doctor.

In one embodiment, the correction module 906 is further configured to, when receiving a message returned by the data correction user through the terminal for passing the inspection of the center line and the contour, generate a three-dimensional grid of the blood vessel according to the center line and the contour of the blood vessel, and notify the simulation module 910 to execute the passing cloud computing service, perform the hydrodynamic simulation process according to the three-dimensional grid, and perform subsequent steps.

In one embodiment, the vascular medical image analysis processing device 900 further includes:

an auditing module 916 for loading the three-dimensional grid through a terminal used by an auditor; when a message of passing the auditing of the three-dimensional grid returned by the auditor through the terminal is received, executing a cloud computing service, performing hydrodynamic simulation processing according to the three-dimensional grid, and obtaining a simulation result file comprising blood flow characteristic values of each point in the three-dimensional grid through simulation prediction and subsequent steps; upon receiving a message returned by the auditor through the terminal that the audit for the three-dimensional grid failed, the notification correction module 906 performs the center line and profile of the terminal-loaded vessel used by the user corrected by the data and subsequent steps until the audit passes.

In one embodiment, the correction module 906 is further configured to correct the terminal loading functional color code map used by the user with data; when a screenshot instruction for the functional color code image sent by the data correction user through the terminal is received, a two-dimensional image of the functional color code image is intercepted according to the screenshot instruction, and an image analysis report is generated according to the blood flow characteristic value and the two-dimensional image of the functional color code image and is sent to the terminal used by the doctor.

In one embodiment, the auditing module 916 is also used to generate an image analysis report; loading the generated image analysis report through a terminal used by an auditor; when receiving a message returned by an auditor through a terminal and passing the audit of the image analysis report, sending the image analysis report to a terminal used by a doctor; and when receiving a message that the auditing of the image analysis report is not passed, which is returned by the auditor through the terminal, returning to the notification correction module 906 to execute the terminal loading functional color code diagram used by the user through data correction and subsequent steps until the auditing is passed.

In one embodiment, the simulation module 910 is further configured to obtain a simulation parameter file; iteratively performing hydrodynamic simulation processing on the blood vessel according to the simulation parameter file and the three-dimensional grid through cloud computing service to generate a blood flow characteristic value on each grid unit in the three-dimensional grid on each time node; and merging the blood flow characteristic values on each grid unit in the three-dimensional grids on each time node in the last time period to generate a simulation result file.

In one embodiment, the simulation result processing module 912 is further configured to take a blood flow characteristic value along a center line of the blood vessel according to the simulation result file, and generate a blood flow characteristic result curve according to the taken blood flow characteristic value. The report generating module 914 is further configured to adjust the current spatial coordinates of each point on the centerline to the target spatial coordinates of each point on the centerline in the functional color chart by adjusting the angle of the functional color chart; screenshot is carried out on the adjusted functional color code diagram to obtain a two-dimensional image of the functional color code diagram; and generating an image analysis report according to the blood flow characteristic value, the two-dimensional image of the functional color code diagram and the blood flow characteristic result curve, and sending the image analysis report to a terminal used by a doctor.

In one embodiment, as shown in fig. 10, the vascular medical image analysis processing device 900 further includes:

a results viewing module 918 for displaying a functional color chart view portal and a centerline modification portal through a terminal used by a doctor; when receiving triggering operation of a doctor for checking an entry aiming at the functional color code diagram, displaying the functional color code diagram; when receiving triggering operation of modifying the entrance by a doctor aiming at the central line, displaying the central line and the outline; when receiving the adjustment instruction for the displayed center line and outline sent by the doctor through the terminal, the model generation module 908 is informed to carry out modeling according to the adjusted result, and three-dimensional grids of the blood vessel are generated and the follow-up steps are carried out.

In one embodiment, the data correction user comprises a doctor. The model generation module 908 is further configured to, when receiving a result of the adjustment of the center line and the contour returned by the doctor through the terminal, perform modeling according to the adjusted result, and generate a three-dimensional grid of the blood vessel. The results view module 918 is also used to present an image analysis report view portal through a terminal used by the doctor; when a trigger operation of a doctor for the image analysis report viewing portal is received, the image analysis report is displayed.

In the vascular medical image analysis processing device, the vascular medical image sent by a medical data system or imported by a doctor through a terminal is received, after the image quality of the vascular medical image is detected, the central line and the outline of the blood vessel in the vascular medical image are generated, then the result of the central line and the outline which are returned by a data correction user through the terminal and are adjusted is received, the central line and the outline are adjusted through the data correction user, the accuracy of the central line and the outline is improved, the three-dimensional grid of the blood vessel is generated through modeling according to the adjusted result, the hydrodynamic simulation processing is carried out according to the three-dimensional grid through a cloud computing service, a more accurate simulation result file can be obtained, an accurate three-dimensional functional color code diagram is generated according to the simulation result file and the three-dimensional grid, the blood flow characteristic value at the narrow position of the blood vessel in the three-dimensional grid is accurately determined according to the accurate simulation result file, and an accurate image analysis report is generated according to the determined blood flow characteristic value and the functional color code diagram and is sent to the terminal used by the doctor. The accuracy of analysis and processing of the vascular medical images is improved through a complete scheme of combining an AI algorithm, a hydrodynamic method and a cloud computing technology and an interaction flow of multi-person cooperation and remote assistance among doctors, data correction users and an automatic program. Through cloud computing service, the large-scale batch processing of the system can be improved, and the processing efficiency is improved

For specific limitations of the vascular medical image analysis processing device, reference may be made to the above limitations of the vascular medical image analysis processing method, and no further description is given here. All or part of the modules in the vascular medical image analysis processing device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 11. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing vascular medical image data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize a vascular medical image analysis processing method.

It will be appreciated by those skilled in the art that the structure shown in FIG. 11 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.

Claims

1. A vascular medical image analysis processing method, the method comprising:

determining a blood flow characteristic value at a blood vessel stenosis position in the three-dimensional grid according to the simulation result file;

generating an image analysis report according to the determined blood flow characteristic value and the functional color code diagram, and sending the image analysis report to a terminal used by a doctor, wherein the method comprises the following steps: adjusting the current space coordinates of each point on the central line to the target space coordinates of each point on the central line in the functional color code diagram by adjusting the angle of the functional color code diagram; screenshot is carried out on the adjusted functional color code diagram to obtain a two-dimensional image of the functional color code diagram; and generating an image analysis report according to the blood flow characteristic value, the two-dimensional image of the functional color code diagram and the blood flow characteristic result curve, and sending the image analysis report to a terminal used by a doctor.

2. The method of claim 1, wherein after loading the centerline and profile of the vessel with the data correction user used terminal, the method further comprises:

3. The method of claim 1, wherein after the modeling based on the adjusted results, generating a three-dimensional grid of the blood vessel, the method further comprises:

loading the three-dimensional grid through a terminal used by an auditor;

4. The method of claim 1, wherein generating an image analysis report based on the determined blood flow characteristic value and the functional color code map and transmitting the image analysis report to a terminal used by a doctor comprises:

5. The method of claim 4, wherein generating and transmitting the visual analysis report to the terminal used by the doctor comprises:

generating an image analysis report;

6. The method according to claim 1, wherein the performing, by the cloud computing service, the hydrodynamic simulation processing according to the three-dimensional grid, and the simulation predicting to obtain the simulation result file including the blood flow characteristic values of each point in the three-dimensional grid includes:

obtaining a simulation parameter file;

7. The method of claim 1, wherein after the generating and transmitting an image analysis report to a terminal used by a doctor based on the determined blood flow characteristic value and the functional color code map, the method further comprises:

8. The method of claim 1, wherein the data correction user comprises a doctor;

9. A vascular medical image analysis processing device, the device comprising:

the model generation module is used for modeling according to the adjusted result when receiving the result of the data correction user, which is returned by the terminal and is used for adjusting the center line and the contour, so as to generate a three-dimensional grid of the blood vessel;

The simulation result processing module is used for generating a three-dimensional functional color code diagram according to the simulation result file and the three-dimensional grid; taking blood flow characteristic values along the central line of the blood vessel according to the simulation result file, and generating a blood flow characteristic result curve according to the taken blood flow characteristic values;

the report generating module is used for determining a blood flow characteristic value at a blood vessel stenosis position in the three-dimensional grid according to the simulation result file, generating an image analysis report according to the determined blood flow characteristic value and the functional color code diagram, and sending the image analysis report to a terminal used by a doctor, and comprises the following steps: adjusting the current space coordinates of each point on the central line to the target space coordinates of each point on the central line in the functional color code diagram by adjusting the angle of the functional color code diagram; screenshot is carried out on the adjusted functional color code diagram to obtain a two-dimensional image of the functional color code diagram; and generating an image analysis report according to the blood flow characteristic value, the two-dimensional image of the functional color code diagram and the blood flow characteristic result curve, and sending the image analysis report to a terminal used by a doctor.

10. The apparatus of claim 9, wherein the correction module is further configured to, when receiving a message returned by the data correction user through a terminal for passing the inspection of the center line and the contour, generate a three-dimensional grid of the blood vessel according to the center line and the contour of the blood vessel, and execute the passing cloud computing service, perform a hydrodynamic simulation process according to the three-dimensional grid, and perform subsequent steps.

11. The apparatus of claim 9, wherein the apparatus further comprises:

the auditing module is used for executing the cloud computing service when receiving the message returned by the auditor through the terminal and aiming at the passing of the auditing of the three-dimensional grid, carrying out hydrodynamic simulation processing according to the three-dimensional grid, and carrying out simulation prediction to obtain a simulation result file comprising the blood flow characteristic values of each point in the three-dimensional grid and subsequent steps; and when receiving a message returned by the auditor through the terminal that the audit of the three-dimensional grid is not passed, notifying the correction module to execute the steps of loading the central line and the outline of the blood vessel and the follow-up steps of the terminal used by the pass data correction user until the audit is passed.

12. The apparatus of claim 9, wherein the correction module is further configured to load the functional color code map via a terminal used by the data correction user; when a screenshot instruction which is sent by the data correction user through the terminal and aims at the functional color code image is received, a two-dimensional image of the functional color code image is intercepted according to the screenshot instruction, and an image analysis report is generated according to the blood flow characteristic value and the two-dimensional image of the functional color code image and is sent to the terminal used by the doctor.

13. The apparatus of claim 12, wherein the apparatus further comprises:

the auditing module is used for generating an image analysis report; loading the generated image analysis report through a terminal used by an auditor; when receiving a message returned by the auditor through a terminal and passing the audit of the image analysis report, sending the image analysis report to a terminal used by a doctor; and when receiving a message which is returned by the auditor through the terminal and is not passed by the audit of the image analysis report, notifying the correction module to execute the terminal loading the functional color code diagram and the follow-up steps used by the data correction user until the audit is passed.

14. The apparatus of claim 9, wherein the simulation module is further configured to obtain a simulation parameter file; iteratively performing hydrodynamic simulation processing on the blood vessel according to the simulation parameter file and the three-dimensional grid through cloud computing service to generate a blood flow characteristic value on each grid unit in the three-dimensional grid on each time node; and merging the blood flow characteristic values on each grid unit in the three-dimensional grid in each time node in the last time period to generate a simulation result file.

15. The apparatus of claim 9, wherein the apparatus further comprises:

the result viewing module is used for displaying a functional color code diagram viewing inlet and a central line modification inlet through a terminal used by the doctor; when receiving triggering operation of the doctor for checking the entrance to the functional color code diagram, displaying the functional color code diagram; when a trigger operation of modifying an entry by the doctor for the center line is received, the center line and the outline are displayed; when receiving the adjustment instruction for the displayed central line and the profile sent by the doctor through the terminal, correspondingly adjusting the central line and the profile, informing the model generating module to return to execute the modeling according to the adjusted result, and generating the three-dimensional grid of the blood vessel and the subsequent steps.

16. The apparatus of claim 9, wherein the data correction user comprises a doctor; the model generation module is also used for modeling according to the adjusted result when receiving the result of the adjustment of the central line and the profile returned by the doctor through the terminal, and generating a three-dimensional grid of the blood vessel;

The apparatus further comprises:

the result viewing module is used for displaying an image analysis report viewing inlet through a terminal used by the doctor; the visual analysis report is presented upon receipt of a trigger operation by the physician for the visual analysis report viewing portal.

17. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 8 when the computer program is executed.

18. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 8.