Aortic valve bilobal malformation diagnosis and treatment suggestion generation method and system

Abstract

The invention discloses an aortic valve bilobal malformation diagnosis and treatment suggestion generation method and system, and relates to the field of intelligent medical treatment, and the method comprises the steps: obtaining aorta computed tomography data and bilobal aortic valve ultrasonic image data of a target patient; according to the aorta computed tomography data and the two-leaf aortic valve ultrasonic image data, constructing an aorta root model; based on the aorta root model, adopting a machine learning method to carry out hemodynamic calculation to obtain hemodynamic parameters; according to the hemodynamic parameters, a regression model and a clustering algorithm are adopted to generate diagnosis and treatment suggestions of the target patient. The accuracy and generation efficiency of the diagnosis and treatment suggestions are improved.

Description

Technical Field

[0001] The present application relates to the field of smart medical care, and in particular to a method and system for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation. Background Art

[0002] Bicuspid Aortic Valve (BAV) is a common type of congenital heart disease, which may lead to aortic valve stenosis or regurgitation, and then cause a series of serious circulatory system problems. At present, the diagnosis of BAV and acute aortic dissection (AAD) mainly relies on imaging examinations such as computed tomography (CTA) and echocardiography, while the choice of treatment plan needs to comprehensively consider the patient's specific condition, physiological and pathological characteristics, and hemodynamic parameters. However, the traditional diagnosis and treatment process is often time-consuming and largely depends on the doctor's subjective experience, which limits the accuracy of diagnosis and the effectiveness of treatment.

[0003] Therefore, it is particularly important to develop a system that can quickly and accurately diagnose BAV based on multimodal imaging data and assist in making treatment decisions. Summary of the invention

[0004] The purpose of this application is to provide a method and system for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation, which can improve the efficiency and accuracy of generating diagnosis and treatment recommendations.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation, comprising:

[0007] Obtaining aortic computed tomography data and bicuspid aortic valve ultrasound imaging data of the target patient;

[0008] constructing an aortic root model according to the aortic computed tomography data and the bicuspid aortic valve ultrasound image data;

[0009] Based on the aortic root model, a machine learning method is used to perform hemodynamic calculations to obtain hemodynamic parameters;

[0010] Based on the hemodynamic parameters, a regression model and a clustering algorithm are used to generate diagnosis and treatment recommendations for the target patient.

[0011] In a second aspect, the present application provides a system for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation, comprising:

[0012] a computer tomography device for acquiring computer tomography data of an aorta of a target patient;

[0013] An ultrasound device, used to collect ultrasound imaging data of a bicuspid aortic valve of a target patient;

[0014] The processor is connected to the computer tomography device and the ultrasound device, respectively, and is used to construct an aortic root model based on the aortic computer tomography data and the bicuspid aortic valve ultrasound image data; based on the aortic root model, a machine learning method is used to perform hemodynamic calculations to obtain hemodynamic parameters; based on the hemodynamic parameters, a regression model and a clustering algorithm are used to generate diagnosis and treatment recommendations for target patients.

[0015] According to the specific embodiments provided in this application, this application has the following technical effects:

[0016] The present application provides a method and system for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation. Based on the patient's aortic computed tomography data and bicuspid aortic valve ultrasound image data, an accurate aortic root model is constructed. A machine learning method is used to quickly and accurately perform hemodynamic calculations, and a regression model and clustering algorithm are used to generate diagnosis and treatment recommendations for target patients, thereby reducing subjective judgment errors and improving the accuracy and generation efficiency of diagnosis and treatment recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 An overall flow chart of a method for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation provided in one embodiment of the present application;

[0019] Figure 2 A detailed flow chart of a method for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation provided in one embodiment of the present application;

[0020] Figure 3 This is a schematic diagram of a process for determining a risk decision level in an embodiment of the present application;

[0021] Figure 4 A schematic diagram of the structure of a system for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation provided in one embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0023] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0024] In an exemplary embodiment, Figure 1 and Figure 2 As shown, a method for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation is provided, including the following steps 101 to 104.

[0025] Step 101, obtaining aortic computed tomography data and bicuspid aortic valve ultrasound image data of a target patient.

[0026] The aortic root of the target patient is scanned using a CTA device to obtain aortic computed tomography data.

[0027] Step 102: construct an aortic root model based on the aortic computed tomography data and the bicuspid aortic valve ultrasound image data.

[0028] In an exemplary embodiment, step 102 includes the following steps 201 to 204 .

[0029] Step 201: establishing an aortic root vascular model based on the aortic computed tomography data.

[0030] Specifically, a personalized aortic root vascular model is established using a three-dimensional reconstruction method based on aortic computed tomography data, wherein a convolutional neural network is used to achieve rapid segmentation and reconstruction of the patient's aortic root vascular CTA image.

[0031] Step 202: establishing a parameterized bicuspid aortic valve model according to the bicuspid aortic valve ultrasound image data.

[0032] Specifically, based on the geometric data measured by ultrasound imaging data of the bicuspid aortic valve, a parametric bicuspid aortic valve model was constructed using Computer Aided Design (CAD) forward engineering technology. The valve parameters included include BAV phenotype, valve ring diameter, joint height, geometric height, free edge length and sinotubular junction diameter.

[0033] Step 203: determining the valve offset angle and valve offset height according to the bicuspid aortic valve ultrasound image data.

[0034] Step 204 , performing Boolean operation assembly on the aortic root vascular model and the parameterized bicuspid aortic valve model according to the valve offset angle and the valve offset height, to obtain an aortic root model.

[0035] During the assembly process, the valve offset angle and valve offset height are used as assembly parameters to construct a complete aortic root geometry, providing an accurate geometric basis for subsequent hemodynamic calculations.

[0036] Step 103: Based on the aortic root model, a machine learning method is used to perform hemodynamic calculations to obtain hemodynamic parameters, thereby providing important physiological parameters for diagnosis and treatment decisions.

[0037] This application is based on the aortic root model and uses relevant hemodynamic deep learning algorithms to achieve rapid fluid-solid coupling calculation of personalized aortic hemodynamic parameters for BAV patients.

[0038] In an exemplary embodiment, the machine learning method is a physical embedding neural network. The physical equation (Navier-Stokes equation, NS equation) is used as part of the loss function of the deep learning neural network to form a physical embedding neural network. The loss function after the NS equation is embedded is:

[0039] Loss = loss data +ω*loss physics ;

[0040]

[0041] Among them, Loss is the total loss function value, loss data is the data fitting term, ω is the physical consistency coefficient, and loss physics is the physical consistency term, N data is the number of training set samples, U true (X j ,t j ) is the true value of the sample point, U pred (X j ,t j ) is the predicted value of the sample point, X j is the spatial coordinate, t j is the time coordinate, e i (X j ,t j ) is the difference between the solution predicted by the neural network and the actual solution to the NS equation.

[0042] The physical embedded neural network is trained in advance using a form-force response database, which includes hemodynamic simulation data corresponding to different bicuspid deformity phenotypes.

[0043] In an exemplary embodiment, the hemodynamic parameters include pre-operative hemodynamic parameters and post-operative hemodynamic parameters. Step 103 includes the following steps 301 to 303 .

[0044] Step 301 : performing a virtual surgery based on the aortic root model to obtain the aortic root model after the virtual surgery.

[0045] Step 302: Based on the aortic root model, a machine learning method is used to perform hemodynamic calculations to obtain pre-operative hemodynamic parameters.

[0046] Step 303, based on the aortic root model after the virtual operation, a machine learning method is used to perform hemodynamic calculations to obtain postoperative hemodynamic parameters.

[0047] This application further integrates the clinical physiological and pathological database, the form-force response database and the virtual surgery database to provide comprehensive information support for hemodynamic calculations.

[0048] Through the existing clinical BAV case data and the patient's aortic computational fluid dynamics results, a clinical physiological and pathological database and a form-force response database are constructed. Specifically, the form-force response database is constructed using computational fluid dynamics technology and the aortic root model. Virtual surgery is performed using clinical BAV case data and CAD technology, and a virtual surgery database is established to provide data set support for machine learning algorithms.

[0049] The form-force response database includes classification data of different BAV phenotypes based on a large number of historical case analyses, and divides BAV phenotypes into fusion type, symmetric type, and partially fusion type. The aortic hemodynamic simulation data of BAV patients with different phenotypes are classified to construct a form-force response database. Different form-force response databases are established for different phenotype types, and different types of databases are directly corresponding to patients with different BAV phenotypes in clinical applications.

[0050] The clinical physiological and pathological database is collected through patient visits, mainly including age, gender, medical history, surgical history, aortic valve auscultation area murmur, nature and degree of heart murmur, symptoms such as chest pain, dyspnea, syncope, blood pressure, heart rate, heart rhythm, etc.

[0051] In building a virtual surgery database, CAD technology is used to create highly accurate three-dimensional models of the aortic root and valve. These models not only provide a solid foundation for virtual surgery, but also allow doctors to simulate and evaluate different surgical options before surgery, such as valve repair or replacement, thereby optimizing treatment plans and improving surgical success rates. In addition, the virtual surgery database achieves continuous optimization and updating of surgical plans by accumulating actual surgical case data and analyzing it using machine learning algorithms.

[0052] Step 104: Generate diagnosis and treatment recommendations for the target patient using a regression model and a clustering algorithm based on the hemodynamic parameters.

[0053] In an exemplary embodiment, first, based on the preoperative hemodynamic parameters and the postoperative hemodynamic parameters, a regression model is used to determine the influence coefficients of different parts. Then, based on the influence coefficients of different parts and the clinical information of the target patient, a clustering algorithm is used to determine the diagnosis and treatment recommendations for the target patient. The diagnosis and treatment recommendations include reference treatment plans and reference surgical strategies.

[0054] like Figure 3 As shown, firstly, the regression model is used to take the hemodynamic parameters of the aortic arch, ascending aorta, sinus, left ventricle, and coronary artery of the patient before and after the virtual operation as input for principal component analysis and correlation coefficient feature extraction, and the influence coefficients of different parts are obtained. These influence coefficients and the clinical information of the patient (gender, age, medical history, BAV classification, etc.) are used as input features of the clustering algorithm (or decision tree), and the risk decision level (such as level one, two, and three) is given through the clustering algorithm (or decision tree), thereby improving the accuracy and stability of the diagnosis and treatment evaluation decision reasoning results in the treatment of BAV-AAD patients.

[0055] Furthermore, the method for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation also includes step 105.

[0056] Step 105 , visualizing the aortic computed tomography data, the bicuspid aortic valve ultrasound image data, the aortic root model, the hemodynamic parameters, and the diagnosis and treatment recommendations.

[0057] This application builds an accurate aortic root model by integrating multimodal imaging data processing and three-dimensional reconstruction technology. It combines clinical physiological and pathological databases, shape-force response databases, and virtual surgery databases. It can quickly calculate hemodynamic parameters through machine learning methods, and uses regression models and clustering algorithms to generate diagnosis and treatment recommendations for target patients, thereby improving the accuracy and efficiency of diagnosis and treatment recommendations, reducing doctors' subjective judgment errors, and greatly shortening the time required in traditional diagnostic processes. It also helps in the rational allocation of medical resources, especially in areas with limited resources. In addition, decision-making diagnostic opinions are provided based on the patient's personalized clinical information. Accurate diagnosis and personalized treatment recommendations help improve patients' treatment experience and satisfaction, and provide an efficient and accurate auxiliary tool for the diagnosis and treatment of BAV-AAD patients.

[0058] Based on the same inventive concept, the embodiment of the present application also provides a system for generating aortic valve bicuspid malformation diagnosis and treatment suggestions for implementing the above-mentioned method for generating aortic valve bicuspid malformation diagnosis and treatment suggestions. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the system for generating aortic valve bicuspid malformation diagnosis and treatment suggestions provided below can refer to the limitations of the method for generating aortic valve bicuspid malformation diagnosis and treatment suggestions above, and will not be repeated here.

[0059] In an exemplary embodiment, Figure 4 As shown, a system for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation is provided, including: a computer tomography device 401, an ultrasound device 402 and a processor 403.

[0060] The computer tomography device 401 is used to acquire aorta computer tomography data of a target patient.

[0061] The ultrasound device 402 is used to collect ultrasound image data of the bicuspid aortic valve of the target patient.

[0062] The processor 403 is connected to the computed tomography device 401 and the ultrasound device 402, respectively, and is used to construct an aortic root model based on the aortic computed tomography data and the bicuspid aortic valve ultrasound image data; based on the aortic root model, a machine learning method is used to perform hemodynamic calculations to obtain hemodynamic parameters; based on the hemodynamic parameters, a regression model and a clustering algorithm are used to generate diagnosis and treatment recommendations for target patients.

[0063] Furthermore, the bicuspid aortic valve malformation diagnosis and treatment recommendation generation system also includes a terminal 404.

[0064] The terminal 404 is connected to the processor 403, and is used to display the aortic computed tomography data, the bicuspid aortic valve ultrasound image data, the aortic root model, the hemodynamic parameters and the diagnosis and treatment recommendations.

[0065] Furthermore, the bicuspid aortic valve malformation diagnosis and treatment suggestion generation system further includes a database 405 . The processor 403 is connected to the database 405 .

[0066] Processor 403 is also used to optimize aortic computed tomography data and bicuspid aortic valve ultrasound image data. Processor 403 simulates hemodynamics under different physiological conditions. Processor 403 is deployed on a cloud computing platform for remote access and use.

[0067] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0068] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0069] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0070] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0071] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0072] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for generating diagnosis and treatment recommendations for bicuspid aortic valve malformation, characterized in that: The method for generating a diagnosis and treatment recommendation for bicuspid aortic valve comprises: Obtaining aortic computed tomography data and bicuspid aortic valve ultrasound imaging data of the target patient; constructing an aortic root model according to the aortic computed tomography data and the bicuspid aortic valve ultrasound image data; Based on the aortic root model, a machine learning method is used to perform hemodynamic calculations to obtain hemodynamic parameters; Based on the hemodynamic parameters, a regression model and a clustering algorithm are used to generate diagnosis and treatment recommendations for the target patient.

2. The method for generating diagnosis and treatment recommendations for bicuspid aortic valve according to claim 1, characterized in that: Constructing an aortic root model according to the aortic computed tomography data and the bicuspid aortic valve ultrasound image data, specifically comprising: establishing an aortic root vascular model according to the aortic computed tomography data; Establishing a parameterized bicuspid aortic valve model according to the bicuspid aortic valve ultrasound image data; Determining a valve offset angle and a valve offset height according to the bicuspid aortic valve ultrasound image data; According to the valve offset angle and the valve offset height, the aortic root vascular model and the parameterized bicuspid aortic valve model are assembled by Boolean operation to obtain an aortic root model.

3. The method for generating diagnosis and treatment recommendations for bicuspid aortic valve according to claim 1, characterized in that: The machine learning method is a physical embedding neural network.

4. The method for generating diagnosis and treatment recommendations for bicuspid aortic valve according to claim 3, characterized in that: The physical embedded neural network is pre-trained using a form-force response database; the form-force response database includes hemodynamic simulation data corresponding to different bicuspid deformity phenotypes.

5. The method for generating diagnosis and treatment recommendations for bicuspid aortic valve according to claim 1, characterized in that: The hemodynamic parameters include pre-operative hemodynamic parameters and post-operative hemodynamic parameters; Based on the aortic root model, a machine learning method is used to perform hemodynamic calculations to obtain hemodynamic parameters, including: Performing a virtual surgery based on the aortic root model to obtain an aortic root model after the virtual surgery; Based on the aortic root model, a machine learning method is used to perform hemodynamic calculations to obtain preoperative hemodynamic parameters; Based on the aortic root model after virtual surgery, machine learning methods were used to calculate hemodynamics and obtain postoperative hemodynamic parameters.

6. The method for generating diagnosis and treatment recommendations for bicuspid aortic valve according to claim 5, characterized in that: Based on the hemodynamic parameters, a regression model and a clustering algorithm are used to generate diagnosis and treatment recommendations for the target patient, specifically including: According to the pre-operative hemodynamic parameters and the post-operative hemodynamic parameters, a regression model is used to determine the influence coefficients of different parts; According to the influence coefficients of different parts and the clinical information of target patients, a clustering algorithm is used to determine the diagnosis and treatment recommendations for target patients.

7. The method for generating diagnosis and treatment recommendations for bicuspid aortic valve according to claim 1, characterized in that: The diagnosis and treatment recommendations include reference treatment plans and reference surgical strategies.

8. The method for generating diagnosis and treatment recommendations for bicuspid aortic valve according to claim 1, characterized in that: The method for generating a diagnosis and treatment recommendation for bicuspid aortic valve malformation also includes: The aortic computed tomography data, the bicuspid aortic valve ultrasound image data, the aortic root model, the hemodynamic parameters and the diagnosis and treatment recommendations are visualized.

9. A system for generating diagnosis and treatment suggestions for bicuspid aortic valve malformation, applied to the method for generating diagnosis and treatment suggestions for bicuspid aortic valve malformation according to any one of claims 1 to 8, characterized in that: The aortic valve bicuspid malformation diagnosis and treatment suggestion generation system comprises: a computer tomography device for acquiring computer tomography data of an aorta of a target patient; An ultrasound device, used to collect ultrasound imaging data of a bicuspid aortic valve of a target patient; The processor is connected to the computer tomography device and the ultrasound device, respectively, and is used to construct an aortic root model based on the aortic computer tomography data and the bicuspid aortic valve ultrasound image data; based on the aortic root model, a machine learning method is used to perform hemodynamic calculations to obtain hemodynamic parameters; based on the hemodynamic parameters, a regression model and a clustering algorithm are used to generate diagnosis and treatment recommendations for target patients.

10. The system for generating diagnosis and treatment recommendations for bicuspid aortic valve according to claim 9, characterized in that: The aortic valve bicuspid malformation diagnosis and treatment suggestion generation system further includes: The terminal is connected to the processor and is used to display the aortic computed tomography data, the bicuspid aortic valve ultrasound image data, the aortic root model, the hemodynamic parameters and the diagnosis and treatment recommendations.

Images