Closed-angle glaucoma disease progress prompting method, device and equipment and storage medium

Abstract

The invention relates to the technical field of medical information processing, and discloses a closed-angle glaucoma disease progress prompting method, device and equipment and a storage medium, and the method comprises the steps: obtaining a fundus photo of a target object; performing recognition detection on the fundus photo by using an image recognition neural network model to obtain a target retinal blood vessel parameter of the target object, the target retinal blood vessel parameters comprise at least one of an artery blood vessel branch included angle asymmetric ratio, an artery blood vessel branch index deviation, an artery curve curvature and an artery blood vessel fractal dimension; inputting the target retinal blood vessel parameters into a target information prediction model; and outputting corresponding prompt information based on an output result of the target information prediction model. According to the invention, the user can carry out advanced intervention means such as adjustment of living habits in an earlier stage to ensure the health of eyes.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information processing, and in particular to a method, device, equipment and storage medium for indicating the progression of angle-closure glaucoma. Background Art

[0002] As people pay more and more attention to eye health, more and more people are beginning to realize the importance of regular eye examinations. Regular examinations can not only detect potential eye diseases at an early stage, but also take timely measures to intervene and treat, thereby effectively preventing the disease from worsening. Therefore, it is particularly necessary to provide risk warnings based on eye examination results. Such risk warnings can not only help individuals better understand their eye health, but also guide them to take appropriate prevention and treatment measures, thereby reducing the risk of serious eye diseases.

[0003] However, in the related art, doctors can only remind people to adjust their lifestyle habits based on some clear abnormalities in examination parameters or values ​​close to abnormalities. In the absence of clear abnormalities in examination parameters, it is generally considered to be healthy eyes and no reminder is needed. However, in the case of clear abnormalities in examination parameters or close to abnormalities, these abnormalities are often irreversible, so reminders are needed at an earlier stage to minimize the occurrence of abnormalities. Summary of the invention

[0004] In view of this, the present invention provides a method, device, equipment and storage medium for warning the progression of angle-closure glaucoma to solve the problem that risk warnings cannot be given at an earlier stage to protect the eyes to the greatest extent and avoid abnormalities.

[0005] In a first aspect, the present invention provides a method for indicating angle-closure glaucoma disease progression, the method comprising:

[0006] Obtain fundus photographs of the target subject;

[0007] Using an image recognition neural network model to identify and detect the fundus photograph, and obtain target retinal vascular parameters of the target object, wherein the target retinal vascular parameters include at least one of an asymmetric ratio of an arterial branch angle, an arterial branch index deviation, an arterial curve curvature, and an arterial fractal dimension;

[0008] inputting the target retinal blood vessel parameters into a target information prediction model;

[0009] Based on the output result of the target information prediction model, corresponding prompt information is output.

[0010] In an optional implementation, before the image recognition neural network model is used to identify and detect the fundus photograph to obtain the retinal vascular parameters of the target object, the method further includes:

[0011] Acquire retinal vascular parameters of multiple dimensions, wherein the retinal vascular parameters include arterial angle asymmetry, venous angle asymmetry, arterial branching coefficient, venous branching coefficient, arterial branch angle asymmetry ratio, venous branch angle asymmetry ratio, arterial branching index deviation, venous branching index deviation, arterial tortuosity, venous tortuosity, arterial curve tortuosity, venous curve tortuosity, arterial fractal dimension, venous fractal dimension;

[0012] Constructing a univariate Logistic regression model for each of the retinal vascular parameters to obtain a first significance value of each of the retinal vascular parameters;

[0013] Incorporating the first retinal vascular parameters corresponding to the significance values ​​less than the first preset threshold into a multi-factor Logistic regression model to obtain second significance values ​​of each of the first retinal vascular parameters;

[0014] gradually deleting the first retinal vascular parameter having the largest second significance value until the second significance values ​​corresponding to the remaining first retinal vascular parameters are all smaller than a second preset threshold;

[0015] The remaining first retinal vessel parameters are determined as the target retinal vessel parameters.

[0016] In an optional implementation, before constructing a univariate logistic regression model for each of the retinal vascular parameters to obtain a first significance value of each of the retinal vascular parameters, the method further includes:

[0017] Obtaining a correlation between every two of the retinal vascular parameters, wherein the correlation indicates multicollinearity between the two retinal vascular parameters;

[0018] Multiple regression was used to eliminate multicollinearity among the retinal vascular parameters.

[0019] In an optional embodiment, before inputting the target retinal vessel parameters into the target information prediction model, the method further includes:

[0020] Acquire retinal vascular parameters of multiple dimensions and corresponding information labels, wherein the retinal vascular parameters include arterial angle asymmetry, venous angle asymmetry, arterial branching coefficient, venous branching coefficient, arterial branch angle asymmetry ratio, venous branch angle asymmetry ratio, arterial branch index deviation, venous branch index deviation, arterial tortuosity, venous tortuosity, arterial curve tortuosity, venous curve tortuosity, arterial fractal dimension, venous fractal dimension;

[0021] Constructing initial information prediction model;

[0022] Using the retinal vascular parameters of the multiple dimensions as training samples and using the information labels to train the initial information prediction model;

[0023] Performing an interpretability analysis on the trained initial information prediction model;

[0024] According to the interpretability analysis result, the target retinal vascular parameters are screened out from the retinal vascular parameters of the multiple dimensions.

[0025] In an optional embodiment, inputting the target retinal blood vessel parameters into a target information prediction model comprises:

[0026] Acquiring intraocular pressure parameters and vertical cup-to-disc ratio of the target object;

[0027] The intraocular pressure parameter, the vertical cup-to-disc ratio, and the target retinal vessel parameter are input into the target information prediction model.

[0028] In an optional embodiment, the image recognition neural network model is a visual transformer model.

[0029] In an optional implementation, the target information prediction model includes a multi-layer perceptron.

[0030] In a second aspect, the present invention provides a device for indicating the progression of angle-closure glaucoma, the device comprising:

[0031] An image acquisition module is used to acquire fundus photos of the target object;

[0032] An image recognition module, used to identify and detect the fundus photograph using an image recognition neural network model to obtain target retinal vascular parameters of the target object, wherein the target retinal vascular parameters include at least one of an asymmetric ratio of an arterial branch angle, an arterial branch index deviation, an arterial curve curvature, and an arterial fractal dimension;

[0033] An information prediction module, used for inputting the target retinal blood vessel parameters into a target information prediction model;

[0034] The prompt module is used to output corresponding prompt information based on the output result of the target information prediction model.

[0035] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for indicating the progression of angle-closure glaucoma according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the angle-closure glaucoma disease progression prompting method of the first aspect or any corresponding embodiment thereof.

[0037] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the angle-closure glaucoma disease progression prompting method of the first aspect or any corresponding embodiment thereof.

[0038] The angle-closure glaucoma disease progression prompt method, device, equipment and storage medium provided in the embodiments of the present invention can obtain at least one of the retinal vascular parameters such as the asymmetric ratio of the arterial branch angle, the deviation of the arterial branch index, the curvature of the arterial curve and the fractal dimension of the arterial vessel based on the fundus photograph, and then provide prompts based on the obtained retinal vascular parameters. The embodiments of the present invention newly propose to provide eye health information prompts based on retinal vascular parameters such as the asymmetric ratio of the arterial branch angle, the deviation of the arterial branch index, the curvature of the arterial curve and the fractal dimension of the arterial vessel, so that users can adjust their living habits based on the prompt information and take other early intervention measures to ensure eye health. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 is a schematic flow chart of a method for indicating angle-closure glaucoma disease progression according to an embodiment of the present invention;

[0041] Figure 2 is a schematic diagram of the ROC curve, sensitivity and specificity of the target information prediction model according to an embodiment of the present invention;

[0042] Figure 3 is a structural block diagram of a device for indicating the progression of angle-closure glaucoma according to an embodiment of the present invention;

[0043] Figure 4 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0045] According to an embodiment of the present invention, an embodiment of a method for indicating the progression of angle-closure glaucoma disease is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of executable computer instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0046] In this embodiment, a method for prompting the progression of angle-closure glaucoma (also referred to as a medical information prompting method) is provided, which can be used in various computer devices, and the computer device can be a medical device. Figure 1 is a flow chart of a method for prompting angle-closure glaucoma disease progression according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0047] Step S101, obtain fundus photographs of the target object. Specifically, a 45-degree digital fundus camera can be used to take fundus photographs to obtain binocular fundus stereoscopic photographs, including two 45-degree fundus photographs (one with the optic disc as the center and one with the macula as the center). The spatial resolution of each photograph is 3072×2048 pixels.

[0048] Step S102, using an image recognition neural network model to identify and detect the fundus photograph to obtain target retinal vascular parameters of the target object, wherein the target retinal vascular parameters include at least one of an arterial branch angle asymmetry ratio, an arterial branch index deviation, an arterial curve curvature, and an arterial fractal dimension.

[0049] In some optional specific implementations, the image recognition neural network model can be a vision transformer model (ViT), or a neural network model in an automatic computer-assisted program (Retinal-based Microvascular Health Assessment System, RMHAS).

[0050] Step S103: input the target retinal blood vessel parameters into a target information prediction model.

[0051] In some optional specific implementations, the target information prediction model may include a multilayer perceptron (MLP). The target information prediction model may also be a convolutional neural network (CNN) or a recurrent neural network (RNN).

[0052] Step S104, based on the output result of the target information prediction model, output corresponding prompt information. The prompt information includes first prompt information and second prompt information, the first prompt information indicates that the eye is healthy and no intervention is required, and the second prompt information indicates that preventive intervention is required. The output result is used to indicate whether the angle-closure glaucoma disease may progress to glaucomatous optic neuropathy (GON). Accordingly, the target object is an object with angle-closure glaucoma.

[0053] The angle-closure glaucoma disease progression prompting method provided in this embodiment can obtain at least one of the retinal vascular parameters such as the asymmetric ratio of the arterial branch angle, the deviation of the arterial branch index, the curvature of the arterial curve, and the fractal dimension of the arterial vessel based on the fundus photograph, and then provide prompts based on the obtained retinal vascular parameters. The embodiment of the present invention newly proposes to provide eye health information prompts based on retinal vascular parameters such as the asymmetric ratio of the arterial branch angle, the deviation of the arterial branch index, the curvature of the arterial curve, and the fractal dimension of the arterial vessel, so that users can adjust their living habits based on the prompt information and other early intervention measures to ensure eye health.

[0054] In some optional specific implementations, before using the image recognition neural network model to identify and detect the fundus photograph to obtain the retinal vascular parameters of the target object, the method further includes:

[0055] Acquire retinal vascular parameters of multiple dimensions, wherein the retinal vascular parameters include arterial angle asymmetry, venous angle asymmetry, arterial branching coefficient, venous branching coefficient, arterial branch angle asymmetry ratio, venous branch angle asymmetry ratio, arterial branching index deviation, venous branching index deviation, arterial tortuosity, venous tortuosity, arterial curve tortuosity, venous curve tortuosity, arterial fractal dimension, venous fractal dimension;

[0056] Constructing a univariate Logistic regression model for each of the retinal vascular parameters to obtain a first significance value of each of the retinal vascular parameters;

[0057] Incorporating the first retinal vascular parameters corresponding to the significance values ​​less than the first preset threshold into a multi-factor Logistic regression model to obtain second significance values ​​of each of the first retinal vascular parameters;

[0058] gradually deleting the first retinal vascular parameter having the largest second significance value until the second significance values ​​corresponding to the remaining first retinal vascular parameters are all smaller than a second preset threshold;

[0059] The remaining first retinal vessel parameters are determined as the target retinal vessel parameters.

[0060] In the embodiment of the present invention, single factor and multi-factor Backward Logistic Regression (BLR) deep learning model algorithms are used to screen parameters. First, single factor logistic regression (implemented by SPSS statistical software) is used to determine the correlation between 14 retinal vascular parameters and eye health (e.g., whether GON occurs) (14 retinal vascular parameters are used as independent variables, and the dependent variable is whether the eyes are healthy), and retinal parameters with a P value of <0.05 are obtained. These parameters are then included in the multi-factor BLR regression (implemented by SPSS software), and finally 4 retinal vascular parameters related to eye health with a P value of <0.05 in the multi-factor regression results are obtained.

[0061] In some optional specific implementations, before constructing a univariate logistic regression model for each of the retinal vascular parameters to obtain a first significance value of each of the retinal vascular parameters, the method further includes:

[0062] Obtaining a correlation between every two of the retinal vascular parameters, wherein the correlation indicates multicollinearity between the two retinal vascular parameters;

[0063] Multiple regression was used to eliminate multicollinearity among the retinal vascular parameters.

[0064] In some other optional specific implementations, before inputting the target retinal vascular parameters into the target information prediction model, the method further includes:

[0065] Acquire retinal vascular parameters of multiple dimensions and corresponding information labels, wherein the retinal vascular parameters include arterial angle asymmetry (angular asymmetry, AA), venous angle asymmetry, arterial branching coefficient (branching coefficient), venous branching coefficient, arterial branch angle asymmetry ratio (asymmetry ratio, AR), venous branch angle asymmetry ratio, arterial branching index deviation (also known as junctional exponent deviation, JED), venous branching index deviation, arterial tortuosity (tortuosity), venous tortuosity, arterial curve tortuosity (curve tortuosity, CT), venous curve tortuosity, arterial fractal dimension (fractal dimension, FD), venous fractal dimension;

[0066] Constructing initial information prediction model;

[0067] Using the retinal vascular parameters of the multiple dimensions as training samples and using the information labels to train the initial information prediction model;

[0068] Performing an interpretability analysis on the trained initial information prediction model;

[0069] According to the interpretability analysis result, the target retinal vascular parameters are screened out from the retinal vascular parameters of the multiple dimensions.

[0070] In some optional specific implementations, inputting the target retinal blood vessel parameters into a target information prediction model comprises:

[0071] Acquiring intraocular pressure parameters and vertical cup-to-disc ratio of the target object;

[0072] The intraocular pressure parameter, the vertical cup-to-disc ratio, and the target retinal vessel parameter are input into the target information prediction model.

[0073] In the embodiment of the present invention, the target information prediction model is a deep learning model. The target information prediction model predicts medical information based on the combined indicators of intraocular pressure, fundus vertical cup-disc ratio, and AR, JED, CT, and FD of retinal arterial vessels, such as Figure 2As shown, the area under the ROC curve is as high as 0.935, the sensitivity is 82.73%, and the specificity is 92.68%, that is, the judgment efficiency is high. The ROC curve, sensitivity and specificity can be obtained through medical statistical software (MedCalc).

[0074] In this embodiment, a device for indicating the progression of angle-closure glaucoma is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0075] This embodiment provides a device for indicating the progression of angle-closure glaucoma. Figure 3 As shown, including:

[0076] The picture acquisition module 301 is used to acquire the fundus photo of the target object;

[0077] An image recognition module 302 is used to recognize and detect the fundus photograph using an image recognition neural network model to obtain target retinal vascular parameters of the target object, wherein the target retinal vascular parameters include at least one of an asymmetric ratio of an arterial branch angle, an arterial branch index deviation, an arterial curve curvature, and an arterial fractal dimension;

[0078] An information prediction module 303, used for inputting the target retinal blood vessel parameters into a target information prediction model;

[0079] The prompt module 304 is used to output corresponding prompt information based on the output result of the target information prediction model.

[0080] In some optional embodiments, the angle-closure glaucoma disease progression prompting device further comprises:

[0081] An initial retinal vascular parameter acquisition module is used to acquire retinal vascular parameters of multiple dimensions, wherein the retinal vascular parameters include arterial angle asymmetry, venous angle asymmetry, arterial branching coefficient, venous branching coefficient, arterial branch angle asymmetry ratio, venous branch angle asymmetry ratio, arterial branch index deviation, venous branch index deviation, arterial tortuosity, venous tortuosity, arterial curve tortuosity, venous curve tortuosity, arterial fractal dimension, venous fractal dimension;

[0082] A first significance value acquisition module, used for constructing a single factor Logistic regression model for each of the retinal vascular parameters to obtain a first significance value of each of the retinal vascular parameters;

[0083] a second significance value acquisition module, configured to incorporate the first retinal vascular parameters corresponding to the significance values ​​less than the first preset threshold into a multi-factor Logistic regression model, and acquire a second significance value of each of the first retinal vascular parameters;

[0084] a deleting module, configured to gradually delete the first retinal vascular parameter having the largest second significance value, until the second significance values ​​corresponding to the remaining first retinal vascular parameters are all smaller than a second preset threshold;

[0085] A parameter determination module is used to determine the remaining first retinal blood vessel parameters as the target retinal blood vessel parameters.

[0086] In some optional embodiments, the angle-closure glaucoma disease progression prompting device further comprises:

[0087] A correlation acquisition module, used for acquiring the correlation between every two of the retinal vascular parameters, wherein the correlation indicates multicollinearity between the two retinal vascular parameters;

[0088] The elimination module is used to eliminate the multicollinearity between the retinal vascular parameters using a multiple regression method.

[0089] In some optional embodiments, the angle-closure glaucoma disease progression prompting device further comprises:

[0090] A sample data acquisition module is used to acquire retinal vascular parameters of multiple dimensions and corresponding information labels, wherein the retinal vascular parameters include arterial angle asymmetry, venous angle asymmetry, arterial branching coefficient, venous branching coefficient, arterial branch angle asymmetry ratio, venous branch angle asymmetry ratio, arterial branch index deviation, venous branch index deviation, arterial tortuosity, venous tortuosity, arterial curve tortuosity, venous curve tortuosity, arterial fractal dimension, venous fractal dimension;

[0091] The initial module building module is used to build the initial information prediction model;

[0092] A training module, used to use the retinal vascular parameters of the multiple dimensions as training samples and to train the initial information prediction model using the information labels;

[0093] An analysis module, used for performing an interpretability analysis on the trained initial information prediction model;

[0094] The parameter screening module is used to screen the target retinal vascular parameters from the retinal vascular parameters of the multiple dimensions according to the interpretability analysis result.

[0095] In some optional specific implementations, the information prediction module 303 includes:

[0096] A parameter value acquisition unit, used to acquire an intraocular pressure parameter and a vertical cup-to-disc ratio of the target object;

[0097] A prediction unit is used to input the intraocular pressure parameter, the vertical cup-to-disc ratio, and the target retinal vessel parameter into the target information prediction model.

[0098] In some optional specific embodiments, the image recognition neural network model is a visual transformer model.

[0099] In some optional specific implementations, the target information prediction model includes a multi-layer perceptron.

[0100] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0101] The angle-closure glaucoma disease progression prompting device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0102] The embodiment of the present invention also provides a computer device having the above Figure 3 Angle-closure glaucoma disease progression reminder device shown.

[0103] See also Figure 4 , Figure 4 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 4As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0104] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0105] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0106] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0107] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0108] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0109] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0110] The computer device also includes a communication interface, which is used for the computer device to communicate with other devices or a communication network.

[0111] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0112] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0113] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for indicating the progression of angle-closure glaucoma, characterized in that: The method comprises: Obtain fundus photographs of the target subject; Using an image recognition neural network model to identify and detect the fundus photograph, and obtain target retinal vascular parameters of the target object, wherein the target retinal vascular parameters include at least one of an asymmetric ratio of an arterial branch angle, an arterial branch index deviation, an arterial curve curvature, and an arterial fractal dimension; inputting the target retinal blood vessel parameters into a target information prediction model; Based on the output result of the target information prediction model, corresponding prompt information is output.

2. The method according to claim 1, characterized in that Before the image recognition neural network model is used to identify and detect the fundus photograph to obtain the retinal vascular parameters of the target object, the method further includes: Acquire retinal vascular parameters of multiple dimensions, wherein the retinal vascular parameters include arterial angle asymmetry, venous angle asymmetry, arterial branching coefficient, venous branching coefficient, arterial branch angle asymmetry ratio, venous branch angle asymmetry ratio, arterial branching index deviation, venous branching index deviation, arterial tortuosity, venous tortuosity, arterial curve tortuosity, venous curve tortuosity, arterial fractal dimension, venous fractal dimension; Constructing a univariate Logistic regression model for each of the retinal vascular parameters to obtain a first significance value of each of the retinal vascular parameters; Incorporating the first retinal vascular parameters corresponding to the significance values ​​less than the first preset threshold into a multi-factor Logistic regression model to obtain second significance values ​​of each of the first retinal vascular parameters; gradually deleting the first retinal vascular parameter having the largest second significance value until the second significance values ​​corresponding to the remaining first retinal vascular parameters are all smaller than a second preset threshold; The remaining first retinal vessel parameters are determined as the target retinal vessel parameters.

3. The method according to claim 2, characterized in that Before constructing a single factor Logistic regression model for each of the retinal vascular parameters to obtain a first significance value of each of the retinal vascular parameters, the method further includes: Obtaining a correlation between every two of the retinal vascular parameters, wherein the correlation indicates multicollinearity between the two retinal vascular parameters; Multiple regression was used to eliminate multicollinearity among the retinal vascular parameters.

4. The method according to claim 1, characterized in that: Before inputting the target retinal blood vessel parameters into the target information prediction model, the method further includes: Acquire retinal vascular parameters of multiple dimensions and corresponding information labels, wherein the retinal vascular parameters include arterial angle asymmetry, venous angle asymmetry, arterial branching coefficient, venous branching coefficient, arterial branch angle asymmetry ratio, venous branch angle asymmetry ratio, arterial branch index deviation, venous branch index deviation, arterial tortuosity, venous tortuosity, arterial curve tortuosity, venous curve tortuosity, arterial fractal dimension, venous fractal dimension; Constructing initial information prediction model; Using the retinal vascular parameters of the multiple dimensions as training samples and using the information labels to train the initial information prediction model; Performing an interpretability analysis on the trained initial information prediction model; According to the interpretability analysis result, the target retinal vascular parameters are screened out from the retinal vascular parameters of the multiple dimensions.

5. The method according to claim 1, characterized in that The step of inputting the target retinal blood vessel parameters into a target information prediction model comprises: Acquiring intraocular pressure parameters and vertical cup-to-disc ratio of the target object; The intraocular pressure parameter, the vertical cup-to-disc ratio, and the target retinal vessel parameter are input into the target information prediction model.

6. The method according to claim 1, characterized in that The image recognition neural network model is a visual transformer model.

7. The method according to claim 1, characterized in that The target information prediction model includes a multi-layer perceptron.

8. A device for indicating the progression of angle-closure glaucoma, characterized in that: The device comprises: An image acquisition module is used to acquire fundus photos of the target object; An image recognition module, used to identify and detect the fundus photograph using an image recognition neural network model to obtain target retinal vascular parameters of the target object, wherein the target retinal vascular parameters include at least one of an asymmetric ratio of an arterial branch angle, an arterial branch index deviation, an arterial curve curvature, and an arterial fractal dimension; An information prediction module, used for inputting the target retinal blood vessel parameters into a target information prediction model; The prompt module is used to output corresponding prompt information based on the output result of the target information prediction model.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images