KR20210025431A - Method and device for recommending corneal incision parameter - Google Patents

Abstract

The present invention relates to a method of recommending a corneal incision parameter. According to one embodiment of the present invention, a method of recommending a corneal incision parameter by using artificial intelligence performed by a computing device, comprises the following steps of: acquiring a corneal nerve image corresponding to an eyeball of an examinee; calculating output data including a corneal incision parameter including at least one among a corneal incision region and a corneal incision depth by inputting first input data including at least the corneal nerve image to a prediction model, wherein the corneal incision depth includes at least one of full-thickness incision and partial incision; and providing at least part of the output data, wherein the prediction model is trained based on at least one among the type of ophthalmic surgery of a plurality of patients who underwent the ophthalmic surgery performing corneal incision, corneal nerve images before the ophthalmic surgery of the patients, corneal incision parameters during the ophthalmic surgery of the patients, and corneal nerve images after the ophthalmic surgery of the patients.

Description

Method and apparatus for recommending corneal incision parameters {METHOD AND DEVICE FOR RECOMMENDING CORNEAL INCISION PARAMETER}

The present invention relates to a method and apparatus for recommending corneal incision parameters, and more particularly, to a method and apparatus for recommending corneal incision parameters to a subject or the like using artificial intelligence.

Some ophthalmic surgeries involve corneal incisions. For example, when performing vision correction such as LASIK, Smile, and lens implantation, a corneal incision is accompanied. Alternatively, corneal incisions are accompanied for removal and replacement of the lens during cataract surgery.

When the cornea is incised, damage to the corneal nerve occurs. It is known that side effects such as dry eye syndrome may occur due to such corneal nerve damage. When dry eye syndrome occurs, there is a need to minimize side effects by reducing damage to the corneal nerves, as discomfort occurs in daily life, such as increased eye fatigue and periodic instillation of artificial tears.

One task is to recommend corneal incision parameters in order to assist in the judgment of a doctor, a counselor, a subject, and the like.

Another task is to predict the degree of corneal nerve damage in order to assist in the judgment of doctors, counselors, subjects, and the like.

Another task is to calculate the corneal nerve recovery rate in order to assist in the judgment of a doctor, a counselor, a subject, and the like.

The problem to be solved is not limited to the above-described problems, and the problems that are not mentioned will be clearly understood by those of ordinary skill in the art from the present specification and the accompanying drawings.

According to an aspect, there is provided a method for recommending corneal incision parameters using artificial intelligence performed by a computing device, the method comprising: acquiring a corneal nerve image corresponding to an eyeball of a subject; Inputting first input data including at least the corneal nerve image into a prediction model to calculate output data including a corneal incision parameter including at least one of a corneal incision region and a corneal incision depth-the corneal incision depth is a full layer Including at least one of an incision and a partial incision -; And providing at least a part of the output data; including, the prediction model, the type of the ophthalmic surgery of a plurality of recipients who have undergone ophthalmic surgery to perform a corneal incision, the cornea before the ophthalmic surgery of the plurality of recipients A method of recommending a corneal incision parameter learned based on at least one of a nerve image, a corneal incision parameter during the ophthalmic surgery of the plurality of people to be treated, and a corneal nerve image after the ophthalmic surgery of the plurality of people to be treated may be provided.

According to another aspect, there is provided a method for recommending corneal incision parameters using artificial intelligence performed by a computing device, the method comprising: acquiring a corneal nerve image corresponding to an eyeball of a subject; Inputting input data including at least the corneal nerve image into a predictive model to calculate output data including a corneal incision parameter-the corneal incision parameter includes a corneal incision risk area in which corneal incision should be avoided -; And providing at least a part of the output data; including, the prediction model, the type of the ophthalmic surgery of a plurality of recipients who have undergone ophthalmic surgery to perform a corneal incision, the cornea before the ophthalmic surgery of the plurality of recipients A method of recommending a corneal incision parameter learned based on at least one of a nerve image, a corneal incision parameter during the ophthalmic surgery of the plurality of people to be treated, and a corneal nerve image after the ophthalmic surgery of the plurality of people to be treated may be provided.

The solution means of the problem is not limited to the above-described solution means, and solutions that are not mentioned will be clearly understood by those of ordinary skill in the technical field to which the present invention pertains from the present specification and the accompanying drawings. .

According to an embodiment, artificial intelligence for recommending a corneal incision parameter may be provided.

According to another embodiment, artificial intelligence for predicting the degree of corneal nerve damage may be provided.

According to another embodiment, an artificial intelligence for calculating a corneal nerve recovery rate may be provided.

The effects are not limited to the above-described effects, and effects that are not mentioned will be clearly understood by those of ordinary skill in the art from the present specification and the accompanying drawings.

1 is a diagram of a system for recommending a corneal incision parameter according to an embodiment.
2 is a diagram for describing a learning device/prediction device according to an exemplary embodiment.
3 is a diagram illustrating a server device and a client device according to an embodiment.
4 is a diagram illustrating configurations of a server device and a client device according to an embodiment.
5 is a diagram of a model related to a corneal incision according to an exemplary embodiment.
6 is a diagram illustrating a learning step and a prediction step of a corneal incision-related model according to an exemplary embodiment.
7 is a diagram of examples of corneal incision parameters in an image form according to an exemplary embodiment.
8 is a diagram of a corneal incision parameter recommendation model according to an exemplary embodiment.
9 is a diagram illustrating a cuttable area according to an exemplary embodiment.
10 is a diagram of an image matching model according to an exemplary embodiment.
11 to 13 are diagrams illustrating an embodiment of a combination of a corneal incision-related model according to an exemplary embodiment.
14 is a diagram illustrating an embodiment of merging a corneal incision-related model according to an embodiment.
15 is a diagram of a first embodiment of a method for recommending a corneal incision parameter according to an embodiment.
16 is a diagram illustrating a second embodiment of a method for recommending a corneal incision parameter according to an embodiment.
17 is a diagram of a third embodiment of a method for recommending a corneal incision parameter according to an embodiment.
18 is a diagram of a fourth embodiment of a method for recommending a corneal incision parameter according to an embodiment.
19 is a diagram illustrating a method of recommending a corneal incision parameter according to a fifth embodiment.
20 is a diagram illustrating a method for recommending a corneal incision parameter according to a sixth embodiment.

The embodiments described in the present specification are intended to clearly explain the spirit of the present invention to those of ordinary skill in the technical field to which the present invention pertains, so the present invention is not limited by the embodiments described herein, and the present invention The scope of should be construed as including modifications or variations that do not depart from the spirit of the present invention.

The terms used in this specification have been selected as general terms currently widely used in consideration of functions in the present invention, but this varies according to the intention, custom, or the emergence of new technologies of those of ordinary skill in the technical field to which the present invention belongs. I can. However, if a specific term is defined and used in an arbitrary meaning unlike this, the meaning of the term will be separately described. Therefore, the terms used in the present specification should be interpreted based on the actual meaning of the term and the entire contents of the present specification, not a simple name of the term.

The drawings attached to the present specification are for easy explanation of the present invention, and the shapes shown in the drawings may be exaggerated and displayed as necessary to aid understanding of the present invention, so the present invention is not limited by the drawings.

In the present specification, when it is determined that a detailed description of a well-known configuration or function related to the present invention may obscure the subject matter of the present invention, a detailed description thereof will be omitted as necessary. In addition, numbers (eg, first, second, etc.) used in the process of the name of the present specification may mean different configurations, but may correspond to the same configuration.

Hereinafter, a method and apparatus for recommending a corneal incision parameter based on a corneal nerve image will be described. In particular, a method and apparatus for generating a model for recommending a corneal incision parameter using artificial intelligence and for recommending a corneal incision parameter using the generated model will be described. This model can be used in ophthalmic surgery involving corneal incisions. For example, it may be applied to various fields such as vision correction and cataract surgery such as LASIK, LASEK, Smile, and lens implantation.

According to an aspect, there is provided a method for recommending corneal incision parameters using artificial intelligence performed by a computing device, the method comprising: acquiring a corneal nerve image corresponding to an eyeball of a subject; Inputting first input data including at least the corneal nerve image into a prediction model to calculate output data including a corneal incision parameter including at least one of a corneal incision region and a corneal incision depth-the corneal incision depth is a full layer Including at least one of an incision and a partial incision -; And providing at least a part of the output data; including, the prediction model, the type of the ophthalmic surgery of a plurality of recipients who have undergone ophthalmic surgery to perform a corneal incision, the cornea before the ophthalmic surgery of the plurality of recipients A method of recommending a corneal incision parameter learned based on at least one of a nerve image, a corneal incision parameter during the ophthalmic surgery of the plurality of people to be treated, and a corneal nerve image after the ophthalmic surgery of the plurality of people to be treated may be provided.

Here, the method of recommending a corneal incision parameter may further include predicting a degree of corneal nerve damage due to a corneal incision based on second input data including at least the calculated corneal incision parameter.

Here, the degree of corneal nerve damage may be predicted based on at least one of the length of the corneal nerve fibers, the number of corneal nerve fibers, and the number of branches of the corneal nerve fibers.

Here, the method for recommending a corneal incision parameter may further include calculating a recovery rate of a corneal nerve based on third input data including at least a degree of corneal nerve damage.

Here, in the step of calculating the output data, the corneal incision parameter may be calculated based on the incision available area determined in consideration of the corneal incision available range of the operator performing the corneal incision.

Here, the incisionable area may be determined in consideration of at least one of whether the eyeball is the left eye or the right eye, the astigmatism axis of the eyeball, and the amount of astigmatism of the eyeball.

Here, the corneal incision region may include at least one of a corneal incision length and a corneal incision location, and the corneal incision depth may include at least one of a full-layer incision and a partial incision.

Here, the input data may further include examination data of the subject, the examination data including at least one of examination data and eye characteristic data.

Here, the corneal nerve image may be generated by at least one of registration in a corneal surface direction and a corneal thickness direction of a plurality of corneal nerve local area images acquired using a corneal nerve measurement device.

Here, the corneal incision parameter may include a first corneal incision parameter and a second corneal incision parameter.

Here, the output data is a first priority corresponding to the first corneal incision parameter and the second corneal incision parameter in order to provide the priority of the first corneal incision parameter and the second corneal incision parameter. It may include a second priority.

Here, the method for recommending a corneal incision parameter further includes: predicting a first corneal nerve damage degree corresponding to the first corneal incision parameter and a second corneal nerve damage degree corresponding to the second corneal incision parameter; I can.

Here, the method of recommending a corneal incision parameter includes the first corneal incision parameter and the second corneal nerve injury in order to provide priority of the first corneal incision parameter and the second corneal nerve injury 1 calculating a first priority corresponding to the corneal incision parameter and a second priority corresponding to the second corneal incision parameter; Or selecting one of the first corneal incision parameter and the second corneal incision parameter based on the first corneal nerve damage degree and the second corneal nerve damage degree.

Here, the corneal incision parameter calculated in the step of calculating the output data is in a numerical form, and the method of recommending the corneal incision parameter generates a corneal incision parameter in the form of an image based on the corneal incision parameter calculated in a numerical form. It may further include a step.

Here, the corneal incision parameter in the form of the image may be characterized by visually expressing at least one of a corneal incision region and a corneal incision depth on a corneal nerve image.

According to another aspect, there is provided a method for recommending corneal incision parameters using artificial intelligence performed by a computing device, the method comprising: acquiring a corneal nerve image corresponding to an eyeball of a subject; Inputting input data including at least the corneal nerve image into a predictive model to calculate output data including a corneal incision parameter-the corneal incision parameter includes a corneal incision risk area in which corneal incision should be avoided -; And providing at least a part of the output data; including, the prediction model, the type of the ophthalmic surgery of a plurality of recipients who have undergone ophthalmic surgery to perform a corneal incision, the cornea before the ophthalmic surgery of the plurality of recipients A method of recommending a corneal incision parameter learned based on at least one of a nerve image, a corneal incision parameter during the ophthalmic surgery of the plurality of people to be treated, and a corneal nerve image after the ophthalmic surgery of the plurality of people to be treated may be provided.

A system for recommending a corneal incision parameter according to an embodiment may include a learning device and a prediction device. Here, the learning device and the prediction device may be a computing device including at least one control unit. Examples of the computing device may include a desktop, a laptop, a tablet PC, and a smartphone, but are not limited thereto.

1 is a diagram of a system 10 for recommending a corneal incision parameter according to an exemplary embodiment. Referring to FIG. 1, the learning apparatus 100 may learn and/or generate a model (hereinafter referred to as “corneal incision related model”) for calculating information related to corneal incision based on the training data. Here, the learning data is data necessary to learn and/or generate a corneal incision-related model such as numbers, letters, and images, and there is no limitation on the expression method thereof. For example, the learning data may include corneal nerve images before/after corneal incision of the operator whose cornea was incised due to ophthalmic surgery or the like.

The prediction device 300 may calculate a prediction result, which is information related to corneal incision, based on the corneal incision-related model and input data generated through the learning device 100. Here, the input data is data that is the basis for calculating the prediction results, such as numbers, characters, and images, and there is no limitation on the expression method.

Specific examples of training data, input data, prediction results, and corneal incision-related models will be described later.

In FIG. 1, the learning device 100 and the prediction device 300 are illustrated as being separate devices, but the learning device 100 and the prediction device 300 may be the same device. For example, a corneal incision-related model may be trained/generated in the same device, and a prediction result may be calculated using the model. Alternatively, at least a partial configuration of the learning device 100 and at least a partial configuration of the prediction device 300 may have the same configuration.

In addition, the system for recommending a corneal incision parameter according to an embodiment may include a plurality of learning devices and/or a plurality of prediction devices.

2 is a diagram for describing a learning device/prediction device according to an exemplary embodiment. Referring to FIG. 2, the learning device/prediction device according to an embodiment may include a memory unit 5000 and a control unit 1000.

The learning device/prediction device according to an embodiment may include a control unit 1000 for controlling its operation. The control unit 1000 includes at least one of a central processing unit (CPU), a random access memory (RAM), a graphic processing unit (GPU), one or more microprocessors, and other electronic components capable of processing input data according to predetermined logic. It may include.

The controller 1000 may read system programs and various processing programs stored in the memory unit 5000. For example, the controller 1000 may develop a data processing process for performing a learning and prediction step of a corneal incision-related model to be described later on the RAM, and perform various processes according to the developed program. For example, the controller 1000 may learn a corneal incision-related model. As another example, the controller 1000 may generate a prediction result using a corneal incision-related model.

The learning device/prediction device according to an embodiment may include a memory unit 5000. The memory unit 5000 may store data necessary for learning, a learning model, and a learned corneal incision-related model. The memory unit 5000 may store parameters and variables of a corneal incision-related model.

The memory unit 5000 is a nonvolatile semiconductor memory, a hard disk, a flash memory, a RAM, a read only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), or other tangible nonvolatile recording medium. It can be implemented as

The memory unit 5000 may store various processing programs, parameters for performing program processing, or processing result data. For example, the memory unit 5000 may include a data processing process program, a diagnostic process program, a parameter for executing each program, and data obtained according to the execution of such a program, for performing a learning and prediction step of a corneal incision-related model described later (Eg, processed data or prediction results) and the like can be stored.

The learning device/prediction device according to an embodiment may further include a communication unit 9000. The communication unit 9000 may communicate with an external device. For example, the communication unit 9000 of the learning device may communicate with the communication unit 9000 of the prediction device. The communication unit 9000 may perform wired or wireless communication. The communication unit 9000 may perform bi-directional or one-way communication.

The learning device/prediction device illustrated in FIG. 2 is only an example, and the configuration of the learning device/prediction device is not limited thereto.

The corneal incision parameter recommendation system according to an embodiment may include a server device and a client device. 3 is a diagram for describing the server device 500 and the client devices 700a and 700b according to an exemplary embodiment.

The server device 500 according to an embodiment may correspond to the above-described learning device/prediction device. The server device 500 according to an embodiment may learn, store, and/or execute a corneal incision-related model.

The client devices 700a and 700b according to an embodiment may correspond to the above-described learning device/prediction device. The client devices 700a and 700b according to an embodiment may learn, store, and/or execute a corneal incision-related model.

The client devices 700a and 700b according to an embodiment may obtain a learned corneal incision-related model from the server device 500. For example, the client devices 700a and 700b may download a corneal incision-related model from the server device 500 through a network.

The server device 500 according to an embodiment may calculate a prediction result based on input data obtained from the client devices 700a and 700b. For example, the client devices 700a and 700b receive a corneal nerve image of a subject and transmit it to the server device 500, and the server device 500 predicts a result of prediction through a corneal incision-related model based on the corneal nerve image of the subject. Can be calculated. The server device 500 according to an embodiment may obtain input data from a plurality of client devices 700a and 700b.

The server device 500 according to an embodiment may transmit the calculated prediction result to the client devices 700a and 700b. For example, the client devices 700a and 700b may provide a prediction result obtained from the server device 500 to a doctor, a counselor, an examinee, and the like. The server device 500 according to an embodiment may obtain feedback from the client devices 700a and 700b. The server device 500 according to an embodiment may transmit a prediction result to a plurality of client devices 700a and 700b.

The client devices 700a and 700b according to an embodiment may request a prediction result from the server device 500.

The client devices 700a and 700b according to an embodiment may transmit the received data to the server device 500. The client devices 700a and 700b according to an embodiment may change at least a part of the received data and transmit it to the server device 500. The client devices 700a and 700b according to an embodiment may provide a prediction result obtained from the server device 500 to a doctor, a counselor, an examinee, and the like. The client devices 700a and 700b according to an embodiment may change at least a part of the prediction result obtained from the server device 500 and provide it to a doctor, a counselor, a subject, and the like.

3 illustrates a relationship between one server device 500 and two client devices 700a and 700b, but is not limited thereto. Can be applied.

4 is a diagram illustrating the configuration of the server device 500 and the client device 700 according to an embodiment. Referring to FIG. 4, the server device 500 and the client device 700 may include memory units 5000a and 5000b, control units 1000a and 1000b, and communication units 9000a and 9000b. The server device 500 and the client device 700 may transmit and acquire information through the communication units 9000a and 9000b. As an example, the client device 700 may acquire a corneal incision-related model learned from the communication unit 9000a of the server device 500 through the communication unit 9000b. As another example, the client device 700 may transmit input data to the communication unit 9000a of the server device 500 through the communication unit 9000b, and the server device 500 transmits the prediction result to the client through the communication unit 9000a. It can be transmitted to the communication unit 9000b of the device 700.

As described above, the corneal incision-related model is a model that calculates various information that can be considered during and before and after corneal incision due to ophthalmic surgery or the like.

5 is a diagram of a corneal incision-related model M according to an exemplary embodiment. Referring to FIG. 5, the corneal incision-related model (M) includes a corneal incision parameter recommendation model (M1), a corneal nerve damage prediction model (M2), a nerve recovery rate calculation model (M3), and an incision risk area prediction model (M4). And an image matching model M5. A detailed description of each model will be described later.

At least some of the corneal incision-related models M may be trained and/or generated in the same learning device. For example, the corneal incision parameter recommendation model M1 and the corneal nerve damage prediction model M2 may be trained and/or generated in the same learning device. Alternatively, at least some of the corneal incision-related models M may be learned and/or generated by different learning devices.

At least some of the corneal incision-related models M may be executed in the same prediction device. For example, the corneal incision parameter recommendation model M1 and the corneal nerve damage prediction model M2 may be executed in the same prediction device. Alternatively, at least some of the corneal incision-related models M may be executed in different prediction devices.

The corneal incision-related model according to an embodiment may be learned and/or implemented as an artificial intelligence model/algorithm, and there is no limitation on the learning and/or implementation method. For example, models related to corneal incision include classification algorithms, regression algorithms, supervised learning, unsupervised learning, reinforcement learning, and support vector machine. ), decision tree, random forest, LASSO, AdaBoost, XGBoost, artificial neural network, convolutional neural network (CNN), generative adversarial network (GAN) ) And the like, and may be learned and/or implemented through various machine learning models/algorithms and deep learning models/algorithms.

The corneal incision-related model according to an embodiment may be learned and/or generated through a learning step. The corneal incision-related model learned and/or generated through the learning step may calculate a prediction result through the prediction step.

6 is a diagram for explaining a learning step (S10) and a prediction step (S30) of a corneal incision-related model according to an exemplary embodiment. Referring to FIG. 6, the learning step S10 may include a learning data acquisition step S110 and a model training step S150.

The learning data acquisition step S110 may be a step in which the learning device acquires training data, which is data for learning and/or generating a corneal incision-related model.

The model learning step S150 may be a step of learning and/or generating a corneal incision-related model. In the model learning step S150, the learning device may train and/or generate the model based on the training data acquired in the training data acquisition step. For example, model parameters constituting the corneal incision-related model may be changed in the model learning step S150. According to the change of the parameter, the accuracy of the model may be improved.

The corneal incision-related model may be learned based on the corneal incision-related information of the operator whose cornea was incised through ophthalmic surgery or the like. For example, the model may include types of ophthalmic surgery of a plurality of recipients who have undergone ophthalmic surgery, corneal nerve images before ophthalmic surgery of the plurality of recipients, corneal incision parameters during ophthalmic surgery of the plurality of recipients, and ophthalmology of the plurality of recipients. It may be learned based on at least one of the corneal nerve images after surgery.

Referring to FIG. 6, the prediction step S30 may include an input data acquisition step S310 and a model execution step S350.

The input data acquisition step S310 may be a step in which the prediction apparatus acquires input data, which is data that can be used to calculate a prediction result using a corneal incision-related model.

The model execution step S350 may be a step of calculating a prediction result based on the corneal incision-related model and input data that are learned and/or generated in the learning step S10. For example, the prediction device may output a prediction result based on input data and model parameters obtained from the learning device.

The input data of the corneal incision-related model may include all information acquired about the subject. Alternatively, the input data may include at least some of the information acquired about the subject. In addition, the input data may be the same or different according to a corneal incision-related model.

The prediction result of the corneal incision-related model may vary according to the training data. Alternatively, the accuracy of the corneal incision-related model may vary according to the training data.

The prediction result may vary depending on the type of true value included in the training data. For example, when the first learning data and the second learning data are obtained from different hospitals, from different doctors, or are learning data at different times, the first learning and/or generated first learning data is based on the first learning data. The model and the second model trained and/or generated based on the second training data may be different from each other. As a result, the first prediction result output from the first model and the second prediction result output from the second model may be different from each other. In addition, the accuracy of the first model and the second model may be different from each other.

However, even if the training data is different, the same corneal incision-related model may be trained and/or generated. Alternatively, the same prediction result may be calculated even in the case of a corneal incision-related model that is trained and/or generated from different training data.

The training data, input data, and prediction results (hereinafter referred to as "input/output data") may include corneal nerve images. The corneal nerve image may mean an image of a corneal nerve photographed using a corneal nerve measuring device. Examples of corneal nerve measurement equipment may include confocal microscopy such as NIDEK ConfoScan4 and HEIDELBERG ENGINEERING HRT+RCM, but are not limited thereto.

The corneal region (hereinafter referred to as “cover region”) represented by the corneal nerve image may vary. The cover area according to an embodiment may be the entire area of the cornea. Alternatively, the cover region according to an embodiment may be a partial region of the cornea. For example, the cover region may be a region in which a corneal incision is likely to be performed.

In the present specification, for convenience of explanation, a case where the corneal nerve image is a two-dimensional image is described, but the image may be a three-dimensional image, and there is no limitation on the dimension thereof.

The input/output data may include corneal incision parameters. The corneal incision parameter may mean a variable that can be considered during corneal incision. The corneal incision parameter may include a corneal incision area and a corneal incision depth. The corneal incision region may mean at least one of an incision length and an incision position in the corneal surface direction. The corneal incision depth may mean an incision amount in the corneal thickness direction. The incision in the thickness direction of the cornea may include a full-layer incision in which the entire cornea is incised and a partial incision in which a portion is incised. The full-thickness incision may be performed in lens implantation, cataract surgery, or the like. The partial incision may be performed in LASIK, Smile surgery, or the like.

7 is a diagram of examples of corneal incision parameters in an image form according to an exemplary embodiment. Hereinafter, a corneal incision region including a corneal incision length and a corneal incision location and a corneal incision depth will be described with reference to FIG. 7.

The corneal incision parameter may include the corneal incision length. 7A illustrates corneal incision parameters having different corneal incision lengths according to an embodiment. The corneal incision parameter in the form of an image may include a corneal incision length visually expressed, such as a straight line or a curve, on a corneal nerve image. Referring to FIG. 7A, the first corneal incision parameter P1 may have a longer corneal incision length than the second corneal incision parameter P2.

The corneal incision parameter may include a corneal incision location. The corneal incision parameter in the form of an image may include a corneal incision position in which a method of representing a position, such as a point, a line, or a plane, on a corneal nerve image is visually expressed.

The corneal incision location may include a location in the circumferential direction on the corneal nerve image. 7B shows corneal incision parameters having different positions in the circumferential direction on a corneal nerve image according to an exemplary embodiment. The third corneal incision parameter P3 and the fourth corneal incision parameter P4 have the same length of corneal incision, but different locations in the circumferential direction on the corneal nerve image may have different incision locations.

The corneal incision location may include a location in the radial direction on the corneal nerve image. 7C illustrates corneal incision parameters having different radial positions on a corneal nerve image according to an exemplary embodiment. The fifth corneal incision parameter P5 and the sixth corneal incision parameter P6 have the same length of corneal incision, but different locations in the radial direction on the corneal nerve image may have different incision locations.

The corneal incision parameter may include a corneal incision depth. 7D shows corneal incision parameters having different corneal incision depths according to an embodiment. Corneal incision depths of the seventh corneal incision parameter P7 and the eighth corneal incision parameter P8 may be different, and to express this, corneal incision parameters are shown in different colors in FIG. 7D, but the corneal incision depth is indicated. The expression method is not limited thereto.

7 illustrates that the corneal incision parameters are shown on the corneal nerve image, but a method of expressing the corneal incision parameters is not limited thereto. Another expression method may be numerical expression of corneal incision parameters. The corneal incision length according to an embodiment may be expressed as a length value such as 2mm, 5mm, and the like. The position in the circumferential direction according to an embodiment may be expressed as an angle value such as 30°, 60°, etc. with respect to a virtual axis having the center of the corneal nerve image as an origin. The position in the radial direction according to an exemplary embodiment may be expressed as a length value such as 5 mm or 7 mm from the center of the corneal nerve image. The corneal incision depth according to an embodiment may be numerically expressed, such as 1mm, 2mm, and the like. The depth of the corneal incision according to an embodiment may include a full-layer incision and a partial incision.

The input/output data may include examination data. Examination data can be expressed in various ways, such as numbers, characters, and images, and there is no limitation on the expression method. In addition, images are not limited in their dimensions, such as 2D or 3D images.

The examination data may include questionnaire data, which is information obtained by asking a question, not through equipment or examination, eye characteristic data, and genetic information, which are information about the eye obtained through equipment or examination.

The questionnaire data may include variables such as gender, age, race, living environment, such as the subject's gender, age, race, and area of residence, demographic characteristics such as occupation, income, education, education, and family size, medical history such as high blood pressure, diabetes, and family history. .

Eye characteristic data can include all kinds of eye-related information. For example, the eye characteristic data may include variables such as visual acuity, intraocular pressure, and/or retinal test results.

The eyeball characteristic data may include information on the physical shape of the eyeball. For example, eye characteristic data includes white-to-white (WTW) distance, angle-to-angle (ATA) distance, internal Anterior Chamber Depth (ACD), sulcus-to-sulcus (STS) distance, and pupil size. It can contain variables such as. As another example, the eye characteristic data may include information on the shape of the cornea, such as a corneal shape factor, a corneal topography image, and the like. Here, the corneal shape factor is a number representing the physical shape of the cornea, index of surface variance (ISV), index of vertical asymmetry (IVA), keratoconus index (KI), central keratoconus index (CKI), minimum radius of curvature (Rmin ), index of height asymmetry (IHA), index of height decentration (IHD), central cornea thickness, and the like. In addition, the corneal topography image is an image related to the shape of the cornea, and may include a corneal topography map, an front corneal curvature image, a corneal posterior curvature image, a corneal thickness map, and the like.

Eye characteristic data can be obtained through tomography such as Pentacam, CASIA2, AL-Scan, OQAS, topography, optical coherence tomography (OCT), ultrasound biomicroscopy (UBM) equipment, etc., but is not limited thereto. Information that can be obtained through the above equipment and similar equipment and information derived therefrom may be included in the eye characteristic data.

Genetic information may be obtained through genetic testing or the like. Genetic information can be used to determine whether ophthalmic surgery is suitable for a subject. Alternatively, the genetic information may be used to predict side effects after ophthalmic surgery. For example, the onset of corneal dystrophy can be predicted through genetic information.

The input/output data may include a predicted value that can be calculated through a corneal incision-related model, as well as a measurement value that can be obtained/measured through a medical examination and examination. For example, corneal nerve damage is not only a measure of the corneal nerve damage of the subject acquired/measured through examination before and after ophthalmic surgery, but also the corneal nerve damage after ophthalmic surgery of the subject calculated through a predictive model of corneal nerve damage. It may include predicted values.

Hereinafter, an individual example of a corneal incision-related model will be described.

The corneal incision parameter recommendation model may recommend a corneal incision parameter corresponding to a subject.

The corneal incision parameter recommendation model may recommend corneal incision parameters in consideration of corneal nerve damage of the subject. For example, the model may recommend a corneal incision parameter to reduce corneal nerve damage in a subject. Alternatively, the model may recommend corneal incision parameters to minimize corneal nerve damage of the subject.

The corneal incision parameter recommendation model may recommend corneal incision parameters in consideration of the corneal nerve recovery rate of the subject. For example, the model may recommend a corneal incision parameter to increase a corneal nerve recovery rate of a subject. Alternatively, the model may recommend a corneal incision parameter to maximize a corneal nerve recovery rate of a subject.

The corneal incision parameter recommendation model may calculate the corneal incision parameter based on the amount of astigmatism in the eye of the patient to be treated. The length of the corneal incision according to an embodiment may be determined in consideration of the amount of astigmatism. For example, as the amount of astigmatism increases, the length of the corneal incision may increase.

The corneal incision parameter recommendation model may recommend a corneal incision parameter based on input data including a corneal nerve image. For example, the model may receive input data including a corneal nerve image and output output data including a corneal incision parameter.

8 is a diagram of a corneal incision parameter recommendation model M1 according to an exemplary embodiment. Referring to FIG. 8, the corneal incision parameter recommendation model M1 may output a corneal nerve image I2 including the corneal incision parameter based on the corneal nerve image I1. As described above, the corneal incision parameter may be output as an image as shown in FIG. 8, but may be output in various ways, such as numerical expression.

The input data of the corneal incision parameter recommendation model may include examination data of the subject. The corneal incision parameter may be calculated based on examination data including the age, medical history, and living environment of the subject.

The recommended model for corneal incision parameters includes at least one of the types of ophthalmic surgery of the patient who underwent ophthalmic surgery to perform corneal incision, the corneal nerve image before the patient's ophthalmic surgery, the corneal incision parameters during the patient's ophthalmic surgery, and the corneal nerve image after the patient's ophthalmic surgery. It can be learned based on one.

As an example of the learning method of the model, the model receives input data including an actual corneal nerve image before ophthalmic surgery of an operator who has already undergone ophthalmic surgery, predicts a corneal incision parameter, and uses the predicted corneal incision parameter as the subject. The model can be trained by comparing it with the corneal incision parameters actually used during surgery. In this case, the trained model may be able to predict corneal incision parameters by receiving input data including a corneal nerve image of the subject in the prediction step.

As another example of the learning method of the model, the model predicts the corneal nerve image after the surgery by receiving input data including the actual corneal nerve image before ophthalmic surgery and the corneal incision parameters actually used during the surgery. Then, the model may be trained by comparing the predicted corneal nerve image with an actual corneal nerve image after surgery of the patient. In this case, the trained model may be able to predict the corneal nerve image after surgery by receiving input data including the corneal nerve image and corneal incision parameters of the subject in the prediction step.

The corneal incision parameter recommendation model may calculate the corneal incision parameter based on the incision available area.

The incisionable area may be determined in consideration of the corneal incision available range of the operator performing the corneal incision.

The operator's possible corneal incision range may be determined based on a position relative to the operator during the operator's corneal incision. For example, the possible corneal incision range when the operator incises the cornea from the top of the person's head looking in the direction of the patient's leg may be different from the corneal incision available range when the operator opens the cornea from the right to the left of the operator. have.

The operator's possible corneal incision range may be determined based on the operator's hand used for corneal incision. For example, when the operator cuts the cornea with the right hand, the available corneal incision range may be different from the corneal incision available range when the cornea is cut with the left hand.

The incisionable area may be determined in consideration of whether the eyeball of the patient to be treated is the left eye or the right eye. For example, the incision available area of the left eye of the person to be treated may be different from the incision available area of the right eye.

The incision available area may be determined in consideration of the astigmatism axis of the eye to be treated. For example, the cuttable region may be determined within a region in a direction perpendicular to the astigmatism axis.

9 is a diagram illustrating a cuttable area according to an exemplary embodiment. Referring to FIG. 9, the incisionable area according to an embodiment may be expressed as an angle (A) between virtual lines extending from the center of the corneal nerve image, but is not limited thereto and can be recognized as an incisionable area. It can be expressed in a variety of ways. The corneal incision parameter recommendation model may calculate the corneal incision parameter P9 within the incision available area.

The corneal incision parameter recommendation model may output output data including a plurality of corneal incision parameters. The output data may include priorities corresponding to a plurality of corneal incision parameters. Hereinafter, a case with a high priority will be described as a corneal incision parameter that is advantageous to a person to be treated, but the opposite will be possible. In addition, being advantageous to a person to be treated may mean that there are few sequelae caused by corneal incision, such as less corneal nerve damage or a high recovery rate.

The priority can be calculated by considering the sequelae caused by the corneal incision. The priority according to an embodiment may be calculated in consideration of the degree of corneal nerve damage. For example, when the corneal nerve damage degree of the first corneal incision parameter is smaller than the corneal nerve damage degree of the second corneal incision parameter, the priority of the first corneal incision parameter may be higher than the priority of the second corneal incision parameter. . The priority according to an embodiment may be calculated in consideration of a corneal nerve recovery rate. For example, when the corneal nerve recovery rate of the first corneal incision parameter is faster than the corneal nerve recovery rate in the second corneal incision parameter, the priority of the first corneal incision parameter may be higher than the priority of the second corneal incision parameter. .

In the above, we have looked at how the corneal incision parameter recommendation model calculates the area in which corneal incision is performed. Alternatively, the model may calculate a region in which corneal incision should be avoided (hereinafter referred to as “corneal incision risk area”), and the like.

Even when the corneal incision parameter recommendation model outputs a corneal incision risk area, the contents of the case in which a corneal incision recommendation area is output may be applied. For example, the model may calculate a risk area for corneal incision in consideration of at least one of a corneal nerve damage degree and a corneal nerve recovery rate.

The corneal nerve damage prediction model can predict the corneal nerve damage corresponding to the corneal incision parameter. The model may predict the degree of corneal nerve damage caused by the corneal incision based on input data including the corneal incision parameter.

The degree of corneal nerve damage may be calculated based on the length of the corneal nerve fibers. For example, as the length of the corneal nerve fiber increases, the degree of corneal nerve damage may decrease.

The degree of corneal nerve damage may be calculated based on the number of corneal nerve fibers. For example, as the number of corneal nerve fibers increases, the degree of corneal nerve damage may decrease.

The degree of corneal nerve damage may be calculated based on the number of branches of the corneal nerve fibers. For example, as the number of branches of the corneal nerve fibers increases, the degree of corneal nerve damage may decrease.

The input data of the corneal nerve damage prediction model may include examination data of the subject. The degree of corneal nerve damage may be calculated based on examination data including the age, medical history, and living environment of the subject. For example, as the subject's age increases, the degree of corneal nerve damage may increase. As another example, if the subject has a specific medical history, the degree of corneal nerve damage may increase.

The corneal nerve damage prediction model may predict corneal nerve damage corresponding to a plurality of corneal incision parameters. For example, the model receives a first corneal incision parameter and a second corneal incision parameter and receives a first corneal nerve injury degree corresponding to the first corneal incision parameter and a second corneal nerve injury degree corresponding to the second corneal incision parameter Can be calculated. As described above, the priority of the corneal incision parameter may be determined based on the degree of corneal nerve damage.

The nerve recovery rate calculation model can calculate the recovery rate of the corneal nerve corresponding to the corneal incision parameter. The model may calculate a corneal nerve recovery rate based on input data including at least one of a corneal incision parameter and a corneal nerve damage degree.

The corneal nerve recovery rate can be calculated based on the corneal incision parameters. For example, as the length of the corneal incision increases, the rate of corneal nerve recovery may decrease. As another example, as the depth of the corneal incision increases, the rate of corneal nerve recovery may decrease.

The corneal nerve recovery rate can be calculated based on the degree of corneal nerve damage. For example, as the degree of corneal nerve damage increases, the rate of corneal nerve recovery may decrease.

Input data of the nerve recovery rate calculation model may include examination data of the subject. The corneal nerve recovery rate may be calculated based on examination data including the age, medical history, and living environment of the subject. For example, as the subject's age increases, the rate of corneal nerve recovery may decrease. As another example, if the subject has a specific medical history, the rate of corneal nerve recovery may decrease.

The nerve recovery rate calculation model may predict a nerve recovery rate corresponding to a plurality of corneal incision parameters and/or a plurality of corneal nerve damage degrees. For example, the model receives a first corneal nerve damage degree and a second corneal nerve damage degree, and receives a first nerve recovery rate corresponding to the first corneal nerve damage degree and a second nerve corresponding to the second corneal nerve damage degree. You can calculate the recovery rate. As described above, the priority of the corneal incision parameter may be determined based on the corneal nerve recovery rate.

Corneal nerve images can be generated using corneal nerve measurement equipment. For example, the corneal nerve image may be a corneal nerve image measured with a confocal microscope.

The number of measurements for generating a corneal nerve image may vary depending on the size of the cover area and the size of the corneal area (hereinafter referred to as “measurement area”) that can be measured by a measuring device through a single measurement. For example, when the measurement area is greater than or equal to the cover area, a corneal nerve image may be generated with a single measurement. On the other hand, when the measurement area is smaller than the cover area, the image may be generated through a plurality of measurements.

When a plurality of measurements are required due to the fact that the measurement area is smaller than the cover area, etc., a corneal nerve image can be generated by matching a plurality of images generated from the plurality of measurements (hereinafter referred to as "local area images"). have. The image matching model can generate a corneal nerve image through registration of local area images.

10 is a diagram of an image matching model M5 according to an exemplary embodiment. Referring to FIG. 10, the image matching model M5 may generate a corneal nerve image FI by matching local area images PI1, PI2, PI3, and PI4. For example, the image matching model M5 may generate a corneal nerve image FI by receiving local area images PI1, PI2, PI3, and PI4 measured with a confocal microscope and matching them.

In FIG. 10, the covering area of the corneal nerve image is shown to be the entire area of the cornea, but is not limited thereto. In addition, the size of the measurement area is exemplary, and the size of the measurement area may vary depending on the measurement equipment.

The matching of local area images can be performed through a general image matching algorithm. Examples of the image matching algorithm may include a brightness value-based method, a feature point-based method, and the like.

The feature point-based matching method may include extracting a feature point from a local area image and generating a corneal nerve image through matching the local area image by matching the extracted feature points.

Examples of feature-based matching methods include Moravec algorithm, Harris algorithm, Shi and Tomasi algorithm, Wang and Brady algorithm, SUSAN algorithm, SIFT (Scale-Invariant Feature Transform) algorithm, SURF (Speeded-Up Robust Featurs) algorithm, FAST (Features from Accelerated Segment Test) algorithm, Binary Robust Independent Elementary Features (BRIEF) algorithm, Oriented FAST and Rotated BRIEF (ORB) algorithm, Trajkovic and Hedley algorithm, corner detection algorithm using curvature, etc., but are not limited thereto.

The corneal nerve image may be generated by at least one of registration of a local area image in a direction of a corneal surface and a direction of a corneal thickness. For example, when only registration in the direction of the corneal surface is performed, a two-dimensional corneal nerve image may be generated. On the other hand, when registration in the corneal thickness direction is performed, a three-dimensional corneal nerve image may be generated.

Models related to corneal incisions can be combined with each other. The models may be combined by at least one of a serial connection and a parallel connection.

The fact that the corneal incision-related model is serially connected may include calculating an output of at least one other corneal incision-related model based on the output of the at least one corneal incision-related model.

The fact that the corneal incision-related models are connected in parallel may include that the output of the corneal incision-related model does not affect the output of the other corneal incision-related models.

Hereinafter, an example of a combination of a corneal incision-related model will be described.

11 to 13 are diagrams illustrating an embodiment of a combination of a corneal incision-related model according to an exemplary embodiment.

Referring to FIG. 11, the corneal nerve damage predictive model M2 may calculate the corneal nerve damage based on the corneal nerve injury parameter that the corneal nerve injury parameter recommendation model M1 receives and outputs first input data. In this case, at least one of a corneal incision parameter and a corneal nerve injury may be calculated by a combination of the corneal incision parameter recommendation model M1 and the corneal nerve damage prediction model M2.

The corneal nerve damage prediction model M2 may calculate the corneal nerve damage degree further based on second input data in addition to the corneal incision parameter. For example, as described above, the second input data may include examination data of the examinee.

Referring to FIG. 12, the nerve recovery rate calculation model M3 may calculate a nerve recovery rate based on the corneal nerve damage degree output by the corneal nerve damage degree prediction model M2 receiving first input data. In this case, at least one of a corneal nerve damage degree and a nerve recovery rate may be calculated by a combination of the corneal nerve damage degree prediction model M2 and the nerve recovery rate calculation model M3.

The nerve recovery rate calculation model M3 may calculate the nerve recovery rate further based on the second input data in addition to the corneal nerve damage degree. For example, as described above, the second input data may include examination data of the examinee.

Referring to FIG. 13, the corneal incision parameter recommendation model M1 may calculate a corneal incision parameter based on a corneal nerve image output by the image matching model M5 receiving first input data. Here, the first input data may include a corneal nerve image measured by a confocal microscope. In this case, at least one of a corneal nerve image and a corneal incision parameter may be calculated by a combination of the image matching model M5 and the corneal incision parameter recommendation model M1.

The corneal incision parameter recommendation model M1 may calculate the corneal incision parameter further based on second input data in addition to the corneal nerve image. For example, as described above, the second input data may include examination data of the examinee.

In FIGS. 11 to 13, a case of combining two models has been described, but the present invention is not limited thereto, and three or more models may be combined.

Models related to corneal incisions can be merged with each other. The plurality of corneal incision-related models may be merged into one model to perform at least some of the functions of the plurality of individual models.

14 is a diagram illustrating an embodiment of merging a corneal incision-related model according to an embodiment. Referring to FIG. 14, a corneal incision parameter recommendation model and a corneal nerve damage prediction model may be merged to form one merged model M12. The merge model M12 may calculate output data based on input data. Here, the output data may include information corresponding to at least one of a corneal incision parameter and a degree of corneal nerve damage. For example, the output data may include at least one of a corneal incision parameter and a corneal nerve damage degree. Alternatively, the output data may include information calculated from at least one of a corneal incision parameter and a corneal nerve damage degree.

In FIG. 14, a case of merging two models has been described, but the present invention is not limited thereto, and it is possible to merge three or more models.

Hereinafter, an embodiment of a method for recommending a corneal incision parameter will be described.

The method of recommending corneal incision parameters may be implemented using one or more corneal incision related models. When the method is implemented with a plurality of corneal incision-related models, whether or not to execute at least one corneal incision-related model may depend on a prediction result of at least one other corneal incision-related model. For example, whether to execute the second corneal incision-related model may depend on the prediction result of the first corneal incision-related model.

Each step of the method for recommending a corneal incision parameter to be described later may be performed by a prediction device.

15 is a diagram of a first embodiment of a method for recommending a corneal incision parameter according to an embodiment. Referring to FIG. 15, the method for recommending a corneal incision parameter according to an embodiment includes acquiring a corneal nerve image (S1100), calculating output data including a corneal incision parameter (S1500), and at least a portion of the output data. It may include a providing step (S1900).

Acquiring the corneal nerve image (S1100) may include obtaining a corneal nerve image corresponding to the eyeball of the subject.

Calculating output data including corneal incision parameters (S1500) may include inputting input data including at least a corneal nerve image into a prediction model to calculate output data including corneal incision parameters.

The corneal nerve image may be generated by at least one of registration in a corneal surface direction and a corneal thickness direction of a plurality of corneal nerve local area images acquired using a corneal nerve measurement device.

The input data may further include examination data of the subject. The examination data may include at least one of an examination data and eye characteristic data.

The predictive model may be a corneal incision parameter recommendation model.

The corneal incision parameter may include at least one of a corneal incision region and a corneal incision depth. The corneal incision region may include at least one of a corneal incision length and a corneal incision location. The corneal incision parameter may include a corneal incision risk area in which corneal incision should be avoided.

The corneal incision parameter may include a first corneal incision parameter and a second corneal incision parameter. In this case, the output data includes a first priority corresponding to the first corneal incision parameter and a second priority corresponding to the second corneal incision parameter in order to provide the priority of the first corneal incision parameter and the second corneal incision parameter. Can include.

Calculating the output data including the corneal incision parameter (S1500) may include calculating the corneal incision parameter based on the incision available area determined in consideration of the corneal incision available range of the operator performing the corneal incision. The incisionable region may be determined in consideration of at least one of whether the eyeball in which corneal incision is performed is the left eye or the right eye, the astigmatism axis of the eyeball, and the amount of astigmatism of the eyeball.

16 is a diagram illustrating a second embodiment of a method for recommending a corneal incision parameter according to an embodiment. Referring to FIG. 16, a method of recommending a corneal incision parameter according to an embodiment may include predicting a degree of corneal nerve damage (S1600 ).

Predicting the degree of corneal nerve damage (S1600) may include predicting the degree of corneal nerve damage due to the corneal incision based on input data including the corneal incision parameter.

The degree of corneal nerve damage may be predicted based on at least one of the length of the corneal nerve fibers, the number of corneal nerve fibers, and the number of branches of the corneal nerve fibers.

The corneal nerve damage degree may be calculated by a corneal nerve damage prediction model.

17 is a diagram of a third embodiment of a method for recommending a corneal incision parameter according to an embodiment. Referring to FIG. 17, a method of recommending a corneal incision parameter according to an embodiment may include calculating a recovery rate of a corneal nerve (S1700 ).

Calculating the recovery rate of the corneal nerve (S1700) may include calculating the recovery rate of the corneal nerve based on input data including a degree of corneal nerve damage.

The recovery rate may be calculated by a nerve recovery rate calculation model.

18 is a diagram of a fourth embodiment of a method for recommending a corneal incision parameter according to an embodiment. Referring to FIG. 18, a method of recommending a corneal incision parameter according to an embodiment may include calculating a priority (S1810 ).

In the step of calculating the priority (S1810), in order to provide priority of the first corneal incision parameter and the second corneal incision parameter, the first corneal incision parameter is based on the first corneal nerve damage degree and the second corneal nerve damage degree. It may include calculating a corresponding first priority and a second priority corresponding to the second corneal incision parameter.

19 is a diagram illustrating a method of recommending a corneal incision parameter according to a fifth embodiment. Referring to FIG. 19, a method of recommending a corneal incision parameter according to an embodiment may include selecting a corneal incision parameter (S1850).

Selecting the corneal incision parameter (S1850) may include selecting one of the first corneal incision parameter and the second corneal incision parameter based on the first corneal nerve damage degree and the second corneal nerve damage degree.

20 is a diagram illustrating a method for recommending a corneal incision parameter according to a sixth embodiment. Referring to FIG. 20, a method of recommending a corneal incision parameter according to an embodiment may include generating a corneal incision parameter in the form of an image (S1890).

Referring to FIG. 15, the corneal incision parameter calculated in the step S1500 of calculating output data including the corneal incision parameter may have a numerical form. The method of recommending a corneal incision parameter may include generating a corneal incision parameter in an image form based on the corneal incision parameter calculated in a numerical form.

The corneal incision parameter in the image form may be expressed in a manner of visually expressing the corneal incision parameter described above. For example, the corneal incision parameter in the form of an image may include visually expressing at least one of a corneal incision region and a corneal incision depth on a corneal nerve image.

The combination and/or merging of the above-described method for recommending a corneal incision parameter and a model related to a corneal incision is merely an example, and in addition, a method for recommending a corneal incision parameter may be implemented in various ways, or a combination and/or merging of a model related to corneal incision.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computing devices and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes magneto-optical media and hardware devices specially configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computing device using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

In the above, the configuration and features of the present invention have been described based on the embodiments, but the present invention is not limited thereto, and that various changes or modifications can be made within the spirit and scope of the present invention to those skilled in the art. It is obvious, and therefore, such changes or modifications are found to be within the scope of the appended claims.

10: corneal incision parameter recommendation system
100: learning device
300: prediction device
500: server device
700: client device
1000: control unit
5000: memory unit
9000: Ministry of Communications

Claims (17)

In the method for recommending corneal incision parameters using artificial intelligence performed by a computing device,
Acquiring a corneal nerve image corresponding to the eyeball of the subject;
Inputting first input data including at least the corneal nerve image into a prediction model to calculate output data including a corneal incision parameter including at least one of a corneal incision region and a corneal incision depth-the corneal incision depth is a full layer Including at least one of an incision and a partial incision -; And
Providing at least a portion of the output data; Including,
The predictive model includes the types of ophthalmic surgery of a plurality of recipients who have undergone ophthalmic surgery to perform corneal incisions, corneal nerve images of the plurality of recipients before the ophthalmic surgery, corneal incision parameters during the ophthalmic surgery of the plurality of recipients, and Learned based on at least one of the corneal nerve images after the ophthalmic surgery of the plurality of recipients
How to recommend corneal incision parameters.
The method of claim 1,
Predicting a degree of corneal nerve damage due to corneal incision based on second input data including at least the calculated corneal incision parameter; further comprising
How to recommend corneal incision parameters.
The method of claim 2,
The corneal nerve damage degree is predicted based on at least one of the length of the corneal nerve fibers, the number of corneal nerve fibers, and the number of branches of the corneal nerve fibers.
How to recommend corneal incision parameters.
The method of claim 2,
Calculating a recovery rate of a corneal nerve based on third input data including at least the degree of corneal nerve damage; further comprising
How to recommend corneal incision parameters.
The method of claim 1,
The calculating of the output data may include calculating a corneal incision parameter based on an incisionable area determined in consideration of a corneal incision available range of an operator performing a corneal incision.
How to recommend corneal incision parameters.
The method of claim 5,
The incisionable area is determined by considering at least one of whether the eyeball is the left eye or the right eye, the astigmatism axis of the eyeball, and the amount of astigmatism of the eyeball
How to recommend corneal incision parameters.
The method of claim 1,
The corneal incision region includes at least one of a corneal incision length and a corneal incision location,
The corneal incision depth includes at least one of a full-layer incision and a partial incision
How to recommend corneal incision parameters.
The method of claim 1,
The input data further comprises examination data of the examinee, the examination data including at least one of examination data and eye characteristic data.
How to recommend corneal incision parameters.
The method of claim 1,
The corneal nerve image is generated by at least one of registration in a corneal surface direction and a corneal thickness direction of a plurality of corneal nerve local area images acquired using a corneal nerve measurement device.
How to recommend corneal incision parameters.
The method of claim 1,
The corneal incision parameter includes a first corneal incision parameter and a second corneal incision parameter
How to recommend corneal incision parameters.
The method of claim 10,
The output data includes a first priority corresponding to the first corneal incision parameter and a second priority corresponding to the second corneal incision parameter in order to provide a priority of the first corneal incision parameter and the second corneal incision parameter. Priority Containing
How to recommend corneal incision parameters.
The method of claim 10,
Predicting a first corneal nerve damage degree corresponding to the first corneal incision parameter and a second corneal nerve damage degree corresponding to the second corneal incision parameter; further comprising
How to recommend corneal incision parameters.
The method of claim 12,
In order to provide priority of the first corneal incision parameter and the second corneal incision parameter, a first priority corresponding to the first corneal incision parameter based on the first corneal nerve damage degree and the second corneal nerve damage degree Calculating a priority and a second priority corresponding to the second corneal incision parameter; or
Selecting one of the first corneal incision parameter and the second corneal incision parameter based on the first corneal nerve damage degree and the second corneal nerve damage degree; further comprising
How to recommend corneal incision parameters.
The method of claim 1,
The corneal incision parameter calculated in the step of calculating the output data is in a numerical form,
The method of recommending a corneal incision parameter further comprises generating a corneal incision parameter in an image form based on the corneal incision parameter calculated in a numerical form.
How to recommend corneal incision parameters.
The method of claim 14,
The corneal incision parameter in the form of the image visually expresses at least one of a corneal incision region and a corneal incision depth on a corneal nerve image.
How to recommend corneal incision parameters.
In the method for recommending corneal incision parameters using artificial intelligence performed by a computing device,
Acquiring a corneal nerve image corresponding to the eyeball of the subject;
Calculating output data including corneal incision parameters by inputting input data including at least the corneal nerve image into a predictive model-the corneal incision parameter includes a corneal incision risk area in which corneal incision should be avoided -; And
Providing at least a portion of the output data; Including,
The predictive model includes the types of ophthalmic surgery of a plurality of recipients who have undergone ophthalmic surgery to perform corneal incisions, corneal nerve images of the plurality of recipients before the ophthalmic surgery, corneal incision parameters during the ophthalmic surgery of the plurality of recipients, and Learned based on at least one of the corneal nerve images after the ophthalmic surgery of the plurality of recipients
How to recommend corneal incision parameters.
A recording medium readable by a computing device in which a program for executing the method according to any one of claims 1 to 16 is recorded on a computing device.

Images