KR20210025429A - Method for predecting a vaulting value and apparatus using the method - Google Patents

Abstract

Disclosed are a method of predicting a vaulting value and an apparatus using the same. According to one embodiment of the present invention, a method of predicting a vaulting value that indicates a distance from a rear side of a lens to be implanted in an eye of a patient scheduled for intraocular lens implantation and a front side of a crystalline lens, comprises the following steps of: inputting multiple test data of the patient and at least one lens size to a vaulting value prediction model; and predicting the vaulting value corresponding to each of the at least one input lens size from the vaulting value prediction model, wherein the vaulting value prediction model is trained based on multiple test data of a patient who underwent the intraocular lens implantation in the past, the size of a lens implanted in the eye of the patient and a vaulting value measured after surgery of the patient.

Description

Method for predicting bolting value and device using the same {METHOD FOR PREDECTING A VAULTING VALUE AND APPARATUS USING THE METHOD}

The following embodiments relate to a method of predicting a bolting value and an apparatus using the same. More specifically, it relates to a method of predicting a bolting value using artificial intelligence and an apparatus using the same.

Intraocular lens implantation, which is one of the surgical methods that corrects the reduced vision of the naked eye due to refractive error, is to insert a special lens designed to correct the refractive error in the normal eyeball with the lens.

In the prior art, during lens implantation, a lens is selected using a program provided by a lens manufacturer, which is only used as input data for basic eyeball-related values of the person who is to be operated, and the lens size and power are not taken into account of the characteristics of the person's eyeball. Is determined. In general, a program provided by a lens manufacturer is made based on a simple formula, and in this formula, only basic eye-related values of the person who is to be operated are used as input data. As a result, there is a problem in that a person who intends to undergo surgery has to perform reoperation such as removal of a lens because side effects such as cataracts and glaucoma occur a lot due to the insertion of an inappropriate size and power.

Recently, various studies have been conducted to prevent side effects and improve the quality of vision related to lens implantation.

One problem is to provide information on an implantable lens suitable for the eye characteristics of a person undergoing lens implantation, using machine learning.

One task is to provide a lens decision assist system and process using artificial intelligence.

One task is to determine a lens that is more suitable for the surgical candidate in consideration of the eye characteristics of each of the surgical candidates for lens implantation, to reduce the likelihood of side effects of the lens implantation, and to improve the quality of vision.

The problem to be solved by the present invention 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 technical field to which the present invention belongs from the present specification and the accompanying drawings. .

According to an embodiment, it is possible to provide a method of determining a lens to be inserted into an eye of a prospective person during lens implantation through a lens determination model learned using machine learning.

The solution means of the subject of the present invention is not limited to the above-described solution means, and solutions not mentioned will be clearly understood by those of ordinary skill in the art from the present specification and the accompanying drawings. I will be able to.

According to an embodiment, by determining a lens size and a lens having a power suitable for the eye of a person undergoing lens insertion surgery, it is possible to minimize the occurrence of side effects after surgery.

According to an embodiment, by determining a lens size and a lens having a power suitable for the eye of a person who will undergo lens insertion surgery, it is possible to prevent reoperation of the lens insertion surgery.

The effects of the present invention 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 illustrating a position where a lens is inserted during a lens implantation procedure.
2 is a diagram illustrating a system for assisting in determining a lens according to an exemplary embodiment.
3 is a diagram illustrating a system for assisting in determining a lens according to another exemplary embodiment.
4 is a diagram illustrating a system for assisting in determining a lens according to another exemplary embodiment.
5 is a schematic diagram of a lens determination assistance system using a server.
6 is a diagram illustrating a relationship between a server device and a client device.
7 is a diagram illustrating a lens determination model according to an exemplary embodiment.
8 is a diagram for a process of assisting in determining a lens according to an exemplary embodiment.
9 is a diagram of a lens size determination module according to an exemplary embodiment.
10 is a diagram for explaining side effects of lens implantation according to an exemplary embodiment.
11 is a diagram for a process of determining a lens size according to an exemplary embodiment.
12 is a diagram illustrating an embodiment of determining a lens size.
13 is a diagram illustrating an embodiment of determining a lens size.
14 is a diagram illustrating another embodiment of determining a lens size.
15 is a diagram illustrating another embodiment of determining a lens size.
16 is a diagram illustrating another embodiment of determining a lens size.
17 is a diagram schematically illustrating a plurality of sub-models of the lens size determination model.
18 is a diagram for defining a bolting value.
19 is a diagram of a bolting value prediction module according to an embodiment.
20 is a diagram for a process of predicting a bolting value according to an embodiment.
21 is a diagram illustrating an embodiment of predicting a bolting value.
22 is a diagram showing another embodiment of predicting a bolting value.
23 is a diagram illustrating a module for determining a lens power according to an exemplary embodiment.
24 is a diagram for a process of determining a lens power according to an exemplary embodiment.
25 is a view for explaining an example that occurs during a corneal incision process of a person to be operated on.
26 is a diagram illustrating an embodiment of determining a lens power.
27 is a diagram illustrating another embodiment of determining a lens power.

A method of determining a lens to be inserted into an eyeball during lens implantation using machine learning according to an embodiment includes: acquiring a plurality of examination data of a person to be operated on; And inputting the acquired plurality of examination data of the subject of surgery into a lens determination model, and determining a size of a lens to be inserted into the eye of the subject of surgery among the plurality of lens sizes, wherein the lens determination model includes the It is different from the formula for determining the lens to be inserted into the eyeball during lens implantation, and may be learned based on examination data of an operator who has undergone lens implantation in the past and size information of the lens to which the operator's intraocular implantation is applied.

The plurality of examination data of the person to be operated on includes any one of first data and second data, and the priority of the input data to increase the accuracy of the lens size determined by inputting into the lens determination model is the first data May be higher than the second data

The determining of the lens size may include inputting the second data to the lens determination model even when the examination data of the prospective person does not include the first data and includes the second data to The lens size to be inserted into the eye is determined, and the accuracy of the lens size determined when the examination data of the person to be operated includes the first data is the second data that the examination data of the person to be operated on is not the first data. It may be higher than the accuracy of the lens size determined in the case of including.

In the step of determining the lens size, the reliability of the accuracy of the lens size derived according to the examination data of the person to be operated on may be calculated, and the calculated reliability may be presented to the user to determine the lens size.

The method for determining a lens according to an exemplary embodiment includes the first data from the second data or other data when the examination data of the person to be operated on includes the second data or other data except for the first data. Estimating; the estimating step, the accuracy of the lens size derived when the first data is input to the lens determination model is the second data is input to the lens determination model In this case, it may be higher than the accuracy for the derived lens size.

The first data of the plurality of examination data of the person who is to be operated is an ATA (Anterior Chamber Angle), ACD-epi (Anterior Chamber Depth), ACD-endo, CCT (Central Corneal Thickness), Crystalline lens rise (CLR), WTW, Axial Length, BUT, distance between the iris, and a space size value for the lens are obtained, and the second data may be obtained using a general ophthalmic examination.

In the step of determining the lens size, the size of the lens to be inserted into the eye of the person to be operated may be determined as any one of a plurality of predetermined lens sizes.

In the step of determining the lens size, it may be determined not as a plurality of predetermined lens sizes, but as any one of non-standardized lens sizes derived by inputting the inspection data into the lens determination model.

The method for determining a lens according to an exemplary embodiment further includes the step of inputting the obtained examination data of a person to be operated on to a lens determination model to determine a lens power to be inserted into the eye of the person to be operated from among a plurality of lens powers, and the The determining of the lens power includes: when a lens to be determined by the lens determination model is inserted into the eye of the person to be operated on, the lens power is determined so that the target vision of the person to be operated is derived, and the lens decision model is , It may be learned based on the examination data of the operator who has undergone lens implantation in the past and the incision information of the operator.

The obtained examination data of the prospective person includes diopter, astigmatism axis, and astigmatism direction parameters measured from the eyeball of the person who will undergo surgery, and the examination data of the person who will undergo surgery in the lens determination model and corneal incision of the lens implantation procedure of the person who will undergo surgery By inputting the incision information expected in the process, it is possible to determine a lens power suitable for the target vision of the person to be operated on.

When all the examination data of the person to be operated on is input to the lens determination model, a lens power for deriving the target vision of the person to be operated and incision information expected during a corneal incision process of the lens implantation procedure of the person to be operated may be determined.

The incision information is at least one of a corneal incision method, a corneal incision location, a corneal incision direction and/or corneal incision degree, a coma location, corneal astigmatism and lens astigmatism, myopia and astigmatism ratio in the corneal incision process of the lens implantation. It may be information including one.

According to an exemplary embodiment, an apparatus for determining a lens to be inserted into an eyeball during lens insertion using machine learning may include: a memory for storing a plurality of examination data of a person to be operated on; And a processor; wherein the processor acquires a plurality of examination data of the prospective person stored from the memory, and inputs the obtained examination data of the prospective person into a lens determination model, among the plurality of lens sizes. The size of the lens to be inserted into the eye of the person to be operated on is determined, and the lens determination model is different from the formula for determining the lens to be inserted into the eye during the lens insertion procedure, and the examination data of the operator who has undergone lens insertion surgery in the past, and It may be learned based on information on the size of the lens to which the operator's intraocular insertion is applied.

A method of predicting a bolting value representing a distance between a rear surface of a lens to be inserted into an eyeball of a person undergoing a lens implantation procedure and a front surface of the lens of a person undergoing a lens implantation procedure according to an embodiment of the present invention includes a bolting value of a plurality of examination data and at least one lens size of the person undergoing surgery. Inputting into a predictive model; And predicting the bolting value corresponding to each of the at least one input lens size from the bolting value prediction model, wherein the bolting value prediction model includes a plurality of examination data of an operator who has previously undergone lens implantation. , It may be learned based on the size of the lens inserted into the eye of the operator and the bolting value measured after the operation of the operator.

The bolting value may be defined as the shortest distance among a plurality of distances between the rear surface of the lens and the front surface of the lens to be inserted into the eye of the person undergoing the lens implantation procedure.

Predicting the bolting value; providing information on a lens suitability of the input lens size to be inserted into the eye of the person who is to be operated, according to whether the predicted bolting value satisfies a condition of a predetermined range. May include;

When the predicted bolting value satisfies the condition of a predetermined range, the input lens size provides information on the fit as a lens to be inserted into the eye of the person who is to be operated on, and the predicted bolting value is the predetermined range. If the condition of is not satisfied, the input lens size may provide information on non-conformity as a lens to be inserted into the eye of the person who is to be operated on.

The condition of the predetermined range may satisfy that the predicted bolting value is included within 250 to 750 μm.

A method of predicting a bolting value indicating a distance between a rear surface of a lens to be inserted into an eyeball of a person undergoing a lens implantation procedure and a front surface of the lens of a person undergoing a lens implantation procedure according to an embodiment includes inputting a plurality of examination data of the person undergoing surgery into a bolting value prediction model. ; And predicting a predicted lens size suitable for the eyeball of the predicted person and the bolting value corresponding to each of the predicted lens sizes from the bolting value prediction model by inputting a plurality of examination data of the person to be operated on. The bolting value prediction model may be learned based on a plurality of examination data of a patient who has undergone a previous operation of the lens implantation procedure, a lens size inserted into the patient's eye, and a bolting value measured after the patient's surgery.

The expected lens size suitable for the eye of the person to be operated on may include selecting any one of a plurality of predetermined lens sizes.

The predicted lens size suitable for the eye of the person to be operated on may include selecting any one of non-standardized lens sizes rather than a plurality of predetermined lens sizes.

An apparatus for estimating a bolting value representing a distance between a rear surface of a lens to be inserted into an eyeball of a person undergoing a lens implantation procedure and a front surface of a lens, including: a memory for storing a plurality of examination data of the person undergoing surgery; And a processor; wherein the processor inputs a plurality of examination data and at least one lens size of the person to be operated on to a bolting value prediction model, and in each of the at least one input lens size from the bolting value prediction model. The corresponding bolting value is predicted, and the bolting value prediction model is based on a plurality of examination data of an operator who has undergone lens implantation in the past, a lens size inserted into the eye of the operator, and a bolting value measured after the operation of the operator. Can be learned with.

Hereinafter, specific embodiments of the present invention will be described in detail with reference to the drawings. However, the spirit of the present invention is not limited to the presented embodiments, and those skilled in the art who understand the spirit of the present invention can add, change, or delete other elements within the scope of the same idea. Other embodiments included within the scope of the inventive concept may be easily proposed, but this will also be said to be included within the scope of the inventive concept.

In addition, components having the same function within the scope of the same idea shown in the drawings of each embodiment will be described using the same reference numerals.

One Definition of Terms

(1) Lens implantation

Lens implantation is one of the surgical methods that corrects the reduced vision of the naked eye due to refractive errors. It is a surgery in which a special lens designed to correct refractive disorders in the normal state of the eye with a lens is inserted.

1 is a diagram illustrating a position where a lens is inserted during a lens implantation procedure. Types of lens implantation include anterior lens implantation in which a lens is inserted between Co (cornea) and I (iris), and posterior lens implantation in which a lens is inserted into the space between the back of the iris and the lens. Referring to FIG. 1, a lens may be inserted at an IN1 (first lens insertion unit) position in a posterior lens insertion procedure, and a lens may be inserted at an IN2 (second lens insertion unit) position in anterior lens insertion procedure. Hereinafter, for convenience of explanation, the present invention will be described with a focus on a posterior lens implantation, also called an ICL (Implantable Collamer Lens). However, the present invention is not limited thereto, and it goes without saying that the present invention can be applied to an anterior lens implantation.

(2) lens

In the present specification, a lens refers to an intraocular lens used for lens implantation, and may be distinguished from a hard lens and a soft lens worn on the surface of the eyeball.

The information on the lens may include information on the lens size and lens power. The lens size may have a plurality of lens sizes. The lens power may have a plurality of lens powers. In addition, the expression “determining a lens” may mean determining any one of a combination of a plurality of lens sizes and a plurality of lens powers.

(3) Lens crystal model

The lens determination model refers to an algorithm and/or model that determines an intraocular lens inserted into the eye by using artificial intelligence. The lens determination model described below is a model that, when input data of a prospective person's examination data as input data through the model, derives information about a lens to be inserted into the eye of a prospective person as output data corresponding to the input data. . Hereinafter, the configuration, generation process, and determination process of the lens determination model will be described in detail.

(4) learning

Learning refers to a process in which a lens decision model is trained based on training data and labeling data or unlabeled data so that the lens decision model can determine output data for input data. In other words, the lens decision model determines the data by forming a rule.

The lens decision model may be trained through training data. Learning the lens decision model means adjusting the weight of the model.

As a learning method, there are various methods such as supervised learning, unsupervised learning, reinforcement learning, and imitation learning.

2 Lens Determination Assistance System

2.1 Composition of lens decision assist system

2 shows a lens determination assist system 1 according to an embodiment. Referring to FIG. 2, the lens determination assistance system 1 includes a lens size determination module 1000 that derives a lens size from information on a lens to be inserted into the eye of a person who is to be operated on, and a bolting value prediction module that assists in determining the lens size. (2000) and a lens power determination module 3000 for deriving the lens power.

The lens determination assist system 1 may perform a function of determining a lens size, predicting a bolting value, and determining a lens power. Specifically, the lens determination assistance system 1 may determine a lens size, predict a bolting value, and determine a lens power using a lens determination model learned through machine learning.

Of course, in FIG. 2, the lens determination assist system 1 is illustrated as including all of the lens size determination module 1000, the bolting value prediction module 2000, and the lens power determination module 3000, but is not limited thereto. Accordingly, the lens determination assist system may include at least one of a lens size determination module, a bolting value prediction module, and a lens power determination module.

Also, the lens size determination module 1000, the bolting value prediction module 2000, and the lens power determination module 3000 may be implemented in one device or different devices. For example, when a lens size determination module for deriving a lens size in the lens determination assist system 1 is implemented in any one device, only information on the size of a lens to be inserted into the eye of a person to be operated may be obtained.

Alternatively, in the lens determination assistance system 1, at least two or more modules of a lens size determination module, a bolting value prediction module, and a lens power determination module may be implemented in conjunction with each other. For example, in order to obtain information on the size of a lens to be inserted into the eye of a person to be operated on, it may be implemented by combining a lens size determination module and a bolting value prediction module to derive a bolting value predicted along with the lens size to be inserted. have. Hereinafter, each module of the lens determination assist system will be described one by one.

3 is a diagram showing the configuration of the learning device 11 and the decision assisting device 21 of the lens determination assist system 1. In one embodiment, the lens decision assist system 1 may include a learning device 11 and a decision assist device 21.

The learning device 11 may train the lens determination model. Specifically, the learning device 11 may train the lens determination model based on the training data. The learning device 11 may train the lens determination model through various learning methods. For example, the learning device 11 may train the lens determination model by methods such as supervised learning, unsupervised learning, reinforcement learning, and imitation learning. The learning device 11 may train the lens determination model by providing labeled data for the training data. However, labeled data is not necessarily used, and unlabeled data may be used.

The decision assist device 21 may receive and use the learned lens decision model from the learning device 11. Specifically, the determination assist device 21 may output auxiliary information for determining a lens to be inserted into the eye of a person who is to be operated on by using the learned lens determination model. Specifically, when receiving input data such as examination data of a person to be operated on, the decision assist device 21 may output information on a lens suitable in the eye of the person to be operated on. The decision assisting device 21 may enable a user to determine a lens to be inserted into the eye of a person who intends to perform lens implantation through information on the output lens.

The information on the lens may be information on a lens size, a predicted bolting value, and a lens power.

The lens decision model learned by using the learning data in the learning device 11 may be transmitted to the decision assist device 21. Of course, in FIG. 3, the learning device 11 and the decision assisting device 21 are illustrated as being separated, but are not limited thereto, and in some cases, the learning device 11 and the decision assisting device 21 are implemented separately. It can be done, or it can be implemented as one without being separated. For example, the decision assist device may be the same device as the learning device, or may be a separate device.

4 is a diagram showing a configuration of a learning device and/or a decision assist device. Referring to FIG. 4, the learning device and/or the decision assist device may include a memory unit 31, a control unit 33, and a communication unit 35.

The learning device and/or the decision assist device may include a control unit 33. The controller 33 may control the operation of the learning device and/or the decision assist device. The control unit 33 may read system programs and various processing programs stored in the memory unit 31.

The control unit 33 includes at least one of a CPU (Central Processing Unit), a RAM (Random Access Memory), a GPU (Graphic Processing Unit), one or more microprocessors, and other electronic components capable of processing input data according to predetermined logic. It may include.

The learning device and/or the decision assist device may include a memory unit 31. The memory unit 31 may store data required for learning and a learning model. The memory unit 31 may store examination data of a person to be operated on.

The memory unit 31 may store training data, labeling data, unlabeled data, input data, output data, and the like.

The memory unit 31 is a nonvolatile semiconductor memory, a hard disk, a flash memory, a RAM, a ROM (Read Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), or other tangible nonvolatile recording medium. It can be implemented as

The memory unit 31 may store various processing programs, parameters for performing processing of the programs, processing result data, and the like.

The learning device and/or the decision assist device may further include a communication unit 35. The communication unit 35 may communicate with an external device. The communication unit 35 may perform wired or wireless communication. The communication unit 35 may perform two-way or one-way communication.

The learning device and/or the decision assist device may include a processor, a volatile memory, a nonvolatile memory, a mass storage device, and a communication interface. The processor may perform learning of the lens decision model through the learning device and/or the decision assist device.

5 is a schematic diagram of a lens determination assistance system using a server. Referring to FIG. 5, the lens determination assist system may include a plurality of client devices and server devices. Hereinafter, a first client device among a plurality of client devices will be exemplarily described, but the second client device may perform the same operation.

The first client device 51 may request information from the server device 40 and obtain information on the lens determination assistance transmitted in response thereto, and may request lens determination assistance information from the server device 40.

The first client device 51 may acquire data necessary for lens determination and may transmit the data acquired from the determination assist device.

The first client device 51 may be a portable device such as a smartphone or a tablet PC.

The server device 40 may store and/or drive the lens determination model. The server device 40 may store weights constituting the learned lens determination model. The server device 40 may collect and/or store data used to assist in lens determination.

The server device 40 may output the result of the lens determination auxiliary process using the lens determination model to the first client device 51. The server device 40 may obtain feedback from the first client device 51.

In an embodiment, the first client device 51 may obtain a lens determination model from the server device 40 and drive the obtained lens determination model. In this case, the first client device 51 may obtain information on the lens determination assistance by driving the lens determination model without providing the input data to the server device 40.

The server device 40 may communicate with the first client device 51 that acquires the first lens determination assistance information and/or the second client device 52 that acquires the second lens determination assistance information.

6 is a diagram schematically illustrating a relationship between the server device 40 and the client device 50. Referring to FIG. 6, the server device 40 may communicate with the client device 50 through a communication unit. The communication unit may perform wired or wireless communication. The communication unit may perform two-way or one-way communication. The client device 50 may also communicate with the server device 40 through a communication unit.

In one embodiment, when the client device 50 transmits the input data of the person to be operated on to the server device, information on the lens to be inserted into the eye of the person to be operated is transmitted using the lens determination model learned by the server device 40 I can receive it.

In one embodiment, the control unit 53 of the client device 50 obtains input data from the memory unit 51, and the obtained input data is transferred to the communication unit 45 of the server device 40 through the communication unit 55. Can be transmitted. In addition, the control unit 43 of the server device 40 obtains a result value by inputting input data to the lens determination model stored in the memory unit 41, and the obtained result value is obtained by using the communication unit 45 to obtain a result value. 50) may be transmitted to the communication unit 55.

2.2 Lens crystal model

7 is a diagram showing the configuration of a lens crystal model. Referring to FIG. 7, the lens determination model 100 may include a lens size determination model 110, a bolting value prediction model 120, and a lens power determination model 130.

Of course, in FIG. 7, the lens determination model 100 is shown to include all of the lens size determination model 110, the bolting value prediction model 120, and the lens power determination model 130, but is not limited thereto. Accordingly, the lens determination model 100 may include at least one of a lens size determination model, a bolting value prediction model, and a lens power determination model.

In an embodiment, the lens determination model 100 may include a lens size determination model and a lens power determination model, or a lens size determination model and a bolting value prediction model.

In addition, the lens determination model 100 may be implemented in one device, or may be implemented in different devices. For example, when the lens determination model includes a lens size determination model and a bolting value prediction model, each model may be implemented in one device by interlocking with each other. Alternatively, when the lens determination model 100 includes a lens size determination model and a lens power determination model, the lens size determination model may be implemented in different devices independently of the lens power determination model.

8 is a diagram for a lens decision assist process. Referring to FIG. 8, the lens determination auxiliary process may be considered divided into a learning step S100 of learning a lens determination model and a determination step S200 of performing a lens determination model using the learned lens determination model.

Referring to FIG. 8, the learning step S100 may be a process of learning a lens determination model using training data. In addition, the learning step S100 may be performed by the learning device.

According to an embodiment, in the learning step S100, training data may be acquired, and a lens determination model may be trained from the acquired data. That is, the learning step S100 is a process of generating a lens determination model, and according to the generation of the lens determination model, model parameters constituting the lens determination model may be obtained. For example, the model parameter may include weights adjusted while learning the lens determination model.

In one embodiment, the learning data is a plurality of examination data of an operator who has undergone a lens implantation in the past, information of a lens to which the intraocular insertion of the operator is applied (lens size and lens power), operation parameters, and a ball measured after the operation of the operator. It may include setting value data.

In addition, the examination data among the learning data may include examination data obtained from a plurality of examination equipment related to eye measurement by a surgeon who has undergone lens implantation in the past.

In an embodiment, the lens information among the learning data may include a lens size and/or a lens power inserted into an eye of an operator who has undergone a lens insertion procedure in the past. In this case, the information on the lens may include a lens size and/or a lens power inserted into the eye of the operator when a side effect has not occurred after the lens insertion surgery by the operator who has undergone the lens insertion surgery in the past. Of course, according to an embodiment, the information on the lens may include a lens size and/or a lens power inserted into the eyeball by the operator when a side effect occurs after the lens insertion operation by the operator who has undergone the lens insertion operation in the past.

In addition, the surgical parameter among the learning data may be information regarding corneal incision information during a corneal incision process of an operator who has undergone lens implantation in the past. As an example, the surgical parameter may include a corneal incision method, a corneal incision location, a corneal incision degree, and the like.

In one embodiment, the bolting value data among the learning data refers to a value representing the distance between the rear surface of the lens to be inserted into the eye of the person who will undergo lens implantation and the front of the lens. It can mean bolting value data.

The lens determination model may be a model that outputs lens information based on training data. At least one of a plurality of learning algorithms for calculating lens information may be selected as the lens determination model. For example, the algorithm may be logistic regression, K-Nearest Neighbors, Support Vector Machine, Decision Tree, and the like.

The lens decision model may use a plurality of learning algorithms among a plurality of learning algorithms for calculating a predicted value. For example, an ensemble method may be used for a lens decision model, and better prediction performance may be obtained compared to the case of using separate learning algorithms.

The lens determination model may be implemented in the form of a classifier that generates lens information. The classifier can perform double classification or multiple classification.

The lens decision model derives lens information, and may be implemented in the form of regression. The regression method may be a linear regression method, a logistic regression method, or the like.

In one embodiment, in the learning step (S100), a result value (output data) is obtained using a model to which arbitrary weights are assigned, and the obtained result value (output data) is compared with the labeling data of the training data. It can be performed by performing backpropagation according to an error and optimizing the weights.

Although not shown, the learning step S100 may include an evaluation step of evaluating the performance of the learned lens determination model. In the evaluation step, the lens decision model can be evaluated using the evaluation data set. The evaluation of the lens decision model may be a step of evaluating the lens decision model learned by the learning step and predicting new data using the lens decision model. Specifically, the evaluation step may be a step of measuring whether the learned lens determination model can be generalized to new data.

In addition, in the learning step S100 of the lens determination model, the training data set and the evaluation data set may be distinguished. Here, the training data set may mean a set of training data used in the learning process in the learning stage, and the evaluation data set may mean a set of evaluation data used in the evaluation process in the evaluation stage. In this case, the training data set used to train the lens decision model may not be used in the evaluation step of the lens decision model.

In addition, referring to FIG. 8, in the determining step S200, a model parameter may be obtained in the learning step and the learned lens determination model may be used. Specifically, in the determining step S200, after acquiring input data such as examination data of a prospective person, information (a result value) of a lens to be inserted into the eye of a person who is undergoing surgery may be obtained using the learned lens determination model. In addition, the determining step S200 may be performed by the determination assisting device.

The input data may include data on a plurality of examinations of a person who will undergo a lens implantation surgery.

The result value may include information on a lens to be inserted into the eye of the person to be operated on. The lens information may include a lens size, a lens power, a bolting value predicted value, and the like. Hereinafter, the determination of the lens size, the prediction of the bolting value, and the determination of the lens power will be described in more detail.

3 Determine the lens size

3.1 Composition of lens size determination module

9 is a diagram showing the configuration of the lens size determination module 1000. In an embodiment, the lens size determination module 1000 may output a lens size to be inserted into an eye of a person to be operated on from input data.

Referring to FIG. 9, the lens size determination module 1000 may include an input unit 1100, a lens size determination unit 1300, and an output unit 1500.

The input unit 1100 may obtain input data from a database. Here, the input data may be data of a plurality of examinations of a person to be operated on.

Specifically, the input unit 1100 may be directly connected to a database to obtain input data. In addition, the input unit 1100 may receive and obtain input data from a server or other external device.

The input data may be examination data of a person to be operated on. The input data may include a plurality of parameters. Specifically, the input data may include test data representing different parameters obtained from the same or different test equipment, or may include test data representing the same parameters obtained from different measurement equipment.

Also, the input data may include test data measured at the same time point or may include test data measured at different time points.

The input data may be the same and/or different parameters obtained from the same test equipment, or may be the same and/or different parameters obtained from different test equipment.

Also, the number of input data may be one or a plurality of input data. Each input data may have a different degree of influence on the result value (the size of the lens to be inserted into the eye of the person who will be operated on). In one embodiment, each input data may include a parameter, and the degree to which the input data affects the result value may vary according to the type of the parameter included in the input data. Here, the parameter is defined to indicate the characteristics of the eyeball of the person who is to be operated on, and may be expressed numerically. For example, the parameter is ATA (angle to angle distance), ACD (Anterior Chamber Depth)-epi, ACD-endo, CCT (Central Corneal Thickness), CLR (Crystalline Lens Rise), WTW (White to white), AL (Axial Length), corneal curvature, refractive error (myopia, astigmatism, farsightedness), pupil size, intraocular pressure, vision, corneal shape, corneal thickness, eyeball length, and lens insertion space. I can.

The person who will undergo surgery may include a person who is planning to perform the surgery by selecting a lens implantation procedure among the vision correction surgery. The person who is to be operated may be a person who is going to perform lens implantation using information on the lens output from the lens determination assistance system. In addition, the user may be a person who obtains information on a lens to be inserted into the eye of the person who is to be operated by using the lens determination assistance system. For example, it may include a doctor, a lens manufacturer, or the like who performs lens implantation.

The plurality of examination data may be data obtained from a plurality of examination equipments that measure the eyeball, and may include a plurality of eye-related parameters.

In addition, the inspection data may include paperweight data. Specifically, it may include a target visual acuity that is desired after the lens implantation of the person who is to be operated.

In addition, the examination data may be measurement data for the cornea. For example, it may include corneal shape, corneal symmetry, corneal thickness measurement data, corneal structure tomography data, corneal shape analysis data, corneal curvature, corneal endothelial cytology data, and the like.

In addition, the test data may be measurement data for visual acuity and/or refraction. For example, it may include frequency data of glasses worn in the past, visual acuity tests, refractive abnormalities (myopia, astigmatism, farsightedness), and the like.

In addition, the test data may be measurement data about a distance or the like in the eyeball. Specifically, it may include the size of the pupil, the length of the eyeball, and the distance of the space in which the lens is to be inserted.

In addition, the test data may be data on eye diseases and/or possessed diseases. For example, it may include data on the presence or absence of retinal disease, glaucoma, retinal degeneration, etc., cataracts, diseases of the back of the iris, and the like.

In addition, the test data may be measurement data for the retina. For example, it may include fundus retinal photography.

And, the inspection data may be measured from one or a plurality of equipment.

Of course, the plurality of examination data may not be limited to only data obtained from a plurality of devices for measuring the eyeball. In addition to that, various data may be included. For example, it may include test data such as eye-related genes and blood.

When the lens size determination unit 1300 inputs input data such as a plurality of examination data of a person to be operated on, it may determine a lens size suitable for the eye of the person to be operated on. Here, the appropriate lens size may mean a lens size at which the possibility of occurrence of side effects is minimized when a lens implantation procedure is performed to a person to be operated on. A specific operation of the lens size determination unit 1300 will be described in more detail with reference to FIG. 11.

In an embodiment, the lens size determination unit 1300 may calculate a reliability of the accuracy of a lens size derived according to examination data of a person who is to be operated on. Information on the reliability may be stored in advance or may be provided from outside. For example, information including that the reliability of the result value of the first equipment among the plurality of inspection equipment is 90% and the reliability of the result value of the second equipment is 80% may be transmitted through a pre-stored external device. . In an embodiment, the lens size determination model 110 may calculate the reliability of the accuracy of the lens size derived according to the examination data of the person to be operated on based on the reliability previously stored in the learning step. For example, when using the test data measured by the first device, it may be calculated that the reliability of the output lens size is 90%, and may be presented to the user through the output unit 1500.

The output unit 1500 may output the lens size obtained through the lens size determination unit 1300 to a user. In an embodiment, the output unit 1500 may provide a display that visually outputs output data on a screen. In addition, the output unit 1500 may output in various formats such as images and text.

The output unit 1500 may output information (output data) on the size of a lens to be inserted into the eye of a person to be operated on through the lens size determination unit 1300.

The output unit 1500 may output a standardized lens size according to a method of learning a lens size determination model.

According to an embodiment, when the lens size determination model is implemented in the form of a classifier, the output unit may output a standardized lens size. The standardized lens size may be a ready-made lens size. The ready-made lens size may be a size that has been made according to a predetermined standard in advance. For example, the standardized lens sizes may be 12.1mm, 12.6mm, 13.2mm, and 13.7mm. It will be described in more detail in Table of Contents 3.3 below. However, the present invention is not limited thereto, and when the lens size determination model is implemented in the form of regression, the output unit may output a non-standardized lens size. The non-standardized lens size does not select any one of predetermined categories, such as a standardized lens size, but refers to a numerical value of the lens size itself, and the output unit may output a numerical value of the lens size. Details of this will be described in Table of Contents 3.3.

10 is a diagram for explaining side effects of lens implantation. Referring to FIG. 10, FIGS. 10A and 10C show that an inappropriate lens size is inserted after a lens implantation procedure, and FIG. 10B shows that a suitable lens size is inserted during a lens implantation procedure. will be. In addition, I is the iris, La, Lb, Lc is the lens inserted into the eye, C is the lens.

The side effects of lens implantation may occur when surgery is performed with an unsuitable lens size without considering the characteristics of the eye of the person to be operated on. For example, referring to (a) of FIG. 10, a lens having a lens size of La may be inserted into an eye of a person to be operated on. This is inserted by selecting a small lens size without considering the characteristics of the eyeball of the person to be operated on, and friction between the lens and the lens may cause damage to the lens, resulting in cataract. Further, referring to (c) of FIG. 10, a lens having a lens size of Lc may be inserted into an eye of a person to be operated on. This is inserted by selecting a large lens size without considering the characteristics of the eyeball of the person to be operated on, and the end of the Lc is sandwiched between the lens and the iris, blocking the flow of waterproofing, which may cause glaucoma.

Therefore, for lens implantation, the size of the lens that minimizes the possibility of side effects should be determined in consideration of the eye characteristics of the person to be operated on. As an example, referring to FIG. 10B, Lb is in consideration of the characteristics of the eyeball of the person who is to be operated on, and may be a lens size suitable for the eyeball of the person to be operated on. Lb is a size that does not cause friction between C and I, and is inserted at a position that maintains an appropriate distance between I and I, and may be a lens size that minimizes the possibility of side effects.

In this way, the possibility of side effects can be minimized only when the lens size inserted in the eyeball, the lens, the iris, and the size of the lens insertion space are inserted in consideration of the characteristics of the eyeball of the person to be operated on.

3.2 Lens size determination process

11 is a diagram showing a flow chart of the lens size determination process S1000. Referring to FIG. 11, the lens size determination process (S1000) includes a step of acquiring input data such as a plurality of examination data of a candidate for surgery (S1100), and a step of deriving a lens size using a lens size determination model (S1300). can do. The lens size determination process S1000 may be performed by the lens size determination module 1000 described above in FIG. 2.

Specifically, in the step of acquiring input data (S1100 ), the input data may be a plurality of examination data obtained from a plurality of examination equipment related to eye measurement of a person who is to be operated on. In one embodiment, the plurality of inspection equipments related to eye measurement may be inspection equipment that measures using laser and/or high-frequency ultrasound. For example, it may include ultrasound biomicroscopy (UBM), optical coherence tomography (OCT), and the like.

In one embodiment, the plurality of inspection data may include the parameters described above with reference to FIG. 9. Specifically, the plurality of examination data includes corneal curvature, refractive error (myopia, astigmatism, farsightedness), pupil size, intraocular pressure, vision, corneal shape, corneal thickness, eye length, lens insertion space, ATA (Anterior Chamber Angle). , ACD(Anterior Chamber Depth)-epi, ACD-endo, CCT(Central Corneal Thickness), CLR(Crystalline Lens Rise), WTW(White to white), AL(Axial Length), BUT, measuring distance between iris, etc. May contain parameters.

The lens size may be derived from the acquired input data using a lens size determination model.

In addition, in an embodiment, since the degree of influence on the result value is different according to the type of parameter included in the input data, the result value may vary for each input data.

Further, in another embodiment, each input data may include at least some of the same parameters, but this may be derived by different inspection equipment. Even if the same parameters are derived from different inspection equipment, the numerical values indicated may be different. This may be due to different methods and principles of measuring parameters for each inspection equipment. For example, the A parameter obtained from the UBM inspection equipment (here, the A parameter represents an arbitrary parameter) is a parameter that performs the same function as the A parameter obtained from the OCT inspection equipment, but a numerical value indicating this may be different. . As described above, since the accuracy of the measured parameter is different depending on the inspection equipment, the degree to which the input data affects the result value may be different.

In addition, each parameter or even the same parameter may have a different degree of influence on the result value depending on whether it is a parameter output from any inspection equipment, and the priority between input data may vary accordingly.

In order to increase the accuracy of the result, the weight can be increased for a parameter with a high priority or a parameter derived from a high-priority inspection equipment.

In one embodiment, the input data may include priority data. Priority data may be prioritized according to the type of parameter included in the input data. For example, when a first parameter having a large degree of influence on deriving a lens size is included, the input data may be first priority data. When the degree of influence on derivation of the lens size includes a second parameter that is smaller than the first parameter, the input data may be second priority data. For convenience of explanation, only the first priority data and the second priority data have been described, but the present disclosure is not limited thereto, and a plurality of priority data may be included.

In an embodiment, when the lens size is determined using input data including first priority data, the first lens size may be derived, and the lens size is determined using input data including second priority data. If determined, a second lens size may be derived. For example, the probability of the accuracy of the result value may be higher in the first lens size than the second lens size. In this case, when the person who is to be operated is operated with the first lens size, side effects may occur less than when the surgery with the second lens size is performed.

In an embodiment, in the lens size derivation step (S1300), when the input data does not include the first priority data and the second priority data is included, the lens size determination unit uses the second priority data to determine the lens size. You can derive the size.

In one embodiment, the input data may necessarily include first priority data. This is to ensure the accuracy of the result value.

In the learning step S100, the first priority data and the second priority data may be learned together, or each of the lens size determination model may be trained separately. According to an embodiment, if the first priority data and the second priority data are learned together, in the lens size derivation step (S1300), any one of the first priority data and the second priority data may be used. According to another embodiment, if only the first priority data is learned, in the lens size derivation step (S1300), only the first priority data may be used, and if only the second priority data is learned, in the lens size derivation step (S1300). , Only the second priority data may be used. Of course, the present invention is not limited thereto, and according to an embodiment, even if only the first priority data is learned, the second priority data may be used in the lens size derivation step (S1300), and even if only the second priority data is learned, the lens size derivation step First priority data may be used in (S1300).

3.3 Example

12 and 13 are diagrams illustrating an embodiment of determining a lens size. That is, in FIGS. 12 and 13, step S1300 described above in FIG. 11 will be described in more detail. 12 and 13, in an embodiment, a lens size determination model may be implemented including a classifier.

In one embodiment, the classifier may use a type of algorithm such as a decision tree, a support vector machine, and a random forest. This is only an example and is not limited thereto.

In an embodiment, the lens size determination module 1000 may input input data to the lens size determination model 110 and derive the lens size from the lens size determination model 110. The lens size determination model 110 may include a classifier, and the classifier may determine any one of lens sizes having a predetermined value.

In addition, a standardized lens size may be obtained using a lens size determination model implemented including a classifier from input data of a person to be operated on. The classifier may determine the size of one lens to be inserted into the eye of the person to be operated on from input data of the person to be operated on.

Also, the standardized lens size may be a ready-made lens size. The ready-made lens size may be a size that has been made according to a predetermined standard in advance. In one embodiment, a lens size of 12.6 mm, which is one of 12.1mm, 12.6mm, 13.2mm, and 13.7mm, is a standardized lens size using a lens size determination model implemented by a classifier from input data of a candidate for surgery. Can be determined.

14 and 15 are diagrams illustrating another embodiment of determining a lens size. That is, in FIGS. 14 and 15, step S1300 described above in FIG. 11 will be described in more detail. Referring to FIGS. 14 and 15, in an embodiment, a lens size determination model may be implemented including a regression model.

In one embodiment, the regression model may use a type of algorithm such as linear regression, regression tree, support vector regression, and kernel regression. This is only an example and is not limited thereto.

In an embodiment, the lens size determination module 1000 may input input data to the lens size determination model 110 and derive the lens size from the lens size determination model 110. The lens size determination model 110 may include a regression model, and the regression model may determine any one of a lens size that may or may not be a predetermined value.

In addition, the input data of the person to be operated on may obtain a standardized and/or non-standardized lens size using a lens size determination model implemented including a regression model. The regression model may derive the probability of the size of the lens to be inserted into the eye of the person who is to be operated from the input data of the person to be operated on. The lens size derived with the highest probability may be the most suitable lens size among the lens sizes to be inserted into the eye of a person to be operated on.

According to an embodiment, the output unit 1500 may output a non-standardized lens size according to a method of learning a lens size determination model. The non-standardized lens size may be expressed as a total lens size including a ready-made lens size. Specifically, the non-standardized lens size is the size of the lens to be inserted into the eyeball in consideration of the characteristics of the eyeball of the person to be operated on, and may be larger or smaller than a pre-made lens size, or may be a size between pre-made lens sizes. The non-standardized lens size may be a lens size to be custom-made in consideration of the characteristics of the eye of a person to be operated on. The non-standardized lens size may be a lens size optimized for the eye of a subject to be operated rather than a standardized lens size. This may be a lens size customized to the eye of the person to be operated on.

In another embodiment, the lens size determination model 110 may be implemented including a classifier and a regression model. That is, the lens size determination model 110 may be implemented by combining a classifier and a regression model serially or in parallel. For example, the lens size determination module 1000 inputs input data to the lens size determination model 110 in which a classifier and a regression model are combined, and may derive the lens size and numerical values from the combined lens size determination model 110. I can. For example, a lens size of 12.5mm output through a regression model can derive a standardized lens size of 12.6mm through a classifier. Alternatively, a lens size of 13.2 mm output through the classifier may derive a non-standardized lens size of 13.3 mm through a regression model. This is merely an example, and the lens size output through the classifier and the lens size output through the regression model may be simultaneously derived.

16 is a diagram illustrating another embodiment of determining a lens size. Referring to FIG. 16, the lens size determination module 1000 may further include a data complementary unit 1200 that supplements input data.

When the priority data cannot be obtained from the test equipment or in an environment where the test equipment capable of obtaining the priority data is not provided, the data supplement unit 1200 is For this, a more accurate lens size can be derived.

According to an embodiment, the input data may include first priority data and second priority data, only first priority data, or only second priority data. When the user can use only the second priority data and cannot use the first priority data as input data, the accuracy of the result value may be lower than when using only the first priority data. As in this case, even when the first priority data is missing, in order to improve the accuracy of the result value, the first priority data may be estimated using the data supplement unit 1200.

The data supplementation unit 1200 may estimate first priority data from the input data.

The priority data may include parameters having a large degree of influence on the result value. In order to increase the accuracy of the result value, data with high priority, that is, data including parameters having a large degree of influence on the result value, can be input. For example, when the lens size determination unit determines the lens size by using the first input data including ATA among parameters, the accuracy of the result value may be high, and the second input data including only CCT without ATA may be used. When determining the lens size by using, the accuracy of the result value may be low. In this case, the first input data includes first priority data having a high priority, and the accuracy of the result value may be high.

In order to increase accuracy even when the first priority data cannot be obtained and only the second priority data can be obtained depending on the situation, the data supplement unit may estimate the first priority data using the second input data. The estimated first priority data may be used as input data in the lens size determination unit 1300. For example, the ATA corresponding to the missing value may be estimated from parameters such as CCT and vision test data included in the second input data.

In an embodiment, when the inspection equipment capable of measuring the first priority data is not provided, the first priority data may be estimated using the data supplement.

In an embodiment, the data supplement unit 1200 may estimate input data other than the first priority data as first priority data using a separate formula.

In an embodiment, the data supplementation unit 1200 may estimate input data other than the first priority data as first priority data using a separate formula using the data supplementation model. Although not shown, the data supplementation model may be learned based on first priority data and second priority data as training data. For example, the data supplementation model may be trained to derive first priority data by receiving second priority data. The learned data supplementation model may derive estimated first priority data by inputting second priority data as input data. This is only an example and is not limited thereto.

Also, in an embodiment, the lens size determination model may use a plurality of machine learning algorithms among a plurality of machine learning algorithms for calculating a predicted value. For example, the lens size determination model may be learned using an ensemble method and the lens size may be estimated. As the ensemble technique is used in the lens size determination model, the accuracy of the lens size determination model may be improved.

17 is a diagram schematically illustrating a plurality of sub-models of the lens size determination model. Referring to FIG. 17, the lens size determination model may include a plurality of sub-models. Each of the plurality of sub-models may independently determine a lens size. For example, the first submodel may be a model that determines the lens size by being trained using a random forest method, and the second submodel may be a model that is trained using a decision tree method to determine the lens size. In addition, although only the first sub-model and the second sub-model are illustrated in FIG. 17, this is only an example, and the sub-model may include a plurality of sub-models.

A plurality of sub-models may be connected in parallel with each other. Here, input data input to the plurality of sub-models and output values output from the plurality of sub-models may be the same or different from each other.

The lens size determination model may output a prediction result based on the output value of the sub-model.

The lens size determination model may include an output sub-model that outputs a prediction result based on output values of a plurality of sub-models connected in parallel. In an embodiment, when the first output value and the second output value, which are output values of the first sub-model and the second sub-model, are the same, the output sub-model may output the same value. In another embodiment, when the first output value and the second output value, which are output values of the first sub-model and the second sub-model, are different, the output sub-model considers the output values of the plurality of sub-models at a predetermined ratio and outputs a prediction result. Alternatively, a specific value among the plurality of output values may be output. In other words, the output sub-model may give a weight to the first output value from the first sub-model and the second output value from the second sub-model, and reflect the weight applied to each output value to output the lens size. For example, a weight of 0.8 is given to the first output value and a weight of 0.2 is given to the second output value, and the first output value represents 12.6 mm of the standardized lens sizes, and the second output value is 13.2 mm of the standardized lens sizes. In the case of, the output sub-model may derive a lens size of 12.6 mm, which is a first output value having a high weight, as an output value.

In addition, for example, a weight of 0.8 is given to the first output value, a weight of 0.2 is given to the second output value, and the first output value represents 12.6 mm among non-standardized lens sizes, and the second output value is non-standardized. When 13.2mm of the lens size is indicated, the output sub-model can derive a lens size of 12.7mm reflecting the weight as an output value.

Also, the weight may be determined during a learning process. That is, for a lens size determination model including a plurality of sub-models, the learning step (S100) described above in FIG. 8 may be performed, and a weight may be determined in the learning step (S100).

In another embodiment, the output sub-model may output another value generated based on the plurality of output values as a prediction result. Here, the output value of the output sub-model may be of the same type or different types as the plurality of output values.

In an embodiment, the first sub-model and the second sub-model may be the same, and input data input to each sub-model may be different. The input data may be first priority data or second priority data. Sub-models to which data with high priority is input may be given a high weight. For example, a first sub-model into which first priority data is input is assigned a higher weight than a second sub-model into which second priority data is input, so that a first output value may be derived as a lens size output value.

4 Bolting value prediction

4.1 Bolting value definition

18 is a diagram for defining a bolting value. The vaulting value (or also referred to as the vault value) is a value representing the distance between the rear surface of the lens to be inserted into the eye of the person who is to be inserted into the eye and the front of the lens. It is defined as the shortest of the plurality of distances between the posterior and the anterior lens. Referring to FIG. 18, L denotes a lens inserted into the eye of a person to be operated on, I denotes an iris, C denotes a lens, and V denotes a bolting value. L can be inserted in the space between I and C. There may be a plurality of distances between the lens inserted into the eye and the front of the lens. Among them, the shortest distance between the rear surface of the lens and the front surface of the lens, that is, the distance between the lens and the lens in a vertical direction from the center of the cornea, may be V.

In general, the bolting value may be measured in order to confirm whether a lens of an appropriate size is inserted into the eye of the operator after lens insertion surgery. When the bolting value measured after the operation is included within a certain range, it may be determined that the size of the lens inserted into the eyeball is a lens size suitable for the eyeball of the operator. For example, in the predetermined range, the bolting value may be included within 250 to 750 μm. In one embodiment, when the bolting value is 250 μm or less, the size of the lens inserted into the eye of the operator may be regarded as having a size smaller than the size suitable for the eye of the operator. When a size smaller than the lens size suitable for the operator's eye is inserted, cataract may be induced, as described in FIG. 10A. In another embodiment, when the bolting value is 750 μm or more, the size of the lens inserted into the eye of the operator may be regarded as having a size larger than the size suitable for the eye of the operator. When a size larger than a lens size suitable for the operator's eye is inserted, glaucoma may be induced as described in (c) of FIG. 10. Therefore, in order to prevent side effects of lens implantation, the bolting value after surgery may have to be included within an appropriate range. That is, there is a need to accurately design and then insert a lens before lens implantation. Hereinafter, a bolting value prediction module for predicting a bolting value and a process therefor will be described.

4.2 Configuring the bolting value prediction module

19 is a diagram showing the configuration of the bolting value prediction module 2000. As shown in FIG. In an embodiment, the bolting value prediction module 2000 may output a predicted bolting value in the eye of a person to be operated on from the input data.

Referring to FIG. 19, the bolting value prediction module 2000 may include an input unit 2100, a bolting value prediction unit 2300, and an output unit 2500.

The input unit 2100 may obtain input data from a database. The input data may be data of a plurality of examinations of a person to be operated on.

Specifically, the input unit 2100 may be directly connected to a database to obtain input data. In addition, the input unit 2100 may receive and obtain input data from a server or another external device.

The input data may be examination data of a person to be operated on. The inspection data may be the same as described in Table of Contents 3.1 above. Hereinafter, only different contents will be described.

According to an embodiment, the input data may include an arbitrary expected lens size to be inserted into the eye of a person who is to be operated on. Any expected lens size may be a standardized or non-standardized lens size.

In an embodiment, the bolting value predictor 2300 may predict a bolting value of a person who is to be operated on from the input data.

In addition, the bolting value predicting unit 2300 may provide the predicted bolting value when the predicted bolting value is within a certain range, and the user may determine that the operation has been performed with an appropriate lens size based on the predicted bolting value. I can.

In an embodiment, the bolting value predictor 2300 may provide information on whether an input lens size is possible for a person who is to be operated on a lens according to the predicted bolting value. For example, when a predicted bolting value of 200 μm that is not included in the range of 250 to 750 μm is derived, it may provide a judgment that a lens implantation procedure is impossible for a person to be operated on. This is only an example and is not limited thereto, and on the contrary, when the predicted bolting value is within a certain range, it may provide a determination that a lens implantation procedure is possible.

In addition, the bolting value predictor 2300 may provide information on whether the input lens size is suitable for a lens implantation procedure of a person who is to be operated according to the predicted bolting value. For example, when the predicted bolting value is 500 μm, information indicating that a lens size of 13.2 mm input as input data is suitable for a lens implantation procedure of a person to be operated may be provided. In addition, when the predicted bolting value is 800 μm, it may provide information that the lens size of 13.2 mm input as input data is not suitable for a lens implantation procedure for a person who is to be operated on. This is only an example and is not limited thereto.

The specific operation of the bolting value predictor 2300 will be described in more detail with reference to FIG. 20.

The output unit 2500 may output the bolting value obtained through the bolting value prediction unit 2300 to the user. In an embodiment, the output unit 2500 may provide a display that visually outputs output data on a screen. In addition, the output unit 2500 may output in various formats such as images and text.

In an embodiment, the predicted bolting value may be a criterion for determining the result of the lens implantation procedure. For example, if the predicted bolting value is included in the range of 250 to 750 μm, the user may determine that the operation has been performed with a lens size suitable for the eye of the person who is to be operated on.

In an embodiment, according to a result value of the bolting value predictor 2300, information on whether or not to perform a lens implantation procedure and/or whether or not a person who is undergoing surgery for a lens size input as input data may be output.

4.3 Bolting value prediction process

20 is a diagram showing a flow chart of a bolting value prediction process (S2000). Referring to FIG. 20, the bolting value prediction process (S2000) includes acquiring input data such as examination data of a candidate for surgery (S2100), and deriving a predicted bolting value using a bolting value prediction model (S2300). I can. The bolting value prediction process S2000 may be performed by the bolting value prediction module 2000 described above in FIG. 2.

Specifically, in the step of acquiring the input data (S2100), the input data may be a plurality of examination data obtained from a plurality of examination equipments related to eye measurement of a person to be operated on. This is the same as the process of determining the lens size in Table of Contents 3.2, so it is omitted.

In one embodiment, the input data may include the plurality of inspection data and an arbitrary lens size.

In the step of deriving the predicted bolting value (S2300 ), a bolting value corresponding to an arbitrary lens size may be predicted using a bolting value predicting model based on a plurality of examination data of a person to be operated on.

In an embodiment, the bolting value prediction model 120 may be learned by the learning device 11 as described with reference to FIG. 3, and the bolting value predicted by the decision assist device 21 may be derived. In addition, the bolting value prediction model 120 may be learned through the learning step S100, and the predicted bolting value may be derived through the determining step S200. The matters described in FIGS. 3 and 8 may be applied to the bolting value prediction model 110 as it is.

4.4 Example

In an embodiment, the bolting value prediction module may predict the bolting value by using a plurality of examination data and/or an expected lens size of a person to be operated on as input data.

21 is a diagram illustrating an embodiment of predicting a bolting value. Referring to FIG. 21, the bolting value predictor 2300 may predict a bolting value and a lens size by using a plurality of examination data of a person to be operated on as input data.

The bolting value may be derived differently depending on the size of the lens to be inserted into the eyeball.

In an embodiment, the bolting value prediction module 2000 may output the lens size and the predicted bolting value together when the inspection data is input to the bolting value prediction model 120. By outputting the lens size and the predicted bolting value together as output data, the user can accurately determine the lens size suitable for the characteristics of the eyeball of the person to be operated on based on the predicted bolting value. For example, when a lens size of 12.6mm and 500㎛ are output, the predicted bolting value is included within an appropriate range, so that the user can determine that the output lens size is a lens size suitable for the characteristics of the eyeball of the person who is to be operated on. . Alternatively, when a lens size of 13.2mm and 900㎛ are output, the predicted bolting value is not included within the appropriate range, so the user can determine that the output lens size is a lens size that does not fit the characteristics of the eye of the person who is to be operated on. . This is only an example and is not limited thereto.

In an embodiment, the bolting value prediction model 120 may be trained using training data for inputting inspection data and outputting a bolting value and a lens size. In the learning step of the bolting value prediction model, the learning step S100 described in FIG. 8 may be applied as it is.

In an embodiment, the predicted bolting value may be a bolting value that satisfies a certain range. That is, the output unit 2500 may output a bolting value that satisfies a certain range and a lens size corresponding thereto. For example, the output unit 2500 may output a lens size of 12.6 mm when the bolting value is 500 μm that satisfies the range of 250 to 750 μm.

22 is a diagram illustrating another embodiment of predicting a bolting value. Referring to FIG. 22, the bolting value predictor 2300 may predict a bolting value by using a plurality of examination data and an arbitrary lens size of a person to be operated on as input data.

In an embodiment, the bolting value prediction module 2000 may output the predicted bolting value when the inspection data and an arbitrary lens size are input to the bolting value prediction model 120. The user can determine whether the input arbitrary lens size is suitable for the characteristics of the eye of the person who is to be operated by looking at the predicted bolting value for the input arbitrary lens size. For example, after inputting examination data and a lens size of 13.2mm as input data, when a predicted bolting value of 450㎛ is output, the lens size of 13.2mm, which is the arbitrary lens size, is the characteristic of the eyeball of the person who is to be operated. It can be determined that the lens size is suitable for. This is only an example and is not limited thereto.

In an embodiment, the bolting value prediction model 120 may be trained using training data for inputting inspection data and a lens size, and outputting a bolting value. In the learning step of the bolting value prediction model, the learning step S100 described in FIG. 8 may be applied as it is.

Although not shown, in an embodiment, the bolting value predicting unit 2300 may be implemented in conjunction with the lens size determining unit 1300. This allows the user to verify the accuracy of the result value derived through the lens size determination unit 1300. For example, when a lens size of 13.2 mm derived through the lens size determination unit 1300 is input as input data of the bolting value predictor 2300 together with inspection data, if the predicted bolting value is 500 μm, this is As the bolting value is included within a certain range, it can be verified that a lens size of 13.2mm, which is a result value of the lens size determination unit, is a suitable result value in the eye of a person who is to be operated on, and that the accuracy of the result value is also high.

In an embodiment, the lens size determining unit 1300 and the bolting value predicting unit 2300 may be connected in series with each other. Specifically, the lens size (output data) derived using the lens size determining unit 1300 may be obtained as input data of the bolting value predicting unit 2300. That is, the bolting value predictor 2300 may be a lens size that is a result value of the lens size determination unit as input data, and a plurality of examination data of a person who is to be operated on. Through this, the bolting value predictor 2300 may output a predicted bolting value corresponding to the input lens size.

5 Lens power determination

5.1 Configuration of lens power determination module

Even if the maximum corrected visual acuity of the surgery eye is greater than the target vision after lens implantation, the quality of vision may be degraded due to residual astigmatism after surgery. For example, even if the corrected visual acuity in the surgical eye reaches 1.2, which is the target visual acuity after lens implantation, and astigmatism correction is partially performed, residual astigmatism may remain. In this case, the operator cannot obtain the expected surgical result due to the residual astigmatism. Therefore, factors of astigmatism, such as corneal astigmatism, may need to be considered when determining the power of a lens used for lens implantation.

In one embodiment, when determining the power of the lens, it is necessary to determine the power of the lens in consideration of not only the maximum corrected vision but also corneal astigmatism caused by surgery. In this case, the residual astigmatism is predicted in advance, and an element for correcting the residual astigmatism may be previously reflected in the lens. Accordingly, the user can obtain not only the target vision but also the desired quality of vision.

23 is a diagram showing the configuration of the lens power determination module 3000. In an embodiment, the lens power determination module 3000 may output a lens power to be inserted into an eye of a person to be operated on from input data.

Referring to FIG. 23, the lens power determination module 3000 may include an input unit 3100, a lens size determination unit 3300, and an output unit 3500.

The input unit 3100 may obtain input data from a database. The input data may be data of a plurality of examinations of a person to be operated on.

Specifically, the input unit 3100 may be directly connected to a database to obtain input data. In addition, the input unit 3100 may receive and obtain input data from a server or other external device.

The input data may be examination data of a person to be operated on. The inspection data may be the same as described in Table of Contents 3.1 above. Hereinafter, only different contents will be described.

According to an embodiment, the examination data may include measured naked eyesight of the person who is to be operated on, a diopter measured from an eyeball, astigmatism axis, astigmatism direction parameter, corneal astigmatism and lens astigmatism, myopia and astigmatism ratio data, etc. .

According to an embodiment, the input data may include corneal incision information. The corneal incision information may mean information on a predicted or planned corneal incision in the process of incising the cornea of a person who is to be operated before the lens is inserted during lens insertion. The corneal incision information may include a corneal incision method, a corneal incision location, a corneal incision direction, and/or a corneal incision degree, etc. in a corneal incision process of a lens implantation procedure of a person to be operated on. Among the corneal incision information, the amount of change in astigmatism may be different depending on the location of the corneal incision, and the astigmatism value (SIA) caused by surgery may be different depending on the size of the corneal incision. Therefore, when determining the power of the lens, determining the power of the lens after predicting astigmatism adjusted for factors such as the amount of change in astigmatism and/or astigmatism caused by surgery in consideration of the corneal incision information will improve the quality of vision. I can bring it.

In an embodiment, the lens power determination unit 3300 may determine a lens power suitable for the eyeball of the person who is undergoing surgery by applying input data such as a plurality of examination data of the person to be operated on to the lens power determination model 130. Here, the appropriate lens power may mean a lens power having a high quality of vision and minimizing the possibility of occurrence of side effects when a lens implantation procedure is performed on a person to be operated on. Side effects in determining the lens power may include decreased vision and headache due to decreased vision.

In one embodiment, in order to determine a suitable lens power, the lens power determination unit 3300 inputs input data such as a plurality of examination data and/or predicted corneal incision information of a person to be operated on to determine an appropriate lens power to the eye of the person to be operated on. It can output a suitable lens power.

A specific operation of the lens power determination unit 3300 will be described in more detail with reference to FIG. 24.

The output unit 3500 may output information (output data) on the power of a lens to be inserted into the eye of a person who is to be operated on through the lens power determination unit 3300.

The output unit may output a lens power suitable for an eyeball of a person who is to be operated on according to a learning method of the lens power determination model.

According to an embodiment, when the lens power determination model is implemented in the form of regression, the output unit may output a lens power suitable for the target vision of the eye of the person who is to be operated on. Among the plurality of lens powers, it is possible to output the lens power with the highest probability that is suitable for the eye of the person who is to be operated on. This is exemplary, and the present invention is not limited thereto, and the lens power determination model may be implemented using a classifier. In this case, it is possible to output a lens power suitable for the eye of a person who is to be operated from among a plurality of standardized lens powers.

5.2 Lens power determination process

24 is a view showing a flow chart of the lens power determination process (S3000). Referring to FIG. 24, the lens power determination process (S3000) includes acquiring input data such as a plurality of examination data of a person to be operated on (S3100), and deriving a lens power using a lens power determination model (S3300). can do. The lens power determination process S3000 may be performed by the lens power determination module 3000 described above in FIG. 2.

Specifically, in the step of acquiring input data (S3100), the input data may be a plurality of examination data obtained from a plurality of examinations related to eye measurement of a person to be operated on. In one embodiment, the plurality of examinations related to eye measurement may include a slit lamp microscopic examination, a fundus examination, an automatic refraction and corneal curvature examination, a corneal topography examination, and the like.

In an exemplary embodiment, the plurality of examination data may include naked eye vision, a position of a coma, corneal astigmatism and lens astigmatism, a ratio between myopia and astigmatism, and the like.

In one embodiment, the input data may include information about an expected corneal incision of a person to be operated on. For example, the predicted corneal incision information may include a corneal incision degree, a cornea incision location, a cornea incision direction, and the like during a corneal incision process of a person who is to be operated on.

In determining the lens power, corneal incision information may be considered. 25 is a diagram for describing corneal incision information. Specifically, (a) of FIG. 25 is a diagram illustrating a corneal incision in the case of no astigmatism correction, and (b) of FIG. 25 is an exemplary schematic diagram of a corneal incision in the case of astigmatism correction.

Referring to FIG. 25A, in an embodiment, when astigmatism is not corrected during vision correction of a person to be operated on, the corneal incision direction may be in the x-axis direction around the pupil. Also, the degree of corneal incision may be 1/4 the length of the pupil.

Referring to FIG. 25B, in an embodiment, when astigmatism is corrected during vision correction of a person to be operated on, a corneal incision direction may be a y-axis direction centering on the pupil. Also, the degree of corneal incision may be 1/4 the length of the pupil.

FIG. 25 illustrates an example that occurs during a corneal incision process of a person to be operated on, but is not limited thereto, and may be different according to the degree of astigmatism and astigmatism ratio of the person to be operated on.

In an embodiment, the input data may be used by inputting predicted corneal incision information as described with reference to FIG. 25 in addition to the examination data. When the corneal incision information is input, the lens power determination unit may determine the lens power in consideration of this.

5.3 Example

26 is a diagram illustrating an embodiment of determining a lens power. Referring to FIG. 26, the lens power determination unit 3300 may output a lens power by using a plurality of examination data of a person to be operated on as input data.

In an embodiment, the lens power determination module 3000 may output the lens power when the test data is input to the lens power determination model 130.

In an embodiment, the lens power determination model 130 may be trained using training data for inputting inspection data and outputting the lens power. In the learning step of the lens power determination model, the learning step S100 described in FIG. 8 may be applied as it is.

Although not shown, in an embodiment, the lens power determiner 3300 may output the lens power and corneal incision information by using examination data of a person who is to be operated as input data. By outputting the corneal incision information such as the degree of corneal incision, the location of the cornea, and the degree of the corneal incision during the corneal incision process, the lens power in consideration of factors such as astigmatism corrected according to the corneal incision information can be output. have.

In an embodiment, the lens power determination model 130 may be trained using training data for inputting examination data and outputting lens power and corneal incision information. In the learning step of the lens power determination model, the learning step S100 described in FIG. 8 may be applied as it is.

Although not shown, in an embodiment, the lens power determination unit 3300 may output astigmatism parameters such as lens power, corneal incision information, and astigmatism value (SIA) caused by surgery by using examination data of a person who is to be operated as input data. have. Factors such as astigmatism corrected according to the corneal incision information and astigmatism induced by surgery are taken into account by outputting the expected lens power at the same time as the astigmatism parameters such as corneal incision information and surgical astigmatism value (SIA) during the corneal incision process. The lens power can be output.

In an embodiment, the lens power determination model 130 may be trained using training data that inputs examination data and outputs astigmatism parameters such as lens power, corneal incision information, and astigmatism value (SIA) caused by surgery. . In the learning step of the lens power determination model, the learning step S100 described in FIG. 8 may be applied as it is.

27 is a diagram illustrating another embodiment of determining a lens power. Referring to FIG. 27, the lens power determination unit 3300 may output a lens power by using a plurality of examination data and corneal incision information of a person to be operated on as input data.

In an embodiment, the lens power determination model 130 may be trained using training data for inputting examination data and corneal incision information and outputting the lens power. In the learning step of the lens power determination model, the learning step S100 described in FIG. 8 may be applied as it is.

Although not shown, in an embodiment, the lens power determination unit 3300 may output astigmatism parameters such as astigmatism values (SIA) caused by the predicted surgery by using a plurality of examination data and corneal incision information of a person to be operated on as input data. I can.

In an embodiment, the lens power determination model 130 may be trained using training data for inputting examination data and corneal incision information and outputting an astigmatism parameter. In the learning step of the lens power determination model, the learning step S100 described in FIG. 8 may be applied as it is.

Although not shown, in an embodiment, the lens power determination unit 3300 uses a plurality of examination data and corneal incision information of a person who is to be operated as input data, and astigmatism parameters such as astigmatism value (SIA) caused by a predicted surgery and corneal incision Information can be printed.

In an embodiment, the lens power determination model 130 may be trained using training data for inputting examination data and corneal incision information, and outputting an astigmatism parameter and corneal incision information. In the learning step of the lens power determination model, the learning step S100 described in FIG. 8 may be applied as it is.

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.

Claims (10)

In a method for predicting a bolting value representing a distance between a rear surface of a lens to be inserted into an eyeball of a person undergoing a lens insertion procedure and an front surface of the lens,
Inputting a plurality of examination data and at least one lens size of the person to be operated on into a bolting value prediction model; And
Predicting the bolting value corresponding to each of the at least one input lens size from the bolting value prediction model; Including,
The bolting value prediction model,
A method of predicting a bolting value learned based on a plurality of examination data of an operator who has undergone lens implantation in the past, a lens size inserted into the eyeball of the operator, and a bolting value measured after surgery of the operator. The method of claim 1,
The bolting value is defined as the shortest distance among a plurality of distances between the rear surface of the lens and the front surface of the lens to be inserted into the eye of the person who will undergo the lens implantation surgery. The method of claim 1,
Predicting the bolting value; The
Including; in accordance with whether the predicted bolting value satisfies the condition of a predetermined range, providing information on the appropriateness of the lens to be inserted into the eyeball of the person who is to be operated with the input lens size.
How to predict the bolting value. The method of claim 1,
When the predicted bolting value satisfies a condition of a predetermined range, the input lens size provides information on the fit as a lens to be inserted into the eye of the person who is to be operated on, and the predicted bolting value is the predetermined range. If the condition of is not satisfied, the input lens size is a method for predicting a bolting value that provides information on a non-conformity to a lens to be inserted into the eye of the person who is to be operated on. The method of claim 1,
The conditions in the predetermined range are
A method for predicting a bolting value satisfying that the predicted bolting value is included within 250 to 750 μm. In a method for predicting a bolting value representing a distance between a rear surface of a lens to be inserted into an eyeball of a person undergoing a lens insertion procedure and an front surface of the lens,
Inputting a plurality of examination data of the person to be operated on into a bolting value prediction model; And
Including, by inputting a plurality of examination data of the person to be operated on, and predicting a predicted lens size suitable for the eyeball of the person to be operated and the bolting value corresponding to each of the predicted lens size from the bolting value prediction model, and including,
The bolting value prediction model,
A method of predicting a bolting value learned based on a plurality of examination data of a patient who has undergone a previous operation of the lens implantation procedure, a lens size inserted into the eyeball of the patient, and a bolting value measured after the patient's surgery. The method of claim 6,
The expected lens size suitable for the eye of the person to be operated on
Including selecting any one of a plurality of predetermined lens sizes,
How to predict the bolting value. The method of claim 6,
The expected lens size suitable for the eye of the person to be operated on
Including selecting any one of non-standardized lens sizes other than a plurality of predetermined lens sizes,
How to predict the bolting value. A computer-readable recording medium on which a program for performing the method of any one of claims 1 to 8 is recorded. In the device for predicting a bolting value representing a distance between a rear surface of a lens to be inserted into an eyeball of a person undergoing lens implantation and an front surface of the lens,
A memory for storing a plurality of examination data of a person to be operated on; And
Including; a processor;
The processor,
Inputting a plurality of examination data and at least one lens size of the person to be operated on into a bolting value prediction model, and predicting the bolting value corresponding to each of the at least one input lens size from the bolting value prediction model,
The bolting value prediction model,
A device for predicting a bolting value learned based on a plurality of examination data of an operator who has undergone lens implantation in the past, a lens size inserted into the eyeball of the operator, and a bolting value measured after surgery of the operator.

Images