KR102320267B1 - Method and device for providing vision correction surgery visualization information - Google Patents

Abstract

The present invention relates to a method for providing a predicted vision image, and the method for providing a predicted vision image after vision correction surgery using artificial intelligence performed by a computing device according to an aspect of the present invention comprises: examination data of a subject - the examination data is questionnaire data and an eye characteristic data measurement value; The first group data obtained from the examination data of the subject is input to the first prediction model, and the predictive value of the eye characteristics data after the eye correction surgery of the subject - The predictive value of the eye characteristics data includes at least one of a predictive value of visual acuity and a predictive value of a corneal shape factor - calculating ; and generating a predicted visual acuity image based on the predicted value of the eye characteristic data; including, wherein the first predictive model includes, the pre-operative ocular characteristic data measurement values of a plurality of recipients who have undergone vision correction surgery, performed to the plurality of recipients It is learned based on at least one of the corrected vision correction surgery parameters and the measurement values of the ocular characteristics data after surgery of the plurality of recipients.

Description

Method and device for providing visualization information for vision correction surgery

The present invention relates to a method and apparatus for providing visual information for vision correction surgery, and more particularly, to a method and apparatus for providing visual information related to vision correction surgery to a subject using artificial intelligence.

Vision correction surgeries such as LASIK and LASEK are attracting a lot of attention from people with poor eyesight, regardless of age or gender. Interest in vision correction surgery is increasing day by day to the extent that statistics exist that the number of people who have undergone vision correction surgery reaches 100,000.

However, it is difficult for a subject who intends to undergo vision correction surgery to determine which vision correction surgery is right for them. The subject must basically choose the type of surgery, such as LASIK, LASEK, Smile, and lens implantation. In addition, within LASIK, selection according to surgical equipment such as Eye LASIK, DaVinci LASIK, Crystal LASIK, Z LASIK, Viju LASIK, and Opti LASIK and surgical methods such as Contura Vision, Extra LASIK, and Wavefront LASIK must be selected. In addition, since the recommended corneal cutting amount varies depending on hospitals and doctors, it is more difficult to select, and it is a reality that has no choice but to rely on the words of the doctor or counselor for the quality of vision or side effects after surgery.

1. US Patent Application Publication No. 2018-0161098 (2018.06.14)

One task is to visually provide information related to vision correction surgery to doctors, counselors, subjects, and the like.

Another task is to provide a predicted visual acuity image to a doctor, a counselor, a subject, and the like.

Another task is to provide a corneal topographic image to a doctor, a counselor, a subject, and the like.

Another task is to provide a cause for calculating a predicted result to a doctor, a counselor, and a subject.

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

According to one aspect, there is provided a method for providing an expected vision image after vision correction surgery using artificial intelligence performed by a computing device, the method comprising: obtaining examination data of a subject, the examination data including questionnaire data and eye characteristic data measurement values; ; The first group data obtained from the examination data of the subject is input to the first prediction model, and the predictive value of the eye characteristics data after the eye correction surgery of the subject - The predictive value of the eye characteristics data includes at least one of a predictive value of visual acuity and a predictive value of a corneal shape factor - calculating ; and generating a predicted visual acuity image based on the predicted value of the eye characteristic data; wherein the first predictive model includes, the preoperative ocular characteristic data measurement values of a plurality of subjects who have undergone vision correction surgery, performed to the plurality of subjects There may be provided a method for providing a predicted vision image learned based on at least one of the corrected vision correction surgery parameters and the measurement values of the ocular characteristics data after surgery of the plurality of recipients.

Solutions of the problem are not limited to the above-described solutions, and solutions not mentioned will be clearly understood by those of ordinary skill in the art to which the present invention belongs from the present specification and the accompanying drawings. .

According to an embodiment, a method for visually providing information related to vision correction surgery to a doctor, a counselor, a subject, and the like, and an apparatus for performing the same may be provided.

According to another embodiment, a method for providing a predicted vision image to a doctor, a counselor, a subject, and the like, and an apparatus for performing the same may be provided.

According to still another embodiment, a method for providing a corneal topography image to a doctor, a counselor, a subject, and the like, and an apparatus for performing the same may be provided.

Again, according to another exemplary embodiment, a method for visually providing a cause for calculating a prediction result to a doctor, a counselor, an examinee, and the like, and an apparatus for performing the same may be provided.

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

1 is a view of a system for assisting vision correction surgery according to an embodiment.
2 is a diagram for explaining a learning apparatus/prediction apparatus according to an embodiment.
3 is a diagram for describing a server device and a client device according to an embodiment.
4 is a diagram illustrating a configuration of a server device and a client device according to an embodiment.
5 is a diagram of a model related to vision correction surgery according to an exemplary embodiment.
6 is a diagram for explaining a learning step and a prediction step of a model related to vision correction surgery according to an embodiment.
7 is a diagram illustrating pre-processing of input/output data according to an embodiment.
8 is a diagram of a model related to vision correction surgery including serially connected sub-models according to an embodiment.
9 is a diagram of a model related to vision correction surgery including submodels connected in parallel according to an embodiment.
10 is a diagram of an expected visual acuity image according to an exemplary embodiment.
11 is a diagram of a prediction vision image generation model using a filter according to an exemplary embodiment.
12 is a view of a corneal topography image according to an embodiment.
13 is a diagram of a predictive result calculation cause analysis model including a vision correction surgery-related model according to an exemplary embodiment.
14 is a diagram of a cause for calculating a prediction result according to an exemplary embodiment.
15 is a diagram illustrating serial connection of models related to vision correction surgery according to an embodiment.
16 to 19 are diagrams illustrating an output calculation of a model related to vision correction surgery based on an output of a corneal shape factor prediction model according to an exemplary embodiment.
20 is a diagram illustrating output calculation of a model related to vision correction based on an output of a model for predicting the need for a custom vision correction surgery according to an embodiment.
21 to 22 are diagrams for calculating the output of the vision correction surgery related model based on the output of the vision correction surgery proposal model according to an exemplary embodiment.
23 is a diagram of an output calculation of a model related to vision correction surgery based on an output of a model proposed for surgical parameters according to an embodiment.
24 to 25 are diagrams for calculating the output of the vision correction surgery related model based on the output of the vision prediction model according to an exemplary embodiment.
26 to 27 are diagrams for calculating the output of the vision correction surgery related model based on the output of the corneal topographic image prediction model according to an embodiment.
28 is a view for explaining a combination of three or more models related to vision correction surgery according to an embodiment.
29 to 30 are diagrams illustrating an output calculation of a model related to vision correction surgery based on the output of the corneal shape factor prediction model and the visual acuity prediction model according to an exemplary embodiment.
31 is a diagram for explaining merging of models related to vision correction surgery according to an embodiment.
32 to 34 are diagrams illustrating an example of merging models related to vision correction surgery according to an embodiment.
35 is a diagram of a first embodiment of a method for recommending a vision correction surgery according to an embodiment.
36 is a diagram of a second embodiment of a method for recommending a vision correction surgery according to an embodiment.
37 is a diagram of a third embodiment of a method for recommending vision correction surgery according to an embodiment.
38 is a diagram of a fourth embodiment of a method for recommending vision correction surgery according to an embodiment.
39 is a view of a fifth embodiment of a method for recommending a vision correction surgery according to an embodiment.
40 is a diagram of a sixth embodiment of a method for recommending vision correction surgery according to an embodiment.
41 is a view of a first embodiment of a method of providing visual information for vision correction surgery according to an embodiment.
42 is a diagram of a second embodiment of a method of providing visual information for vision correction surgery according to an embodiment.
43 is a diagram of a third embodiment of a method for providing visual information for vision correction surgery according to an embodiment.
44 is a diagram of a fourth embodiment of a method of providing visual information for vision correction surgery according to an embodiment.

The embodiments described in this specification are for clearly explaining the spirit of the present invention to those of ordinary skill in the art to which the present invention belongs, so the present invention is not limited by the embodiments described in this specification, and the present invention It should be construed as including modifications or variations that do not depart from the spirit of the present invention.

The terms used in the present specification are selected as widely used general terms as possible in consideration of the functions in the present invention, but they may vary depending on the intention, custom, or emergence of new technology of those of ordinary skill in the art to which the present invention belongs. can However, if a specific term is defined and used with an arbitrary meaning, the meaning of the term will be separately described. Therefore, the terms used in this specification should be interpreted based on the actual meaning of the terms and the contents of the entire specification, rather than the names of simple terms.

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

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

Hereinafter, a method and apparatus for recommending vision correction to a subject based on examination data will be described. In particular, a method and apparatus for generating a model for recommending vision correction surgery using artificial intelligence and recommending vision correction surgery to a subject using the generated model will be described.

In addition, a method and apparatus for providing visualized vision correction surgery related information to a subject based on examination data will be described. In particular, artificial intelligence is used to create a model that provides visual information for vision correction surgery, such as providing an expected vision image after vision correction surgery, predicting a corneal topography image, or analyzing the cause of prediction result, and using the generated model to give the subject A method and apparatus for providing vision correction visualization information will be described.

In the present specification, vision correction surgery is an operation that corrects the eyesight of the recipient. In addition to surgery to correct the vision through corneal cutting using a laser, such as LASIK, LASEK, and small incision lenticule extraction, SMILE, as well as lenses It should be interpreted broadly, including vision correction surgery that does not use lasers, such as implantation.

In addition, in the present specification, visual acuity includes visual acuity that can be measured based on judgment of a subject, and visual acuity that can be measured through an eye exam. For example, visual acuity may be measured through an eye exam table. Alternatively, visual acuity is lower-order aberrations that are more than basic refractive errors such as myopia, farsightedness, and astigmatism, and higher-order aberrations such as spherical aberration, coma aberration, trefoil aberration, etc. aberrations) may be included. In addition, visual acuity may include unaided visual acuity and corrected visual acuity.

According to one aspect, there is provided a method for providing an expected vision image after vision correction surgery using artificial intelligence performed by a computing device, the method comprising: obtaining examination data of a subject, the examination data including questionnaire data and eye characteristic data measurement values; ; The first group data obtained from the examination data of the subject is input to the first prediction model, and the predictive value of the eye characteristics data after the eye correction surgery of the subject - The predictive value of the eye characteristics data includes at least one of a predictive value of visual acuity and a predictive value of a corneal shape factor - calculating ; and generating a predicted visual acuity image based on the predicted value of the eye characteristic data; wherein the first predictive model includes, the preoperative ocular characteristic data measurement values of a plurality of subjects who have undergone vision correction surgery, performed to the plurality of subjects There may be provided a method for providing a predicted vision image learned based on at least one of the corrected vision correction surgery parameters and the measurement values of the ocular characteristics data after surgery of the plurality of recipients.

Here, the generating of the predicted visual acuity image may include calculating or selecting a filter based on the predicted value of the eye characteristic data, and applying the filter to the original image to generate the predicted visual acuity image. .

Here, the predicted eye characteristic data includes a first predicted eye characteristic data and a second predicted eye characteristic data, and the predicted vision image includes a first predicted vision image generated based on the first predicted eye characteristic data and the The second predicted visual acuity image generated based on the predicted value of the second eye characteristic data may include a second predicted visual acuity image different from the first predicted visual acuity image.

Here, the first predicted eye characteristics data and the second predicted eye characteristics data respectively correspond to the predicted eye characteristics data after standard vision correction surgery and the predicted eye characteristics data after custom vision correction surgery, and the first predicted vision image and the second Each of the predicted visual acuity images may correspond to the predicted visual acuity image after the standard vision correction surgery and the predicted vision image after the custom vision correction surgery.

Here, the predicted visual acuity image may include information on at least one of sharpness of vision, light blur, contrast sensitivity, night vision, glare, double vision, and afterimages expected after vision correction of the subject.

Here, the method for providing the predicted visual acuity image further includes: inputting second group data obtained from the examination data of the examinee into a second prediction model to predict the corneal topographic image of the subject after vision correction surgery; 2 The predictive model can be learned based on at least one of pre-operative corneal topographic images of a plurality of recipients who have undergone vision correction surgery, vision correction surgery surgical parameters performed on the plurality of recipients, and post-operative corneal topographic images of the plurality of recipients have.

Here, the method for providing the predicted visual acuity image may further include calculating a dependence of the eye characteristic data prediction value on the first group data.

Here, the predictive value of the eye characteristic data includes a first predicted value of the eye characteristic data and a predicted value of the second eye characteristic data, the dependence includes a dependence coefficient corresponding to at least a portion of the first group data, and the dependence coefficient is , a first dependence coefficient corresponding to the first prediction value of the eye characteristic data and a second coefficient of dependence corresponding to the predicted value of the second eye characteristic data but different from the first dependence coefficient.

Here, each of the first predicted ocular characteristic data and the second predicted ocular characteristic data corresponds to the predicted ocular characteristic data after standard vision correction surgery and the predicted ocular characteristic data after custom vision correction surgery, and the first dependence coefficient and the second dependence Each of the coefficients may correspond to the dependence of the predictive value of the ocular characteristic data on the first group data after the standard correction surgery and the dependence of the predictive value of the ocular characteristic data on the first group data after the custom vision correction operation.

Here, the method for providing the predicted visual acuity image may further include outputting a dependence coefficient greater than a predetermined value among the dependence coefficients or outputting a predetermined number of dependence coefficients.

Here, the corneal shape factor predicted value may include at least one of an index of height decentration (IHD) predicted value, an index of surface variance (ISV) predicted value, and an index of vertical asymmetry (IVA) predicted value.

Here, the visual acuity prediction value may include at least one of a lower-order aberrations prediction value and a higher-order aberrations prediction value.

According to another aspect, there is provided a method for recommending vision correction surgery using artificial intelligence performed by a computing device, the method comprising: obtaining examination data of a subject, the examination data including questionnaire data and eye characteristic data measurement values; predicting whether the subject is suitable for vision correction surgery by inputting the first group data obtained from the examination data of the subject into a first prediction model; predicting whether or not vision correction surgery using a laser is possible by inputting second group data obtained from the examination data of the examinee into a second prediction model when the eye correction surgery is suitable for the subject; If the subject can undergo vision correction using a laser, the third group data obtained from the examination data of the subject is input to the third predictive model so as to be used for determining whether a custom vision correction surgery is necessary after the standard vision correction surgery of the subject calculating a corneal shape factor predicted value and a corneal shape factor predicted value after custom vision correction surgery; and if the subject is capable of vision correction using a laser, inputting the fourth group data obtained from the examination data of the subject into a fourth predictive model to propose a vision correction surgery corresponding to the subject; 4 The predictive model is a method of recommending vision correction surgery learned based on at least one of examination data of a plurality of recipients who have undergone vision correction surgery, vision correction surgery corresponding to the plurality of recipients, and vision after vision correction surgery of the plurality of recipients. can

Here, in the step of proposing the vision correction surgery, the vision correction surgery may be suggested based on the predicted value of the visual acuity after the vision correction surgery of the subject.

Here, in the step of proposing the vision correction surgery, the vision correction surgery may be suggested by calculating an acuity prediction value after the vision correction surgery of the subject corresponding to each of the plurality of vision correction surgery.

Here, in the step of proposing the vision correction surgery, the vision correction surgery may be proposed by calculating a plurality of prediction values of vision corresponding to a plurality of different visions.

Here, the method for recommending vision correction surgery may further include the step of estimating whether the subject needs custom vision correction surgery based on the calculated corneal shape factor predicted value after standard vision correction surgery and the corneal shape factor predicted value after custom vision correction surgery.

Here, in the step of proposing the vision correction surgery, the vision correction surgery may be suggested based on the calculated predicted values of the corneal shape factor after standard vision correction surgery and the corneal shape factor prediction values after the custom vision correction surgery.

Here, when the fourth predictive model is learned in consideration of the preference for vision correction surgery of the plurality of subjects, the fourth group data may include preference for vision correction surgery of the subjects.

Here, at least one of the first predictive model, the second predictive model, the third predictive model, and the fourth predictive model includes a plurality of submodels, and calculates a result value based on the results of the plurality of submodels. can be calculated.

Here, at least one of the first group data, the second group data, the third group data, and the fourth group data includes at least a portion of the examinee's examination data as it is, or at least a part of the examinee's examination data. It may be characterized in that it includes a new type of data calculated from

Here, the corneal shape factor predicted value may include at least one of an index of height decentration (IHD) predicted value, an index of surface variance (ISV) predicted value, and an index of vertical asymmetry (IVA) predicted value.

Here, the examination data may further include genetic information.

According to another aspect, there is provided a method for recommending vision correction surgery using artificial intelligence performed by a computing device, the method comprising: obtaining examination data of a subject, the examination data including questionnaire data and eye characteristic data measurement values; predicting whether the subject is suitable for vision correction surgery by inputting the first group data obtained from the examination data of the subject into a first prediction model; predicting whether or not vision correction surgery using a laser is possible by inputting second group data obtained from the examination data of the examinee into a second prediction model when the eye correction surgery is suitable for the subject; predicting whether or not the subject's custom vision correction surgery is necessary by inputting third group data obtained from the examination data of the subject into a third prediction model when the subject is capable of vision correction using a laser; and if the subject is capable of vision correction using a laser, inputting the fourth group data obtained from the examination data of the subject into a fourth predictive model to propose a vision correction surgery corresponding to the subject; including, but the custom Predicting whether or not the vision correction surgery is necessary is based on the predicted value of the corneal shape factor after the standard vision correction surgery and the predicted value of the corneal shape factor after the custom vision correction surgery. A method of recommending a vision correction surgery learned based on at least one of checkup data of a plurality of recipients who have undergone orthodontic surgery, vision correction surgery corresponding to the plurality of recipients, and eyesight after vision correction surgery of the plurality of recipients may be provided.

According to another aspect, there is provided a method for recommending vision correction surgery using artificial intelligence performed by a computing device, the method comprising: obtaining examination data of a subject, the examination data including questionnaire data and eye characteristic data measurement values; predicting whether the subject is suitable for vision correction surgery by inputting the first group data obtained from the examination data of the subject into a first prediction model; predicting whether or not vision correction surgery using a laser is possible by inputting second group data obtained from the examination data of the examinee into a second prediction model when the eye correction surgery is suitable for the subject; and if the subject is capable of vision correction using a laser, inputting third group data obtained from the examination data of the subject into a third predictive model to suggest vision correction surgery corresponding to the subject; In the step of proposing corrective surgery, the vision correction surgery is suggested based on the predicted value of the corneal shape factor after the standard vision correction surgery and the corneal shape factor predicted value after the custom vision correction surgery, and the third predictive model is a plurality of patients who have received the vision correction surgery. A method of recommending a vision correction surgery learned based on at least one of the examination data of , vision correction surgery corresponding to the plurality of recipients, and eyesight after vision correction surgery of the plurality of recipients may be provided.

According to another aspect, there is provided a method for recommending vision correction surgery using artificial intelligence performed by a computing device, the method comprising: obtaining examination data of a subject, the examination data including questionnaire data and eye characteristic data measurement values; predicting whether the subject is suitable for vision correction surgery by inputting the first group data obtained from the examination data of the subject into a first prediction model; and, when vision correction surgery is suitable for the subject, inputting the second group data obtained from the examination data of the subject into a second prediction model to propose a vision correction surgery corresponding to the subject; including, but suggesting the vision correction surgery The step of proposing a vision correction surgery based on the predicted value of the corneal shape factor after the standard vision correction surgery and the predicted value of the corneal shape factor after the custom vision correction surgery, and the second predictive model is the examination data of a plurality of subjects who have received the vision correction surgery , and a method of recommending a vision correction surgery learned based on at least one of vision correction surgery corresponding to the plurality of recipients and the vision after vision correction surgery of the plurality of recipients may be provided.

According to another aspect, there is provided a method for recommending vision correction surgery using artificial intelligence performed by a computing device, the method comprising: obtaining examination data of a subject, the examination data including questionnaire data and eye characteristic data measurement values; and inputting group data obtained from the examination data of the subject into a predictive model to propose a vision correction surgery corresponding to the examinee, wherein the step of proposing the vision correction surgery includes: the cornea after standard vision correction surgery of the subject A vision correction surgery is proposed based on the shape factor predicted value and the corneal shape factor predicted value after custom vision correction surgery, and the prediction model is, A method of recommending vision correction surgery learned based on at least one of vision after vision correction surgery of the recipient may be provided.

A vision correction assisting system according to an embodiment may include a learning device and a prediction device. Here, the learning device and the prediction device may be a computing device including at least one control unit. Examples of the computing device may include, but are not limited to, a desktop, a laptop, a tablet PC, and a smart phone.

1 is a view of a vision correction assisting system 10 according to an embodiment. Referring to FIG. 1 , the learning apparatus 100 may learn and/or generate a model for calculating information related to vision correction surgery (hereinafter referred to as a “vision surgery related model”) based on learning data. Here, the learning data is data necessary for learning and/or generating a model related to vision correction surgery, such as numbers, letters, and images, and there is no limitation in the expression method thereof. For example, the learning data may include examination data and surgical parameters of a recipient who has undergone vision correction surgery.

The prediction device 300 may calculate a prediction result, which is information related to the vision correction surgery, based on the model and input data related to the vision correction surgery generated by the learning device 100 . Here, the input data is data that is the basis for calculating the prediction result, such as numbers, characters, and images, and there is no limitation in the expression method thereof.

Specific examples of learning data, input data, prediction results, and models related to vision correction will be described later.

Although the learning apparatus 100 and the prediction apparatus 300 are illustrated as separate apparatuses in FIG. 1 , the learning apparatus 100 and the prediction apparatus 300 may be the same apparatus. For example, it is possible to learn/create a model related to vision correction surgery in the same device and calculate a prediction result using the model. Alternatively, at least some components of the learning apparatus 100 and at least some components of the prediction apparatus 300 may be the same.

Also, the vision correction assisting system according to an embodiment may include a plurality of learning devices and/or a plurality of prediction devices.

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

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

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

The learning apparatus/prediction apparatus according to an embodiment may include a memory unit 5000 . The memory unit 5000 may store data necessary for learning, a learning model, and a learned model related to vision correction surgery. The memory unit 5000 may store parameters, variables, and the like of a model related to vision correction surgery.

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

The memory unit 5000 may store various processing programs, parameters for performing program processing, or data as a result of such processing. For example, the memory unit 5000 may include a data processing process program, a diagnostic process program, parameters for performing each program, and data obtained according to the execution of these programs for performing the learning and prediction steps of the vision correction surgery-related model to be described later. (eg, processed data or prediction results) and the like can be stored.

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

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

A vision correction assistance system according to an embodiment may include a server device and a client device. 3 is a diagram for describing a server device 500 and client devices 700a and 700b according to an embodiment.

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

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

The client devices 700a and 700b according to an exemplary embodiment may acquire the learned vision correction surgery-related model from the server device 500 . For example, the client devices 700a and 700b may download a model related to vision correction surgery from the server device 500 through a network.

The server device 500 according to an embodiment may calculate a prediction result based on input data obtained from the client devices 700a and 700b. For example, the client devices 700a and 700b receive information about the subject and transmit it to the server device 500, and the server device 500 can calculate a prediction result through a model related to vision correction surgery based on the information of the subject. have. The server device 500 according to an embodiment may obtain input data from a plurality of client devices 700a and 700b.

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

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

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

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

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

As described above, the vision correction surgery-related model is a model that calculates various information that can be considered before and after performing the vision correction surgery.

5 is a view of a model (M) related to vision correction surgery according to an embodiment. Referring to Figure 5, the vision correction surgery-related model (M) is a surgical suitability prediction model (M10), a laser surgery failure prediction model (M11), a corneal shape factor prediction model (M12), a custom vision correction surgery necessity prediction model (M13), Vision correction surgery suggestion model (M14), surgical parameter suggestion model (M15), vision prediction model (M16), predicted vision image generation model (M17), corneal topographic image prediction model (M18), and predictive result calculation cause analysis model (M19) may include. A detailed description of each model will be provided later.

At least some of the corrective vision surgery-related models M may be trained and/or generated in the same learning device. For example, the surgical suitability prediction model M10 and the laser surgery failure prediction model M11 may be trained and/or generated in the same learning device. Alternatively, at least some of the corrective vision surgery-related models M may be learned and/or generated by different learning devices.

At least some of the vision correction surgery-related models M may be executed in the same prediction device. For example, the surgical suitability prediction model M10 and the laser surgery failure prediction model M11 may be executed in the same prediction device. Alternatively, at least some of the corrective vision surgery-related models M may be executed in different prediction devices.

The vision correction surgery-related model according to an embodiment may be learned and/or implemented as an artificial intelligence model/algorithm, and there is no limitation in the learning and/or implementation method. For example, models related to vision correction surgery include a classification algorithm, a regression algorithm, supervised learning, unsupervised learning, reinforcement learning, and a support vector machine. ), decision tree, random forest, LASSO, AdaBoost, XGBoost, artificial neural network, etc. train and/or implement various machine learning models/algorithms and deep learning models/algorithms. can be

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

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

The learning data acquisition step S110 may be a step in which the learning apparatus acquires learning data, which is data for learning and/or generating a model related to vision correction surgery.

The model learning step ( S150 ) may be a step of learning and/or generating a model related to vision correction surgery. In the model learning step ( S150 ), the learning apparatus may learn and/or generate the model based on the training data acquired in the learning data acquisition step. For example, model parameters constituting the vision correction surgery related model may be changed in the model learning step ( S150 ). According to the change of the parameter, the accuracy of the model may be improved.

The vision correction surgery-related model may be learned based on vision correction surgery-related information of a recipient who has undergone vision correction surgery. For example, the model learns based on at least one of pre-vision examination data of a plurality of recipients who have undergone vision correction surgery, vision correction surgery parameters performed on the plurality of recipients, and checkup data after vision correction of the plurality of recipients. can be

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

The step of obtaining input data ( S310 ) may be a step of obtaining, by the prediction apparatus, input data, which is data that can be used to calculate a prediction result using a model related to vision correction surgery.

The model execution step S350 may be a step of calculating a prediction result based on the vision correction surgery-related model learned and/or generated in the learning step S10 and input data. For example, the prediction apparatus may output a prediction result based on input data and model parameters obtained from the learning apparatus.

The input data of the vision correction surgery related model may include all information obtained about the subject. Alternatively, the input data may include at least a part of information obtained about the subject. In addition, the input data may be the same or different according to a model related to vision correction surgery.

The prediction result of the vision correction surgery-related model may vary depending on the learning data. Alternatively, the accuracy of the vision correction surgery-related model may vary depending on the learning data.

The prediction result may vary depending on the type of true value included in the training data. For example, the prediction result may vary depending on whether the true value considers the subject's subjective intention. Here, the subjective doctor of the subject may include preference such as whether he or she prefers a specific vision correction surgery, and ability to pay costs, such as how much money can be paid for the vision correction surgery. If the subjective intention of the subject is not taken into consideration, the predicted result may be a medically suggested result. On the other hand, when the subjective intention of the subject is taken into consideration, the predicted result may be the same as the medically suggested result, but may be different.

When the first learning data and the second learning data are obtained at different hospitals, obtained from different doctors, or learning data at different times, the first model and the first model learned and/or generated based on the first learning data 2 The second model trained and/or generated based on the training data may be different from each other. As a result, the first prediction result output by the first model and the second prediction result output by the second model may be different from each other. Also, the accuracy of the first model and the second model may be different from each other.

However, even if the learning data are different, the same vision correction surgery-related model may be learned and/or generated. Alternatively, the same prediction result may be calculated even for models related to vision correction surgery that are learned and/or generated with different learning data.

Learning data, input data, and prediction results (hereinafter referred to as "input/output data") may include variables such as examination data and surgical parameters. Examination data and surgical parameters can be expressed in various ways such as numbers, letters, images, etc., and there is no limitation in the expression method. In addition, the image is not limited in its dimension, such as a two-dimensional image or a three-dimensional image.

The examination data may include questionnaire data, which is information obtained by asking questions without going through equipment or examination, and eye characteristic data and genetic information, which is information about the eye obtained through equipment or examination.

The questionnaire data includes variables such as the subject's living environment such as gender, age, race, and region of residence, occupation, income, educational background, education, and demographic characteristics such as family size, medical and family history of hypertension and diabetes, and preference for vision correction surgery. may include

The eye characteristic data may include all kinds of information related to the eye. For example, the eye characteristic data may include variables such as visual acuity, intraocular pressure, and/or retinal examination results.

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

The eye characteristic data may be acquired through tomography such as Pentacam, CASIA2, AL-Scan, OQAS, topography, optical coherence tomography (OCT), ultrasound biomicroscopy (UBM), but is not limited thereto. Information obtainable through the device and similar devices and information derived therefrom may be included in the eye characteristic data.

Genetic information may be obtained through genetic testing or the like. The genetic information may be used to determine whether vision correction surgery is appropriate for the subject. Alternatively, genetic information can be used to predict side effects after vision correction surgery. For example, the occurrence of corneal dystrophy can be predicted through genetic information.

Surgical parameters are variables related to the performance of vision correction surgery, such as LASIK, LASEK, Smile, lens implantation, standard vision correction surgery, custom vision correction surgery, etc., corneal flap thickness, flap diameter, flap It may include variables that can be changed during vision correction surgery, such as side cut angle, corneal cutting profile, eye suction ring operation time, optic zone, hinge position, hinge structure such as hinge angle and hinge width.

Standard vision correction surgery may mean vision correction for correcting low order aberrations, and custom vision correction surgery may mean vision correction surgery for correcting low order aberrations and high order aberrations.

The types of surgical parameters considered may differ depending on the recipient of standard vision correction surgery and custom vision correction surgery. For example, the type of the surgical parameter considered according to the recipient of the custom vision correction surgery may include the type of the surgical parameter considered according to the recipient of the standard vision correction surgery.

The number of surgical parameters that change according to the recipient of standard vision correction surgery may be different from that of custom vision correction surgery. Standard vision correction surgery and custom vision correction surgery can be classified according to the number of surgical parameters that change in response to the recipient. The number of surgical parameters (hereinafter referred to as “reference values”) that change in response to a recipient that distinguishes standard vision correction surgery and custom vision correction surgery may be a predetermined value. For example, if the number of surgical parameters that change in response to the recipient is equal to or greater than the reference value, it may be custom vision correction surgery, and if it is less than the reference value, it may be standard vision correction surgery.

Standard vision correction surgery and custom vision correction surgery may vary depending on the hospital, doctor, and/or when performing the vision correction surgery. For example, the reference value may vary by hospital, physician and/or time period.

Custom vision correction surgery may include contour vision surgery and wavefront surgery.

When custom vision correction surgery is performed, the quality of vision can be improved compared to when standard vision correction surgery is performed. Visual acuity quality is a comprehensive term that refers to good or bad visual acuity, as well as visual acuity, low-order aberration, and high-order aberration measured through an optometry table, as well as sharpness of vision, light blur, contrast sensitivity, night vision, glare, double vision, afterimage, It can be judged based on other inconveniences, etc.

The input/output data may include not only measured values that can be acquired/measured through questionnaires and examinations, but also predicted values that can be calculated through models related to vision correction surgery. For example, the ocular characteristic data may include not only the measured value of the subject's ocular characteristic data acquired/measured through an examination before vision correction surgery, etc., but also the predicted value of the ocular characteristic data after the vision correction surgery of the subject calculated through a model related to vision correction surgery. have.

The input/output data may be input to a model related to vision correction surgery through pre-processing. For example, the learning apparatus may pre-process the acquired input/output data and then use it to learn a model related to vision correction surgery. Alternatively, the prediction device may pre-process the obtained input/output data and then input it into the vision correction surgery-related model to calculate the prediction result.

Preprocessing should be broadly interpreted to include all changes applied to input/output data, and is not limited to the examples disclosed herein.

The preprocessing may include selecting at least some of the variables included in the input/output data, such as feature selection. For example, the preprocessing may include t-test, Gini index, information gain, relief, DistAUC, signal to noice, MRMR, Fisher score, Laplacian score, SPEC, and the like.

The preprocessing may include generating a new variable from at least some of the variables included in the input/output data, such as feature extraction. As an example, the preprocessing may include principle component analysis, linear discriminant analysis, canonical correlation analysis, singular value decomposition, ISOMAP, locally linear embedding, and the like. As another example, preprocessing may include generating a spectrum from a numerical value or generating an image from a numerical value.

The preprocessing may include a processing method when the input/output data does not include a variable required by the vision correction surgery-related model (or the learning device and/or the prediction device), such as missing value processing. For example, preprocessing may include treating missing values as the mean or mode of the corresponding variable.

Pre-processing can improve the accuracy of models related to vision correction surgery. For example, the accuracy of a model related to vision correction including the feature selection step may be better than that of a model not including it. As another example, the accuracy of the vision correction surgery-related model that generates an image from numerical values and calculates a prediction result based on the image may be better than the accuracy of a vision correction surgery-related model that calculates a prediction result based on the numerical value.

7 is a diagram illustrating pre-processing of input/output data according to an embodiment. Referring to FIG. 7 , input/output data may be input to a model related to vision correction surgery through a pre-processing step ( S500 ). The vision correction surgery-related model may calculate a prediction result based on the pre-processed input/output data (S700).

The vision correction surgery-related model may include a plurality of sub-models (sub-models). The plurality of sub-models may calculate prediction results based on input data.

The vision correction surgery-related model may include submodels connected in series and/or in parallel, such as an ensemble model.

The vision correction surgery-related model may include a plurality of submodels connected in series. Here, the serial connection of the submodels includes calculating the output of at least one submodel based on the output of at least one submodel, such as the output of the first submodel becoming the input of the second submodel. can do. Alternatively, the serial connection of the sub-models may include sequentially passing through a plurality of sub-models in order to obtain a prediction result from the input data through a model related to vision correction surgery.

8 is a diagram of a model M for corrective vision surgery including submodels M1 and M2 connected in series according to an embodiment. Referring to FIG. 8 , the vision correction surgery-related model M may include a first sub-model M1 and a second sub-model M2 connected in series. The first submodel M1 may calculate an output based on input/output data, and the second submodel M2 may calculate a prediction result based on the output of the first submodel M1.

The vision correction surgery related model may include a plurality of submodels connected in parallel. Here, that the submodels are connected in parallel may include that the output of the submodel does not affect the output of other submodels, such as the output of the first submodel does not depend on the output of the second submodel.

Inputs of a plurality of submodels connected in parallel may be the same. Alternatively, inputs of a plurality of submodels connected in parallel may be different. For example, the first examination data input to the first sub-model may be different from the second examination data input to the second sub-model.

The first examination data may include at least some other variables compared to the second examination data. For example, the first examination data may include a vision correction surgery preference, but the second examination data may not include a vision correction operation preference.

The first examination data may include the same type of variable as the second examination data, but may have different values. For example, the first examination data and the second examination data may include corneal thickness, but the values may be different due to different methods of obtaining the values (for example, measuring the corneal thickness with different devices). have.

The vision correction surgery-related model may include an output sub-model that calculates an output based on the output of a plurality of sub-models connected in parallel. For example, when the outputs of the plurality of submodels are the same, the output submodels may provide the same outputs. As another example, when the outputs of the plurality of submodels are different, the output submodel may output a result of considering the outputs of the plurality of submodels at a certain ratio or provide a specific output among the plurality of outputs. As another example, the output submodel may output a result generated based on the outputs of the plurality of submodels.

9 is a diagram of a model M for corrective vision surgery including sub-models M1 and M2 connected in parallel according to an embodiment. Referring to FIG. 9 , the vision correction surgery-related model M may include a first sub-model M1 and a second sub-model M2 connected in parallel. In addition, the vision correction surgery-related model M may include an output sub-model M3 that calculates an output based on the outputs of the first sub-model M1 and the second sub-model M2. The first sub-model M1 and the second sub-model M2 calculate a first output and a second output, respectively, based on input/output data, and the output sub-model M3 is based on the first output and the second output. Prediction results can be calculated.

An example of the vision correction surgery-related model including submodels connected in parallel may include an ensemble, but is not limited thereto.

Hereinafter, individual examples of models related to vision correction surgery will be described.

The surgical suitability prediction model can predict whether or not vision correction surgery is appropriate for a subject. The surgical suitability prediction model may predict surgery suitability based on input data.

The suitability of vision correction surgery may mean medical suitability. Accordingly, the input data of the surgical suitability prediction model may not include the subject's preference for vision correction surgery. Alternatively, the surgical suitability prediction model may predict the surgical suitability without considering the subject's preference for vision correction surgery.

Eligibility for surgery may include whether surgery is possible and whether surgery is necessary. As an example, the surgical suitability prediction model may determine that a subject who does not need surgery because of good visual acuity is unsuitable for surgery. As another example, the surgical suitability prediction model may determine a subject whose visual acuity cannot be increased through vision correction surgery as unsuitable for surgery.

Surgical suitability may be output as surgical fit/unsuitable. Alternatively, the surgical suitability may be digitized or visualized to output the surgical suitability.

The laser surgery failure prediction model can predict whether or not vision correction using laser is possible for a subject. Here, the vision correction surgery using a laser may refer to an operation for correcting the vision through corneal cutting using a laser. The laser surgery failure prediction model may predict laser surgery failure or not based on input data.

Whether or not laser vision correction is performed may mean medical approval. Accordingly, the input data of the laser surgery failure prediction model may not include the subject's preference for vision correction surgery. Alternatively, the laser surgery failure prediction model may predict the laser operation failure rate without considering the subject's vision correction surgery preference.

Whether or not to have laser surgery can be output as enabling/disabling laser surgery. Alternatively, the laser surgery decision may be output by quantifying or visualizing the possibility of surgery.

The corneal shape factor prediction model can predict the corneal shape factor after vision correction surgery of the subject. The model may predict one or more corneal shape factors. The corneal shape factor prediction model may predict the corneal shape factor based on input data.

The input data of the corneal shape factor prediction model may include surgical parameters. For example, the input data may include a surgical type as a surgical parameter. The model may predict the corneal shape factor corresponding to the received surgical parameter. For example, when the input data includes LASIK, LASEK, and Smile as surgical parameters, the output of the model may include a post-LASIK corneal shape factor predicted value, a post-Lasik corneal shape factor predicted value, and a post-Smile corneal shape factor predicted value. As another example, when the input data includes standard vision correction surgery and custom vision correction surgery as surgical parameters, the output of the model may include a corneal shape factor predicted value after standard vision correction surgery and a corneal shape factor predicted value after custom vision correction surgery.

The corneal shape factor prediction model can predict the corneal shape factor corresponding to a predetermined surgical parameter regardless of whether the input data includes the surgical parameter. For example, when the model is trained to predict the corneal shape factor after standard vision correction surgery and the corneal shape factor after custom vision correction surgery, even if the input data of the model does not include surgical parameters, the model is the corneal shape factor after standard vision correction surgery It is possible to output the predicted value and the predicted value of the corneal shape factor after custom vision correction surgery.

Table 1 is an output of a corneal shape factor prediction model according to an embodiment. Referring to Table 1, the corneal shape factor prediction model may output the IHD, ISV, and IVA values of the subject. In addition, the corneal shape factor prediction model includes the IHD, ISV, and IVA measurement values of the subject acquired before vision correction surgery, the IHD, ISV, IVA predicted values after standard vision correction surgery, and the IHD, ISV, IVA predicted values after the custom vision correction surgery. can do.

item today Expectations after standard vision correction surgery Expectations after custom vision correction surgery IHD 0.015 0.021 0.018 ISV 20.0 27.8 25.0 IVA 0.19 0.23 0.22

The custom vision correction surgery necessity prediction model can predict whether a subject needs custom vision correction surgery. The custom vision correction surgery necessity prediction model may predict the custom vision correction surgery need based on input data.

The custom vision correction surgery necessity prediction model can predict the need for custom vision correction surgery without considering the subject's vision correction surgery preference. Alternatively, the custom vision correction surgery necessity prediction model may predict the need for custom vision correction surgery in consideration of the subject's vision correction surgery preference. Depending on whether the subject's preference for vision correction surgery is considered or not, the output of the custom vision correction surgery necessity prediction model may vary.

The custom vision correction surgery necessity prediction model may determine whether the subject needs custom vision correction surgery based on eye characteristic data such as a corneal shape factor and a corneal topography image.

The custom vision correction surgery necessity prediction model may determine the need for custom vision correction surgery based on the absolute value of the corneal shape factor. For example, the custom vision correction surgery necessity prediction model may predict that the subject needs custom vision correction surgery when the corneal shape factor is out of a certain range.

The custom vision correction surgery necessity prediction model may determine the need for custom vision correction surgery based on the relative values of the corneal shape factors. For example, the custom vision correction surgery necessity prediction model may determine the need for custom vision correction surgery by comparing the difference between the corneal shape factor after standard vision correction surgery and the corneal shape factor after the custom vision correction surgery.

The vision correction surgery proposal model may suggest vision correction surgery corresponding to the subject. For example, the model may output one vision correction technique. As another example, the model may output a plurality of vision correction techniques. As another example, the model may output a plurality of vision correction surgeries together with information on their priorities.

The vision correction surgery proposal model may suggest vision correction surgery based on input data.

The vision correction surgery corresponding to the subject may refer to the vision correction surgery calculated by the vision correction surgery proposal model without considering the subject's vision correction surgery preference. Alternatively, the vision correction surgery corresponding to the subject may mean a vision correction surgery in which the vision correction surgery proposal model is calculated in consideration of the subject's preference for the vision correction surgery. The output of the vision correction surgery proposal model may vary depending on whether the subject's preference for vision correction surgery is considered.

The output of the vision correction surgery proposal model may be in consideration of the need for custom vision correction surgery. For example, the output may be in consideration of the need for custom vision correction surgery, such as standard LASIK, custom LASIK, standard LASIK, custom LASIK, standard smile, custom smile, and the like.

Alternatively, the output of the vision correction surgery proposal model may not consider the need for custom vision correction surgery. For example, the output may not consider the need for custom vision correction surgery, such as LASIK, LASEK, Smile, or lens implantation.

The vision correction surgery proposal model can suggest vision correction surgery based on the quality of vision after vision correction surgery. For example, the model may suggest a vision correction operation based on a vision prediction value after vision correction surgery corresponding to a plurality of vision correction procedures.

Table 2 is an output of the vision correction surgery proposal model according to an embodiment. Referring to Table 2, the vision correction surgery proposal model can output LASIK, LASEK, and Smile surgery together with information on priorities such as fitness. In Table 2, a value corresponding to a smile is greater than a value corresponding to LASIK and LASEK, which may mean that the vision correction surgery proposal model proposes a smile as the first priority. In addition to the methods shown in Table 2, information on priorities may be output in various methods indicating priorities.

Types of vision correction surgery fit lasik 15.45% Lasik 13.30% smile 71.25%

The surgical parameter suggestion model can suggest the surgical parameter. The model may suggest one or more surgical parameters. The surgical parameter proposal model may suggest surgical parameters based on input data.

The input data of the surgical parameter proposal model may include data in the form of an image. Here, the image may be an image obtained through measurement and/or examination using equipment, such as a corneal topography. Alternatively, the image may be an image generated through interpolation, extrapolation, artificial intelligence, or the like based on the measured values. For example, the image may be an image generated from the corneal shape factor.

The surgical parameter proposal model based on the surgical parameters suggested based on the image may be better than the surgical results after the vision correction surgery performed based on the surgical parameters suggested based on numerical values. For example, the surgical result after the vision correction surgery performed based on the surgical parameters proposed by the model based on the corneal topographic image is the vision correction surgery performed based on the surgical parameters proposed based on the corneal shape factors such as IHD, ISV, IVA, etc. It may be better than the results of surgery after surgery. Here, the surgical result may mean the quality of visual acuity after surgery. Alternatively, the surgical result may refer to the shape of the cornea after surgery.

The visual acuity prediction model may predict the visual acuity of the subject after vision correction surgery. The visual acuity prediction model may output a visual acuity prediction value based on input data. The model may predict one or more visual acuity.

The input data of the vision prediction model may include surgical parameters. For example, the input data may include a surgical type as a surgical parameter. The model may predict the visual acuity corresponding to the received surgical parameter. For example, when the input data includes LASIK, LASEK, and Smile as surgical parameters, the output of the model may include a post-LASIK visual acuity predictive value, a post-LASIK visual acuity predictive value, and a post-Smile visual acuity predictive value. As another example, when the input data includes standard vision correction surgery and custom vision correction surgery as surgical parameters, the output of the model may include a vision prediction value after standard vision correction surgery and a vision prediction value after custom vision correction surgery.

The visual acuity prediction model may predict visual acuity corresponding to a predetermined surgical parameter regardless of whether the input data includes the surgical parameter. For example, if the model is trained to predict visual acuity after standard vision correction surgery and visual acuity after custom vision correction surgery, even if the input data of the model does not include surgical parameters, the model is a predictive value after standard vision correction surgery and custom vision correction surgery It is possible to output a visual acuity prediction value.

The visual acuity prediction model may predict visual acuity corresponding to a plurality of different visual angles. For example, the model may predict the visual acuity corresponding to the first vision and the second vision after vision correction surgery. Examples of the plurality of different times include, but are not limited to, one day, one week, one month, six months, one year, and the like, after vision correction surgery.

The visual acuity prediction model may predict a vision recovery speed of a subject based on visual acuity prediction values corresponding to a plurality of different visual angles. For example, the model may predict the speed of vision recovery based on the first time and the second time after vision correction surgery.

The predicted vision image generation model may predict the visual field of the subject after vision correction surgery. The model may generate an image (hereinafter, referred to as “predicted visual acuity image”) visualizing the quality of visual acuity of the subject after vision correction surgery. As the model outputs the predicted visual acuity image, it is possible to more easily explain the vision correction operation to the subject. As the model visualizes and outputs the visual field after vision correction surgery, the subject can more clearly understand the expected results after the vision correction surgery and can be helped in the selection of vision correction surgery.

The input data of the predicted vision image generation model may include surgical parameters. For example, the input data may include a surgical type as a surgical parameter. The model may predict an expected visual acuity image corresponding to the received surgical parameter. For example, when the input data includes LASIK, LASEK, and smile as surgical parameters, the output of the model may include a post-LASIK predicted visual acuity image, a post-LASIK predicted visual acuity image, and a post-Smile predicted visual acuity image. As another example, when the input data includes the standard vision correction surgery and the custom vision correction surgery as surgical parameters, the output of the model may include the predicted vision image after the standard vision correction surgery and the predicted vision image after the custom vision correction surgery. As another example, when the input data includes a plurality of optic zones, the output of the model may include a plurality of predicted vision images corresponding to the plurality of optic zones.

The predicted vision image generation model may generate a predicted vision image corresponding to a predetermined surgical parameter regardless of whether the input data includes the surgical parameter. For example, if the model is trained to generate a predicted vision image after standard vision correction surgery and a predicted vision image after a custom vision correction surgery, the model is a predicted vision image after standard vision correction surgery even if the input data of the model does not include surgical parameters and an expected visual acuity image after custom vision correction surgery.

The predicted visual acuity image may include information on at least one of sharpness of vision, light blurring, contrast sensitivity, night vision, glare, double vision, and afterimage predicted after vision correction surgery of the subject.

10 is a diagram of an expected visual acuity image according to an exemplary embodiment. Referring to FIG. 10A , the predicted visual acuity images I1 and I2 may be expressed by visualizing information on the sharpness of the visual acuity. Referring to FIG. 10B , the predicted visual acuity images I3 , I4 , I5 , and I6 may be expressed by visualizing information about light blur.

The plurality of predicted vision images may correspond to different surgical parameters. Referring to FIG. 10A , the first predicted visual acuity image I1 may correspond to the sharpness of visual acuity after custom vision correction surgery, and the second predicted visual acuity image I2 may correspond to the visual acuity sharpness after the standard visual acuity correction surgery. Referring to FIG. 10B , the third to sixth predicted vision images I3-I6 may be predicted vision images corresponding to different optic zones. For example, the operative range of the third predicted visual acuity image I3 may be greater than the operative range of the fourth to sixth predicted visual acuity images I4-I6 .

The predicted visual acuity image according to an embodiment may be generated through filtering using a filter. Here, filtering is a concept used in a general image processing field, and may mean generating a filtered image by convolving an image and a filter. Examples of filters include an average filter, a weighted average filter, a low-pass filter, a Gaussian filter, a median filter, a bilateral filter. ), blurring filter, high-pass filter, unsharp masking, high-boost filter, sharpening filter, etc. The present invention is not limited thereto.

11 is a diagram of a predictive vision image generation model M17 using a filter according to an exemplary embodiment. Referring to FIG. 11 , the predicted visual acuity image generation model M17 may include a first sub-model M171 and a second sub-model M172.

The first sub-model M171 may calculate and/or select a filter based on input data. For example, the input data may include a predicted value of the eye characteristic data after vision correction of the subject, and the first sub-model M171 may calculate and/or select a filter based on the predicted value of the eye characteristic data. As another example, the input data may include a measurement value of the eye characteristic data of the subject and surgical parameters, and the first sub-model M171 may calculate and/or select a filter based on the measurement value of the eye characteristic data and the operation parameter. .

The second submodel M172 may generate a predicted visual acuity image based on the filter calculated and/or selected by the first submodel M171 . For example, the second submodel M172 may generate a predicted visual acuity image by applying the filter to the original image. Here, the original image is an image that is a basis for generating the predicted vision image, and may be input from the outside of the predicted vision image generation model M17 or may be included in the model M17.

The corneal topographic image prediction model can predict the corneal topographic image after vision correction surgery of the subject. The model may predict one or more corneal topographic images. The corneal topographic image prediction model may generate a corneal topographic image based on input data.

The input data of the corneal topography image prediction model may include surgical parameters. For example, the input data may include a surgical type as a surgical parameter. The model may predict a corneal topography image corresponding to the received surgical parameter. For example, when the input data includes LASIK, LASEK, and Smile as surgical parameters, the output of the model may include a post-LASIK corneal topography image, a post-LASIK corneal topography image, and a post-Smile corneal topography image. As another example, when the input data includes standard vision correction surgery and custom vision correction surgery as surgical parameters, the output of the model may include a topographic image after standard vision correction surgery and a topography image after custom vision correction surgery.

The corneal topographic image prediction model may generate a corneal topographic image corresponding to a predetermined surgical parameter regardless of whether the input data includes the surgical parameter. For example, if the model is trained to generate visual acuity after standard vision correction surgery and corneal topography image after custom vision correction surgery, even if the input data of the model does not include surgical parameters, the model is After vision correction surgery, corneal topographic images can be printed.

The input data of the corneal topographic image prediction model may include a corneal topographic image of the subject measured before vision correction surgery. 12 is a view of a corneal topography image according to an embodiment. Referring to FIG. 12 , the corneal topography image prediction model M18 may predict the corneal topography image CI2 after the vision correction surgery of the subject based on the subject's corneal topography image CI1 measured before the vision correction surgery. Although it is shown that only the corneal topography image CI1 is input to the model M18 in FIG. 12 , other input data may be input as well.

The predictive result calculation cause analysis model may analyze the cause of the prediction result generated by the vision correction surgery related model. The model may calculate a dependency on input data of a model related to vision correction surgery. Here, the dependence may include how a specific variable of the input data has an effect on the prediction result.

The prediction result calculation cause analysis model may output the prediction result calculation cause. The model may output one or more prediction result calculation causes. Hereinafter, for convenience of explanation, a case in which the cause of the prediction result is expressed as a numerical value such as a dependence coefficient will be described. none.

The prediction result calculation cause analysis model may output at least a part of the dependence coefficient. For example, the model may output all of the calculated dependency coefficients.

The predictive result calculation cause analysis model may output a dependence coefficient belonging to a certain range among the calculated dependence coefficients. For example, the model may output a dependence coefficient greater than a predetermined value among the calculated dependence coefficients. Alternatively, the model may output when the absolute value of the calculated dependency coefficient is greater than a predetermined value.

The predictive result calculation cause analysis model may output a certain number of dependency coefficients. For example, the model may output a predetermined number of dependence coefficients.

The cause analysis model for predicting results is a predictive cause analysis model for surgery suitability, a predictive cause analysis model for laser surgery, a predictive cause analysis model for a corneal shape factor, a predictive cause analysis model for the need for custom vision correction surgery, a cause analysis model for a suggested vision correction surgery, and a suggested cause for surgical parameters It may include an analysis model, an acuity prediction cause analysis model, a predicted visual acuity image generation cause analysis model, and a corneal topographic image prediction cause analysis model. For example, the visual acuity prediction cause analysis model may calculate what effect the variables included in the input data of the visual acuity prediction model have to predict the visual acuity of the visual acuity prediction model. Alternatively, the visual acuity prediction cause analysis model may calculate the dependence of the visual acuity prediction value calculated by the visual acuity prediction model on the input data of the visual acuity prediction model.

The predictive result calculation cause analysis model may include at least a part of models related to vision correction surgery. For example, the predictive visual acuity analysis model may include the visual acuity predictive model.

13 is a diagram of a predictive result calculation cause analysis model M19 including a vision correction surgery related model M192 according to an embodiment. Referring to FIG. 27 , the prediction result calculation cause analysis model M19 may include an input data disturbance model M191 , a vision correction surgery related model M192 , and a prediction result analysis model M193 .

The input data disturbance model M191 may output disturbed input data based on the input data. The model M191 may output one or more disturbed input data. Here, the perturbation of the input data may mean changing the input data, such as changing the values of at least some variables included in the input data. For example, if a variable is a numerical value, then perturbation may mean increasing or decreasing the numerical value. Alternatively, when the variable is an image, the disturbance may mean increasing or decreasing the pixel value of at least some pixels of the image.

The vision correction surgery related model M192 may output a first prediction result corresponding to the input data and a second prediction result corresponding to the disturbed input data based on the input data and the disturbed input data. For example, when the vision correction surgery-related model M192 included in the prediction result calculation cause analysis model M19 is the vision prediction model, the first prediction result and the second prediction result may be different vision prediction values. Also, when there are a plurality of disturbed input data, the model may output a plurality of prediction results corresponding to the plurality of disturbed input data.

The prediction result analysis model M193 may output a cause for calculating the prediction result based on the prediction result. For example, the model M193 may calculate the cause of the prediction result based on the difference between the first prediction result calculated from the unperturbed input data and the second prediction result calculated from the perturbed input data. Specifically, the dependence of the first prediction result on the first variable may be calculated based on a difference between the first prediction result and the second prediction result calculated from input data in which the first variable is disturbed.

14 is a diagram of a cause for calculating a prediction result according to an exemplary embodiment, and more specifically, a diagram of a cause of predicting visual acuity. Referring to FIG. 14 , a cause for calculating a prediction result may be expressed as a numerical value and an image. Characters such as Cornea_Back_Rmin(V1), Astigmatism(V2), Mono(V3), Nearsightedness(V4), Op_flag(V5), and Pupil_Dia(V6) shown in FIG. 14 may correspond to variables included in the input data. 5.95(N1), -0.5(N2), 0(N3), -1.37(N4), 2(N5), 3.1(N6), etc. expressed to correspond to the above characters correspond to the numerical values of the variables included in the input data. can be

The dependence of the prediction result on the variable can be visualized and expressed. For example, the dependence may be expressed by the length, color, direction, or the like of an arrow. Referring to FIG. 14 , the length of the arrow may correspond to the absolute value of the dependence coefficient. Also, the direction and color of the arrow may correspond to the sign of the dependence coefficient. 14 shows that the predicted visual acuity (OV) is 1.18, Cornea_Back_Rmin (V1), Astigmatism (V2), Mono (V3) and Nearsightedness (V4) have a positive effect on the predicted visual acuity value, and Op_flag (V5) and Pupul_Dia (V6) are It can be interpreted as having a negative effect on the predictive value of visual acuity.

Examples of the predictive result generation cause analysis model may include, but are not limited to, LIME (Local Interpretable Model-agnostic Explanations).

Models related to vision correction surgery may be combined with each other. The model may be combined by at least one of a series connection and a parallel connection.

The serial connection of the vision correction surgery-related models may include calculating the output of at least one other vision correction surgery-related model based on the output of the at least one vision correction surgery-related model.

That the models related to vision correction surgery are connected in parallel may include that the output of the model related to vision correction surgery does not affect the output of other models related to vision correction surgery.

Hereinafter, examples of combinations of models related to vision correction surgery will be described.

15 is a diagram illustrating serial connection of models related to vision correction surgery according to an embodiment. Referring to FIG. 15 , the first vision correction surgery-related model Ma and the second vision correction surgery-related model Mb may be combined by serial connection. The first vision correction surgery-related model Ma may calculate a first prediction result based on first input data and a second prediction result output by the second vision correction surgery-related model Mb receiving the second input data. have.

16 to 19 are diagrams illustrating an output calculation of a model related to vision correction surgery based on an output of a corneal shape factor prediction model according to an exemplary embodiment.

Referring to FIG. 16 , the custom vision correction surgery necessity prediction model M13 receives the second input data from the corneal shape factor prediction model M12 and outputs the corneal shape factor and the first input data based on the subject's custom vision correction surgery need can be foreseen.

Referring to FIG. 17 , the vision correction surgery proposal model M14 receives the second input data from the corneal shape factor prediction model M12 and performs vision correction surgery corresponding to the subject based on the first input data and the corneal shape factor. can suggest

Referring to FIG. 18 , the predicted visual acuity image generation model M17 is predicted after vision correction surgery of the subject based on the corneal shape factor and the first input data output by the corneal shape factor prediction model M12 receiving the second input data. A vision image can be created.

Referring to FIG. 19 , the corneal topography image prediction model M18 receives the second input data from the corneal shape factor prediction model M12 and outputs the corneal shape factor and the first input data, based on the first input data, the cornea after vision correction surgery. The terrain image can be predicted.

20 is a diagram illustrating output calculation of a model related to vision correction based on an output of a model for predicting the need for a custom vision correction surgery according to an embodiment. Referring to FIG. 20 , the vision correction surgery proposal model M14 is a visual acuity corresponding to the subject based on the custom vision correction surgery necessity and the first input data output by the custom vision correction surgery necessity prediction model M13 receiving the second input data. Corrective surgery may be suggested.

21 to 22 are diagrams for calculating the output of the vision correction surgery related model based on the output of the vision correction surgery proposal model according to an exemplary embodiment.

Referring to FIG. 21 , the corneal shape factor prediction model M12 receives the second input data from the vision correction surgery proposal model M14, and based on the first input data and the vision correction surgery, the shape of the cornea after the vision correction surgery of the subject factors can be predicted.

Referring to FIG. 22 , the vision prediction model M16 calculates the vision prediction value after the vision correction surgery of the subject based on the vision correction surgery and the first input data output by the vision correction surgery proposal model M14 receiving the second input data. can do.

The predicted vision image generation model may generate the predicted vision image after the vision correction surgery of the subject based on the vision correction surgery and the first input data output by the vision correction surgery proposal model receiving the second input data.

The corneal topographic image prediction model may predict the olfactory corneal topographic image of the subject based on the vision correction surgery and the first input data output by the vision correction surgery proposal model receiving the second input data.

23 is a diagram of an output calculation of a model related to vision correction surgery based on an output of a model proposed for surgical parameters according to an embodiment.

Referring to FIG. 23 , the vision prediction model M16 receives the second input data from the surgical parameter proposal model M15 and outputs the surgical parameter and the first input data to calculate the vision prediction value after vision correction of the subject. can

The corneal shape factor prediction model may predict the corneal shape factor after vision correction of the subject based on the first input data and the surgical parameters output by the surgical parameter proposal model receiving the second input data.

The predicted visual acuity image generation model may generate a predicted visual acuity image after vision correction surgery of the subject based on the surgical parameter and the first input data output by the surgical parameter proposal model receiving the second input data.

The corneal topographic image prediction model may predict the corneal topographic image after vision correction surgery of the subject based on the surgical parameters and the first input data output by the surgical parameter proposal model receiving the second input data.

24 to 25 are diagrams for calculating the output of the vision correction surgery related model based on the output of the vision prediction model according to an exemplary embodiment.

Referring to FIG. 24 , the vision correction surgery proposal model M14 may suggest vision correction surgery corresponding to the subject based on the vision prediction value and the first input data output by the vision prediction model M16 receiving the second input data. have.

Referring to FIG. 25 , the predicted visual acuity image generating model M17 generates an expected visual acuity image after vision correction surgery of the subject based on the visual acuity prediction value and the first input data output by the visual acuity prediction model M16 receiving the second input data. can create

26 to 27 are diagrams for calculating the output of the vision correction surgery related model based on the output of the corneal topographic image prediction model according to an embodiment.

Referring to FIG. 26 , the custom vision correction surgery necessity prediction model M13 is based on the corneal topography image and the first input data output by the corneal topography image prediction model M18 receiving the second input data. need can be foreseen.

Referring to FIG. 27 , the vision correction surgery proposal model M14 receives the second input data from the corneal topography image prediction model M18, and based on the first input data and the corneal topography image, the vision correction surgery corresponding to the subject is performed. can suggest

The corneal shape factor prediction model may predict the corneal shape factor after vision correction of the subject based on the corneal topography image and the first input data output by the corneal topography image prediction model receiving the second input data.

The predicted visual acuity image generation model may generate a predicted visual acuity image after vision correction surgery of the subject based on the corneal topography image output by the corneal topographic image prediction model receiving the second input data and the first input data.

Three or more vision correction related models may be combined with each other serially and/or in parallel. 28 is a view for explaining a combination of three or more models related to vision correction surgery according to an embodiment. Referring to FIG. 28 , in the first vision correction surgery-related model Ma, the second vision correction surgery-related model Mb receives the second input data and outputs the second prediction result, and the third vision correction surgery-related model Mc A third prediction result obtained by receiving and outputting the third input data and a first prediction result may be calculated by receiving the first input data. Here, the first vision correction surgery-related model Ma may be considered as serially connected to the second vision correction surgery-related model Mb and the third vision correction surgery-related model Mc. In addition, the second vision correction surgery-related model (Mb) and the third vision correction surgery-related model (Mc) can be viewed as being connected in parallel.

29 to 30 are diagrams for calculating the output of a model related to vision correction surgery based on the output of the corneal shape factor prediction model and the visual acuity prediction model according to an exemplary embodiment.

Referring to FIG. 29 , in the vision correction surgery proposal model M14, the corneal shape factor prediction model M12 receives the second input data and outputs the corneal shape factor, and the vision prediction model M16 receives the third input data. Based on the outputted visual acuity prediction value and the first input data, a vision correction operation corresponding to the subject may be suggested.

Referring to FIG. 30 , the predicted visual acuity image generation model M17 inputs the corneal shape factor that the corneal shape factor prediction model M12 receives and outputs the second input data, and the vision prediction model M16 inputs the third input data. Based on the received and outputted visual acuity prediction value and the first input data, it is possible to generate a predicted visual acuity image after vision correction surgery of the subject.

Models related to vision correction surgery can be merged with each other. A plurality of models related to vision correction surgery may be merged into one model to perform at least some of the functions of the plurality of individual models.

31 is a diagram for explaining merging of models related to vision correction surgery according to an embodiment. Referring to FIG. 31 , the first vision correction surgery-related model and the second vision correction surgery-related model may be merged to form one model Mab. The one model Mab may calculate a prediction result based on input data. Here, the prediction result may include information corresponding to at least one of a first prediction result corresponding to an output of the first vision correction surgery-related model and a second prediction result corresponding to an output of the second vision correction surgery-related model. For example, the prediction result may include at least one of a first prediction result and a second prediction result. Alternatively, the prediction result may include at least one of the first prediction result and the second prediction result.

Although the case of merging two models has been described in FIG. 31 , the present invention is not limited thereto, and three or more models may be merged.

32 to 34 are diagrams illustrating an example of merging models related to vision correction surgery according to an embodiment.

Referring to FIG. 32 , the corneal shape factor prediction model and the custom vision correction surgery necessity prediction model may be merged. The merged model M25 may calculate a prediction result based on input data. The prediction result may include information corresponding to at least one of a corneal shape factor and a need for custom vision correction surgery. For example, the prediction result may include at least one of a corneal shape factor and a need for custom vision correction surgery.

Referring to FIG. 33 , the custom vision correction surgery necessity prediction model and the vision correction surgery suggestion model may be merged. The merged model M27 may calculate a prediction result based on input data. The prediction result may include information corresponding to at least one of the need for custom vision correction surgery and vision correction surgery. For example, the prediction result may include at least one of the need for custom vision correction surgery and vision correction surgery.

Referring to FIG. 34 , the laser surgery failure prediction model, the custom vision correction surgery necessity prediction model, and the vision correction surgery suggestion model may be merged. The merged model M38 may calculate a prediction result based on input data. The prediction result may include information corresponding to at least one of whether or not laser surgery is successful, the need for custom vision correction surgery, and vision correction surgery. For example, the prediction result may include at least one of whether or not laser surgery is successful, the need for custom vision correction surgery, and vision correction surgery.

Hereinafter, an embodiment of a method for recommending vision correction surgery will be described.

The vision correction surgery recommendation method may be implemented using one or more vision correction surgery related models. When the method is implemented with a plurality of models related to vision correction surgery, whether at least one model related to vision correction surgery is executed may depend on a prediction result of at least one model related to vision correction surgery. For example, whether the second vision correction surgery-related model is executed may depend on a prediction result of the first vision correction surgery-related model.

Each step of the method for recommending vision correction surgery to be described later may be performed by a prediction device.

35 is a diagram of a first embodiment of a method for recommending a vision correction surgery according to an embodiment.

Referring to FIG. 35 , the method for recommending vision correction surgery according to an embodiment includes the steps of acquiring examination data of the subject (S1100), predicting whether the subject is suitable for vision correction surgery (S1200), and enabling vision correction using a laser of the subject It may include a step of predicting whether or not (S1300), calculating a predicted value of a corneal shape factor of the subject (S1400), and a step of suggesting a vision correction surgery corresponding to the subject (S1500).

Acquiring the examination data of the subject ( S1100 ) may include obtaining, by the computing device, examination data including the questionnaire data and the measurement values of the eye characteristics data.

Predicting whether the subject is suitable for vision correction surgery ( S1200 ) may include predicting whether the subject is suitable for vision correction surgery by inputting the first group data obtained from the examination data of the examinee into the first prediction model. The first predictive model may be a surgical suitability predictive model. The surgical suitability prediction model may predict the corrective vision surgery suitability of the subject based on the first group data.

Predicting whether the subject's vision correction using laser is possible (S1300) includes inputting the second group data obtained from the examination data of the subject into the second prediction model to predict whether the subject's vision correction using laser is possible can do. Whether the step S1300 is performed may depend on whether vision correction surgery is suitable for the subject. For example, the step S1300 may be performed when vision correction surgery is suitable for the subject. The second predictive model may be a laser surgery failure predictive model. The laser operation failure prediction model may predict the laser operation failure rate of the examinee based on the second group data.

In the step of calculating the predictive value of the corneal shape factor of the subject (S1400), the third group data obtained from the examination data of the subject is input to the third predictive model, and the predicted value of the corneal shape factor after the standard vision correction surgery and the corneal shape after the custom vision correction surgery It may include calculating factor prediction values. Whether the step ( S1400 ) is performed may depend on whether or not vision correction using a laser is possible for the examinee. For example, the step ( S1400 ) may be performed when the subject can undergo vision correction using a laser. The third prediction model may be a corneal shape factor prediction model. The third prediction model may predict the corneal shape factor based on the third group data. In this case, the need for custom vision correction surgery may be determined based on the corneal shape factor.

The step of suggesting a vision correction surgery corresponding to the examinee ( S1500 ) may include suggesting a vision correction surgery corresponding to the examinee by inputting fourth group data obtained from the examination data of the examinee into a fourth predictive model. Whether the step (S1500) is performed may depend on whether or not a laser vision correction operation is possible for the examinee. For example, the step (S1500) may be performed when the subject can undergo vision correction using a laser. The fourth predictive model may be learned based on at least one of examination data of a plurality of recipients who have undergone vision correction surgery, vision correction surgery corresponding to the plurality of recipients, and visual acuity after vision correction surgery of the plurality of recipients. The fourth predictive model may be a vision correction surgery proposal model. The fourth predictive model may suggest vision correction surgery corresponding to the subject based on the fourth group data.

Referring to FIG. 35 , the vision correction surgery may not take into consideration the predicted values of the corneal shape factor and/or the need for custom vision correction surgery. For example, the vision correction surgery may include LASIK, LASEK and Smile. In addition, even when laser vision correction is possible, since lens insertion is not impossible, the vision correction surgery may include lens insertion, which is the same in other embodiments and embodiments of the present specification. In this case, the vision correction surgery in consideration of the corneal shape factor prediction value and/or the need for custom vision correction surgery may be decided by a doctor and/or a counselor. For example, the doctor and/or counselor can provide custom vision, such as standard LASIK, standard LASIK, standard smile, custom LASIK, custom LASIK, and custom smile, based on the corneal shape factor predicted value output by the vision correction method of FIG. Vision correction surgery can be determined considering the need for corrective surgery.

36 is a diagram of a second embodiment of a method for recommending a vision correction surgery according to an embodiment.

Referring to FIG. 36 , the method for recommending vision correction surgery according to an embodiment includes the steps of acquiring examination data of the subject (S2100), predicting whether the subject is suitable for vision correction surgery (S2200), and enabling vision correction using a laser of the subject It may include a step of predicting whether or not (S2300), a step of calculating a predicted value of a corneal shape factor of the subject (S2400), and a step of suggesting a vision correction surgery corresponding to the subject (S2500).

Since the method for recommending vision correction surgery of FIG. 36 is similar to that of FIG. 35 , the difference from FIG. 35 will be mainly described.

Referring to FIG. 36 , the step (S2500) of suggesting a vision correction surgery corresponding to the subject is the predicted value of the corneal shape factor after standard vision correction surgery calculated in the step of calculating the predicted value of the corneal shape factor of the subject and the predicted value of the corneal shape factor after the custom vision correction surgery Based on this, vision correction surgery can be suggested. The vision correction surgery may be in consideration of the need for custom vision correction surgery. For example, the vision correction surgery may include standard LASIK, standard LASIK, standard smile, custom LASIK, custom LASIK, and custom smile. In addition, the vision correction surgery may include lens implantation.

37 is a diagram of a third embodiment of a method for recommending vision correction surgery according to an embodiment.

Referring to FIG. 37 , the method for recommending vision correction surgery according to an embodiment includes the steps of acquiring examination data of the subject (S3100), predicting whether the subject is suitable for vision correction surgery (S3200), and enabling vision correction using a laser of the subject It may include a step of predicting whether or not (S3300), a step of predicting whether the subject needs custom vision correction surgery (S3400), and a step of suggesting a vision correction surgery corresponding to the examinee (S3500).

Since the method of recommending vision correction surgery of FIG. 37 is similar to that of FIG. 35 , differences from FIG. 35 will be mainly described.

Referring to FIG. 37, the step of predicting whether the subject's custom vision correction surgery is necessary (S3400) is to input the third group data obtained from the examinee's examination data into the third prediction model to predict whether the subject needs custom vision correction surgery. may include Whether the step S3400 is performed may depend on whether or not the subject can undergo vision correction using a laser. For example, the step ( S3400 ) may be performed when the subject can undergo vision correction using a laser. The third predictive model may be a predictive model of the need for custom vision correction surgery. The third predictive model may predict the need for custom vision correction surgery based on the third group data. In the above step, it is possible to predict whether or not a custom vision correction surgery is necessary based on the predicted value of the corneal shape factor after the standard vision correction surgery and the predicted value of the corneal shape factor after the custom vision correction surgery.

The step of predicting whether or not the subject's custom vision correction surgery is necessary (S3400) and the step of suggesting the vision correction surgery corresponding to the examinee (S3500) may be connected. For example, the output of the step S3500 of suggesting a vision correction surgery corresponding to the subject may be calculated based on the output of the step S3400 of predicting whether the subject needs custom vision correction surgery. Alternatively, the output of the step (S3400) of predicting whether the subject needs custom vision correction surgery based on the output of the step (S3500) of suggesting a vision correction surgery corresponding to the subject may be calculated.

As an example, in the step of suggesting a vision correction surgery corresponding to the subject ( S3500 ), the vision correction surgery may be suggested based on the need for a custom vision correction surgery calculated in the step ( S3400 ) of predicting whether the subject needs custom vision correction surgery. For example, the vision correction surgery may include standard LASIK, standard LASIK, standard smile, custom LASIK, custom LASIK, and custom smile. In addition, the vision correction surgery may include lens implantation.

As another example, in the step of predicting whether or not the subject's custom vision correction surgery is necessary (S3400), the second vision correction technique may be output based on the first vision correction technique calculated in the step (S3500) of suggesting the vision correction technique corresponding to the subject. . Here, the first vision correction surgery may not consider the need for a custom vision correction surgery, and the second vision correction surgery may take into account the need for a custom vision correction surgery.

As another example, in the step (S3400) of predicting whether the subject's custom vision correction surgery is necessary, based on the type of the first vision correction surgery calculated in the step (S3500) of suggesting the vision correction surgery corresponding to the subject, whether or not to be executed may be determined. . For example, when the first vision correction surgery is the first type, the custom vision correction surgery necessity prediction model is not executed, and when the first vision correction surgery is the second type, the custom vision correction surgery necessity prediction model may be executed.

The first type and the second type may be classified according to whether the cornea is cut using a laser. For example, the first type may be a non-laser vision correction surgery such as lens implantation, and the second type may be a laser vision correction surgery such as LASIK, LASEK, and Smile.

The first type and the second type may be classified according to whether custom surgery is possible. For example, the first type may be a vision correction surgery in which custom surgery is not possible, and the second type may be a vision correction surgery in which a custom surgery is possible. Here, there may be a predetermined criterion as to whether or not a custom surgery is possible for vision correction. However, these standards may vary depending on technological developments, hospitals, surgical instruments, and the circumstances and judgment of doctors. For example, if custom smile surgery is not possible, the first type may include smile and lens implantation and the second type may include LASIK and LASEK, but if custom smile surgery is possible, the first type includes lens implantation and second type Type 2 may include LASIK, LASEK and SMILE.

38 is a diagram of a fourth embodiment of a method for recommending vision correction surgery according to an embodiment.

Referring to FIG. 38 , the method for recommending vision correction surgery according to an embodiment includes the steps of acquiring examination data of the subject (S4100), predicting whether the subject is suitable for vision correction surgery (S4200), and enabling vision correction using the laser of the subject It may include a step of predicting whether or not (S4300) and a step (S4400) of suggesting a vision correction surgery corresponding to the examinee.

The step of obtaining the examination data of the subject of FIG. 38 (S4100), the step of predicting whether the subject's vision correction surgery is suitable (S4200), and the step of predicting whether the subject's vision correction operation using the laser is possible (S4300) are the same as in FIG. 35 Therefore, a description thereof will be omitted.

The step of suggesting a vision correction surgery corresponding to the examinee ( S4400 ) may include suggesting a vision correction surgery corresponding to the examinee by inputting third group data obtained from the examination data of the examinee into a third prediction model.

Whether the step S4400 is performed may depend on whether or not the subject can undergo vision correction using a laser. For example, the step (S4400) may be performed when the subject can undergo vision correction using a laser. In the step S4400, the vision correction surgery may be suggested based on the predicted value of the corneal shape factor after the standard vision correction surgery and the predicted value of the corneal shape factor after the custom vision correction surgery.

The third predictive model may be a model in which a custom vision correction surgery necessity prediction model and a vision correction surgery proposal model are merged. The third predictive model may be learned based on at least one of examination data of a plurality of recipients who have undergone vision correction surgery, vision correction surgery corresponding to the plurality of recipients, and visual acuity after vision correction surgery of the plurality of recipients. The third predictive model may output information on at least one of a need for a custom vision correction surgery and a vision correction surgery based on the third group data. For example, the output of the third predictive model may include at least one of a need for a custom vision correction surgery and a vision correction surgery.

39 is a view of a fifth embodiment of a method for recommending a vision correction surgery according to an embodiment.

Referring to FIG. 39 , the method of recommending vision correction surgery according to an embodiment includes the steps of acquiring examination data of the subject (S5100), predicting whether the subject is suitable for vision correction surgery (S5200), and suggesting vision correction surgery corresponding to the subject. It may include a step (S5300) of doing.

The step (S5100) of obtaining the examination data of the subject of FIG. 39 and the step of predicting whether the examinee is suitable for vision correction surgery (S5200) are the same as those of FIG. 35, and thus a description thereof will be omitted.

The step of suggesting a vision correction surgery corresponding to the examinee ( S5300 ) may include suggesting a vision correction surgery corresponding to the examinee by inputting second group data obtained from the examination data of the examinee into a second prediction model.

Whether the step S5300 is performed may depend on whether vision correction surgery is suitable for the examinee. For example, the step S5300 may be performed when vision correction surgery is suitable for the subject. In the step S5300, the vision correction surgery may be suggested based on the predicted value of the corneal shape factor after the standard vision correction surgery and the predicted value of the corneal shape factor after the custom vision correction surgery.

The second prediction model may be a model in which a laser surgery failure prediction model, a custom vision correction surgery necessity prediction model, and a vision correction surgery suggestion model are merged. The second predictive model may be learned based on at least one of examination data of a plurality of recipients who have undergone vision correction surgery, vision correction surgery corresponding to the plurality of recipients, and vision after vision correction surgery of the plurality of recipients. The second predictive model may output information on at least one of whether laser surgery is possible, a need for custom vision correction surgery, and vision correction surgery based on the second group data. For example, the output of the second predictive model may include at least one of whether or not laser surgery is successful, the need for custom vision correction surgery, and vision correction surgery.

40 is a diagram of a sixth embodiment of a method for recommending vision correction surgery according to an embodiment.

Referring to FIG. 40 , the method of recommending a vision correction surgery according to an exemplary embodiment may include acquiring examination data of a subject ( S6100 ) and proposing a vision correction surgery corresponding to the subject ( S6200 ).

The step (S6100) of obtaining the examination data of the examinee of FIG. 40 is the same as that of FIG. 35, and thus a description thereof will be omitted.

The step of suggesting a vision correction surgery corresponding to the examinee ( S6200 ) may include inputting group data obtained from the examination data of the examinee into a predictive model to suggest a vision correction surgery corresponding to the examinee. In the step S6200, the vision correction surgery may be suggested based on the predicted value of the corneal shape factor after the standard vision correction surgery and the predicted value of the corneal shape factor after the custom vision correction surgery.

The predictive model may be a model in which a surgical suitability prediction model, a laser surgery failure prediction model, a custom vision correction surgery necessity prediction model, and a vision correction surgery proposal model are merged. The predictive model may be learned based on at least one of examination data of a plurality of recipients who have undergone vision correction surgery, vision correction surgery corresponding to the plurality of recipients, and visual acuity after vision correction surgery of the plurality of recipients. The predictive model may output information on at least one of surgery suitability, laser surgery availability, the need for custom vision correction surgery, and vision correction surgery based on the input data. For example, the output of the predictive model may include at least one of a surgical suitability, laser surgery or not, a need for custom vision correction surgery, and vision correction surgery.

The combination and/or merging of the above-described method for recommending a vision correction surgery and a model related to a vision correction surgery is merely an example, and in addition to this, a method for recommending a vision correction surgery may be implemented or a model related to a vision correction surgery may be combined and/or combined in various ways.

Hereinafter, an embodiment of a method for providing visual information for vision correction surgery will be described.

The method for providing vision correction surgery visualization information may be implemented using one or more models related to vision correction surgery. When the method is implemented with a plurality of models related to vision correction surgery, whether at least one model related to vision correction surgery is executed may depend on a prediction result of at least one model related to vision correction surgery. For example, whether the second vision correction surgery-related model is executed may depend on a prediction result of the first vision correction surgery-related model.

The method of providing visualization information for vision correction surgery may include a method of providing an expected visual acuity image, a method of providing a corneal topography image, and a method of providing a cause for calculating a prediction result.

The predicted vision image providing method may be implemented through a predicted vision image generation model. The corneal topographic image providing method may be implemented through a corneal topographic image prediction model. The method of providing the cause of the prediction result may be implemented through an analysis model of the cause of the prediction result.

Each step of a method of providing visual information for vision correction surgery to be described later may be performed by a prediction device.

41 is a view of a first embodiment of a method of providing visual information for vision correction surgery according to an embodiment.

Referring to FIG. 41 , the method of providing visual information for vision correction surgery according to an embodiment includes the steps of acquiring the examination data of the subject (S7100), calculating the predicted values of the eye characteristics data after the vision correction of the subject (S7200), and the expected vision image It may include the step of generating (S7300). Also, although not shown, the method for providing visual acuity correction information according to an embodiment may further include outputting an expected visual acuity image.

Acquiring the examination data of the subject ( S7100 ) may include obtaining, by the computing device, examination data including the questionnaire data and the measurement values of the eye characteristics data.

In the step (S7200) of calculating the predictive value of the eye characteristics data after vision correction of the subject, the first group data obtained from the examination data of the subject is input to the first predictive model, and at least one of the predictive value of the visual acuity and the predictive value of the corneal shape factor after the corrective eye surgery of the subject It may include calculating a predicted value of the eye characteristic data including one.

The first predictive model is at least one of pre-operative ocular characteristic data measurement values of a plurality of recipients who have undergone vision correction surgery, vision correction surgery surgical parameters performed on the plurality of recipients, and post-operative ocular characteristic data measurement values of the plurality of recipients. can be learned based on The first prediction model may include at least one of a vision prediction model and a corneal shape factor prediction model. Alternatively, the first prediction model may be a model in which a vision prediction model and a corneal shape factor prediction model are merged. The first predictive model may calculate a predicted value of the eye characteristic data after vision correction of the subject based on the first group data.

The generating of the predicted visual acuity image ( S7300 ) may include generating the predicted visual acuity image based on the predicted value of the eye characteristic data.

42 is a diagram of a second embodiment of a method of providing visual information for vision correction surgery according to an embodiment.

Referring to FIG. 42 , the method of providing visual information for vision correction surgery according to an embodiment further includes the steps of calculating and/or selecting a filter (S7600) and applying the filter to the original image (S7700) based on the predicted value of the eye characteristic data. may include

Calculating and/or selecting a filter based on the predicted eye characteristic data ( S7600 ) may be performed by the first sub-model M171 of FIG. 11 .

The step of applying the filter to the original image ( S7700 ) may include applying the filter to the original image in order to generate a predicted vision image. The step S7700 may be performed by the second sub-model M172 of FIG. 11 .

43 is a diagram of a third embodiment of a method for providing visual information for vision correction surgery according to an embodiment.

Referring to FIG. 43 , the method for providing visual information for vision correction surgery according to an embodiment may further include predicting a topographic image of the cornea after vision correction surgery ( S7400 ).

Predicting the corneal topographic image after vision correction of the subject (S7400) may include predicting the topographic image of the cornea after vision correction of the subject by inputting the second group data obtained from the examination data of the subject into the second prediction model. have.

The second predictive model may be learned based on at least one of pre-operative corneal topographic images of a plurality of recipients who have undergone vision correction surgery, vision correction surgery surgical parameters performed on the plurality of recipients, and post-operative corneal topographic images of the plurality of recipients. can The second prediction model may be a corneal topographic image prediction model. The second prediction model may predict a topographical image of the cornea after vision correction of the subject based on the second group data.

44 is a diagram of a fourth embodiment of a method of providing visual information for vision correction surgery according to an embodiment.

Referring to FIG. 44 , the method of providing visual information for vision correction surgery according to an embodiment may further include calculating ( S7500 ) the dependence of the predictive value of the eye characteristic data on the first group data. Also, although not shown, the method of providing visual information for vision correction surgery according to an embodiment may further include outputting a dependency coefficient.

The step of outputting the dependency coefficient may include outputting a dependency coefficient greater than a predetermined value among the dependency coefficients or outputting a predetermined number of dependency coefficients.

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, etc. 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 available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy 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 generated 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 devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

In the above, the configuration and features of the present invention have been described with reference to the embodiments, but the present invention is not limited thereto, and it will be appreciated by those skilled in the art that various changes or modifications can be made within the spirit and scope of the present invention. It is evident that such changes or modifications are intended to fall within the scope of the appended claims.

10: Vision correction assist system
100: learning device
300: prediction device
500: server device
700: client device
1000: control unit
5000: memory unit
9000: Ministry of Communications

Claims (13)

In the method of providing an expected vision image after vision correction using artificial intelligence performed by a computing device,
obtaining examination data of the subject, the examination data including questionnaire data and measurement values of eye characteristic data;
The first group data obtained from the examination data of the subject is input to the first prediction model, and the predictive value of the eye characteristics data after the eye correction surgery of the subject - The predictive value of the eye characteristics data includes at least one of a predictive value of visual acuity and a predictive value of a corneal shape factor - calculating ;
generating a predicted visual acuity image based on the predicted value of the eye characteristic data; and
Predicting the corneal topographic image after vision correction of the subject by inputting the second group data obtained from the examination data of the subject into a second prediction model;
The first predictive model may include at least one of a pre-operative ocular characteristic data measurement value of a plurality of recipients who have undergone vision correction surgery, a vision correction surgery surgical parameter performed on the plurality of recipients, and a post-operative ocular characteristic data measurement value of the plurality of recipients. is learned based on
The second prediction model is learned based on at least one of pre-operative corneal topographic images of a plurality of recipients who have undergone vision correction surgery, vision correction surgery surgical parameters performed on the plurality of recipients, and post-operative corneal topographic images of the plurality of recipients. been done,
How to provide a projected vision image.
According to claim 1,
The generating of the predicted visual acuity image includes calculating or selecting a filter based on the predicted value of the eye characteristic data and applying the filter to the original image to generate the predicted visual acuity image.
How to provide a projected vision image.
According to claim 1,
The prediction value of the eye characteristic data includes a first prediction value of the eye characteristic data and a prediction value of the second eye characteristic data,
The predicted vision image may include a first predicted vision image generated based on the first predicted eye characteristic data and a second predicted vision image that is different from the first predicted vision image generated based on the second predicted eye characteristic data. containing
How to provide a projected vision image.
4. The method of claim 3,
Each of the predictive value of the first ocular characteristic data and the predicted value of the second ocular characteristic data corresponds to the predicted value of the ocular characteristic data after standard vision correction surgery and the predicted value of the ocular characteristic data after the custom vision correction surgery,
Each of the first predicted visual acuity image and the second predicted visual acuity image corresponds to a predicted visual acuity image after standard vision correction surgery and a custom vision correction surgery predicted vision image.
How to provide a projected vision image.
According to claim 1,
The predicted vision image includes information on at least one of sharpness of vision, light blur, contrast sensitivity, night vision, glare, diplopia, and afterimage expected after vision correction of the subject
How to provide a projected vision image.
delete According to claim 1,
Calculating the dependence of the predictive value of the eye characteristic data on the first group data; further comprising
How to provide a projected vision image.
8. The method of claim 7,
The prediction value of the eye characteristic data includes a first prediction value of the eye characteristic data and a prediction value of the second eye characteristic data,
The dependency includes a dependency coefficient corresponding to at least a part of the first group data,
wherein the dependence coefficient includes a first dependence coefficient corresponding to the first prediction value of the eye characteristic data and a second coefficient of dependence corresponding to the predicted value of the second eye characteristic data but different from the first dependence coefficient
How to provide a projected vision image.
9. The method of claim 8,
Each of the predictive value of the first ocular characteristic data and the predicted value of the second ocular characteristic data corresponds to the predicted value of the ocular characteristic data after standard vision correction surgery and the predicted value of the ocular characteristic data after the custom vision correction surgery,
Each of the first dependence coefficient and the second dependence coefficient corresponds to the dependence of the predictive value of the ocular characteristic data after standard vision correction surgery on the first group data and the dependence of the predictive value of the ocular characteristic data after the custom vision correction operation on the first group data. felled
How to provide a projected vision image.
9. The method of claim 8,
Outputting a dependence coefficient greater than a predetermined value among the dependence coefficients or outputting a predetermined number of dependence coefficients; further comprising
How to provide a projected vision image.
According to claim 1,
The corneal shape factor predicted value includes at least one of an index of height decentration (IHD) predicted value, an index of surface variance (ISV) predicted value, and an index of vertical asymmetry (IVA) predicted value
How to provide a projected vision image.
According to claim 1,
The visual acuity prediction value includes at least one of a lower-order aberrations prediction value and a higher-order aberrations prediction value
How to provide a projected vision image.
A recording medium readable by a computing device in which a program for executing the method according to any one of claims 1 to 5 and 7 to 12 is recorded in the computing device.

Images