A production device for orthokeratology lenses

By using deep learning algorithms and linear regression models in the corneal reshaping mirror production device, the corneal curvature value is automatically calculated, which solves the problem of inconsistent acquisition of corneal reshaping mirror parameters in the existing technology, and achieves efficient and accurate corneal reshaping mirror Production.

CN110908140BActive Publication Date: 2024-11-22MINGHAO TECHNOLOGY (BEIJING) CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN201911150866.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-11-21
Publication Date
2024-11-22
Estimated Expiration
2039-11-21

AI Technical Summary

Technical Problem

During the production process of existing corneal resizing lenses, the acquisition of corneal topographic map parameters was manually tried on many times and relied on the experience of an optometrist, resulting in inconsistent parameters, affecting the user experience and the matching degree of the shaping lenses.

Method used

Design a production device for corneal reshaping mirror, including acquisition module, corneal reshaping mirror parameter calculation module and production module, use deep learning algorithm to build neural network model and linear regression model, automatically calculate the user's corneal curvature value, and then produce suitable production A shaping mirror.

Benefits of technology

Regardless of whether the optometrist has trial-on experience, he can accurately calculate the user's corneal curvature value and produce a corneal resizing lens that matches the user, improving productivity and user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN110908140B_ABST
    Figure CN110908140B_ABST
Patent Text Reader

Abstract

The present invention provides a production device for orthokeratology lenses, which includes: an acquisition module, an orthokeratology lens parameter calculation module and an orthokeratology lens production module; the acquisition module acquires the user's corneal data; the orthokeratology lens parameter calculation module calculates the user's corneal curvature value based on the user's corneal data; the orthokeratology lens production module produces orthokeratology lenses adapted to the user based on the obtained corneal curvature value of the user. The user's corneal data is acquired by the acquisition module, and then the user's corneal curvature value is calculated based on the user's corneal data; the orthokeratology lens production module then produces orthokeratology lenses adapted to the user based on the user's corneal curvature value. Using this production device, regardless of whether the optometrist has relevant work experience in manually trying on trial lenses of orthokeratology lenses for users, it can help the user conveniently calculate the orthokeratology lens parameters of the user, and then produce orthokeratology lenses adapted to the user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of eyeglass processing, and in particular to a production device for orthokeratology lenses. Background Art

[0002] The current way to fit orthokeratology lenses is for optometrists to manually try on trial lenses for users multiple times, and then derive a set of orthokeratology lens parameters. Based on the obtained orthokeratology lens parameters, the corresponding orthokeratology lenses are processed. However, this way of obtaining orthokeratology lens parameters means that for the same user's corneal topography parameters, the orthokeratology lens parameters may be different when fitted by different optometrists. Furthermore, the accuracy of the orthokeratology lens parameters is also related to the optometrist's work experience in related aspects, which may result in the orthokeratology lenses produced not matching the user, affecting the user experience. Summary of the invention

[0003] In view of the above problems, the present invention provides a production device for orthokeratology lenses.

[0004] The purpose of the present invention is achieved by the following technical solutions:

[0005] A production device for orthokeratology lenses, the production device comprising: an acquisition module, an orthokeratology lens parameter calculation module and an orthokeratology lens production module;

[0006] The acquisition module is used to acquire the user's corneal data;

[0007] The orthokeratology lens parameter calculation module is used to calculate the user's corneal curvature value based on the user's corneal data;

[0008] The orthokeratology lens production module is used to produce orthokeratology lenses suitable for the user based on the obtained corneal curvature value of the user.

[0009] In a feasible implementation manner, the user's corneal data includes: the user's corneal topography, or the user's corneal topography parameters.

[0010] In a feasible implementation, the orthokeratology lens parameter calculation module includes: a first calculation submodule and a second calculation submodule;

[0011] The first calculation submodule is used to calculate the corneal curvature value of the user according to the corneal topography image of the user;

[0012] The second calculation submodule is used to calculate the corneal curvature value of the user according to the corneal topography parameters of the user.

[0013] In a feasible implementation manner, the first calculation submodule includes:

[0014] A first historical data acquisition unit, configured to acquire first historical data, wherein the first historical data includes: a corneal topography of a fitted user and corresponding corneal curvature value data;

[0015] A first model building unit is used to build a neural network model for calculating corneal curvature values ​​according to color pixel values ​​of corneal topography based on the first historical data;

[0016] The first corneal curvature value calculation unit is used to input the user's corneal topography image into the model to obtain the user's corneal curvature value.

[0017] In a feasible implementation manner, the neural network model is constructed using a deep learning algorithm, and the construction process includes:

[0018] S1: performing image segmentation processing on the corneal topography of the fitted user to obtain a characteristic region image of the user's corneal topography and a characteristic region image of the color reference identification plate, and taking the characteristic region image of the user's corneal topography and its corresponding corneal curvature value as sample data;

[0019] S2: Divide all sample data into training set and test set;

[0020] S3: retaining a color reference identification plate feature area image, and establishing a correspondence between color pixel values ​​and corneal curvature values ​​according to color pixel values ​​of the color reference identification plate feature area image;

[0021] According to the correspondence between the color pixel value and the corneal curvature value, each sample data in the training set is processed to obtain the corneal curvature prediction value of each sample data, and the error value between the corneal curvature prediction value of each sample data and the corneal curvature value corresponding to the sample data is calculated, and the model parameters are adjusted according to the obtained error value so that the model reaches a stable state.

[0022] In a feasible implementation, the deep learning algorithm is: CNN convolutional neural network algorithm;

[0023] The step S3 comprises:

[0024] Performing noise reduction processing on each pixel point in the characteristic region image of the color control identification plate to obtain a color pixel value of each pixel point in the characteristic region image of the color control identification plate after noise reduction;

[0025] Establishing a corresponding relationship between the color pixel value and the corneal curvature value according to the color pixel value of each pixel point in the characteristic area image of the color control identification plate after noise reduction;

[0026] Performing noise reduction processing on each sample data in the training set to obtain the color pixel value of the pixel point in each sample data after noise reduction;

[0027] According to the established correspondence between color pixel values ​​and corneal curvature values, the predicted corneal curvature value of each sample data in the training set is determined, and the error value between the predicted corneal curvature value of each sample data and the corneal curvature value corresponding to its sample data is calculated. According to the obtained error value, the model parameters are adjusted to make the model reach a stable state.

[0028] In a feasible implementation manner, the second calculation submodule includes:

[0029] A second historical data acquisition unit is used to acquire second historical data, wherein the second historical data includes: corneal topography parameters of the fitted user and corresponding corneal curvature true values;

[0030] A second data processing unit, used for preprocessing the second historical data to remove invalid data;

[0031] A second model building unit, configured to build, based on the second historical data, a linear regression model for calculating a corneal curvature value based on the preprocessed second historical data;

[0032] The second corneal curvature value calculation unit is used to obtain corneal topography parameters of the user to be measured, and input the corneal topography parameters into the model to obtain the corneal curvature value of the user to be measured.

[0033] In a feasible implementation, the linear regression model is constructed using a supervised learning algorithm, specifically including:

[0034] T1: taking the pre-processed corneal topography parameters of the user and the true value of the corneal curvature of the corresponding orthokeratology lens as a sample data; wherein the sample data includes: a plurality of independent variables and a dependent variable;

[0035] T2: Based on all the sample data obtained, a supervised learning algorithm is used to build a multivariate linear regression model;

[0036] T3: Use a stepwise regression algorithm to eliminate insignificant independent variables until the insignificant independent variables are eliminated from the multivariate linear regression model; thereby obtaining a linear regression model:

[0037] Ke=b0+b1×Kf+b2×min K+b3×Em

[0038] Where Ke is the corneal curvature value, b0 is a constant term, b1, b2, and b3 are the regression coefficients of Kf, minK, and Em, respectively, Kf is the flat meridian refractive power, that is, the horizontal curvature, minK is the minimum meridian refractive power, that is, the minimum curvature, and Em is the corneal eccentricity in the meridian direction of the minimum corneal curvature.

[0039] In a feasible implementation, in step T3, the stepwise regression algorithm is used to eliminate insignificant independent variables until the insignificant independent variables are eliminated from the multiple linear regression model, including:

[0040] T31: Perform an F test on the introduced independent variable to determine whether the independent variable is significant;

[0041] T32: If the result is significant, the independent variable is introduced into the established multiple linear regression model, and the introduced independent variables are tested one by one. If the originally introduced independent variable is no longer significant due to the newly introduced independent variable, the originally introduced independent variable is eliminated so that the model only contains significant independent variables.

[0042] T33: According to steps T31-T32, the independent variables are introduced one by one until all insignificant independent variables are eliminated from the multiple linear regression model.

[0043] In a feasible implementation manner, the second calculation submodule further includes: a model optimization unit:

[0044] The model optimization unit is used to optimize the linear regression model. The specific optimization process is:

[0045] Re-obtain corneal topography parameters of a new fitted user and the corresponding true value of corneal curvature;

[0046] Substituting the re-acquired corneal topography parameters into the linear regression model to calculate the corresponding corneal curvature value;

[0047] The error value between each corneal curvature value and the corresponding true value of the corneal curvature is calculated, and the model parameters are adjusted according to the obtained error value to obtain the optimization model of the linear regression model:

[0048] Ke=b0′+b1′×Kf+b2′×min K+b3′×Em

[0049] Wherein, Ke is the corneal curvature value, b0' is a constant term, b1', b2', and b3' are the optimized regression coefficients of Kf, minK, and Em, respectively, wherein b0'=6.3982, b1'=0.3395, b2'=0.5234, and b3'=-0.9399.

[0050] The beneficial effects of the present invention are as follows: the present invention provides a device for producing orthokeratology lenses, which obtains the user's corneal data through an acquisition module, and then calculates the user's corneal curvature value based on the user's corneal data. The corneal curvature value is the orthokeratology lens parameter adapted for the user, and the orthokeratology lens production module produces orthokeratology lenses adapted for the user based on the user's corneal curvature value. Using the production device, regardless of whether the optometrist has relevant work experience in manually trying on trial lenses of orthokeratology lenses for users, the orthokeratology lens parameters of the user can be conveniently calculated to produce orthokeratology lenses adapted for the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0052] Figure 1 It is a frame structure diagram of a corneal reshaping lens production device provided by an embodiment of the present invention;

[0053] Figure 2 is a framework structure diagram of the first computing submodule provided in an embodiment of the present invention;

[0054] Figure 3 It is a framework structure diagram of the second computing submodule provided in an embodiment of the present invention.

[0055] Figure numerals: acquisition module 100, orthokeratology lens parameter calculation module 200, orthokeratology lens production module 300, first calculation submodule 210, second calculation submodule 220, first historical data acquisition unit 211, first model building unit 212, first corneal curvature value calculation unit 213, evaluation unit 214, second historical data acquisition unit 221, second data processing unit 222, second model building unit 223, second corneal curvature value calculation unit 224, model optimization unit 225. DETAILED DESCRIPTION

[0056] The present invention is further described in conjunction with the following examples.

[0057] Figure 1 A production device for orthokeratology lenses is shown, the production device comprising: an acquisition module 100, an orthokeratology lens parameter calculation module 200 and an orthokeratology lens production module 300;

[0058] The acquisition module 100 is used to acquire the user's corneal data;

[0059] The orthokeratology lens parameter calculation module 200 is used to calculate the user's corneal curvature value based on the user's corneal data;

[0060] The orthokeratology lens production module 300 is used to produce orthokeratology lenses suitable for the user based on the obtained corneal curvature value of the user.

[0061] In a feasible implementation manner, the user's corneal data includes: the user's corneal topography, or the user's corneal topography parameters.

[0062] In a feasible implementation, the orthokeratology lens parameter calculation module 200 includes: a first calculation submodule 210 and a second calculation submodule 220;

[0063] The first calculation submodule 210 is used to calculate the corneal curvature value of the user according to the corneal topography image of the user;

[0064] The second calculation submodule 220 is used to calculate the corneal curvature value of the user according to the corneal topography parameters of the user.

[0065] In one possible implementation, see Figure 2 The first calculation submodule 210 includes: a first historical data acquisition unit 211, a first model construction unit 212, a first corneal curvature value calculation unit 213 and an evaluation unit 215.

[0066] A first historical data acquisition unit 211 is used to acquire first historical data, wherein the first historical data includes: a corneal topography of a fitted user and corresponding corneal curvature value data;

[0067] A first model building unit 212, configured to build, based on the first historical data, a neural network model for calculating corneal curvature values ​​based on color pixel values ​​of a corneal topography;

[0068] In an optional implementation, the neural network model is constructed using a deep learning algorithm, and the construction process includes:

[0069] Performing image segmentation processing on the corneal topography of the fitted user to obtain a characteristic region image of the user's corneal topography and a characteristic region image of the color reference identification plate, and taking the characteristic region image of the user's corneal topography and its corresponding corneal curvature value as sample data;

[0070] Divide all sample data into training set and test set;

[0071] A color control identification plate characteristic region image is retained, and a corresponding relationship between color pixel values ​​and corneal curvature values ​​is established according to color pixel values ​​of the color control identification plate characteristic region image;

[0072] According to the correspondence between the color pixel value and the corneal curvature value, each sample data in the training set is processed to obtain the corneal curvature prediction value of each sample data, and the error value between the corneal curvature prediction value of each sample data and the corneal curvature value corresponding to the sample data is calculated, and the model parameters are adjusted according to the obtained error value so that the model reaches a stable state.

[0073] Preferably, the deep learning algorithm is: CNN convolutional neural network algorithm;

[0074] The process of constructing the neural network model using the CNN convolutional neural network algorithm includes:

[0075] Performing image segmentation processing on the corneal topography of the fitted user to obtain a characteristic region image of the user's corneal topography and a characteristic region image of the color reference identification plate, and taking the characteristic region image of the user's corneal topography and its corresponding corneal curvature value as sample data;

[0076] Divide all sample data into training set and test set;

[0077] A color control identification plate feature area image is retained. In the first step, the convolution layer is used to identify the color of each pixel in the color control identification plate feature area image to obtain the color pixel value of each pixel; in the second step, the pooling layer is used to perform denoising on the color pixel value of each pixel obtained by the convolution layer, so as to retain only the useful information in the color control identification plate feature area image and reduce unnecessary noise transmission; in the third step, the color pixel value of each pixel is summarized by the fully connected layer; in the fourth step, the classification and comparison conversion is performed. The corneal curvature value corresponding to the color in the color control identification plate feature area image is a continuous value of 0 to 101.5, which corresponds to the continuous value of the color pixel value of 0 to 255. The corneal curvature value is evenly divided into 255 parts, and then the specific corneal curvature value is corresponded to the color pixel value of 0 to 255, so that the color pixel value and the corneal curvature value in the color control identification plate feature area image form a one-to-one correspondence, and the established correspondence between the color pixel value and the corneal curvature value is further stored. After that, each sample data in the training set is processed by the convolution layer, the pooling layer and the fully connected layer in turn to obtain the color pixel value of the pixel point in each sample data in the training set. According to the established correspondence between the color pixel value and the corneal curvature value, the corneal curvature prediction value of each sample data in the training set is determined, and the error value between the corneal curvature prediction value of each sample data and the corneal curvature value corresponding to its sample data is calculated. According to the obtained error value, the model parameters are adjusted to make the model reach a stable state.

[0078] The first corneal curvature value calculation unit 213 is used to input the corneal topography image of the user into the model to obtain the corneal curvature value of the user.

[0079] The evaluation unit 214 is used to input each sample data of the test set into the neural network model to obtain the corneal curvature prediction value of each sample data of the test set, and evaluate the accuracy of the neural network model based on the obtained corneal curvature prediction value of each sample data in the test set and the corneal curvature value of the corresponding sample data.

[0080] In order to fit a suitable orthokeratology lens for a user, it is necessary to obtain the user's corneal curvature value, and then fit a suitable orthokeratology lens based on the corneal curvature value. The first calculation submodule 210 provided in the above embodiment of the present invention can obtain the corneal curvature value of the user to be tested based on the constructed neural network model, only based on the corneal topography of the user to be tested, and then produce the orthokeratology lens suitable for the user to be tested using the orthokeratology lens production module 300 based on the obtained corneal curvature value. The first calculation submodule 210 eliminates the steps of multiple trial wearing of orthokeratology lenses, and also facilitates the work of optometrists and ensures the eye safety of patients.

[0081] In a feasible implementation manner, the second calculation submodule 220 includes: a second historical data acquisition unit 221 , a second data processing unit 222 , a second model construction unit 223 , a second corneal curvature value calculation unit 224 and a model optimization unit 225 .

[0082] A second historical data acquisition unit 221 is used to acquire second historical data, wherein the second historical data includes: corneal topography parameters of the fitted user and corresponding corneal curvature true values;

[0083] A second data processing unit 222 is used to pre-process the second historical data to remove invalid data;

[0084] A second model building unit 223 is used to build, according to the second historical data, a linear regression model for calculating the corneal curvature value according to the preprocessed second historical data;

[0085] The second corneal curvature value calculation unit 224 is used to obtain corneal topography parameters of the user to be measured, and input the corneal topography parameters into the model to obtain the corneal curvature value of the user to be measured.

[0086] The model optimization unit 225 is used to optimize the linear regression model.

[0087] In a feasible implementation, the linear regression model is constructed using a supervised learning algorithm, specifically including:

[0088] T1: taking the pre-processed corneal topography parameters of the user and the true value of the corneal curvature of the corresponding orthokeratology lens as a sample data; wherein the sample data includes: a plurality of independent variables and a dependent variable;

[0089] T2: Based on all the sample data obtained, a supervised learning algorithm is used to build a multivariate linear regression model;

[0090] T3: Use a stepwise regression algorithm to eliminate insignificant independent variables until the insignificant independent variables are eliminated from the multivariate linear regression model; thereby obtaining a linear regression model:

[0091] Ke=b0+b1×Kf+b2×min K+b3×Em

[0092] Where Ke is the corneal curvature value, b0 is a constant term, b1, b2, and b3 are the regression coefficients of Kf, minK, and Em, respectively, Kf is the flat meridian refractive power, that is, the horizontal curvature, minK is the minimum meridian refractive power, that is, the minimum curvature, and Em is the corneal eccentricity in the meridian direction of the minimum corneal curvature.

[0093] In a feasible implementation, in step T3, the stepwise regression algorithm is used to eliminate insignificant independent variables until the insignificant independent variables are eliminated from the multiple linear regression model, including:

[0094] T31: Perform an F test on the introduced independent variable to determine whether the independent variable is significant;

[0095] T32: If the result is significant, the independent variable is introduced into the established multiple linear regression model, and the introduced independent variables are tested one by one. If the originally introduced independent variable is no longer significant due to the newly introduced independent variable, the originally introduced independent variable is eliminated so that the model only contains significant independent variables.

[0096] T33: According to steps T31-T32, the independent variables are introduced one by one until all insignificant independent variables are eliminated from the multivariate linear regression model.

[0097] In a feasible implementation manner, the specific optimization process of the model optimization unit 225 is:

[0098] Re-obtain corneal topography parameters of a new fitted user and the corresponding true value of corneal curvature;

[0099] Substituting the re-acquired corneal topography parameters into the linear regression model to calculate the corresponding corneal curvature value;

[0100] The error value between each corneal curvature value and the corresponding true value of the corneal curvature is calculated, and the model parameters are adjusted according to the obtained error value to obtain the optimization model of the linear regression model:

[0101] Ke=b0′+b1′×Kf+b2′×min K+b3′×Em

[0102] Wherein, Ke is the corneal curvature value, b0' is a constant term, b1', b2', and b3' are the optimized regression coefficients of Kf, minK, and Em, respectively, wherein b0'=6.3982, b1'=0.3395, b2'=0.5234, and b3'=-0.9399.

[0103] A model optimization unit 225 is set up to obtain the corneal topography parameters of the new user, and substitute the parameters into the established linear regression model to obtain the corneal curvature value of the user. The obtained corneal curvature value is compared with the actual corneal curvature value obtained by the optometrist for the user, and the model is further tuned according to the comparison result to achieve higher accuracy, thereby providing the user with accurate corneal curvature value, which is convenient for the subsequent configuration of suitable orthokeratology lenses for the user.

[0104] The second calculation submodule 220 of the above embodiment of the present invention can obtain a linear regression model based on the corneal topography parameters of the fitted user and the corresponding corneal curvature true value, and then use the model to obtain the orthokeratology lens parameters that the user to be tested needs to wear (i.e., the user's corneal curvature value). The above embodiment of the present invention is based on the existing corneal topography parameters, and the above linear regression model can be used to calculate the user's corneal curvature value, and then configure a suitable orthokeratology lens for the user, thereby eliminating the steps of multiple trial wearing of orthokeratology lenses, facilitating the work of optometrists and ensuring the patient's eye safety.

[0105] The beneficial effects of the present invention are as follows: the present invention provides a device for producing orthokeratology lenses, which obtains the user's corneal data through an acquisition module, and then calculates the user's corneal curvature value based on the user's corneal data. The corneal curvature value is the orthokeratology lens parameter adapted for the user, and the orthokeratology lens production module produces orthokeratology lenses adapted for the user based on the user's corneal curvature value. Using the production device, regardless of whether the optometrist has relevant work experience in manually trying on trial lenses of orthokeratology lenses for users, the orthokeratology lens parameters of the user can be conveniently calculated to produce orthokeratology lenses adapted for the user.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention, rather than to limit the scope of protection of the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the essence and scope of the technical solution of the present invention.

Claims

1. A device for producing orthokeratology lenses, characterized in that: include: Acquisition module, orthokeratology lens parameter calculation module and orthokeratology lens production module; The acquisition module is used to acquire the user's corneal data; the orthokeratology lens parameter calculation module is used to calculate the user's corneal curvature value based on the user's corneal data; The orthokeratology lens production module is used to produce orthokeratology lenses adapted to the user according to the obtained corneal curvature value of the user; The user's corneal data includes: the user's corneal topography, or the user's corneal topography parameters; The orthokeratology lens parameter calculation module includes: a first calculation submodule and a second calculation submodule; the first calculation submodule is used to calculate the user's corneal curvature value according to the user's corneal topography; the second calculation submodule is used to calculate the user's corneal curvature value according to the user's corneal topography parameters; The first calculation submodule includes: a first historical data acquisition unit, used to acquire first historical data, wherein the first historical data includes: a corneal topography of a fitted user and corresponding corneal curvature value data; a first model construction unit, used to construct, according to the first historical data, a neural network model for calculating a corneal curvature value according to color pixel values ​​of the corneal topography; a first corneal curvature value calculation unit, used to input the corneal topography of the user into the model to obtain the corneal curvature value of the user; The neural network model is constructed by using a deep learning algorithm, and the construction process includes: S1: performing image segmentation processing on the corneal topography of the fitted user to obtain a characteristic area image of the user's corneal topography and a characteristic area image of a color control identification plate, and taking the characteristic area image of the user's corneal topography and its corresponding corneal curvature value as a sample data; S2: dividing all sample data into a training set and a test set; S3: retaining a characteristic area image of a color control identification plate, and establishing a corresponding relationship between a color pixel value and a corneal curvature value according to the color pixel value of the characteristic area image of the color control identification plate; processing each sample data in the training set according to the corresponding relationship between the color pixel value and the corneal curvature value to obtain a corneal curvature prediction value of each sample data, calculating an error value between the corneal curvature prediction value of each sample data and the corneal curvature value corresponding to the sample data, and adjusting the model parameters according to the obtained error value so that the model reaches a stable state; The second calculation submodule includes: a second historical data acquisition unit, used to acquire second historical data, the second historical data including: corneal topography parameters of the fitted user and the corresponding true value of corneal curvature; a second data processing unit, used to preprocess the second historical data and eliminate invalid data; a second model construction unit, used to construct, based on the second historical data, a linear regression model for calculating the corneal curvature value based on the preprocessed second historical data; a second corneal curvature value calculation unit, used to acquire the corneal topography parameters of the user to be tested, input the corneal topography parameters into the model, and obtain the corneal curvature value of the user to be tested.

2. The production device of orthokeratology lenses according to claim 1, characterized in that: The deep learning algorithm is: CNN convolutional neural network algorithm; step S3 includes: performing noise reduction processing on each pixel point in the characteristic area image of the color control identification plate to obtain the color pixel value of each pixel point in the characteristic area image of the color control identification plate after noise reduction; establishing a corresponding relationship between color pixel value and corneal curvature value according to the color pixel value of each pixel point in the characteristic area image of the color control identification plate after noise reduction; performing noise reduction processing on each sample data in the training set to obtain the color pixel value of the pixel point in each sample data after noise reduction; determining the corneal curvature prediction value of each sample data in the training set according to the established corresponding relationship between the color pixel value and the corneal curvature value, calculating the error value between the corneal curvature prediction value of each sample data and the corneal curvature value corresponding to the sample data, and adjusting the model parameters according to the obtained error value so that the model reaches a stable state.

3. The production device of orthokeratology lenses according to claim 1, characterized in that: The linear regression model is constructed by using a supervised learning algorithm, specifically including: T1: taking the pre-processed corneal topography parameters of the user and the true value of the corneal curvature of the corresponding orthokeratology lens as a sample data; wherein the sample data includes: multiple independent variables and one dependent variable; T2: constructing a multivariate linear regression model by using a supervised learning algorithm based on all the obtained sample data; T3: using a stepwise regression algorithm to eliminate independent variables with insignificant effects until the insignificant independent variables are eliminated from the multivariate linear regression model; thereby obtaining a linear regression model: Ke=b0+b1×Kf+b2×min K+b3×Em Where Ke is the corneal curvature value, b0 is a constant term, b1, b2, and b3 are the regression coefficients of Kf, minK, and Em, respectively, Kf is the flat meridian refractive power, that is, the horizontal curvature, minK is the minimum meridian refractive power, that is, the minimum curvature, and Em is the corneal eccentricity in the meridian direction of the minimum corneal curvature.

4. The production device of orthokeratology lenses according to claim 3, characterized in that: In step T3, the stepwise regression algorithm is used to eliminate insignificant independent variables until the insignificant independent variables are eliminated from the multiple linear regression model, including: T31: performing an F test on the introduced independent variable to determine whether the independent variable is significant; T32: if the judgment result is significant, introducing the independent variable into the established multiple linear regression model, and testing the introduced independent variables one by one. If the originally introduced independent variable becomes no longer significant due to the newly introduced independent variable, the originally introduced independent variable is eliminated so that the model only contains significant independent variables; T33: according to steps T31-T32, the independent variables are introduced one by one until all insignificant independent variables are eliminated from the multiple linear regression model.

5. The device for producing orthokeratology lenses according to claim 1, characterized in that: The second calculation submodule further includes: a model optimization unit: the model optimization unit is used to optimize the linear regression model. The specific optimization process is: re-acquire the corneal topography parameters of the new fitted user and the corresponding corneal curvature true value; substitute the re-acquired corneal topography parameters into the linear regression model to calculate the corresponding corneal curvature value; calculate the error value between each corneal curvature value and the corresponding corneal curvature true value, adjust the model parameters according to the obtained error value, and obtain the optimization model of the linear regression model: Ke=b0'+b1'×Kf+b2'×min K+b3'×Em Wherein, Ke is the corneal curvature value, b0' is a constant term, b1', b2', and b3' are the optimized regression coefficients of Kf, minK, and Em, respectively, wherein b0'=6.3982, b1'=0.3395, b2'=0.5234, and b3'=-0.9399.

Citation Information

Patent Citations

  • Orthokeratology lens and method for generating customized arc segment parameters

    CN107783314A

  • Method and device for checking and fitting orthokeratology lens

    CN107861261A

  • Production device of orthokeratology lens

    CN211786441U

  • Customized intraocular lens power calculation system and method

    EP2605696A1

  • Selection system of best trial lens in orthokeratology specification

    JP2007000255A