How to calculate eyeglass lenses based on big data techniques and machine learning

JP2023548196A5Active Publication Date: 2024-11-05RODENSTOCK GMBH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2023527096
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2020-11-03
Filing Date
2021-11-02
Publication Date
2024-11-05
Estimated Expiration
2041-11-02

AI Technical Summary

Technical Problem

Existing methods for calculating biometric spectacle lenses require extensive and costly measurements, limiting their availability to a small proportion of visually impaired patients.

Method used

A computer-implemented method using standard refraction data and statistical models to predict individual biometric parameters, allowing for the calculation and manufacturing of high-quality biometric spectacle lenses without complex measurements.

Benefits of technology

Enables the production of high-quality biometric spectacle lenses with wearing comfort by predicting individual biological parameters using standard data and statistical models, reducing the need for costly and complex measurements.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention relates to a computer-implemented method for determining ocular biometric data and a corresponding method for manufacturing spectacle lenses taking into account the determined biometric data. Furthermore, the present invention relates to corresponding computer program products and devices. The method for determining biometric data includes the steps of providing individualized normative data for a user, the normative data including prescription data including a distance prescription and / or a near prescription for at least one of the user's eyes, and calculating, based on the individualized normative data, individualized additional data including at least one individual biometric parameter for at least one of the user's eyes using a statistical model that describes a relationship between the normative data and the additional data, the statistical model being derived using statistical analysis of a training data set with a plurality of reference data sets, each of the reference data sets including the normative data and the additional data associated with the normative data.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] The present invention relates to a computer-implemented method for determining biometric data of an eye and a corresponding method for manufacturing a spectacle lens taking into account the determined biometric data. Furthermore, the present invention relates to a corresponding computer program product and device. [Background technology]

[0002] In the calculation of spectacle lenses, especially progressive spectacle lenses, the eye biometrics of the spectacle wearer can be taken into account, as described, for example, in U.S. Pat. No. 9,910,294 (B2). These biometric spectacle lenses offer a great advantage, since the quality of the image is no longer evaluated at a virtual point, the vertex sphere, as in a simple model, but is actually formed on the retina of the eye. Therefore, the interaction between the individual aberrations occurring during refraction and propagation through the ocular media is also taken into account.

[0003] However, the drawback of this method is that it requires extensive measurements using complex equipment and devices, which is labor-intensive and expensive, limiting the benefits of high-quality biometric eyeglass lenses to a relatively small percentage of visually impaired patients. Summary of the Invention [Problem to be solved by the invention]

[0004] The object of the present invention is to make widespread use of the advantages of biometric spectacle lenses without the drawbacks of complex measurements. [Means for solving the problem]

[0005] This object is achieved by a computer-implemented method for determining eye biometric data, a corresponding device and a corresponding computer program product, as well as a method and a corresponding device for manufacturing spectacle lenses having the features specified in the respective independent claims.

[0006] The present invention is based on the surprising discovery that it is possible to determine or predict with sufficient precision and accuracy individual biometric parameters of at least one of a user's eyes using standard values ​​of the user's eyes that are determined as part of a regular refraction determination, so that it is possible to calculate and manufacture individual biometric spectacle lenses with high imaging quality and wearing comfort, without requiring complex and cost-intensive measurements of additional biometric data for this purpose.

[0007] A first aspect of the present invention relates to a computer-implemented method for determining individual biometric parameters of at least one eye of a user, the method comprising: providing individualized standard data for the user, the standard data including prescription data for at least one of the user's eyes; calculating, based on the individual standard data, individual additional data including at least one individual biological parameter of at least one eye of the user using a statistical model that describes a relationship between the standard data and the additional data; The statistical model is derived using statistical analysis of a training data set with multiple reference data sets, each of which includes standard data and additional data associated with the standard data.

[0008] The method may also include providing a statistical model that describes the relationship between the standard data and the additional data.

[0009] Further, the method can include providing a training data set and deriving a statistical model using statistical analysis of the training data set. Deriving the statistical model can include, for example, training an original (untrained) model using the training data set. For example, the model can include some model parameters that are changed or adapted during training with the training data set.

[0010] Within the meaning of this application, the term "providing" includes "specifying," "transmitting," "obtaining," "reading," "retrieving from a memory, database, and / or table," "receiving," and the like.

[0011] Within the meaning of this application, the term "determine" also includes "designate," "calculate," "identify," "predict," and the like.

[0012] Standard Data The standard data (basic data) is data of at least one of the user's eyes and possibly other data recorded in connection with ordering eyeglasses (e.g., by an optician or ophthalmologist). For example, the standard data can include data that is usually always recorded in connection with ordering eyeglasses, such as prescription data. The standard data can also include data that is optionally recorded or measured in connection with ordering eyeglasses, such as higher-order aberrations of at least one of the user's eyes. This data can then be used to determine further auxiliary data (additional data).

[0013] For example, the standard data may include data recorded by the first measurement device or first measurement method. The additional data may be calculated based on this data and not determined or measured by the first measurement device or first measurement method. Alternatively or additionally, the additional data may include data that may be determined or measured by the first measurement device or first measurement method but that does not have sufficient quality (e.g., sufficient precision, accuracy, and / or reproducibility).

[0014] For example, a measurement device may be available that allows determining at least a portion of the standard data, which portion of at least one biometric parameter of the user's eye should be taken into account when calculating an individual biometric eyeglass lens. The data recorded by this measurement device may then be used to determine additional individual biometric parameters that cannot be determined by this measurement device. The first measurement device may be an aberrometer, allowing for the determination of ocular aberrations, rather than, for example, corneal aberrations (e.g., measured by a topographer) and / or anterior chamber depth (e.g., measured by a Scheimpflug camera). This method may be used to determine further biometric data, such as corneal aberrations and / or anterior chamber depth, based on the ocular aberration data recorded by the aberrometer. If a topographer and / or a Scheimpflug camera are available, the corresponding measurement data may be used to determine ocular aberrations.

[0015] As described above, this method can also be used when data cannot be determined or measured (e.g., because a suitable measurement device is not available), as well as when corresponding data can only be determined or measured with poor or insufficient quality. For example, the standard data can include data measured by a first (e.g., simple) measurement device or measurement method that delivers data with low or insufficient quality. The data recorded by the first measurement device or first measurement method can be used to determine additional data with higher quality. For example, the additional data can correspond to data recorded or that can be measured by a second, more accurate measurement device / measurement device type or a second measurement method.

[0016] The standard data includes at least prescription data. The prescription data includes a distance prescription (i.e., refraction data when looking at a distant distance, for example, at infinity) and / or a near prescription (i.e., refraction data when looking at a close distance, for example, at reading distance). The distance prescription of at least one of the user's eyes is composed of sphere (Sph), cylinder (Cyl) parameters, and axis, or variables derived therefrom, such as components M (spherical equivalent), J0 (vertical astigmatism), and J45 (oblique astigmatism) of the power vector of the distance prescription. The near prescription is also composed of sphere (Sph), cylinder (Cyl), and axis parameters of at least one of the user's eyes, or variables derived therefrom, such as components M, J0, and J45 of the power vector of the near prescription. The prescription data can also include an add power, for example, in the case of progressive and multifocal lenses.

[0017] The distance prescription, add power, and / or near prescription can be determined using, for example, subjective refraction. It is also possible to determine the distance prescription, add power, and / or near prescription using objective refraction, or a combination of objective and subjective refraction.

[0018] Subjective refraction assessment is a refraction assessment method in which the visual impression subjectively perceived by the user is taken into account. Typically, different refractive lenses are placed in front of the user, who informs the refraction specialist of an improvement or deterioration in his visual impression as the optical properties of the previous refractive lens change.

[0019] However, objective refraction does not take into account feedback from the user. Objective refraction is performed using only the device configuration, and the refractive properties and geometry of the eye can also be recorded. Objective refraction can be performed using a variety of devices, such as refractometers, aberrometers, and wavefront scanners.

[0020] Optionally, the standard data is pupillary distance PD, and Pupil diameter The parameter may include at least one of:

[0021] Pupillary distance and pupil diameter can be determined using conventional measurement methods.

[0022] Additionally, the standard data may optionally be - low- and / or high-order aberrations of the eye, such as sphere (Sph), cylinder (Cyl), axis (or M, J0, J45), coma, trefoil, secondary astigmatism, spherical aberration, and / or other aberrations; and / or - Corneal low- and high-order aberrations, such as sphere (Sph), cylinder (Cyl), axis (or M, J0, J45), coma, trefoil, secondary astigmatism, spherical aberration, and / or other aberrations; and / or - physical dimensions of the eye, such as anterior chamber depth and ocular length, and / or - lens data, including for example low- and high-order aberrations of the lens (such as sphere (Sph), cylinder (Cyl), axis (or M, J0, J45), coma, trefoil, secondary astigmatism, spherical aberration, and / or other aberrations), and / or the structure and / or physical dimensions of the lens, such as curvature and / or thickness; and / or - Pupil diameter during distance and near vision, and / or pupil diameter under mesopic and photopic conditions wherein the data is recorded using a first measurement method or device.

[0023] Furthermore, the standard data may also optionally include additional parameters such as age, sex, ethnicity, order location, height, intraocular pressure, blood values, medical history data or medical records (e.g., possibly diabetes), retinal images, intraocular pressure values, data on the anterior segment of the eye (anterior chamber angle), and / or data on old spectacle lenses.

[0024] Additional Data The additional data is biometric data of at least one of the user's eyes and is determined (e.g., by an optician) in connection with ordering the glasses. The additional data can, for example, be data that is typically and optionally determined (e.g., by an optician) in connection with ordering the glasses. As described above, the additional data and the standard data can at least partially include the same parameters (such as aberrations of at least one of the user's eyes), and the parameters included in the additional data and the parameters included in the standard data can be recorded using different measurement methods or devices.

[0025] For example, the additional data can include data measured by an aberrometer, a topographer, a Scheimpflug camera, an OCT (i.e., optical coherence tomography), a biometer, and / or another measurement device, or data recorded or that can be recorded using another objective refraction method.

[0026] The additional data may, for example, be related to at least one of the user's eyes: - low- and / or high-order aberrations of the eye, such as sphere (Sph), cylinder (Cyl), axis (or M, J0, J45), coma, trefoil, secondary astigmatism, spherical aberration, and / or other aberrations; and / or - Corneal low- and high-order aberrations, such as sphere (Sph), cylinder (Cyl), axis (or M, J0, J45), coma, trefoil, secondary astigmatism, spherical aberration, and / or other aberrations; and / or - physical dimensions of the eye, such as anterior chamber depth and ocular length, and / or - lens data, including for example low- and high-order aberrations of the lens (such as sphere (Sph), cylinder (Cyl), axis (or M, J0, J45), coma, trefoil, secondary astigmatism, spherical aberration, and / or other aberrations), and / or the structure and / or physical dimensions of the lens, such as curvature and / or thickness; and / or - Pupil diameter during distance and near vision, and / or pupil diameter under mesopic and photopic conditions The biometric data or parameters may include:

[0027] The additional data preferably includes at least some of the following data or parameters: ocular higher order aberrations (such as coma, trefoil, secondary astigmatism, spherical aberration), corneal low and higher order aberrations (such as sphere (Sph), cylinder (Cyl), axis (or M, J0, J45), coma, trefoil, secondary astigmatism, spherical aberration), anterior chamber depth, distance and near and / or pupil diameter under mesopic and photopic conditions.

[0028] The additional data in the reference data set may be, in addition to the standard data, data recorded or measured for a previous order of biometric spectacle lenses, for example by an aberrometer, a topographer, a Scheimpflug camera, an OCT, a biometer, and / or another measuring device.

[0029] The individual additional data specified based on the user's standard individual data and the additional data determined using the statistical model may be, but is not required to be, the same type of additional data included in the reference data set and used to derive the statistical model.

[0030] Statistical Model A statistical model can be derived from an existing data set (training data set) using statistical methods. Exemplary statistical methods include regression (linear regression, nonlinear regression, attentional nonlinear regression, nonlinear multitask regression, nonparametric or semiparametric regression, etc.), classification methods, and other machine learning methods. Machine learning algorithms are described, for example, in Jeremy Watt, Reza Borhani, and Aggelos Katsaggelos, "Machine Learning Refined: Foundations, Algorithms, and Applications," Cambridge University Press, 2020.

[0031] The statistical model receives as input variables at least a portion of the individual normative data and / or variables derived therefrom and uses these to calculate at least a portion of the additional individual biological parameters or additional data. The relationship between the normative data and the additional data specified by the statistical model may be a linear or non-linear relationship. Furthermore, the relationship may be multi-parametric.

[0032] Exemplary statistical models are linear or nonlinear regression models. For example, neural networks, including deep neural networks, may be used as nonlinear regression models. Other nonlinear regression models known from the field of machine learning may also be used. Regression models, such as neural networks, may be trained using a provided training data set.

[0033] The statistical model can also be a combination of several statistical models of different types, such as a linear regression model, a non-linear regression model (such as a neural network), a classification model, and / or another statistical model.

[0034] The statistical model derived from the training data set may be stored in a suitable storage device, such as a database, calculator, computer, or data cloud. At least a portion of the training data set used for derivation may be stored along with the statistical model.

[0035] The statistical model derived from the training data set may also be validated and / or revised continuously or at periodic intervals, for example, based on a new reference data set, and the method may include revising the statistical model accordingly.

[0036] Neural Networks as Statistical Models If the statistical model includes or consists of a neural network, the input layer of the neural network is filled with at least a portion of the standard data and / or auxiliary variables calculated therefrom. The output layer outputs values ​​for at least one additional biological parameter or at least a portion of the additional data. The neural network may also preferably include one or more hidden layers in addition to the input and output layers.

[0037] During training of the original, untrained neural network, the weights are modified using an appropriate learning algorithm. The trained neural network specifies the relationship between the standard data and the additional data.

[0038] The structure of the neural network (number and type of layers, number and type of neurons in different layers, how the layers and neurons are connected to each other, etc.) and the learning algorithms may vary.

[0039] training data set A statistical model describing the relationship between the standard data and the additional data is derived using statistical methods based on a training data set that includes a plurality of individual data sets (reference data sets). Each of the reference data sets can include, for example, the standard data and additional data for a specific user determined using a suitable measurement method. Different reference data sets within the training data set can preferably include data (standard data and additional data) for a plurality of different users (reference users).

[0040] The additional data included in the reference data set may include biometric parameters not included in the standard data assigned to the additional data. The additional data included in the reference data set may also include biometric parameters included in the standard data assigned to the additional data but of lower quality. For example, the values ​​of the standard data and the additional data assigned to this standard data may have been recorded using different measurement methods and / or measurement devices.

[0041] For this purpose, an existing order for a biometric eyeglass lens can be used to train a neural network or another statistical model with a data set. In the case of a new standard order, additional measurement data (additional data) can be calculated or predicted based on the individual standard parameters included in the new order using the trained statistical model. Thus, a biometric eyeglass lens can be calculated based on the individual standard parameters and the additional data calculated therefrom using a neural network or other statistical model.

[0042] The number of reference data sets may vary. For example, 10, 100, 1,000, 10,000, 100,000, or more than 1,000,000 reference data sets may be used. The reference data sets preferably cover a wide range, preferably the entire range, for which spectacle lenses may subsequently be ordered. For example, the reference data sets may cover a range of refractive values, e.g., from -20 dpt to +20 dpt for sphere and from -8 dpt to +8 dpt for cylinder.

[0043] Furthermore, the method for determining individual biological parameters of at least one eye of a user may include transmitting the individual standard data and the calculated individual additional data to an external entity, such as an ophthalmic lens manufacturer, manufacturing unit, manufacturing device, etc.

[0044] A second aspect of the present invention is a method for manufacturing a spectacle lens, comprising the steps of: providing individualized standard data for the user, the standard data including a distance prescription for at least one of the user's eyes; Determining individual biometric parameters of at least one of the user's eyes based on the individual standard data provided by the user by the method according to one of the above aspects; and calculating a spectacle lens based on the provided individual standard data and the determined individual biometric parameters.

[0045] For example, spectacle lenses can be calculated using the method described in U.S. Pat. No. 9,910,294 (B2) or using another known method in which individual biometric parameters are taken into account when calculating spectacle lenses.

[0046] The method may also include manufacturing the calculated spectacle lens. The spectacle lens may be a single vision spectacle lens, a multifocal spectacle lens, or a progressive multifocal spectacle lens.

[0047] A third aspect of the present invention is a computer-implemented method for determining a statistical model, comprising the steps of: - providing a plurality of reference data sets to the training data set, each of the reference data sets including standard data and additional data associated with the standard data; - using statistical analysis of the training data set to derive a statistical model that describes the relationship between the standard data and the additional data; - storing the statistical model in a storage device.

[0048] A fourth aspect of the present invention relates to a computer program product which, when loaded into a computer memory and executed, causes the computer to carry out a method according to one of the above aspects.

[0049] In connection with the above methods and computer program products, the aforementioned preferred embodiments and the aforementioned advantages apply as well.

[0050] A method according to one of the above aspects may be implemented using a correspondingly designed device.

[0051] A fifth aspect of the invention relates to a device for determining an individual biological parameter of at least one eye of a user, the device comprising a computing device designed to implement the aforementioned method for determining an individual biological parameter.

[0052] The computing device preferably comprises: a standard data input interface for providing individual standard data of a user, the standard data including prescription data of at least one of the user's eyes (such as a distance prescription and / or a near prescription, and optionally an add power); and an additional data calculation device for calculating the individual additional data, the additional data including at least one individual biological parameter of at least one eye of the user, the calculation being performed using a statistical model based on the individual standard data, the statistical model being derived using statistical analysis of a training data set with a plurality of reference data sets, each of the reference data sets including the standard data and the additional data associated with the standard data.

[0053] Additionally, the device may include a model input interface for providing a statistical model. For example, the statistical model may be stored in a device such as a database, a calculator, and / or a data or calculator cloud. Additionally, the device may provide a training data set input interface for providing a training data set and a model calculation device for deriving or calculating the statistical model using statistical analysis of the training data set. The statistical model may be derived or calculated, for example, by training an original (untrained) model using the training data set.

[0054] A sixth aspect of the present invention is a device for manufacturing spectacle lenses, comprising: A device for determining an individual biological parameter of at least one eye of a user according to a fifth aspect; and a lens calculation device designed to calculate spectacle lenses based on the provided individual standard data and the calculated individual biometric parameters.

[0055] The manufacturing device may also comprise a manufacturing device for manufacturing the calculated spectacle lens.

[0056] The aforementioned devices for providing, determining, specifying or calculating data ((individual) standard data, (individual) additional data, statistical models, model parameters, weights, etc.) may be realized by suitably configured or programmed data processing devices (in particular specialized hardware modules, computers or computer systems such as computers or data clouds) having appropriate computing units, electronic interfaces, storage and data transmission units. The devices may further comprise at least a preferably interactive graphical user interface (GUI) allowing a user to view and / or input and / or modify data.

[0057] The device may also have a suitable interface that allows data (training data set, reference data set, (individual) standard data, (individual) additional data, etc.) to be transmitted, input, and / or read out. The device may also include at least one storage unit for storing the used data, for example in the form of a database.

[0058] The manufacturing device may, for example, comprise at least one CNC-controlled machine for direct processing of blanks according to the determined optimization specifications. Alternatively, the spectacle lens may be manufactured using a casting process. The finished spectacle lens may have a first simple spherical or rotationally symmetric aspheric surface and a second individual surface calculated as a function of the individual standard data and the calculated individual additional data. The simple spherical or rotationally symmetric aspheric surface may be the front surface (i.e., the object-side surface) of the spectacle lens. However, it is of course also possible to arrange an individual surface as the front surface of the spectacle lens. Both surfaces of the spectacle lens may be calculated individually.

[0059] A further aspect of the present invention relates to a spectacle lens manufactured by the above manufacturing method. Furthermore, the present invention provides the use of a spectacle lens manufactured by the above manufacturing method in a predetermined mean or concept or individual wearing position of the spectacle lens in front of the eyes of a specific user to correct a visual defect of the user.

[0060] Preferred embodiments of the present invention will now be described by way of example with reference to the accompanying drawings. Individual elements of the described embodiments are not intended to be limiting of the respective embodiments. On the contrary, elements of these embodiments may be combined with one another, if desired, to create new embodiments. [Brief explanation of the drawings]

[0061] [Figure 1] 1 is a diagram of an exemplary method for determining individual biometric data of at least one of a user's eyes and calculating a spectacle lens; [Figure 2] FIG. 1 is a diagram of an exemplary reference data set. [Figure 3] FIG. 1 is a diagram of an exemplary linear regression model. [Figure 4] FIG. 1 is a diagram of an exemplary nonlinear regression model. [Figure 5] FIG. 1 illustrates an exemplary nonlinear regression model with an attention mechanism. [Figure 6]FIG. 1 illustrates an exemplary multi-task nonlinear regression model. [Figure 7A] FIG. 1 shows the corneal spherical equivalent M [in Dpt] as a function of pupil diameter [in mm]. [Figure 7B] FIG. 1 shows the component J0 [in Dpt] of the corneal power vector as a function of the subjective vertical astigmatism [in Dpt] included in the normative data. [Figure 7C] FIG. 1 shows the component J45 [in Dpt] of the corneal power vector as a function of the subjective oblique astigmatism J45 [in Dpt] included in the normative data. [Figure 8A] FIG. 1 shows the eye length as a function of the subjective spherical equivalent M [unit: Dpt] included in the standard data. [Figure 8B] FIG. 1 shows anterior chamber depth as a function of subjective spherical equivalent M [unit: Dpt] included in standard data. [Figure 9] FIG. 10 is a table showing different additional biometric parameters of a user's right eye. [Figure 10] FIG. 10 shows a table of different additional biometric parameters for the user's left eye. [Figure 11] FIG. 10 shows the difference in maximum peripheral astigmatism of an eye for a spectacle lens calculated using a method according to an example of the present invention and a conventional spectacle lens that does not use biometric data or biometric standard parameters represented by a Gullstrand eye. [Figure 12] FIG. 10 shows the difference in percentage of change in refractive power for a spectacle lens calculated using a method according to an example of the present invention and a conventional spectacle lens that does not use biometric data or biometric standard parameters represented by a Gullstrand eye. [Figure 13] FIG. 2 shows the astigmatism in the image plane of the spectacle lens-eye system, for which the spectacle lens has been calculated using a method according to an example of the present invention. [Figure 14] 1 is a graph of an exemplary statistical model. [Figures 15A-15D] FIG. 1 shows exemplary predictions of corneal topography for different standard parameters. [Figures 16A-16C]FIG. 10 shows the deviation of predicted additional data (in this case, eye length) from the actually measured data. DETAILED DESCRIPTION OF THE INVENTION

[0062] 1 shows an exemplary method for determining individual biometric parameters of at least one of a user's eyes and calculating spectacle lenses based on the determined individual biometric parameters, the method comprising the following steps:

[0063] Step S1: A training data set is created from a plurality of data sets (reference data sets) 10, each of which includes standard data 12 and additional data 14 assigned to the standard data.

[0064] An exemplary reference data set 10 is shown in Figure 2. The standard data 12 includes distance prescriptions (Sph, Cyl, Axis, or M, J0, J45) and add powers (Add) for bifocal, multifocal, and progressive lenses. Optionally, the standard data further includes pupillary distance (PD), pupil diameter, and near prescriptions (Sph, Cyl, Axis, or M, J0, J45). The additional data 14 may be, for example, low- and high-order aberrations of the eye, low- and high-order corneal aberrations, Ocular parameters such as anterior chamber depth and ocular length, Pupil diameter (far distance, near distance, mesopic vision, photopic vision), Crystalline Lens Data The data set may include at least one of:

[0065] To form the training data set, an existing order for a biometric eyeglass lens may be used, for which additional data has been recorded using a measurement method, such as an aberrometer, a topographer, a Scheimpflug camera, an OCT, and / or a biometer.

[0066] Step S2: Using statistical methods, relationships between the standard data and the additional data are derived from multiple reference data sets. In other words, a statistical model describing the relationships, such as correlations, between the standard data and the additional data is determined based on the training data set.

[0067] Determining the statistical model can include, for example, training an originally untrained neural network with a training data set, where the training data set includes multiple reference data sets. The trained neural network can be tested using a test data set and / or validated using a validation data set. The test data set and validation data set can each include multiple data sets (reference data sets) from previous orders, such as the multiple reference data sets shown in FIG. 2. Preferably, a reference data set included in the test data set is not included in either the validation data set or the training data set. Similarly, a reference data set included in the validation data set is preferably not included in either the test data set or the training data set.

[0068] Step S3: Providing an individual data set containing only the individual standard data The individual standard data may be recorded by the optician as part of an individual order for glasses for the user.

[0069] Step S4: Based on the individual standard data contained in the individual data set provided in step S3 and based on the relationship between the standard data and the additional data determined in step S2, individual additional data (additional data) is calculated. For example, the individual standard data can be input into the trained neural network of step S2. The corresponding output data of the neural network can be directly used as the individual additional data. In addition to using the output data of the neural network directly, it is also possible to first subject this output data to further processing (validation, smoothing, filtering, categorization, transformation, etc.).

[0070] Step S5: Calculate the individual spectacle lens based on the individual standard data included in the individual data set provided in step S3 and further based on the individual additional data calculated in step S4.

[0071] The calculation of an individual spectacle lens includes the calculation of at least one surface of the spectacle lens based on the individual standard data and the calculated individual additional data. The surface thus calculated may be the back or the front surface of the spectacle lens. "Calculation of at least one surface of the spectacle lens" includes the calculation of at least a portion of the surface or a part of the surface. In other words, "calculation of at least one surface of the spectacle lens" means the calculation of at least a portion of the surface or the calculation of the entire surface.

[0072] The surface opposite to the surface being calculated can be a simple surface, such as a spherical, rotationally symmetric, aspherical, toric or non-toric surface. It is also possible to calculate both surfaces separately.

[0073] The individual spectacle lenses can be calculated using known methods, for example using the method known from US Pat. No. 9,910,294 (B2).

[0074] Figures 3-6 show exemplary statistical models 2 each trained based on Data Set 1 (training data set).

[0075] 3 shows an exemplary linear regression model with an input layer and an output layer. An output variable f(x) with K variables is calculated with dimension D (e.g., D=26) from multidimensional input variables x.

[0076] f(x)=Wx (1) In the above equation,

number

[0077] 4 shows an exemplary nonlinear regression model with an input layer, an output layer, and several hidden layers, where an output variable f(x) with k variables is computed with dimension D (e.g., D=26) from multidimensional input variables x.

[0078] f(x)=σ(W 3 σ(W 2 σ(W 1 x))) (2) In the above equation, σ(a) denotes the activation function, For example, σ(a)=max(a,0) (rectified linear unit (ReLU)),

number

number

number

[0079] Figure 5 shows an example nonlinear regression model with attention. The model has an input layer, an output layer, several hidden layers, and an attention layer, with "H" attention heads. The following operations are performed for each of the attention heads:

number

number

[0080] The output f(x) is calculated by:

[0081] f(x)=σ(W 3 σ(W 2 σ(W 1Attention(x)))) (4) In the above equation, σ(a) denotes the activation function (eg, rectified linear unit (ReLU)).

number

number

number

number

number

number

[0082] Figure 6 shows an example nonlinear multitask regression model for processing several tasks (Task 1 to Task T). The model shown in Figure 6 is based on the model shown in Figure 5 and has been modified for several tasks (Task 1 to Task T). Here, a general representation in the attention layer is used: weight matrix

number

number

number

[0083] Figures 7 and 8 show the results of different individual biometric additional parameters (i.e., parameters included in the additional data) calculated by the method described above using the model shown in Figure 3 (i.e., linear regression), compared to the actually measured individual additional parameters and additional parameters from the Gullstrand eye model. In Figures 7 and 8, measured values ​​are indicated by small circles. The solid lines show the statistically determined linear relationship between each additional parameter and the corresponding standard parameter (i.e., parameters included in the standard data) using the method described above. The dashed lines show the parameter values ​​from the Gullstrand eye model.

[0084] Figure 7 shows the results for the components of the corneal power vector, corneal "M" (spherical equivalent), "J0" (vertical astigmatism), and "J45" (oblique astigmatism), Figure 7A shows the corneal spherical equivalent M [in Dpt] as a function of pupil diameter [in mm] included in the standard data. FIG. 7B shows the corneal vertical astigmatism J0 [in Dpt] as a function of the subjective (Rx) vertical astigmatism J0 [in Dpt] included in the normative data; FIG. 7C shows the corneal oblique astigmatism J45 [in Dpt] as a function of the subjective (Rx) oblique astigmatism J45 [in Dpt] included in the normative data.

[0085] FIG. 8 shows the ocular length (FIG. 8A) and anterior chamber depth (FIG. 8B), each as a function of the subjective (Rx) spherical equivalent M [unit: Dpt] included in the standard data.

[0086] The subjective (Rx) spherical equivalent M, the subjective (Rx) vertical astigmatism J0, and the subjective oblique astigmatism J45 are components of the power vector of the distance prescription determined using subjective refraction. The distance prescription is part of the normative data.

[0087] As can be seen from Figures 7 and 8, the values ​​determined using the above method for the additional biometric parameters corneal spherical equivalent M, corneal vertical astigmatism J, corneal oblique astigmatism J, ocular length, and anterior chamber depth are very close to the values ​​determined by the complex measurement method.

[0088] 9 and 10 respectively show in tables different additional biometric parameters for the user's right eye (FIG. 9) and left eye (FIG. 10), together with the following normative data:

[0089] right eye Long-distance prescription Sph=-3.00dpt Cyl=-1.75dpt, Axis=173° Added power=0.00dpt Pupil distance PD=61.7mm left eye Long-distance prescription Sph=-4.50dpt Cyl=-1.00dpt, Axis=179° Added power=0.00dpt Pupil distance PD=61.7mm Column 1 of the tables shown in FIGS. 9 and 10 shows values ​​for additional biometric parameters from the Gullstrand eye model. Column 2 shows values ​​for additional biometric parameters determined using the method described above based on a statistical model. The statistical model is a linear regression model, such as the model shown in FIG. 3, corrected for multiple tasks. Column 3 shows actual measured values. The measured values ​​were recorded using a "LenStar900" (Haag-Streit) low-coherence reflectometer, suitable for measuring the distance between the refractive surfaces of the eye.

[0090] As can be seen from Figures 9-10, the calculated additional parameters mainly correspond to the actually measured parameters.

[0091] 11 and 12 each show the difference between the properties of spectacle lenses (813 spectacle lenses in total) calculated using a method according to an example of the present invention and the properties of conventional spectacle lenses that do not use a biometric model based on biometric standard parameters such as those represented by the Gullstrand eye.

[0092] The mean power of the prescription in Dpt (sph+cyl / 2) (also called spherical equivalent) is shown on the abscissa in Figures 11 and 12 .

[0093] The difference (in Dpt) between the maximum astigmatism of an eye with a spectacle lens calculated using a method according to an example of the present invention and the maximum astigmatism of an eye with a conventional spectacle lens is shown on the ordinate of FIG. 11, both spectacle lenses having the same standard parameters.

[0094] The percentage difference between the change in refractive power for a spectacle lens calculated by a method according to an example of the invention and the change in refractive power for a conventional spectacle lens is shown on the ordinate of FIG. 12, both spectacle lenses having the same standard parameters.

[0095] 13 shows the astigmatism in the image plane of the spectacle lens-eye system, where the distance between the two equal lines is 0.25 Dpt. The spectacle lens was calculated using the exemplary method according to the present invention for a distance prescription (Sph=0.0 Dpt, Ast=0.0 Dpt) and an add power Add=2.0 Dpt. The spectacle lens shows a reduction of the maximum peripheral astigmatism (Cyl) by approximately 15%.

[0096] As can be seen from Figures 11 to 13, spectacle lenses optimized based on individual additional biological parameters (additional data) have very good optical properties when the additional data are calculated or predicted based on standard data using statistical models, and therefore, complex and cost-intensive measurements of the individual additional data are not required.

[0097] An exemplary method used in the calculation of spectacle lenses according to the values ​​shown in FIGS. 11-13 is described below.

[0098] The training data set includes approximately 20,000 reference data sets. Each reference data set includes standard data and additional data associated with the standard data. The standard data includes prescription data for the user's right eye (distance prescription converted to M, J0, and J45) obtained by subjective refraction. The additional data includes corneal topography in Zernike representation and anterior chamber depth for the user's right eye. The training data set is used to train a linear regression model, such as the model shown in Figure 3.

[0099] The trained model is calculated as a linear regression of the following features: Zernike coefficients c of the corneal topography n,m (x) and anterior chamber depth d CL (x) allows for the prediction of each of them.

[0100] x=(1,M,J0,J 45 ,Add,M·J0,M·J 45 ,M·Add,J0·J 45 ,J0·Add,J 45 Add) T (5) In a linear regression model,

number

[0101] Predicted anterior chamber depth d CL In the case of (x),

number

[0102] In equations (6) and (7),

number

number

[0103] For the corneal apex depth z, the feature vector x and pupil coordinate X pup ,Y pup As a function of the position of z(x,X pup ,Y pup )=Σ n,m c n,m (x)Z n,m (X pup ,Y pup )=Σ i x i z i (X pup ,Y pup ) (8) is valid, and in the above equation,

number

[0104] The summation terms from equation (8) are determined by training a model.

[0105] Figure 14 shows a graph of the trained model for the corneal topography. As explained above, for a vertex depth z of the corneal topography, z(x,X pup ,Y pup )=Σ i x i z i (X pup ,Y pup ) (10) is valid.

[0106] In Figure 14, the sum terms of equation (10) determined by training the model are shown as a vertex depth plot, where the vertex depth isolines correspond to the respective features (constant terms, M, J0, J 45 ,Add,M·J0,M·J 45 , M·Add, J0·J 45 , J0·Add, J 45 Add) is expressed in units of μm and the pupil coordinate X pup ,Y pup is shown in mm.

[0107] 15A-15D show exemplary predictions for corneal topography based on trained models with different standard parameters M (spherical equivalent), J0, J45, and Add. FIG. 15A shows the results (as isotropic plots) for M=0D, J0=0D, J45=0D, and Add=0D. FIG. 15B shows the results (as isotropic plots) for M=0D, J0=2D, J45=0D, and Add=0D. FIG. 15C shows the results (as isotropic plots) for M=0D, J0=0D, J45=2D, and Add=0D. FIG. 15D shows the results (as isotropic plots) for M=0D, J0=0D, J45=0D, and Add=2D. Pupil coordinate x pup ,ypup are shown on the abscissa and ordinate of Figures 15A-15D, respectively. In particular, Figures 15A-15D each show, from left to right, the mean corneal power in Dpt, the corneal apex depth (corneal topography) in μm, and the deviation of the corneal apex depth from the constant term of the corneal topography expression according to Equation (10) (topography deviation).

[0108] 16A-16C show the deviation of predicted additional data (in this case, ocular length) from the actually measured data. The measured ocular length in mm is shown on the abscissa. The predicted ocular length in mm is shown on the ordinate.

[0109] The predicted ocular length shown in Figure 16A is the ocular length according to the Gullstrand eye model. This model has zero input parameters. The accuracy of the prediction (95% confidence interval) is ±2.4 mm.

[0110] The predicted ocular length shown in Figure 16B was determined using a trained statistical model with spherical equivalent as an input parameter. The accuracy of the prediction (95% confidence interval) is ±1.5 mm.

[0111] The predicted eye length shown in Figure 16C was determined using a trained statistical model with spherical equivalent and pupillary distance as input parameters. The accuracy of the prediction (95% confidence interval) is ±1.4 mm.

[0112] As can be seen from Figures 16A-16C, taking multiple input parameters into account can improve the accuracy of the prediction. [Explanation of symbols]

[0113] 1. Training Data Set 2. Statistical Model 10. Reference Data Set 12 Standard Data 14 Additional Data S1 to S5: Method steps

Claims

1. 1. A computer-implemented method for determining an individual biometric parameter of at least one eye of a user, comprising: Providing individual standard data (12) for the user, the standard data (12) including prescription data including a distance prescription and / or a near prescription for at least one of the user's eyes; Calculating individual additional data (14) comprising at least one individual biometric parameter of at least one eye of the user based on the individual standard data (12) using a statistical model (2) describing a relationship between the standard data and the additional data, 1. The method of claim 1, wherein the statistical model (2) is derived using statistical analysis of a training data set (1) with a plurality of reference data sets (10), each of the reference data sets (10) comprising standard data and additional data associated with the standard data.

2. Providing said training data set (1); deriving the statistical model (2) using a statistical analysis of the training data set (1), where deriving the statistical model (2) may include training an original model using the training data set (1). The method of claim 1.

3. The method of claim 1 or 2, wherein the statistical model (2) is a linear regression model, a non-linear regression model, a non-parametric regression model, or a semi-parametric regression model.

4. The method according to one of claims 1 to 3, wherein the statistical model (2) is a neural network trained using the training data set.

5. The standard data (12) further includes an add power and / or a pupil distance and / or a pupil diameter. The method according to one of claims 1 to 4.

6. the additional data (14) contained in the reference data set (10) comprises a biometric parameter not contained in the standard data (12) that is assigned to the additional data (14); and / or the additional data (14) included in the reference data set (10) comprises a biological parameter included in the standard data (12) assigned to the additional data (14), and the values ​​of the standard data (12) and the additional data (14) assigned to the standard data (12) have been recorded by different measurement methods and / or measurement devices; The method according to one of claims 1 to 5.

7. 7. The method of claim 1, wherein the prescription has been determined using subjective refraction.

8. 8. The method according to claim 1, wherein the additional data (14) included in the reference data set (10) comprises data recorded by an aberrometer, a topographer, a Scheimpflug camera, an OCT, and / or a biometer.

9. The additional data (14) low and / or high order aberrations of the eye, and / or - the anterior chamber depth and / or length of the eye, and / or - low and high order aberrations of the cornea, and / or low and / or high order aberrations of the crystalline lens, and / or the structure of the lens, and / or the lens curvature, and / or the lens thickness, and / or The method according to one of claims 1 to 8, comprising the pupil diameter of the user during distance and near vision and / or under mesopic and photopic conditions.

10. 1. A method for manufacturing a spectacle lens, comprising the steps of: - determining individual additional data (14) comprising at least one individual biometric parameter of at least one eye of the user based on the provided individual standard data (12) of the user according to a method according to one of claims 1 to 9; and calculating the spectacle lens based on the determined individual additional data.

11. A computer program product which, when loaded into the memory of a computer and executed, causes said computer to carry out a method according to one of claims 1 to 10.

12. A device for determining an individual biometric parameter of at least one of a user's eyes, comprising a computing device designed to implement the method according to one of claims 1 to 9.

13. 1. A device for manufacturing spectacle lenses, comprising: A device for determining an individual biological parameter of at least one eye of a user according to claim 12, and a lens calculation device designed to calculate the spectacle lens based on the determined individual biometric parameters.