Method and apparatus for determining corneal axial curvature

Abstract

This application relates to a method and apparatus for determining corneal axial curvature. The method includes: acquiring the anterior corneal surface layering line and / or posterior corneal surface layering line for each of multiple corneal images of a target cornea; determining the axial position of the target cornea based on the anterior and / or posterior corneal surface layering lines of each corneal image; and determining the axial curvature of the target cornea based on the axial position of the target cornea. This method, by introducing the axial position of the cornea, and thus determining the axial curvature of the cornea based on the axial position, achieves the effect of accurately calculating the corneal axial curvature even when the scanning center is not on the axial direction due to systematic errors.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method and apparatus for determining corneal axial curvature. Background Technology

[0002] With the continuous advancement and development of science and technology, among numerous corneal topographic maps, the corneal axial curvature map can fully express the situation of corneal astigmatism. Furthermore, by observing the changes in the corneal axial curvature map before and after surgery, the degree of astigmatism after corneal transplantation surgery can be accurately diagnosed, guiding the correction of astigmatism.

[0003] In related technologies, in devices used to measure corneal axial curvature, due to the existence of systematic errors, the scanning center may not be in the same position as the axial length of the eye. If the corneal axial curvature is calculated based on the scanning center in this case, the calculated corneal curvature value will have a large error. Summary of the Invention

[0004] Therefore, it is necessary to provide a method and apparatus for determining corneal axial curvature to address the above-mentioned technical problems. This method and apparatus can determine the position of the cornea's axial axis and accurately determine the corneal axial curvature by using the position of the axial axis. This achieves the effect of accurately calculating the corneal axial curvature even when the scanning center is not on the axial axis due to systematic errors.

[0005] In a first aspect, embodiments of this application provide a method for determining corneal axial curvature. The method includes:

[0006] Based on multiple corneal images of the target cornea, the anterior corneal surface layering line and / or posterior corneal surface layering line of each corneal image are obtained; the multiple corneal images are acquired through different scanning angles;

[0007] The axial position of the target cornea is determined based on the corneal anterior surface layering lines and / or corneal posterior surface layering lines in each corneal image.

[0008] The axial curvature of the target cornea is determined based on its axial position.

[0009] In one embodiment, based on multiple corneal images of the target cornea, the anterior corneal surface delineation line and the posterior corneal surface delineation line of each corneal image are obtained, including:

[0010] The corneal images are layered using a pre-defined neural network model to obtain the anterior corneal surface layering line and the initial posterior corneal surface layering line for each corneal image.

[0011] Refraction correction was performed on each initial posterior corneal delineation line to obtain the anterior and posterior corneal delineation lines for each corneal image.

[0012] In one embodiment, determining the axial position of the target cornea based on the anterior corneal delineation lines and / or posterior corneal delineation lines of each corneal image includes:

[0013] Based on the physical length and physical depth information of each pixel in each of the corneal anterior surface layer lines and each of the corneal posterior surface layer lines, obtain the corneal position physical coordinate values ​​of each pixel on each of the corneal anterior surface layer lines and the corneal position physical coordinate values ​​of each pixel on each of the corneal posterior surface layer lines;

[0014] Based on the coordinates of each corneal location and the expression of the ellipsoid model, the surface coefficients of the corneal ellipsoid are obtained; the corneal ellipsoid represents a three-dimensional ellipsoid formed by the anterior and / or posterior corneal surface layering lines of multiple corneal images.

[0015] The axial position of the target cornea is determined based on the surface curvature coefficient of the corneal ellipsoid.

[0016] In one embodiment, determining the axial position of the target cornea based on the curvature coefficient of the corneal ellipsoid includes:

[0017] The axial position of the target cornea is obtained based on the curvature coefficient of the corneal ellipsoid and the functional relationship between the corneal axial position and the scanning center of each acquired corneal image.

[0018] In one embodiment, determining the axial curvature of the target cornea based on its axial position includes:

[0019] Based on the axial position of the target cornea, determine the axial radius of curvature of multiple sampling points in the target cornea;

[0020] Based on the axial radius of curvature of each sampling point, the axial curvature of each sampling point is obtained accordingly;

[0021] The axial curvature of the target cornea is obtained based on the axial curvature of each sampling point.

[0022] In one embodiment, the axial radius of curvature of multiple sampling points in the target cornea is determined based on the axial position of the target cornea, including:

[0023] For any given sampling point, the axial curvature radius model of the sampling point is obtained based on the axial position of the target cornea and the corneal position coordinates of the sampling points within a preset range around the sampling point.

[0024] The axial radius of curvature of the sampling points is determined based on the axial radius of curvature model of the sampling points.

[0025] In one embodiment, determining the axial radius of curvature of the sampling point based on the axial radius of curvature model of the sampling point includes:

[0026] The curvature coefficients of the sampling points are obtained based on the axial radius of curvature model of the sampling points;

[0027] The axial radius of curvature of the sampling point is determined based on the curvature coefficient of the sampling point and the functional relationship between the corneal axial position and the axial radius of curvature.

[0028] In one embodiment, the axial curvature of each sampling point is obtained according to the axial radius of curvature of each sampling point, including:

[0029] For any given sampling point, the ratio between the refractive index and the axial radius of curvature corresponding to the sampling point is taken as the axial curvature of the sampling point.

[0030] In one embodiment, obtaining the axial curvature of the target cornea based on the axial curvature of each sampling point includes:

[0031] Obtain the remaining pixels in the target cornea excluding each sampling point;

[0032] The axial curvature of each remaining pixel is obtained based on the position information of each remaining pixel and the axial curvature of each sampling point.

[0033] The axial curvature of each remaining pixel and the axial curvature of each sampling point are used as the axial curvature of the target cornea.

[0034] Secondly, embodiments of this application also provide a device for determining corneal axial curvature. The device includes:

[0035] The layering line acquisition module is used to acquire the anterior corneal layering line and / or posterior corneal layering line of each corneal image based on multiple corneal images of the target cornea; the multiple corneal images are acquired through different scanning angles;

[0036] The first determining module is used to determine the axial position of the target cornea based on the corneal anterior surface layering line and / or corneal posterior surface layering line of each corneal image.

[0037] The second determining module is used to determine the axial curvature of the target cornea based on the axial position of the target cornea.

[0038] Thirdly, embodiments of this application also provide a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in any of the embodiments of the first aspect described above.

[0039] Fourthly, embodiments of this application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps in any of the embodiments of the first aspect described above.

[0040] Fifthly, embodiments of this application also provide a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps in any of the embodiments of the first aspect described above.

[0041] The aforementioned method and apparatus for determining corneal axial curvature first acquires the anterior and posterior corneal surface delineation lines for each of multiple corneal images of the target cornea. Then, based on these delineation lines, the axial position of the target cornea is determined. Finally, the axial curvature of the target cornea is determined based on its axial position. This method, by incorporating the axial position of the cornea, allows for the accurate calculation of corneal axial curvature even when the scanning center is not aligned with the axial direction due to system errors. Attached Figure Description

[0042] Figure 1 This is an application environment diagram of the corneal axial curvature determination method in one embodiment;

[0043] Figure 2 This is a flowchart illustrating a method for determining corneal axial curvature in one embodiment;

[0044] Figure 3 This is a schematic diagram of scanning the target cornea in one embodiment;

[0045] Figure 4 This is a schematic diagram of the corneal anterior surface delineation line and the corneal posterior surface delineation line in one embodiment;

[0046] Figure 5 This is a flowchart illustrating the process of determining the axial length of a target cornea in one embodiment;

[0047] Figure 6 This is a flowchart illustrating the process of determining the axial curvature of a target cornea in one embodiment;

[0048] Figure 7 This is a flowchart illustrating the process of determining the axial radius of curvature in one embodiment;

[0049] Figure 8 This is a flowchart illustrating the method for determining corneal axial curvature in another embodiment;

[0050] Figure 9 This is a schematic diagram of the corneal axial curvature determination device in one embodiment;

[0051] Figure 10 This is a schematic diagram of the corneal axial curvature determination device in another embodiment;

[0052] Figure 11 This is a schematic diagram of the corneal axial curvature determination device in another embodiment;

[0053] Figure 12 This is a schematic diagram of the corneal axial curvature determination device in another embodiment;

[0054] Figure 13 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] The corneal axial curvature determination method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, the corneal axial curvature measurement device 102 communicates with the server 104 via a network. A data storage system can store the data that the server 104 needs to process. Optionally, the corneal axial curvature measurement device 102, used to acquire corneal images, can be a keratometer or biometer, etc. The data storage system can be integrated into the corneal axial curvature measurement device 102, or it can be located on the server 104, in the cloud, or on another network server. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0057] In one embodiment, such as Figure 2 As shown, a method for determining corneal axial curvature is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation may include the following steps:

[0058] S201, based on multiple corneal images of the target cornea, obtain the anterior corneal surface layering line and the posterior corneal surface layering line of each corneal image.

[0059] In this embodiment, multiple corneal images are acquired through different scanning angles.

[0060] Optionally, multiple corneal images of the target cornea can be obtained from an image database. Alternatively, the cornea of ​​the target eye can be scanned directly to obtain multiple corneal images; for example, the target cornea can be scanned using a biometric instrument, such as... Figure 3As shown, the axial length of the eye is first roughly assessed, and the scanning center (i.e., the center of the circle) is locked at the axial length of the eye. Starting from 90° and ending at 270°, the image is rotated clockwise to acquire corneal images from 90° to 270°. The target eye can be a human eye, an animal eye, or a bionic eye. The acquired corneal images include at least a clear cornea, and each corneal image is a two-dimensional image. The anterior and posterior surfaces of the cornea can be seen through the vertical content.

[0061] One possible approach is to use traditional image processing algorithms to segment each corneal image to obtain the anterior corneal surface segmentation line and the initial posterior corneal surface segmentation line. For example, the corneal image can be segmented to divide the corneal region, with the upper boundary being the anterior corneal surface segmentation line and the lower boundary being the initial posterior corneal surface segmentation line. Further refraction correction processing can be performed on the initial posterior corneal surface segmentation line to obtain the posterior corneal surface segmentation line of the corneal image.

[0062] Another possible approach is to use a pre-defined neural network model to segment each corneal image, obtaining the anterior corneal surface segmentation line and the initial posterior corneal surface segmentation line for each corneal image; and to perform refraction correction processing on each initial posterior corneal surface segmentation line to obtain the anterior corneal surface segmentation line and the posterior corneal surface segmentation line for each corneal image.

[0063] Optionally, the device for acquiring corneal images employs optical imaging technology, which obtains corneal morphological information by projecting a light beam onto the cornea and measuring the reflection of light. However, due to the difference in refractive index between the anterior corneal surface and air, light rays bend as they pass through the anterior corneal surface, thus distorting the morphological information of the posterior corneal surface in the corneal image.

[0064] Therefore, to accurately obtain the posterior corneal delamination line, the refractive index difference between the anterior corneal surface and air can be measured, and the initial posterior corneal delamination line can be refractively corrected according to Snell's law to obtain the final posterior corneal delamination line. Figure 4 As shown, this is one of several corneal images, where the upper boundary line a is the anterior corneal surface delineation line and the lower boundary line b is the posterior corneal surface delineation line after refraction correction.

[0065] S202, determine the axial position of the target cornea based on the corneal anterior surface layering line and / or corneal posterior surface layering line of each corneal image.

[0066] For example, the axial length of the target cornea can be determined based on a pre-defined logic for determining the axial length. For instance, a mathematical model for determining the axial length can be pre-defined, and then the axial length of the target cornea can be determined based on this mathematical model, the anterior corneal surface layering lines of each corneal image, and the posterior corneal surface layering lines.

[0067] S203, determine the axial curvature of the target cornea based on the axial position of the target cornea.

[0068] In this embodiment, the axial curvature of the cornea represents the change in corneal curvature measured along the central axis of the cornea; wherein, axial curvature exists at each position on the anterior and posterior surfaces of the cornea.

[0069] For example, the axial curvature of the target cornea can be determined by using a pre-set determination logic for determining the axial curvature of the cornea, based on the axial position of the target cornea and the degree of relative axial curvature of the cornea.

[0070] In the aforementioned method for determining corneal axial curvature, firstly, based on multiple corneal images of the target cornea, the anterior and posterior corneal surface delineation lines are obtained for each image. Then, based on these delineation lines, the axial position of the target cornea is determined. Finally, the axial curvature of the target cornea is determined based on its axial position. This method, by introducing the axial position of the cornea, allows for the determination of corneal axial curvature directly, achieving accurate calculation even when the scanning center is not aligned with the axial direction due to systematic errors.

[0071] To ensure a more accurate determination of the axial curvature of the target cornea, the axial length of the target cornea needs to be more precisely positioned. Therefore, in one embodiment, an optional method for determining the axial length of the target cornea is provided. For example... Figure 5 As shown, the method includes the following steps:

[0072] S301, based on the physical length and physical depth information of each pixel on each anterior corneal surface layer line and each posterior corneal surface layer line, obtain the physical coordinate values ​​of the corneal position of each pixel on each anterior corneal surface layer line and the physical coordinate values ​​of the corneal position of each pixel on each posterior corneal surface layer line.

[0073] For each corneal image containing the anterior and posterior corneal surface delineation lines, first, the image coordinates of each pixel on the anterior and posterior corneal surface delineation lines are obtained in the image coordinate system. The physical position and image physical depth information of each pixel in the anterior and posterior corneal surface delineation lines are recorded. Further, for each pixel in the anterior and posterior corneal surface delineation lines, based on its physical position and image depth information, the image coordinates of the pixel in the image coordinate system are transformed to physical coordinates in the physical coordinate system, i.e., the corneal physical position coordinates of that pixel. At this point, the corneal position coordinates of each pixel in the anterior and posterior corneal surface delineation lines of each corneal image are coordinates in the polar coordinate system.

[0074] S302, based on the coordinate values ​​of each corneal location and the expression of the ellipsoidal model, obtain the surface coefficients of the corneal ellipsoid.

[0075] In this embodiment, the corneal ellipsoid represents a three-dimensional ellipsoid formed by the corneal anterior surface layering lines and / or corneal posterior surface layering lines of multiple corneal images; optionally, the corneal anterior surface layering lines of multiple corneal images can form a three-dimensional ellipsoid, and the corneal posterior surface layering lines of multiple corneal images can also form a three-dimensional ellipsoid.

[0076] The ellipsoid model expression is the general expression for a three-dimensional ellipsoid in a mathematical model.

[0077] For example, the expression for the corneal ellipsoid can be derived from the ellipsoid model expression, as shown in formula (1) below.

[0078] a1*x n 2 +a2*y n 2 +a3*z n 2 +2*a4*x n *y n +2*a5*x n +2*a6*y n +2*a7*z n =1 (1)

[0080] Where a1, a2, a3, a4, a5, a6, and a7 are the surface coefficients of the corneal ellipsoid; x n y n and z n x represents the corneal position coordinates of each pixel on the corneal ellipsoid; if the corneal ellipsoid is a three-dimensional ellipsoid formed by the layering lines of the anterior corneal surface of multiple corneal images, then x... n yn and z n This refers to the corneal position coordinates of each pixel on the anterior corneal surface layering line; if the corneal ellipsoid is a three-dimensional ellipsoid formed by the posterior corneal surface layering lines of multiple corneal images, then x... n y n and z n This refers to the corneal position coordinates of each pixel on the posterior corneal surface layer line.

[0081] Optionally, when determining the surface coefficient of the corneal ellipsoid according to formula (1), at least seven pixels on the corneal ellipsoid need to be selected. These pixels can be selected from any point on the corneal ellipsoid that is less than half the scanning length from the scanning center.

[0082] S303 determines the axial position of the target cornea based on the surface coefficient of the corneal ellipsoid.

[0083] Optionally, there are three ways to determine the axial length of the target cornea: one way is to determine the axial length of the target cornea based on the corneal ellipsoid formed by the corneal anterior surface layering lines of multiple corneal images; another way is to determine the axial length of the target cornea based on the corneal ellipsoid formed by the corneal posterior surface layering lines of multiple corneal images; and yet another way is to determine a first axial length position based on the corneal ellipsoid formed by the corneal anterior surface layering lines of multiple corneal images, then determine a second axial length position based on the corneal ellipsoid formed by the corneal posterior surface layering lines of multiple corneal images, and finally determine the axial length of the target cornea based on the first and second axial length positions.

[0084] In one possible implementation, the axial position of the target cornea can be determined by using a pre-defined determination logic for determining the axial position, based on the curvature coefficient of the corneal ellipsoid.

[0085] For example, the axial position of the target cornea can be obtained based on the curvature coefficient of the corneal ellipsoid and the functional relationship between the corneal axial position and the scanning center of each acquired corneal image.

[0086] The functional relationship between the corneal axial length and the scanning center of each corneal image is shown in the following formula (2).

[0087]

[0088] Where, x c y c The coordinates of the eye axis on the axial curvature topographic map.

[0089] Optionally, if the first method described above is used to determine the axial position of the target cornea, the surface curvature coefficient of the corneal ellipsoid is determined by the surface curvature coefficient of the corneal ellipsoid formed by the corneal anterior surface layering lines of multiple corneal images. If the second method described above is used to determine the axial position of the target cornea, the surface curvature coefficient of the corneal ellipsoid is determined by the surface curvature coefficient of the corneal ellipsoid formed by the corneal posterior surface layering lines of multiple corneal images. If the third method described above is used to determine the axial position of the target cornea, the first axial position needs to be determined first by the surface curvature coefficient of the corneal ellipsoid formed by the corneal anterior surface layering lines of multiple corneal images and the above formula (2); then the second axial position needs to be determined by the surface curvature coefficient of the corneal ellipsoid formed by the corneal posterior surface layering lines of multiple corneal images and the above formula (2); finally, the average of the first and second axial positions is taken as the axial position of the target cornea.

[0090] In this embodiment, by introducing a corneal ellipsoid, the axial position of the target cornea can be accurately determined based on the relationship between each pixel on the corneal ellipsoid and the axial position of the target cornea, providing data support for subsequently determining the axial curvature of the target cornea.

[0091] Based on the accurate determination of the target corneal axial position according to the above-mentioned application embodiments, the method of determining the axial curvature of the target cornea according to the target corneal axial position is further explained in detail in S203.

[0092] like Figure 6 As shown, the method also includes the following steps:

[0093] S401, based on the axial position of the target cornea, determines the axial radius of curvature of multiple sampling points in the target cornea.

[0094] Optionally, the axial radius of curvature of multiple sampling points in the target cornea can be determined according to a pre-defined logic for determining the axial radius of curvature. For example, the axial radius of curvature of multiple sampling points in the target cornea can be determined based on a pre-defined mathematical model for determining the axial radius of curvature and the axial length of the target cornea.

[0095] S402, based on the axial curvature radius of each sampling point, obtain the axial curvature of each sampling point.

[0096] In one possible implementation, a pre-defined logic for determining the axial curvature of each sampling point can be used to determine the axial curvature of each sampling point based on the axial curvature radius of each sampling point.

[0097] Optionally, for any given sampling point, the ratio between the refractive index and the axial radius of curvature corresponding to that sampling point can be used as the axial curvature of that sampling point.

[0098] For each sampling point, the axial curvature of that sampling point can be determined according to the following formula (3).

[0099]

[0100] Where, r p The axial radius of curvature corresponding to the p-th sampling point; η is the refractive index, which is a fixed constant; k p Let be the axial curvature of the p-th sampling point.

[0101] S403, obtains the axial curvature of the target cornea based on the axial curvature of each sampling point.

[0102] One possible approach is to input the axial curvature of each sampling point into a pre-trained model, and then have the model output the axial curvature of the target cornea.

[0103] Another possible approach is to obtain the remaining pixels in the target cornea excluding each sampling point; obtain the axial curvature of each remaining pixel based on the position information of each remaining pixel and the axial curvature of each sampling point; and use the axial curvature of each remaining pixel and the axial curvature of each sampling point as the axial curvature of the target cornea.

[0104] The remaining pixels are the unscanned pixels in the target cornea.

[0105] Optionally, the remaining area of ​​the target cornea can be scanned using a biometer to obtain the position information of each remaining pixel. Then, the position information of each remaining pixel and the axial curvature of each sampling point can be input into a pre-trained model, and the model can output the axial curvature of each remaining pixel. Alternatively, for each remaining pixel, the axial curvature of the remaining pixel can be interpolated with the axial curvature of each sampling point within a preset range of the remaining pixel to obtain the axial curvature of the remaining pixel. Finally, the axial curvature of each remaining pixel and the axial curvature of each sampling point are used as the axial curvature of the target cornea.

[0106] In this embodiment of the application, an optional method is provided for quickly determining the axial curvature of the target cornea; by introducing the axial curvature radius, the axial curvature of the target cornea can be quickly determined based on the axial curvature radius.

[0107] In one embodiment, based on the above embodiment, a more detailed explanation is provided regarding S401, which determines the axial curvature radius of multiple sampling points in the target cornea according to the axial position of the target cornea. For example... Figure 7 As shown, the method also includes the following steps:

[0108] S501: For any given sampling point, obtain the axial curvature radius model of the sampling point based on the axial position of the target cornea and the corneal position coordinates of the sampling points within a preset range around the sampling point.

[0109] The axial curvature radius model is a mathematical model used to represent the axial curvature radius of the sampling point.

[0110] For any given sampling point, the axial radius of curvature model of that sampling point can be represented by the following formula (4).

[0111] x m 2 +y m 2 +z m 2 +2*x c *x m +2*y c *y m +s1*z m +s2=0 (4)

[0112] Where s1 and s2 are the curvature coefficients of the sampling point; x m y m and z m The coordinates of the corneal location of the sampling points within a preset range around the sampling point.

[0113] Optionally, when solving for the curvature coefficients, at least two sampling points need to be selected, which can be the two sampling points closest to the selected point.

[0114] S502, based on the axial curvature radius model of the sampling points, determines the axial curvature radius of the sampling points.

[0115] In one possible implementation, for each sampling point, the curvature coefficient of the sampling point can be obtained according to the axial curvature radius model of the sampling point; based on the curvature coefficient of the sampling point and the functional relationship between the corneal axial position and the axial curvature radius, the axial curvature radius of the sampling point is determined.

[0116] For example, the functional relationship between the corneal axial position and the axial radius of curvature is shown in the following formula (5).

[0117]

[0118] In this embodiment of the application, by introducing an axial curvature radius model, the axial curvature radius of each sampling point is determined based on the axial curvature radius model of each sampling point, providing data support for determining the axial curvature of the target cornea.

[0119] Additionally, in one embodiment, this application also provides an optional example of a method for determining corneal axial curvature. (In conjunction with...) Figure 8 As shown, it includes:

[0120] S601, acquire multiple corneal images of the target cornea.

[0121] S602 uses a preset neural network model to divide each corneal image into layers, and obtains the corneal anterior surface layering line and the initial corneal posterior surface layering line for each corneal image.

[0122] S603 performs refractive correction processing on each initial corneal posterior surface delineation line to obtain the corneal anterior surface delineation line and corneal posterior surface delineation line for each corneal image.

[0123] S604, based on the physical length and physical depth information of each pixel on each anterior corneal surface layer line and each posterior corneal surface layer line, obtain the corneal position coordinates of each pixel on each anterior corneal surface layer line and each pixel on each posterior corneal surface layer line.

[0124] S605: Obtain the surface coefficients of the corneal ellipsoid based on the coordinates of each corneal location and the expression of the ellipsoid model.

[0125] S606: Based on the curvature coefficient of the corneal ellipsoid and the functional relationship between the corneal axial length and the scanning center of each acquired corneal image, the axial length of the target cornea is obtained.

[0126] S607: For any given sampling point, obtain the axial curvature radius model of the sampling point based on the axial position of the target cornea and the corneal position coordinates of the sampling points within a preset range around the sampling point.

[0127] S608, obtain the curvature coefficient of the sampling point based on the axial curvature radius model of the sampling point.

[0128] S609. Determine the axial radius of curvature of the sampling point based on the curvature coefficient of the sampling point and the functional relationship between the corneal axial position and the axial radius of curvature.

[0129] S610: For any given sampling point, the ratio between the refractive index and the axial radius of curvature corresponding to the sampling point is taken as the axial curvature of the sampling point.

[0130] S611, acquire the remaining pixels in the target cornea excluding each sampling point.

[0131] S612: Obtain the axial curvature of each remaining pixel based on the position information of each remaining pixel and the axial curvature of each sampling point.

[0132] S613, the axial curvature of each remaining pixel and the axial curvature of each sampling point are used as the axial curvature of the target cornea.

[0133] The processes S601-S613 described above can be found in the description of the above method embodiments, and their implementation principles and technical effects are similar, so they will not be repeated here.

[0134] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0135] Based on the same inventive concept, this application also provides a corneal axial curvature determination device for implementing the corneal axial curvature determination method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more corneal axial curvature determination device embodiments provided below can be found in the limitations of the corneal axial curvature determination method described above, and will not be repeated here.

[0136] In one embodiment, such as Figure 9 As shown, a corneal axial curvature determination device 1 is provided, comprising: a layer line acquisition module 10, a first determination module 20, and a second determination module 30, wherein:

[0137] The layering line acquisition module 10 is used to acquire the anterior corneal layering line and the posterior corneal layering line of each corneal image based on multiple corneal images of the target cornea; the multiple corneal images are acquired through different scanning angles;

[0138] The first determining module 20 is used to determine the axial position of the target cornea based on the corneal anterior surface layering line and / or corneal posterior surface layering line of each corneal image.

[0139] The second determining module 30 is used to determine the axial curvature of the target cornea based on the axial position of the target cornea.

[0140] In one embodiment, the layer line acquisition module 10 described above can be used to:

[0141] The corneal images are layered using a pre-defined neural network model to obtain the anterior corneal surface layering line and the initial posterior corneal surface layering line for each corneal image. The initial posterior corneal surface layering line is then subjected to refraction correction processing to obtain the anterior corneal surface layering line and the posterior corneal surface layering line for each corneal image.

[0142] In one embodiment, such as Figure 10 As shown, the first determining module 20 includes:

[0143] The first acquisition unit 21 is used to acquire the corneal position coordinates of each pixel on each corneal anterior surface layer line and each corneal posterior surface layer line based on the physical length information and physical depth information of each pixel in each corneal anterior surface layer line and each corneal posterior surface layer line.

[0144] The second acquisition unit 22 is used to acquire the surface coefficient of the corneal ellipsoid based on the coordinate values ​​of each corneal position and the expression of the ellipsoid model; the corneal ellipsoid represents a three-dimensional ellipsoid formed by the corneal anterior surface layering lines and / or corneal posterior surface layering lines of multiple corneal images;

[0145] The first determining unit 23 is used to determine the axial position of the target cornea based on the surface coefficient of the corneal ellipsoid.

[0146] In one embodiment, the first determining unit 23 described above can be used to:

[0147] The axial position of the target cornea is obtained based on the curvature coefficient of the corneal ellipsoid and the functional relationship between the corneal axial position and the scanning center of each acquired corneal image.

[0148] In one embodiment, such as Figure 11 As shown, the second determining module 30 includes:

[0149] The second determining unit 31 is used to determine the axial radius of curvature of multiple sampling points in the target cornea based on the axial position of the target cornea;

[0150] The third acquisition unit 32 is used to acquire the axial curvature of each sampling point according to the axial curvature radius of each sampling point.

[0151] The fourth acquisition unit 33 is used to acquire the axial curvature of the target cornea based on the axial curvature of each sampling point.

[0152] In one embodiment, such as Figure 12 As shown, the second determining unit 31 includes:

[0153] The acquisition subunit 311 is used to acquire the axial curvature radius model of any sampling point based on the axial position of the target cornea and the corneal position coordinates of the sampling points within a preset range around the sampling point.

[0154] Subunit 312 is defined to determine the axial radius of curvature of the sampling points based on the axial radius of curvature model of the sampling points.

[0155] In one embodiment, the aforementioned determining subunit 312 can be used to:

[0156] The curvature coefficient of the sampling point is obtained based on the axial curvature radius model of the sampling point; the axial curvature radius of the sampling point is determined based on the curvature coefficient of the sampling point and the functional relationship between the corneal axial position and the axial curvature radius.

[0157] In one embodiment, the third acquisition unit 32 described above can be used to:

[0158] For any given sampling point, the ratio between the refractive index and the axial radius of curvature corresponding to the sampling point is taken as the axial curvature of the sampling point.

[0159] In one embodiment, the fourth acquisition unit 33 described above can be used to:

[0160] Obtain the remaining pixels in the target cornea excluding each sampling point; obtain the axial curvature of each remaining pixel based on the position information of each remaining pixel and the axial curvature of each sampling point; use the axial curvature of each remaining pixel and the axial curvature of each sampling point as the axial curvature of the target cornea.

[0161] Each module in the aforementioned corneal axial curvature determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0162] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 13As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores corneal axial curvature determination data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a method for determining corneal axial curvature.

[0163] Those skilled in the art will understand that Figure 13 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0164] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0165] Based on multiple corneal images of the target cornea, the anterior and posterior corneal surface delineation lines are obtained for each corneal image; the multiple corneal images are acquired through different scanning angles.

[0166] The axial position of the target cornea is determined based on the corneal anterior surface layering lines and / or corneal posterior surface layering lines in each corneal image.

[0167] The axial curvature of the target cornea is determined based on its axial position.

[0168] In one embodiment, when the processor executes the logic in the computer program to obtain the anterior corneal surface layering line and the posterior corneal surface layering line of each corneal image based on multiple corneal images of the target cornea, the following steps can be implemented:

[0169] The corneal images are layered using a pre-defined neural network model to obtain the anterior corneal surface layering line and the initial posterior corneal surface layering line for each corneal image. The initial posterior corneal surface layering line is then subjected to refraction correction processing to obtain the anterior corneal surface layering line and the posterior corneal surface layering line for each corneal image.

[0170] In one embodiment, when the processor executes the logic in the computer program that determines the axial position of the target cornea based on the anterior corneal layering lines and / or posterior corneal layering lines of each corneal image, the following steps can be implemented:

[0171] Based on the physical length and depth information of each pixel in each anterior and posterior corneal surface layering line, the corneal position coordinates of each pixel on each anterior and posterior corneal surface layering line are obtained. Based on the corneal position coordinates and the ellipsoid model expression, the surface coefficients of the corneal ellipsoid are obtained. The corneal ellipsoid represents a three-dimensional ellipsoid formed by the anterior and / or posterior corneal surface layering lines of multiple corneal images. Based on the surface coefficients of the corneal ellipsoid, the axial position of the target cornea is determined.

[0172] In one embodiment, when the processor executes the logic in the computer program to determine the axial position of the target cornea based on the surface coefficients of the corneal ellipsoid, it can perform the following steps:

[0173] The axial position of the target cornea is obtained based on the curvature coefficient of the corneal ellipsoid and the functional relationship between the corneal axial position and the scanning center of each acquired corneal image.

[0174] In one embodiment, when the processor executes the logic in the computer program that determines the axial curvature of the target cornea based on the axial position of the target cornea, it can perform the following steps:

[0175] Based on the axial position of the target cornea, determine the axial curvature radius of multiple sampling points in the target cornea; based on the axial curvature radius of each sampling point, obtain the axial curvature of each sampling point; based on the axial curvature of each sampling point, obtain the axial curvature of the target cornea.

[0176] In one embodiment, when the processor executes the logic in the computer program that determines the axial radius of curvature of multiple sampling points in the target cornea based on the axial position of the target cornea, it can implement the following steps:

[0177] For any given sampling point, the axial curvature radius model of the sampling point is obtained based on the axial position of the target cornea and the corneal position coordinates of the sampling points within a preset range around the sampling point; based on the axial curvature radius model of the sampling point, the axial curvature radius of the sampling point is determined.

[0178] In one embodiment, when the processor executes the logic in the computer program to determine the axial radius of curvature of the sampling points based on the axial radius of curvature model of the sampling points, it can perform the following steps:

[0179] The curvature coefficient of the sampling point is obtained based on the axial curvature radius model of the sampling point; the axial curvature radius of the sampling point is determined based on the curvature coefficient of the sampling point and the functional relationship between the corneal axial position and the axial curvature radius.

[0180] In one embodiment, when the processor executes the logic in the computer program to obtain the axial curvature of each sampling point based on the axial radius of curvature of each sampling point, it can implement the following steps:

[0181] For any given sampling point, the ratio between the refractive index and the axial radius of curvature corresponding to the sampling point is taken as the axial curvature of the sampling point.

[0182] In one embodiment, when the processor executes the logic in the computer program to obtain the axial curvature of the target cornea based on the axial curvature of each sampling point, it can implement the following steps:

[0183] Obtain the remaining pixels in the target cornea excluding each sampling point; obtain the axial curvature of each remaining pixel based on the position information of each remaining pixel and the axial curvature of each sampling point; use the axial curvature of each remaining pixel and the axial curvature of each sampling point as the axial curvature of the target cornea.

[0184] The principles and processes of the computer equipment provided above in implementing the various embodiments can be found in the description of the corneal axial curvature determination method in the foregoing embodiments, and will not be repeated here.

[0185] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0186] Based on multiple corneal images of the target cornea, the anterior and posterior corneal surface delineation lines are obtained for each corneal image; the multiple corneal images are acquired through different scanning angles.

[0187] The axial position of the target cornea is determined based on the corneal anterior surface layering lines and / or corneal posterior surface layering lines in each corneal image.

[0188] The axial curvature of the target cornea is determined based on its axial position.

[0189] In one embodiment, when the logic in the computer program for obtaining the anterior corneal surface layering line and the posterior corneal surface layering line of each corneal image based on multiple corneal images of the target cornea is executed by the processor, the following steps can be implemented:

[0190] The corneal images are layered using a pre-defined neural network model to obtain the anterior corneal surface layering line and the initial posterior corneal surface layering line for each corneal image. The initial posterior corneal surface layering line is then subjected to refraction correction processing to obtain the anterior corneal surface layering line and the posterior corneal surface layering line for each corneal image.

[0191] In one embodiment, when the logic in the computer program that determines the axial position of the target cornea based on the anterior and / or posterior corneal layering lines of each corneal image is executed by the processor, the following steps can be implemented:

[0192] Based on the physical length and depth information of each pixel in each anterior and posterior corneal surface layering line, the corneal position coordinates of each pixel on each anterior and posterior corneal surface layering line are obtained. Based on the corneal position coordinates and the ellipsoid model expression, the surface coefficients of the corneal ellipsoid are obtained. The corneal ellipsoid represents a three-dimensional ellipsoid formed by the anterior and / or posterior corneal surface layering lines of multiple corneal images. Based on the surface coefficients of the corneal ellipsoid, the axial position of the target cornea is determined.

[0193] In one embodiment, when the logic in the computer program that determines the axial position of the target cornea based on the curvature coefficient of the corneal ellipsoid is executed by the processor, the following steps can be implemented:

[0194] The axial position of the target cornea is obtained based on the curvature coefficient of the corneal ellipsoid and the functional relationship between the corneal axial position and the scanning center of each acquired corneal image.

[0195] In one embodiment, when the logic in the computer program that determines the axial curvature of the target cornea based on the axial position of the target cornea is executed by the processor, the following steps can be implemented:

[0196] Based on the axial position of the target cornea, determine the axial curvature radius of multiple sampling points in the target cornea; based on the axial curvature radius of each sampling point, obtain the axial curvature of each sampling point; based on the axial curvature of each sampling point, obtain the axial curvature of the target cornea.

[0197] In one embodiment, when the logic in the computer program that determines the axial radius of curvature of multiple sampling points in the target cornea based on the axial position of the target cornea is executed by the processor, the following steps can be implemented:

[0198] For any given sampling point, the axial curvature radius model of the sampling point is obtained based on the axial position of the target cornea and the corneal position coordinates of the sampling points within a preset range around the sampling point; based on the axial curvature radius model of the sampling point, the axial curvature radius of the sampling point is determined.

[0199] In one embodiment, when the logic in the computer program that determines the axial radius of curvature of a sampling point based on the axial radius of curvature model of the sampling point is executed by the processor, the following steps can be implemented:

[0200] The curvature coefficient of the sampling point is obtained based on the axial curvature radius model of the sampling point; the axial curvature radius of the sampling point is determined based on the curvature coefficient of the sampling point and the functional relationship between the corneal axial position and the axial curvature radius.

[0201] In one embodiment, when the logic in the computer program that obtains the axial curvature of each sampling point based on the axial radius of curvature of each sampling point is executed by the processor, the following steps can be implemented:

[0202] For any given sampling point, the ratio between the refractive index and the axial radius of curvature corresponding to the sampling point is taken as the axial curvature of the sampling point.

[0203] In one embodiment, when the logic in the computer program that obtains the axial curvature of the target cornea based on the axial curvature of each sampling point is executed by the processor, the following steps can be implemented:

[0204] Obtain the remaining pixels in the target cornea excluding each sampling point; obtain the axial curvature of each remaining pixel based on the position information of each remaining pixel and the axial curvature of each sampling point; use the axial curvature of each remaining pixel and the axial curvature of each sampling point as the axial curvature of the target cornea.

[0205] The principles and processes of the computer-readable storage medium provided above in implementing the various embodiments can be found in the description of the corneal axial curvature determination method in the foregoing embodiments, and will not be repeated here.

[0206] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0207] Based on multiple corneal images of the target cornea, the anterior and posterior corneal surface delineation lines are obtained for each corneal image; the multiple corneal images are acquired through different scanning angles.

[0208] The axial position of the target cornea is determined based on the corneal anterior surface layering lines and / or corneal posterior surface layering lines in each corneal image.

[0209] The axial curvature of the target cornea is determined based on its axial position.

[0210] In one embodiment, when the logic in the computer program for obtaining the anterior corneal surface layering line and the posterior corneal surface layering line of each corneal image based on multiple corneal images of the target cornea is executed by the processor, the following steps can be implemented:

[0211] The corneal images are layered using a pre-defined neural network model to obtain the anterior corneal surface layering line and the initial posterior corneal surface layering line for each corneal image. The initial posterior corneal surface layering line is then subjected to refraction correction processing to obtain the anterior corneal surface layering line and the posterior corneal surface layering line for each corneal image.

[0212] In one embodiment, when the logic in the computer program that determines the axial position of the target cornea based on the anterior and / or posterior corneal layering lines of each corneal image is executed by the processor, the following steps can be implemented:

[0213] Based on the physical length and depth information of each pixel in each anterior and posterior corneal surface layering line, the corneal position coordinates of each pixel on each anterior and posterior corneal surface layering line are obtained. Based on the corneal position coordinates and the ellipsoid model expression, the surface coefficients of the corneal ellipsoid are obtained. The corneal ellipsoid represents a three-dimensional ellipsoid formed by the anterior and / or posterior corneal surface layering lines of multiple corneal images. Based on the surface coefficients of the corneal ellipsoid, the axial position of the target cornea is determined.

[0214] In one embodiment, when the logic in the computer program that determines the axial position of the target cornea based on the curvature coefficient of the corneal ellipsoid is executed by the processor, the following steps can be implemented:

[0215] The axial position of the target cornea is obtained based on the curvature coefficient of the corneal ellipsoid and the functional relationship between the corneal axial position and the scanning center of each acquired corneal image.

[0216] In one embodiment, when the logic in the computer program that determines the axial curvature of the target cornea based on the axial position of the target cornea is executed by the processor, the following steps can be implemented:

[0217] Based on the axial position of the target cornea, determine the axial curvature radius of multiple sampling points in the target cornea; based on the axial curvature radius of each sampling point, obtain the axial curvature of each sampling point; based on the axial curvature of each sampling point, obtain the axial curvature of the target cornea.

[0218] In one embodiment, when the logic in the computer program that determines the axial radius of curvature of multiple sampling points in the target cornea based on the axial position of the target cornea is executed by the processor, the following steps can be implemented:

[0219] For any given sampling point, the axial curvature radius model of the sampling point is obtained based on the axial position of the target cornea and the corneal position coordinates of the sampling points within a preset range around the sampling point; based on the axial curvature radius model of the sampling point, the axial curvature radius of the sampling point is determined.

[0220] In one embodiment, when the logic in the computer program that determines the axial radius of curvature of a sampling point based on the axial radius of curvature model of the sampling point is executed by the processor, the following steps can be implemented:

[0221] The curvature coefficient of the sampling point is obtained based on the axial curvature radius model of the sampling point; the axial curvature radius of the sampling point is determined based on the curvature coefficient of the sampling point and the functional relationship between the corneal axial position and the axial curvature radius.

[0222] In one embodiment, when the logic in the computer program that obtains the axial curvature of each sampling point based on the axial radius of curvature of each sampling point is executed by the processor, the following steps can be implemented:

[0223] For any given sampling point, the ratio between the refractive index and the axial radius of curvature corresponding to the sampling point is taken as the axial curvature of the sampling point.

[0224] In one embodiment, when the logic in the computer program that obtains the axial curvature of the target cornea based on the axial curvature of each sampling point is executed by the processor, the following steps can be implemented:

[0225] Obtain the remaining pixels in the target cornea excluding each sampling point; obtain the axial curvature of each remaining pixel based on the position information of each remaining pixel and the axial curvature of each sampling point; use the axial curvature of each remaining pixel and the axial curvature of each sampling point as the axial curvature of the target cornea.

[0226] The principles and processes of implementing the computer program products provided above in the various embodiments can be found in the description of the corneal axial curvature determination method in the foregoing embodiments, and will not be repeated here.

[0227] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0228] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0229] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining the axial curvature of the cornea, characterized in that, The method includes: Based on multiple corneal images of the target cornea, the anterior corneal surface delineation line and / or posterior corneal surface delineation line of each corneal image are obtained; the multiple corneal images are acquired through different scanning angles; The axial position of the target cornea is determined based on the corneal anterior surface layering line and / or corneal posterior surface layering line of each corneal image. The axial curvature of the target cornea is determined based on the axial position of the target cornea; The step of obtaining the anterior corneal surface delineation line and the posterior corneal surface delineation line of each corneal image based on multiple corneal images of the target cornea includes: The corneal images are layered using a preset neural network model and / or a traditional image processing algorithm to obtain the anterior corneal surface layering line and the initial posterior corneal surface layering line for each corneal image. Refraction correction processing is performed on each of the initial corneal posterior surface delineation lines to obtain the corneal anterior surface delineation line and the corneal posterior surface delineation line for each corneal image; Determining the axial length of the target cornea based on the anterior and / or posterior corneal surface delineation lines of each corneal image includes: Based on the physical length and physical depth information of each pixel in each of the corneal anterior surface layer lines and / or each of the corneal posterior surface layer lines, obtain the corneal position physical coordinate values ​​of each pixel on each of the corneal anterior surface layer lines and the corneal position physical coordinate values ​​of each pixel on each of the corneal posterior surface layer lines; Based on the corneal position coordinates and the ellipsoid model expression, the surface coefficient of the corneal ellipsoid is obtained; the corneal ellipsoid represents the three-dimensional ellipsoid formed by the corneal anterior surface layering lines and / or corneal posterior surface layering lines of the multiple corneal images; The expression for the ellipsoidal model is: （1） in, , , , , , and is the surface curvature coefficient of the corneal ellipsoid; , and These represent the corneal position coordinates of each pixel on the corneal ellipsoid; if the corneal ellipsoid is a three-dimensional ellipsoid formed by the layering lines of the anterior corneal surface of multiple corneal images, then... , and This refers to the corneal position coordinates of each pixel on the anterior corneal surface layering line; if the corneal ellipsoid is a three-dimensional ellipsoid formed by the posterior corneal surface layering lines of multiple corneal images, then... , and That is, the corneal position coordinates of each pixel on the posterior corneal surface layer line; The axial position of the target cornea is obtained based on the curvature coefficient of the corneal ellipsoid and the functional relationship between the corneal axial position and the scanning center of each acquired corneal image. The functional relationship between the corneal axial length and the scanning center of each acquired corneal image is as follows: （2） in, , The coordinates of the eye axis on the axial curvature topographic map.

2. The method according to claim 1, characterized in that, Determining the axial curvature of the target cornea based on its axial position includes: Based on the axial position of the target cornea, the axial radius of curvature of multiple sampling points in the target cornea is determined; Based on the axial radius of curvature of each sampling point, the axial curvature of each sampling point is obtained accordingly; The axial curvature of the target cornea is obtained based on the axial curvature of each sampling point.

3. The method according to claim 2, characterized in that, The step of determining the axial radius of curvature of multiple sampling points in the target cornea based on the axial position of the target cornea includes: For any given sampling point, based on the axial position of the target cornea and the corneal position coordinates of the sampling points within a preset range around the sampling point, the axial radius of curvature model of the sampling point is obtained. The axial radius of curvature of the sampling point is determined based on the axial radius of curvature model of the sampling point.

4. The method according to claim 3, characterized in that, The determination of the axial radius of curvature of the sampling point based on the axial radius of curvature model of the sampling point includes: The curvature coefficient of the sampling point is obtained based on the axial radius of curvature model of the sampling point; The axial radius of curvature of the sampling point is determined based on the curvature coefficient of the sampling point and the functional relationship between the corneal axial position and the axial radius of curvature.

5. The method according to claim 2, characterized in that, The step of obtaining the axial curvature of each sampling point based on the axial curvature radius of each sampling point includes: For any given sampling point, the ratio between the refractive index and the axial radius of curvature corresponding to that sampling point is taken as the axial curvature of that sampling point.

6. The method according to claim 2, characterized in that, The step of obtaining the axial curvature of the target cornea based on the axial curvature of each sampling point includes: Obtain the remaining pixels in the target cornea excluding each of the sampling points; The axial curvature of each remaining pixel is obtained based on the position information of each remaining pixel and the axial curvature of each sampling point. The axial curvature of each remaining pixel and the axial curvature of each sampling point are used as the axial curvature of the target cornea.

7. A device for determining the axial curvature of the cornea, characterized in that, The device includes: The corneal layering line acquisition module is used to acquire the corneal anterior surface layering line and / or corneal posterior surface layering line of each corneal image based on multiple corneal images of the target cornea; the multiple corneal images are acquired through different scanning angles; The first determining module is used to determine the axial position of the target cornea based on the corneal anterior surface layering line and / or corneal posterior surface layering line of each corneal image. The second determining module is used to determine the axial curvature of the target cornea based on the axial position of the target cornea; The layering line acquisition module is further configured to layer each corneal image using a preset neural network model and / or a traditional image processing algorithm to obtain the corneal anterior surface layering line and the initial corneal posterior surface layering line of each corneal image; and to perform refraction correction processing on each initial corneal posterior surface layering line to obtain the corneal anterior surface layering line and the corneal posterior surface layering line of each corneal image. The second determining module is further configured to obtain the physical coordinate values ​​of the corneal position of each pixel on each of the corneal anterior surface layering lines and the physical coordinate values ​​of the corneal position of each pixel on each of the corneal posterior surface layering lines based on the physical length information and physical depth information of each pixel in each of the corneal anterior surface layering lines and / or each of the corneal posterior surface layering lines; Based on the corneal position coordinates and the ellipsoid model expression, the surface coefficient of the corneal ellipsoid is obtained; the corneal ellipsoid represents the three-dimensional ellipsoid formed by the corneal anterior surface layering lines and / or corneal posterior surface layering lines of the multiple corneal images; The expression for the ellipsoidal model is: （1） in, , , , , , and is the surface curvature coefficient of the corneal ellipsoid; , and These represent the corneal position coordinates of each pixel on the corneal ellipsoid; if the corneal ellipsoid is a three-dimensional ellipsoid formed by the layering lines of the anterior corneal surface of multiple corneal images, then... , and This refers to the corneal position coordinates of each pixel on the anterior corneal surface layering line; if the corneal ellipsoid is a three-dimensional ellipsoid formed by the posterior corneal surface layering lines of multiple corneal images, then... , and That is, the corneal position coordinates of each pixel on the posterior corneal surface layer line; The axial position of the target cornea is obtained based on the curvature coefficient of the corneal ellipsoid and the functional relationship between the corneal axial position and the scanning center of each acquired corneal image. The functional relationship between the corneal axial length and the scanning center of each acquired corneal image is as follows: （2） in, , The coordinates of the eye axis on the axial curvature topographic map.

Images