Method, apparatus, and computer device for measuring axial length of the eye
By aligning the OCT focus with the retina and employing neural networks to identify segment endpoints, the method addresses the inaccuracy of existing OCT methods, enabling precise axial length measurement in severe ophthalmic diseases.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- SVISION IMAGING LTD
- Filing Date
- 2024-06-07
- Publication Date
- 2026-06-11
Smart Images
Figure 2026519176000001_ABST
Abstract
Description
[Technical Field] 【0001】 This application relates to the field of image processing technology, and more particularly to a method, apparatus, and computer apparatus for measuring axial length of the eye. 【0002】 Cross-reference of related applications 【0003】 This application claims priority based on a Chinese patent application filed with the China Patent Administration on June 7, 2023, with application number 202310673845.6, titled "Method and Apparatus for Measuring Axial Length of the Eye," the entire contents of which are incorporated herein by reference. [Background technology] 【0004】 Axial measurement is important for the diagnosis and treatment of many ophthalmic diseases, including cataracts, refractive errors, glaucoma, strabismus, and amblyopia. 【0005】 In related technologies, optical coherence tomography (i.e., OCT) is typically used to measure the axial length of the eye. The OCT optical focus is mainly placed on the cornea to acquire an optical image that includes a clearly visible cornea and part of the fundus, and axial length information is obtained from the optical image. 【0006】 However, in cases of severe ophthalmic diseases, there is a problem in that the methods used in related technologies result in inaccurate measurement of the eye axis. [Overview of the project] 【0007】 Based on this, in order to solve the above technical problems, it is necessary to provide an axial length measurement method, apparatus, and computer equipment that can identify the anterior and posterior segmental endpoints of the eye under examination, and further determine the axial length of the eye under examination based on the anterior and posterior segmental endpoints, thereby achieving the effect of accurately measuring the axial length even in cases of serious ophthalmic diseases. 【0008】 In the first aspect, an embodiment of the present invention provides a method for measuring axial length of the eye. The method includes the steps of: acquiring an optical image of the eye under examination, including the cornea and fovea of the retina, with the OCT optical focus aligned to the posterior segment of the eye under examination; acquiring the anterior segment endpoint and the posterior segment endpoint of the eye under examination based on the optical image; and determining the axial length of the eye under examination based on the anterior segment endpoint and the posterior segment endpoint. 【0009】 In one embodiment, the step of acquiring an optical image by aligning the OCT optical focus with the posterior segment of the eye under examination includes the step of acquiring an optical image by aligning the OCT optical focus with the retina of the eye under examination. 【0010】 In one embodiment, the step of obtaining the anterior and posterior segmental endpoints of the eye under examination based on an optical image includes inputting the optical image into a pre-trained first neural network model and obtaining the anterior and posterior segmental endpoints output from the first neural network model, the first neural network model being obtained by training on a first optical image sample and a corresponding label, the label of the first optical image sample including an anterior segmental endpoint mark and a posterior segmental endpoint mark. 【0011】 In one embodiment, the step of obtaining the anterior and posterior segments of the eye under examination based on an optical image includes the steps of obtaining the cornea and fovea of the eye under examination based on an optical image, identifying the anterior segment based on the cornea, and identifying the posterior segment based on the fovea. 【0012】 In one embodiment, the step of acquiring the cornea and fovea of the eye under examination based on an optical image includes inputting the optical image into a pre-trained second neural network model and obtaining the cornea and fovea output from the second neural network model, the second neural network model being acquired by training on a second optical image sample and corresponding labels, the labels of the second optical image sample including a corneal mark and a fovea mark. 【0013】 In one embodiment, the step of identifying the anterior segment endpoint based on the cornea includes the step of defining the corneal apex of the cornea as the anterior segment endpoint, or, if the optical image is obtained by aligning the OCT scanning center with the corneal apex and fovea of the eye under examination, the step of defining the intersection of the OCT scanning center line and the anterior surface of the cornea as the anterior segment endpoint. 【0014】 In one embodiment, the step of identifying the posterior segment endpoint of the eyeball based on the fovea centralis includes the step of setting the fovea centralis as the posterior segment endpoint, or the step of stratifying the retina, obtaining the result of stratifying at least one retinal layer in the fovea centralis, and identifying the posterior segment endpoint based on the stratification result. 【0015】 In one embodiment, the step of identifying the posterior segment endpoint based on the stratification results includes selecting one target layer from the stratification results and designating a target point in the target layer as the posterior segment endpoint, or, if the optical image is obtained by aligning the OCT scanning center with the corneal apex and fovea of the eye under examination, designating the intersection of the OCT scanning center line and one of the target layers from the stratification results as the posterior segment endpoint, wherein the target layer includes one of the retinal pigment epithelium-choroidal complex layer, the interdigitation zone layer, and the choroidal layer, and the target point is a point on the line where the fovea and the corneal apex are located. 【0016】 In one embodiment, the step of determining the axial length of the eye under examination based on the anterior and posterior segments of the eye includes the steps of obtaining the endpoint distance between the anterior and posterior segments of the eye and a correction value corresponding to the retinal thickness of the eye under examination; determining the initial axial length of the eye under examination based on the endpoint distance and the correction value corresponding to the retinal thickness; and performing refractive correction processing on the initial axial length to obtain the axial length of the eye under examination. 【0017】 In one embodiment, the correction value corresponding to the retinal thickness is a preset value, the retinal thickness at the fovea, or the thickness from the anterior surface of the retina to the posterior segment of the eyeball at the fovea. 【0018】 In one embodiment, the preset value is in the range of 100 μm to 300 μm. 【0019】 In one embodiment, the step of identifying the initial axial length of the subject eye based on the endpoint distance and the correction value corresponding to the retinal thickness includes the step of taking the difference between the endpoint distance and the correction value corresponding to the retinal thickness as the initial axial length of the subject eye. 【0020】 In one embodiment, the step of performing refractive correction processing on the initial axial length to obtain the axial length of the subject eye includes the step of performing refractive correction processing on the initial axial length based on a preset refractive index correction coefficient to obtain the axial length of the subject eye. 【0021】 In one embodiment, the refractive index correction coefficient includes an average refractive index correction coefficient, and the step of performing refractive correction processing on the initial axial length based on a preset refractive index correction coefficient to obtain the axial length of the subject eye calculates the axial length L2 of the subject eye by the following formula: 【0022】 L2 = k × L1 【0023】 Here, k represents the average refractive index correction coefficient, and L1 represents the initial axial length. 【0024】 In one embodiment, the average refractive index correction coefficient is in the range of 1.33 to 1.45. 【0025】 In one embodiment, the step of identifying the axial length of the subject eye based on the anterior segment endpoint and the posterior segment endpoint of the eyeball includes the step of obtaining, based on an optical image, a plurality of structural layers of the subject eye between the anterior segment endpoint and the posterior segment endpoint of the eyeball, including the posterior surface of the cornea, the anterior surface of the lens, and the posterior surface of the lens; the step of obtaining the lengths of a plurality of segments corresponding one-to-one to the cornea, the anterior chamber, the lens, and the vitreous body of the subject eye in the axial direction based on the plurality of structural layers, the anterior segment endpoint, and the posterior segment endpoint; and the step of performing refractive correction and addition processing on the lengths of the plurality of segments to obtain the axial length of the subject eye. 【0026】 In one embodiment, the method further includes the steps of obtaining an anterior segment mark at the anterior segment endpoint and a posterior segment mark at the posterior segment endpoint of the eyeball based on an optical image, and displaying the axial length of the eye based on the anterior segment mark and the posterior segment mark. 【0027】 In one embodiment, the step of displaying the axial length based on the anterior and posterior markings includes the steps of displaying the anterior and posterior markings, obtaining position adjustment information after the user has adjusted the anterior and posterior markings, and identifying and displaying the axial length based on the position adjustment information. 【0028】 In the second aspect, the present invention further provides an axial length measuring device. The device includes a first acquisition module that acquires an optical image of the eye under examination, including the cornea and fovea of the retina, with the OCT optical focus aligned to the posterior segment of the eye under examination; a second acquisition module that acquires the anterior segment endpoint and the posterior segment endpoint of the eye under examination based on the optical image; and a length determination module that determines the axial length of the eye under examination based on the anterior segment endpoint and the posterior segment endpoint. 【0029】 In a third aspect, the present invention further provides a computer device. The computer device includes a storage device and a processor, the storage device storing a computer program, and the processor, when executing the computer program, causes the steps in any of the embodiments of the first aspect described above to be realized. 【0030】 In the above-described method, apparatus, and computer apparatus for measuring axial length, first, an optical image is acquired by aligning the OCT optical focus with the posterior segment of the eye being examined. Then, the anterior and posterior segment endpoints of the eye being examined are acquired based on the optical image, and finally, the axial length of the eye being examined is determined based on the anterior and posterior segment endpoints. The above method allows for the identification of the anterior and posterior segmental endpoints of the eye under examination. Based on these endpoints, the axial length can be determined. In other words, by acquiring an optical image that includes a clearly visible retina, the axial length can be determined based on the optical image that includes a clearly visible retina. This method enables accurate measurement of the axial length even in cases of severe ophthalmic diseases. [Brief explanation of the drawing] 【0031】 [Figure 1] This is a diagram illustrating the usage environment for the method of measuring axial length of the eye in one embodiment. [Figure 2] This is a flowchart of the method for measuring axial length of the eye in one embodiment. [Figure 3] This is a schematic diagram of an optical image focused on the cornea of the eye being examined in one embodiment. [Figure 4] This is a schematic diagram of an optical image focused on the retina of the eye being examined in one embodiment. [Figure 5] This is a schematic diagram of the corneal reflection point and corneal apex in one embodiment. [Figure 6] This is a schematic diagram of the user interface in one embodiment. [Figure 7] This is a flowchart for identifying the anterior and posterior segments of the eye in one embodiment. [Figure 8] This is a flowchart for determining the axial length of the eye in one embodiment. [Figure 9] This is a schematic diagram of the endpoint distance between the anterior and posterior segments of the eye in one embodiment. [Figure 10] This is a schematic diagram of the structural surfaces between the anterior and posterior segments of the eyeball in one embodiment. [Figure 11] This is a flowchart of the method for measuring axial length in another embodiment. [Figure 12] This is a schematic diagram of the structure of an axial length measuring device in one embodiment. [Figure 13] This is a schematic diagram of the structure of an axial length measuring device in another embodiment. [Figure 14]This is a schematic diagram of the structure of an axial length measuring device in another embodiment. [Figure 15] This is an internal configuration diagram of a computer device in one embodiment. [Modes for carrying out the invention] 【0032】 To clarify the purpose, technical form, and advantages of the embodiments of this application, the application will be described in detail below with reference to the drawings and embodiments. The specific embodiments described herein are merely for the purpose of interpreting this application and are not intended to limit it. 【0033】 The method for measuring axial length of the eye according to the embodiment of this application can be applied to the usage environment shown in Figure 1. Here, OCT102 communicates with server 104 via the network. The data storage system can store the data that server 104 is processing. Optionally, OCT102 is used to acquire optical images of the eye under examination, and time-domain OCT, frequency-domain OCT, and frequency-scanning OCT are available. The data storage system may be integrated on OCT102, or it may be located on server 104, the cloud, or other network servers. Server 104 can be implemented as an independent server or as a cluster of multiple servers. 【0034】 In one embodiment, a method for measuring axial length of the eye is provided, as shown in Figure 2. This method is described as an example applied to server 104 in Figure 1 and includes the following steps. 【0035】 S201: An optical image is acquired by aligning the OCT optical focus with the posterior segment of the eye being examined. 【0036】 By selectively controlling the OCT, the eye under examination can be scanned, and an optical image of the eye can be obtained. The OCT then transmits the obtained optical image to a server, which can then acquire the optical image of the eye. 【0037】 In related technologies, the OCT optical focus is placed on the cornea to acquire an optical image that includes a clearly visible cornea and part of the fundus, and then axial information is obtained from the optical image. As shown in Figure 3, the optical image obtained by scanning the cornea of the eye examined with the OCT optical focus aligned is shown, and a relatively clear cornea (a) and part of the retina (b) can be seen. However, when using OCT to focus optically on the cornea in cases of severe ophthalmic disease, the retina in the optical image obtained by this method becomes blurred, making it impossible to accurately measure the axial length of the eye. 【0038】 In view of this, this embodiment acquires an optical image of the eye under examination by focusing the OCT optical focus on the posterior segment of the eyeball, thereby acquiring an optical image that includes a clearly visible retina. Furthermore, as shown in Figure 4, the axial length of the eye being examined is determined based on an optical image that includes a clearly visible retina. To obtain an optical image including a clearly defined retina, the human eye is scanned using OCT, and based on the obtained preview image, the reference arm is adjusted in real time so that the resolution of the retina in the image meets the requirements, thereby obtaining the optical image described above. Specifically, it is possible to manually determine whether the resolution of the retina in the image meets the requirements, or to perform automatic determination by acquiring the resolution of the retina in the image and determining whether the resolution of the retina has reached a preset resolution threshold. When the resolution of the retina in the image reaches a certain resolution threshold, a presentation indicating that the retinal resolution meets the requirements can be output, such as an audio presentation and / or a text presentation. Here, the resolution threshold can be set according to the actual needs and is not limited to this. When the resolution of the retinal image met the needs, it is thought that the OCT optical focus was adjusted to the posterior segment of the eye being examined. 【0039】 The posterior segment of the eyeball described above includes the vitreous humor and posterior structures of the vitreous humor along the axial direction of the eye, such as the retina. In one possible embodiment, acquiring an optical image by aligning the OCT optical focus with the posterior segment of the eye under examination includes acquiring an optical image by aligning the OCT optical focus with the retina of the eye under examination. 【0040】 For example, when acquiring an optical image of the eye under examination, the OCT scanning center is aligned with the corneal apex of the eye under examination, and at the same time, the OCT optical focus is aligned with the retina of the eye under examination, and then the eye under examination is scanned. After aligning the OCT scanning center with the corneal apex of the eye under examination, an initial image is displayed on the screen. Observe whether the initial image includes a clearly defined retina and fovea. If the initial image does not include a clearly defined retina and / or fovea, further adjust the OCT scanning center based on the initial image to align with the corneal apex and fovea of the eye under examination. If the initial image clearly shows the retina and fovea, press the capture button to collect the current image and obtain the target optical image, i.e., an optical image in which the OCT scanning center is aligned with the corneal apex of the eye being examined. The optical image includes at least the cornea, retina, and fovea of the eye being examined. 【0041】 Optionally, the OCT scanning center can be adjusted using a fixation lamp to align with the fovea centralis of the retina. The fixation light is turned on, and the patient's fixation direction is adjusted using the visible light emitted from the fixation light, thereby adjusting the position of the fovea and aligning the OCT scanning center with the fovea. During OCT, the illumination light from the fixation lamp is projected onto the cornea during initial imaging to obtain the corneal reflection point. Based on the position of the corneal reflection point, the corneal apex of the eye under examination is identified, and the OCT scanning center is then aligned with the corneal apex of the eye under examination. For example, as shown in Figure 5, the center of the corneal reflection point is the corneal apex, and the OCT scanning center is further aligned with the corneal apex of the eye being examined. By adjusting the OCT device to align the corneal reflection point with the center of the pupil camera and adjusting the working distance so that the image of the corneal reflection point is as clear as possible, the corneal apex can be identified on the image at this time. 【0042】 Furthermore, the OCT scanning center does not need to be aligned with the corneal apex of the eye being examined. It is sufficient that the cornea, the clearly defined retina, and the fovea of the retina can be fully seen in the optical image. In other words, a certain degree of misalignment between the OCT scanning center and the corneal apex is acceptable in the optical image. 【0043】 S202: Obtain the anterior and posterior segmental endpoints of the eye being examined based on the optical image. 【0044】 In the embodiments of the present invention, the anterior segment endpoint represents the endpoint in the anterior segment of the eye under examination and may be identified based on the cornea or based on the OCT scanning centerline and the cornea. The posterior segment endpoint represents the endpoint in the posterior segment of the eye being examined and may be identified based on the fovea of the retina or based on the scanning centerline and the retina. When the OCT scanning center is aligned with the corneal apex and fovea of the eye being examined, the corneal apex and fovea are located in the middle of the resulting optical image, and the OCT scanning center line becomes the center line of the optical image. 【0045】 In one possible embodiment, the cornea and fovea of the eye under examination are obtained, with the corneal apex as the anterior segment endpoint and the fovea as the posterior segment endpoint. 【0046】 In another possible embodiment, the cornea and fovea of the eye under examination are obtained, with the corneal apex as the anterior segment endpoint. The retina is layered to obtain at least one retinal layer, and the posterior segment endpoint of the eye under examination is defined as a point on the line where the fovea of the retina and the corneal apex are located in one of the at least one retinal layer. Here, each retinal layer refers to a common edge between adjacent tissue structures. Here, the straight line through which the fovea centralis and the corneal apex are located can be considered a straight line in the direction of the eye axis. 【0047】 In another possible embodiment, the cornea and retina of the eye under examination are acquired, and the intersection of the OCT scanning centerline and the cornea of the eye under examination is defined as the anterior segment endpoint of the eye under examination. The intersection of the OCT scanning centerline and the retina of the eye being examined is defined as the posterior segment endpoint of the eye being examined. For example, the cornea and fovea of the eye under examination are acquired, and the intersection of the OCT scanning center line and the anterior surface of the cornea of the eye under examination is defined as the anterior segment endpoint of the eye under examination. The retina is layered, and at least one retinal layer is obtained. The intersection of the OCT scanning centerline and one of the at least one retinal layer in the fovea of the eye being examined is defined as the posterior segment endpoint of the eye being examined. 【0048】 In another possible embodiment, an optical image of the eye under examination is input to a pre-trained first neural network model, and the anterior and posterior segmental endpoints of the eye under examination are output from this model. Here, the first neural network model is obtained by training on a first optical image sample and its corresponding label, where the label of the first optical image sample includes the anterior segment endpoint mark and the posterior segment endpoint mark. 【0049】 S203: Determine the axial length of the eye under examination based on the anterior and posterior segmental endpoints of the eye. 【0050】 In the embodiments of the present invention, the axial length of the eye represents the length from the front to the back of the eyeball of the eye being examined. 【0051】 Optionally, the axial length of the eye under examination can be determined based on the anterior and posterior segmental endpoints of the eye, using a pre-configured identification logic for determining the axial length. 【0052】 In one possible embodiment, the endpoint distance between the anterior and posterior segments of the eye can be measured, and this endpoint distance can be taken as the axial length of the eye under examination. 【0053】 After determining the axial length, it is necessary to display the axial length, and different methods of measuring the axial length correspond to different methods of displaying the axial length. The method for displaying the axial length of the eye according to the present invention includes the steps of: acquiring an optical image with the OCT scanning center aligned with the pupil center of the eye under examination; acquiring the anterior segment endpoint and the posterior segment endpoint of the eye under examination based on the optical image; determining the axial length of the eye under examination based on the anterior segment endpoint and the posterior segment endpoint; acquiring an anterior segment mark at the anterior segment endpoint and a posterior segment mark at the posterior segment endpoint based on the optical image; and displaying the axial length based on the anterior segment mark and the posterior segment mark. 【0054】 Optionally, the axial length can be directly displayed based on the current positions of the anterior and posterior segment marks. Because there may be multiple locations for the posterior segmental endpoint of the eye, there may also be multiple axial lengths depending on the location of the posterior segmental endpoint. Based on this, we provide an optional method for displaying different axial lengths. The method includes the steps of displaying anterior and posterior district marks, obtaining positional adjustment information after the user has adjusted the anterior and posterior district marks, and identifying and displaying the axial length based on the positional adjustment information. 【0055】 Figure 6 shows a schematic diagram of the user interface, where the arrows indicate scleral division lines. When adjusting the posterior segment marker, the user must not move it to the right beyond the scleral dividing line. The scleral division line can present the user with an adjustment range for the posterior segment mark, preventing the user from moving the posterior segment mark too far. 【0056】 Furthermore, by adjusting the anterior and posterior segment markers, users can display different axial lengths, thus meeting their diverse needs regarding the display of axial length. 【0057】 In the method for measuring axial length of the eye according to an embodiment of the present invention, first, an optical image is acquired by aligning the OCT optical focus with the posterior segment of the eye under examination. Then, the anterior segment endpoint and posterior segment endpoint of the eye under examination are acquired based on the optical image. Finally, the axial length of the eye under examination is determined based on the anterior segment endpoint and posterior segment endpoint. The above method allows for the determination of the axial length of the eye based on the anterior and posterior segmental endpoints of the eye being examined. In other words, by acquiring an optical image that includes a clearly visible retina, the axial length can be further determined based on the optical image that includes a clearly visible retina. This makes it possible to accurately measure axial length even in cases of severe ophthalmic diseases. 【0058】 The axial length of the eyeball represents the length from the front to the back of the eyeball. To measure the axial length, it is necessary to identify the anterior and posterior ends of the eyeball, that is, the anterior and posterior ends of the eyeball in this application. To accurately measure the axial length of the eye, it is necessary to precisely identify the anterior and posterior segments of the eyeball. Based on this, one embodiment provides an optional method for identifying the anterior and posterior segmental endpoints of the eye under examination. As shown in Figure 7, the following steps are included. 【0059】 S301: Obtain the corneal apex and retinal fovea of the eye under examination based on optical images. 【0060】 S302: The corneal apex is defined as the anterior segment endpoint of the eyeball. 【0061】 S303: The fovea centralis is defined as the posterior segment of the eyeball. 【0062】 In the embodiments of the present invention, the fovea of the retina is the location of the recess in the center of the retina. 【0063】 In one possible embodiment, the corneal apex and fovea of the eye under examination are obtained by a pre-configured neural network model, with the corneal apex designated as the anterior segment endpoint and the fovea as the posterior segment endpoint. Specifically, an optical image is input into a pre-trained second neural network model, and the cornea and fovea of the retina are output from the second neural network model, with the cornea including the corneal apex or the anterior surface of the cornea. The second neural network model is obtained by training on a second optical image sample and its corresponding label, the label of the second optical image sample includes corneal marks and foveal marks. The second optical image sample may be different from or the same as the first optical image sample, but a different label will be used. 【0064】 Furthermore, in related technologies, there are no clear regulations regarding the anterior and posterior segments of the eye, so there are some differences in how technicians identify these segments. Based on this, in this embodiment, as a method for identifying the anterior segment endpoint and the posterior segment endpoint, if the optical image is obtained by aligning the OCT scanning center with the corneal apex and fovea of the eye under examination, the OCT scanning center line may be determined as the center line of the optical image, and the intersection of the OCT scanning center line and the anterior surface of the cornea may be defined as the anterior segment endpoint. Alternatively, the retina may be layered, the layering result of at least one retinal layer in the fovea may be obtained, and the posterior segment endpoint may be identified based on the layering result. 【0065】 Optionally, the cornea includes the anterior and posterior surfaces. The cornea is processed in a layered manner to obtain the anterior surface, and the intersection of the OCT scanning centerline and the anterior surface is defined as the anterior segment endpoint. 【0066】 The retina is selectively stratified as follows, and the result of stratifying at least one retinal layer in the fovea is obtained. In other words, optical images are input into a pre-trained third neural network model, and the hierarchical results output from the third neural network model are obtained. The third neural network model is obtained by training on a third optical image sample and its corresponding label, the label of the third optical image sample includes retinal layer marks in the fovea centralis. The third optical image sample may be different from both the first and second optical image samples, or it may be the same as the first and / or second optical image samples, but a different label will be used. 【0067】 Furthermore, in one possible embodiment, identifying the posterior segment endpoint based on the stratification results involves selecting a target layer from the stratification results and designating a target point within that target layer as the posterior segment endpoint. The target layer includes one of the following: the retinal pigment epithelium-choroidal complex layer, the interdigitation zone layer, and the choroidal layer. The target point is a point on the line where the fovea centralis and the corneal apex are located. 【0068】 In one possible embodiment, identifying the posterior segment endpoint based on the stratification results means that, if the optical image is obtained by aligning the OCT scanning center with the corneal apex and fovea of the eye under examination, the intersection of the OCT scanning center line and one of the target layers in the stratification results is defined as the posterior segment endpoint. For example, the retina is layered, and at least one retinal layer from the retinal pigment epithelium-choroidal complex layer, the interdigitation zone layer, and the choroidal layer in the fovea of the retina is obtained, and the intersection of the OCT scanning center line and that one retinal layer is defined as the posterior segment endpoint of the eyeball. 【0069】 For example, an optical image is input into a pre-trained third neural network model, and this model layers the retina in the optical image to obtain retinal layers such as the retinal pigment epithelium-choroidal complex layer, the interdigitation zone layer, and the choroidal layer in the fovea of the retina. Subsequently, the intersection point of the OCT scanning centerline with any of the retinal layers is defined as the posterior segment endpoint of the eyeball. Note that there are different methods for measuring axial length of the eye, such as ultrasound measurement and photobiological measurement. Different methods of measuring axial length also result in different corresponding axial lengths. For example, the axial length measured by ultrasound is the length from the corneal surface to the intraretinal boundary, while the axial length measured by photobiological measurement is the length from the lacrimal surface to the retinal pigment epithelium. In other words, different measurement methods also differ in how the anterior and posterior segments of the eye are identified. On the other hand, in this invention, the axial length of the eye is measured using the OCT method, the anterior segment endpoint may be the corneal apex, and the posterior segment endpoint may be the central concave of the retina. Alternatively, the anterior segment endpoint may be the intersection of the anterior surface of the cornea and the OCT scanning centerline, and the posterior segment endpoint may be the intersection of the OCT scanning center and any layer in the fovea retina. For example, the posterior segment endpoint may be the intersection of the OCT scanning center and the choroidal layer in the fovea retina. 【0070】 In embodiments of the present invention, an optional method is provided for rapidly identifying the anterior and posterior segmental endpoints of the eye under examination. By obtaining the corneal apex and fovea of the eye under examination, and further defining the corneal apex as the anterior segment endpoint and the fovea as the posterior segment endpoint, data is provided to identify the axial length of the eye to be measured. 【0071】 In one embodiment, an optional method for determining the axial length of the eye is provided based on the above embodiment. As shown in Figure 8, this method includes the following steps. 【0072】 S401: Obtain the endpoint distance between the anterior and posterior segments of the eye, and a correction value corresponding to the retinal thickness of the eye being examined. 【0073】 Optionally, the correction value corresponding to the retinal thickness may be a preset value, the same as the retinal thickness at the fovea, or the thickness from the anterior surface of the retina at the fovea to the posterior segment of the eyeball. The preset values can be set based on statistical results of retinal thickness in the fovea. In the embodiment of the present invention, the retinal thickness of the eye under examination is 200 μm, and the preset value is in the range of 100 μm to 300 μm, for example, 200 μm. Note that retinal thickness may vary depending on the eye being examined. 【0074】 After optionally identifying the anterior and posterior segments of the eye, the distance between them can be directly measured. As shown in Figure 9, point B indicates the anterior segment endpoint, point C indicates the posterior segment endpoint, and AL is the endpoint distance between the anterior and posterior segments. 【0075】 S402: Determine the initial axial length of the eye under examination based on correction values corresponding to the endpoint distance and retinal thickness. 【0076】 In one possible embodiment, the difference between the endpoint distance and a correction value corresponding to the retinal thickness is defined as the initial axial length of the eye under examination, i.e., initial axial length = endpoint distance - correction value. 【0077】 Since the retina of the eye being examined has a certain thickness, which can affect the accuracy of axial length measurement, processing for retinal thickness is necessary to ensure the accuracy of axial length measurement; that is, a correction value corresponding to retinal thickness must be subtracted. 【0078】 S403: Refractive correction is applied to the initial axial length to obtain the axial length of the eye being examined. 【0079】 Selectively, because the eye contains a large amount of fluid, refraction occurs when light passes through the eye, which has a certain effect on measuring axial length. Therefore, refractive correction processing is necessary to obtain an accurate and true axial length. 【0080】 In one possible embodiment, refractive correction is performed on the initial axial length of the eye based on a preset refractive index correction coefficient to obtain the axial length of the eye under examination. 【0081】 As shown in Figure 10, the eye includes structures such as the cornea, lens, and retina, and within the eye, there are certain differences in the refractive index of different structures. The refractive index of the cornea (i.e., between the anterior and posterior surfaces of the cornea), the anterior chamber (i.e., between the posterior surface of the cornea and the anterior surface of the lens), the lens (i.e., between the anterior and posterior surfaces of the lens), and the vitreous humor (i.e., between the posterior surface of the lens and the anterior surface of the retinal RPE layer) all have slight differences. To calculate the accurate axial length of the eye, refractive correction processing is performed on the initial axial length based on refractive index correction coefficients. This is done by correcting the length from the anterior to the posterior surface of the cornea using the first refractive index correction coefficient, correcting the length from the posterior surface of the cornea to the anterior surface of the lens using the second refractive index correction coefficient, correcting the length from the anterior surface of the lens to the posterior surface of the lens using the third refractive index correction coefficient, and correcting the length from the posterior surface of the lens to the anterior surface of the retinal RPE layer using the fourth refractive index correction coefficient, and then adding the corrected lengths to obtain the axial length of the eye under examination. Here, the first refractive index correction coefficient, the second refractive index correction coefficient, the third refractive index correction coefficient, and the fourth refractive index correction coefficient are empirical values and are all stored in the system in advance. 【0082】 Selectively, considering that the proportion of length occupied by each structure in the eye is usually similar even in different individuals, the proportion occupied by each structure of the eye can be predetermined, the length of the segment corresponding to each different structure can be identified, and further corrections can be made to the length of each segment on a segment-by-segment basis. Based on this, in one possible embodiment, the refractive index correction coefficient includes a first refractive index correction coefficient corresponding to the cornea, a second refractive index correction coefficient corresponding to the anterior chamber, a third refractive index correction coefficient corresponding to the lens, and a fourth refractive index correction coefficient corresponding to the vitreous humor. The axial length of the eye under examination is determined by the following method. 【0083】 First, based on the initial axial length and pre-set ratio data, the lengths of multiple segments that correspond one-to-one with the refractive index correction coefficient are identified. Here, the percentage data includes a first percentage value corresponding to the cornea, a second percentage value corresponding to the anterior chamber, a third percentage value corresponding to the lens, and a fourth percentage value corresponding to the vitreous humor, with the sum of the first, second, third, and fourth percentage values being 1. 【0084】 Next, the axial length L2 of the eye being examined is calculated using the following formula. 【0085】 L2 = k1 × L 11 +k2×L 12 +k3×L 13 +k4×L 14 【0086】 Here, k1 is the length L of the segment. 11 This represents the first refractive index correction coefficient corresponding to the segment length L. 12 This represents the second refractive index correction coefficient corresponding to the segment length L. 13 This represents the third refractive index correction coefficient corresponding to the segment length L. 14 This represents the fourth refractive index correction coefficient corresponding to [the specified value]. 【0087】 To accelerate calculation speed, an average refractive index correction coefficient is calculated for each refractive index correction coefficient corresponding to the structure within the eye, and the axial length of the eye under examination can be quickly calculated based on this average refractive index correction coefficient. Based on this, in another possible embodiment, the refractive index correction coefficient includes an average refractive index correction coefficient, and the axial length of the eye under examination is determined as follows: 【0088】 The axial length L2 of the eye being examined is calculated using the following formula. 【0089】 L2 = k × L1 【0090】 Here, k represents the average refractive index correction coefficient, and L1 represents the initial axial length of the eye. 【0091】 Optionally, the average refractive index correction factor is in the range of 1.33 to 1.45, for example, the average refractive index correction factor is 1.41. 【0092】 In embodiments of the present invention, an optional method for determining the axial length of the eye is provided. The initial axial length is determined by the endpoint distance between the anterior and posterior segments of the eyeball and the retinal thickness of the eye being examined. Furthermore, refractive correction is applied to the initial axial length to ensure the truthfulness and accuracy of the axial length. 【0093】 In another embodiment, based on the above embodiment, we provide another optional method for determining the axial length of the eye, which includes the following steps. 【0094】 Step a1: Based on optical images, multiple structural layers of the eye between the anterior and posterior segments of the eye are obtained. The multiple structural layers include the corneal surface, the anterior surface of the lens, and the crystalline lens surface. 【0095】 Based on a pre-trained neural network model, structural layers can be identified in optical images, and multiple structural layers located between the anterior and posterior segments of the eye can be obtained. Specifically, an optical image is input into a pre-trained fourth neural network model, and multiple structural layers are obtained from the output of the fourth neural network model. The fourth neural network model is obtained by training on a fourth optical image sample and its corresponding label, where the label of the fourth optical image sample includes multiple structural layer marks. The fourth optical image sample may be different from the three samples described above, or it may be the same as one or more of the first, second, and third optical image samples, but a different label will be used. 【0096】 Step a2: Based on multiple structural layers, anterior segmental endpoints, and posterior segmental endpoints, obtain the lengths of multiple segments corresponding one-to-one in the cornea, anterior chamber, lens, and vitreous humor of the eye examined in the axial direction of the eye. 【0097】 Optionally, the lengths of the plurality of segments can be obtained as follows. That is, first, identify the intersection points of each structural layer with the target line, which is the line connecting the anterior eye segment endpoint and the posterior eye segment endpoint, obtain the distances between the anterior eye segment endpoint, the posterior eye segment endpoint, and adjacent two points between each intersection point, and obtain the lengths of the plurality of segments. 【0098】 Step a3: Perform refractive correction and addition processing on the lengths of the plurality of segments to obtain the axial length of the eye to be examined. 【0099】 Optionally, when calculating the axial length of the eye to be examined, first perform refractive correction on the length of each segment, and then perform addition processing on the corrected lengths to obtain the axial length. For the length of each segment, the corrected length is calculated by the following formula. 【0100】 L′ 1i =k i ×L 1i 【0101】 Here, L′ 1i represents the corrected length corresponding to the length L 1i of the i-th segment, and k i represents the refractive index correction coefficient corresponding to the length L 1i of the i-th segment. 【0102】 Also, in one embodiment, the embodiment of the present invention provides an optional example of an axial length measurement method. As shown in FIG. 11, it includes the following steps. 【0103】 S501: Obtain an optical image including the cornea and the fovea of the eye to be examined with the OCT optical focus aligned below the retina of the eye to be examined. 【0104】 S502: Obtain the corneal apex and the fovea of the eye to be examined based on the optical image. 【0105】 S503: Use the corneal apex as the anterior eye segment endpoint. 【0106】 Optionally, the intersection of the OCT scanning centerline and the anterior surface of the cornea is defined as the anterior segment endpoint. 【0107】 S504: The fovea centralis is defined as the posterior segment of the eyeball. 【0108】 Optionally, the posterior segment endpoint of the eyeball is identified based on the OCT scanning centerline and the fovea centralis. This includes the steps of layering the retina to obtain at least one retinal layer, consisting of a retinal pigment epithelium-choroidal complex layer, an interdigitation zone layer, and a choroidal layer, at the fovea of the retina, and defining the intersection of the OCT scanning centerline and one of the retinal layers as the posterior segment endpoint. 【0109】 S505: Obtain the endpoint distance between the anterior and posterior segments of the eye, and the retinal thickness of the eye being examined. 【0110】 S506: The difference between the endpoint distance and the retinal thickness is defined as the initial axial length of the eye being examined. 【0111】 S507: Refractive correction processing is performed on the initial axial length based on the refractive index correction coefficient to obtain the axial length of the eye being examined. 【0112】 S508: Based on the optical image, obtain the anterior segment mark at the anterior segment endpoint and the posterior segment mark at the posterior segment endpoint. 【0113】 S509: Displays the previous and next district markers. 【0114】 S510: Retrieves position adjustment information after the user has adjusted the previous and next zone markers. 【0115】 S511: Determines the axial length of the eye based on the position adjustment information and displays the axial length. 【0116】 The processes S501 to S511 described above can be found in the description of the embodiments of the above method, and since their implementation principles and technical effects are similar, their description is omitted here. 【0117】 In the flowcharts for each of the embodiments described above, the steps are shown sequentially according to the direction of the arrows, but it should be understood that these steps are not necessarily performed in the same order as the arrows. Unless otherwise explicitly stated herein, there are no strict order restrictions on the execution of these steps, and they may be performed in any other order. Furthermore, at least some of the steps in the flowcharts relating to each of the embodiments described above may include multiple steps or stages, and these steps or stages may not necessarily be executed at the same time but at different times, and the execution order of these steps or stages may not necessarily be sequential but may be performed alternately with other steps or at least some of the steps or stages in other steps. 【0118】 Based on a similar inventive concept, an embodiment of the present invention provides an axial length measuring device for realizing the above-described axial length measuring method. Since the method of realizing the solution provided by this device is similar to the method described above, specific limitations in the embodiments of one or more axial length measuring devices described below can be made by referring to the limitations on the axial length measuring method described above, and are therefore omitted here. 【0119】 In one embodiment, an axial length measuring device 1 is provided, as shown in Figure 12. The axial length measuring device 1 includes a first acquisition module 10, a second acquisition module 20, and a length identification module 30. 【0120】 The first acquisition module 10 acquires optical images of the eye under examination, including the cornea and fovea of the retina, with the OCT optical focus aligned to the posterior segment of the eye. 【0121】 The second acquisition module 20 acquires the anterior and posterior segment endpoints of the eye under examination based on optical images. 【0122】 The length determination module 30 determines the axial length of the eye under examination based on the anterior segment endpoint and the posterior segment endpoint of the eye. 【0123】 In one embodiment, the first acquisition module 10 further acquires an optical image by adjusting the OCT optical focus to the retina of the eye being examined. 【0124】 In one embodiment, the second acquisition module 20 further inputs an optical image to a pre-trained first neural network model and obtains the anterior segment endpoint and posterior segment endpoint output from the first neural network model. The first neural network model is obtained by training on a first optical image sample and its corresponding label, the label of the first optical image sample includes the anterior segment endpoint mark and the posterior segment endpoint mark. 【0125】 In one embodiment, as shown in Figure 13, the second acquisition module 20 includes a first acquisition unit 21 for acquiring the cornea and fovea of the eye under examination based on an optical image, a first identification unit 22 for identifying the anterior segment endpoint of the eyeball based on the cornea, and a second identification unit 23 for identifying the posterior segment endpoint of the eyeball based on the fovea. 【0126】 In one embodiment, the first acquisition unit 21 further inputs the optical image to a pre-trained second neural network model and obtains the cornea and fovea retina output from the second neural network model. The second neural network model is obtained by training on a second optical image sample and its corresponding label, the labels of which include corneal marks and foveal marks. 【0127】 In one embodiment, the first specific unit 22 further uses the corneal apex of the cornea as the anterior segment endpoint, or, if the optical image is obtained by aligning the OCT scanning center with the corneal apex and fovea of the eye under examination, the intersection of the OCT scanning center line and the anterior surface of the cornea as the anterior segment endpoint. 【0128】 The second identification unit 23 further uses the fovea centralis as the posterior segment endpoint of the eyeball, or stratifies the retina, obtains the result of stratification of at least one retinal layer in the fovea centralis, and identifies the posterior segment endpoint based on the stratification result. 【0129】 In one embodiment, the second identification unit 23 further performs the step of identifying the posterior segment endpoint of the eye based on the stratification results, by selecting one target layer from the stratification results and designating a target point in the target layer as the posterior segment endpoint. The target layer includes one of the retinal pigment epithelium-choroidal complex layer, the interdigitation zone layer, and the choroidal layer, and the target point is a point on the line where the fovea retina and corneal apex are located, or, if the optical image is obtained by aligning the OCT scanning center with the corneal apex and fovea retina of the eye under examination, the intersection of the OCT scanning center line and one of the target layers from the stratification results is designated as the posterior segment endpoint. 【0130】 In one embodiment, as shown in Figure 14, the length identification module 30 includes a second acquisition unit 31 that acquires the endpoint distance between the anterior segment endpoint and the posterior segment endpoint and a correction value corresponding to the retinal thickness of the eye under examination; a third identification unit 32 for identifying the initial axial length of the eye under examination based on the endpoint distance and the correction value corresponding to the retinal thickness; and a fourth identification unit 33 for performing refractive correction processing on the initial axial length to obtain the axial length of the eye under examination. 【0131】 In one embodiment, the correction value corresponding to the retinal thickness is a preset value, the retinal thickness at the fovea, or the thickness from the anterior surface of the retina to the posterior segment of the eyeball at the fovea. 【0132】 In one embodiment, the preset value is in the range of 100 μm to 300 μm. 【0133】 In one embodiment, the third specific unit 32 further uses the difference between the endpoint distance and a correction value corresponding to the retinal thickness as the initial axial length of the eye under examination. 【0134】 In one embodiment, the fourth specific unit 33 further performs refractive correction processing on the initial axial length of the eye based on a preset refractive index correction coefficient to obtain the axial length of the eye under examination. 【0135】 In one embodiment, the refractive index correction coefficient includes the average refractive index correction coefficient, and the fourth specific unit 33 further calculates the axial length L2 of the eye under examination using the following formula. 【0136】 L2 = k × L1 【0137】 Here, k represents the average refractive index correction coefficient, and L1 represents the initial axial length of the eye. 【0138】 In one embodiment, the average refractive index correction coefficient is in the range of 1.33 to 1.45. 【0139】 In one embodiment, the length-specific module 30 further includes a third acquisition unit that acquires multiple structural layers of the eye under examination between the anterior segment endpoint and the posterior segment endpoint based on an optical image, and the multiple structural layers include the corneal surface, the anterior surface and the crystalline lens, a fourth acquisition unit that acquires the lengths of multiple segments corresponding one-to-one in the axial direction of the eye under examination, such as the cornea, anterior chamber, crystalline lens and vitreous humor, based on the multiple structural layers, the anterior segment endpoint and the posterior segment endpoint, and a correction processing unit that performs refractive correction and addition processing on the lengths of the multiple segments to obtain the axial length of the eye under examination. 【0140】 In one embodiment, the axial length measuring device 1 further includes a third acquisition module 40 that acquires an anterior segment mark at the anterior segment endpoint and a posterior segment mark at the posterior segment endpoint of the eyeball based on an optical image, and a length display module 50 that displays the axial length based on the anterior segment mark and the posterior segment mark. 【0141】 In one embodiment, the length display module 50 further includes a mark display unit that displays a front mark and a rear mark, an information acquisition unit that acquires position adjustment information after the user has adjusted the front mark and the rear mark, and a length display unit that identifies the axial length based on the position adjustment information and displays the axial length. 【0142】 Each module in the above-described axial length measuring device can be implemented in whole or in part by software, hardware, or a combination thereof. To facilitate the processor calling and executing operations corresponding to each of the above modules, each of the above modules can be incorporated into the processor of the computer device in hardware form, or it can be located independently of the processor, or it can be stored in the storage device of the computer device in software form. 【0143】 In one embodiment, a computer device is provided. This computer device may be a server. Its internal structure is shown in Figure 15. This computer device includes a processor, storage devices, and network interfaces connected via a system bus. The processor in a computer device is used to provide arithmetic and control functions. The storage devices of a computer include non-volatile storage media and memory. This non-volatile storage medium stores operating systems, computer programs, and databases. Memory provides an environment for running operating systems and computer programs on non-volatile storage media. The computer system's database stores data on axial length measurement. The network interface of a computer device communicates with external terminals via a network connection. The computer program, when executed by the processor, implements a method for measuring axial length of the eye. 【0144】 In one embodiment, a computer device is provided. The computer device includes a storage device and a processor, the storage device storing a computer program, and the processor, when executing the computer program, performs the steps of: acquiring an optical image including the cornea and fovea of the eye under examination with the OCT optical focus aligned to the posterior segment of the eye under examination; acquiring the anterior segment endpoint and posterior segment endpoint of the eye under examination based on the optical image; and determining the axial length of the eye under examination based on the anterior segment endpoint and posterior segment endpoint. 【0145】 The principles and processes for implementing each embodiment of the computer device described above can be found by referring to the description of the embodiment of the axial length measurement method in the above embodiment, and are therefore omitted here. 【0146】 In one embodiment, a computer program product is provided. The computer program product includes a computer program which, when executed by a processor, performs the following steps: acquiring an optical image of the eye under examination, including the cornea and fovea of the eye under examination, with the OCT optical focus aligned to the posterior segment of the eye under examination; acquiring the anterior and posterior segment endpoints of the eye under examination based on the optical image; and determining the axial length of the eye under examination based on the anterior and posterior segment endpoints. 【0147】 Industrial applicability 【0148】 By applying the technical embodiments of the present invention, it is possible to accurately measure the axial length of the eye even in cases of severe ophthalmic diseases.
Claims
[Claim 1] The steps include: adjusting the OCT optical focus to the posterior segment of the eye under examination and acquiring an optical image including the cornea and fovea of the eye under examination; The steps include obtaining the anterior segment endpoint and the posterior segment endpoint of the eye under examination based on the optical image, A method for measuring axial length of an eye, characterized by comprising the step of determining the axial length of the eye under examination based on the anterior segment endpoint and the posterior segment endpoint of the eye. [Claim 2] The method according to claim 1, characterized in that the step of acquiring an optical image by aligning the OCT optical focus with the posterior segment of the eye under examination includes the step of acquiring an optical image by aligning the OCT optical focus with the retina of the eye under examination. [Claim 3] The step of obtaining the anterior segment endpoint and posterior segment endpoint of the eye under examination based on the optical image includes inputting the optical image into a pre-trained first neural network model and obtaining the anterior segment endpoint and posterior segment endpoint output from the first neural network model. The method according to claim 1, wherein the first neural network model is obtained by learning based on a first optical image sample and a corresponding label, and the label of the first optical image sample includes an anterior segment endpoint mark and a posterior segment endpoint mark. [Claim 4] The step of obtaining the anterior segment endpoint and posterior segment endpoint of the eye under examination based on the optical image is: The steps include obtaining the cornea and the fovea of the eye under examination based on the optical image, A step of identifying the anterior segment endpoint of the eyeball based on the cornea, The method according to claim 1, characterized by comprising the step of identifying the posterior segment endpoint of the eyeball based on the fovea centralis of the retina. [Claim 5] The step of obtaining the cornea and fovea of the eye under examination based on the optical image includes inputting the optical image into a pre-trained second neural network model and obtaining the cornea and fovea output from the second neural network model. The method according to 4, wherein the second neural network model is obtained by learning based on a second optical image sample and a corresponding label, and the label of the second optical image sample includes a corneal mark and a foveal mark. [Claim 6] The step of identifying the anterior segment endpoint of the eyeball based on the cornea is: A step of making the corneal apex of the cornea the anterior segment endpoint of the eyeball, or The method according to 4 or 5, characterized in that, if the optical image is obtained by aligning the OCT scanning center with the corneal apex and fovea of the eye under examination, the step of setting the intersection of the OCT scanning center line and the anterior surface of the cornea as the anterior segment endpoint of the eyeball. [Claim 7] The step of identifying the posterior segment endpoint of the eyeball based on the fovea centralis of the retina is, A step in which the fovea central retina is defined as the endpoint of the posterior segment of the eyeball, or The method according to 4 or 5, characterized by comprising the steps of layering the retina, obtaining the result of layering at least one retinal layer in the fovea of the retina, and identifying the posterior segment endpoint based on the layering result. [Claim 8] The step of identifying the posterior segment endpoint of the eyeball based on the stratification results is: A step of selecting one target layer from the stratification results and setting the target point in the target layer as the posterior segment endpoint of the eyeball, or If the optical image is obtained by aligning the OCT scanning center with the corneal apex and fovea of the eye under examination, the step includes setting the intersection of the OCT scanning center line and one of the target layers among the stratification results as the posterior segment endpoint of the eyeball. The method according to 7, characterized in that the target layer includes one of the retinal pigment epithelium-choroidal complex layer, the interdigitation zone layer, and the choroidal layer, and the target point is a point on the straight line where the fovea centralis and the corneal apex are located. [Claim 9] The step of determining the axial length of the eye under examination based on the anterior segment endpoint and the posterior segment endpoint is as follows: The steps include obtaining the endpoint distance between the anterior segment endpoint and the posterior segment endpoint, and a correction value corresponding to the retinal thickness of the eye under examination, A step of determining the initial axial length of the eye under examination based on the endpoint distance and a correction value corresponding to the retinal thickness, The method according to any one of claims 1 to 8, characterized by comprising the step of performing a refractive correction process on the initial axial length of the eye to obtain the axial length of the eye to be examined. [Claim 10] The method according to 9, characterized in that the correction value corresponding to the retinal thickness is a preset value, the retinal thickness at the fovea, or the thickness from the anterior surface of the retina at the fovea to the posterior segment of the eyeball. [Claim 11] The method according to 10, characterized in that the preset value is in the range of 100 μm to 300 μm. [Claim 12] The method according to any one of claims 9 to 11, wherein the step of determining the initial axial length of the eye under examination based on the endpoint distance and a correction value corresponding to the retinal thickness includes the step of setting the difference between the endpoint distance and the correction value corresponding to the retinal thickness as the initial axial length of the eye under examination. [Claim 13] The method according to any one of claims 9 to 12, characterized in that the step of performing refractive correction processing on the initial axial length to obtain the axial length of the eye under examination includes the step of performing refractive correction processing on the initial axial length based on a preset refractive index correction coefficient to obtain the axial length of the eye under examination. [Claim 14] The aforementioned refractive index correction coefficient includes the average refractive index correction coefficient. The step of performing refractive correction processing on the initial axial length of the eye to obtain the axial length of the eye under examination, based on a preset refractive index correction coefficient, is: Axial length L of the eye being examined ２ Calculate using the following formula: L ２ =k×L １ Here, k represents the average refractive index correction coefficient, L １ The method according to 13, characterized in that it includes representing the initial axial length of the eye. [Claim 15] The method according to 14, characterized in that the average refractive index correction coefficient is in the range of 1.33 to 1.
45. [Claim 16] The step of determining the axial length of the eye under examination based on the anterior segment endpoint and the posterior segment endpoint is as follows: The steps include obtaining a plurality of structural layers of the eye to be examined, including the corneal surface, the anterior surface of the lens, and the crystalline surface, between the anterior and posterior segments of the eye, based on the optical image, A step of obtaining the lengths of a plurality of segments that correspond one-to-one in the cornea, anterior chamber, lens, and vitreous humor of the eye under examination in the axial direction of the eye, based on the plurality of structural layers, the anterior segment endpoint and the posterior segment endpoint of the eye, The method according to any one of claims 1 to 8, characterized by comprising the step of performing refractive correction and addition processing on the lengths of the plurality of segments to obtain the axial length of the eye under examination. [Claim 17] A step of obtaining an anterior segment mark at the anterior segment endpoint of the eyeball and a posterior segment mark at the posterior segment endpoint of the eyeball based on the optical image, The method according to any one of claims 1 to 6, further comprising the step of displaying the axial length of the eye based on the front mark and the rear mark. [Claim 18] The step of displaying the axial length of the eye based on the anterior and posterior markings is: The steps include displaying the preceding section mark and the following section mark, A step of obtaining position adjustment information after the user has adjusted the preceding and succeeding section marks, The method according to 17, characterized by comprising the step of identifying the axial length of the eye based on the position adjustment information and displaying the axial length of the eye. [Claim 19] A first acquisition module that acquires an optical image of the eye under examination, including the cornea and fovea of the retina, with the OCT optical focus aligned to the posterior segment of the eye under examination, A second acquisition module that acquires the anterior segment endpoint and posterior segment endpoint of the eye under examination based on the optical image, An axial length measuring device characterized by including a length determination module that determines the axial length of the eye under examination based on the anterior segment endpoint and the posterior segment endpoint of the eye. [Claim 20] A computer device comprising a memory device and a processor, wherein a computer program is stored in the memory device, The computer device is characterized in that the processor, when executing the computer program, realizes the method for measuring the axial length of the eye according to any one of claims 1 to 18.