Tomographic eye image generation method

Abstract

Provided is a tomographic eye image generation method whereby a tomographic eye image can be acquired by an optical system with a simple configuration even when an eye under examination and an ophthalmologic analysis device are far apart.　The tomographic eye image generation method includes: a first step for acquiring depth information about the intraocular structure of an eye under examination using a distance measuring sensor; a second step for acquiring a plurality of pieces of the depth information while changing the relative positions of the eye under examination and the distance measuring sensor; a third step for specifying the three-dimensional position of the depth information in the eye; and a fourth step for generating a tomographic eye image by synthesizing the plurality of pieces of depth information on the basis of the position information.

Description

Eye tomographic image generation method CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application is based on Japanese Patent Application No. 2023-121603 filed on July 26, 2023, the contents of which are incorporated herein by reference.

[0002] The present disclosure relates to a method for generating a tomographic image of an eyeball.

[0003] Generating tomographic images of the eye is extremely important for diagnosing ocular fundus diseases and assessing the risk of glaucoma attacks. A common method for generating tomographic images of the eye is to use optical coherence tomography (OCT). OCT can obtain tomographic images of the eye by irradiating the subject's eye with near-infrared light and analyzing the reflection from intraocular structures. Furthermore, eye diseases such as fundus macular disease and glaucoma often require long-term follow-up. Therefore, various methods for generating tomographic images of the eye have been developed to efficiently and appropriately monitor the follow-up of the subject's eye. For example, Patent Document 1 discloses a specific ophthalmic analysis device that obtains analysis results of tomographic images of the subject's eye acquired on different days using an ophthalmic optical coherence tomography device and outputs statistical information formed from the time-series data of the analysis results.

[0004] JP 2014-83266 A

[0005] When generating a tomographic image of the eye using such an ophthalmic analysis device, the patient's chin must be placed on the chin rest of the table-mounted device, and the subject's eye must be observed at a very close distance from the device. In addition, when performing intraocular observation, the ophthalmic analysis device installed in the hospital is required for the examination, making it impossible to provide remote medical care.

[0006] Therefore, the present invention has been made in consideration of the above-mentioned problems, and aims to provide a method for generating a tomographic image of an eyeball that can acquire a tomographic image of an eyeball using a simple optical system configuration, even when the distance between the test eye and an ophthalmic analysis device is great.

[0007] As a result of extensive research into solving the above problems, the present inventors have found that the above problems can be solved by the following method for generating a tomographic image of an eyeball.

[0008] That is, a method for generating a tomographic image of an eye according to one aspect of the present disclosure includes a first step of acquiring depth information of an intraocular structure in a test eye using a ranging sensor, a second step of acquiring multiple pieces of the depth information while changing the relative position between the test eye and the ranging sensor, a third step of identifying the three-dimensional position of the depth information within the eye, and a fourth step of synthesizing the multiple pieces of depth information based on the position information to generate a tomographic image of the eye.

[0009] In the third step, the three-dimensional position of the depth information may be identified based on an incident angle of incident light from the distance measurement sensor with respect to the corneal vertex of the subject's eye and / or a thickness of the retina.

[0010] In the fourth step, the tomographic image of the eye may be generated using a mathematical model trained by machine learning or deep learning.

[0011] In the fourth step, the tomographic image of the eye may be supplemented with a standard tomographic image.

[0012] In the fourth step, the plurality of pieces of depth information acquired in the second step may be used as training data for the mathematical model.

[0013] In the first step, resolution processing may be performed using adaptive optics.

[0014] The method for generating a tomographic image of an eye according to claim 1 may further include a disease risk information acquisition step of acquiring information on the presence or absence of a disease risk by inputting the depth information into a mathematical model trained by machine learning or deep learning using eye tomographic image data related to an eye disease as training data.

[0015] The method may further include a display step of displaying the depth information.

[0016] The distance measurement sensor may be a distance measurement unit of a mobile terminal.

[0017] The distance measuring sensor may be a distance measuring unit of a stationary device.

[0018] The distance measuring sensor may be a distance measuring unit of a head-mounted device.

[0019] According to the present disclosure, it is possible to provide a method for generating a tomographic image of an eye that can acquire a tomographic image of an eye using a simple optical system configuration, even when the distance between the test eye and an ophthalmic analysis device is great.

[0020] 1 is an example of a diagram illustrating an aspect of acquiring depth information of an intraocular structure in a test eye using a distance measurement sensor. FIG. 1 is an example of a diagram illustrating an example of depth information relating to the cornea, iris, and retina. FIG. 2 is an example of a diagram illustrating an aspect of acquiring a plurality of pieces of depth information of intraocular structures while changing the relative position between the test eye and a distance measurement sensor. FIG. 2 is an example of a diagram illustrating a change in the scenery reflected in the test eye, a change in the corneal limbus of the test eye, a movement of the pupil center within the corneal limbus, or a change in the pupil limbus according to an embodiment of the present disclosure. FIG. 3 is an example of a diagram illustrating a portion of an eye tomographic image including the cornea and iris among eye tomographic images obtained by the eye tomographic image generation method of the present embodiment. FIG. 4 is an example of a diagram illustrating a portion of an eye tomographic image including the retina among eye tomographic images obtained by the eye tomographic image generation method of the present embodiment. FIG. 5 is a schematic diagram illustrating an example of using a mobile terminal according to an embodiment of the present disclosure as an eye tomographic image generation device. FIG. 6 is a schematic diagram illustrating an example of using a stationary device according to an embodiment of the present disclosure as an eye tomographic image generation device. FIG. 1 is a schematic diagram showing an example of using a head-mounted device according to an embodiment of the present disclosure as an eye tomographic image generating device; FIG. 2 is a flowchart relating to the implementation of an eye tomographic image generating device according to an embodiment of the present disclosure; FIG. 3 is a hardware configuration of an eye tomographic image generating device according to an embodiment of the present disclosure; and FIG. 4 is a functional block configuration of an eye tomographic image generating device according to an embodiment of the present disclosure.

[0021] Embodiments of the present invention will be described with reference to the accompanying drawings. Note that the following embodiments are intended to facilitate understanding of the present invention and are not intended to limit the present invention. Furthermore, the present invention can be modified in various ways without departing from the gist of the present invention. Furthermore, those skilled in the art can adopt embodiments in which the elements described below are replaced with equivalents, and such embodiments are also included in the scope of the present invention.

[0022] 1 is a diagram showing an example of a method for acquiring depth information of intraocular structures in a subject's eye using an eye tomographic image generating device 4. The eye tomographic image generating device 4 of this embodiment is a device that acquires depth information of intraocular structures in the subject's eye 20 by using a light source 41 and a beam splitter 42 of a distance measuring sensor 40 to direct incident light 31 into the subject's eye 20, and detecting various reflected light beams originating from intraocular structures, such as reflected light 32 from the cornea 21, reflected light 33 from the iris 22, and reflected light 34 from the retina 24, using a detector 43.

[0023] 11 is a diagram showing an example of the hardware configuration of the eyeball tomographic image generating device 4. The eyeball tomographic image generating device 4 includes a processor 11 such as a CPU (Central Processing Unit) or a GPU (Graphical Processing Unit), a storage device 12 such as a memory, an HDD (Hard Disk Drive) and / or an SSD (Solid State Drive), a communication IF (Interface) 13 for wired or wireless communication, an input device 14 for accepting input operations, and an output device 15 for outputting information. The input device 14 is, for example, a keyboard, a touch panel, a mouse, and / or a microphone. The output device 15 is, for example, a display, a touch panel, and / or a speaker.

[0024] In this embodiment, the ranging sensor 40 may be configured to be included in the input device 14, or the ranging sensor 40 may be configured to be included in an external device of the eye tomographic image generating device 4, and the depth information obtained by the ranging sensor 40 may be input from the input device 14 via a communication line or the like.

[0025] <Functional Block Configuration> Fig. 12 is a diagram showing an example of the functional block configuration of the eyeball tomogram generating device 4. The eyeball tomogram generating device 4 includes a storage unit 110 and a control unit 120. The storage unit 110 can be realized using the storage unit 12 included in the eyeball tomogram generating device 4. The control unit 120 can be realized by the processor 11 of the eyeball tomogram generating device 4 executing a program stored in the storage unit 12. The program can be stored in a storage medium. The storage medium storing the program may be a non-transitory computer-readable medium. The non-transitory storage medium is not particularly limited, and may be, for example, a storage medium such as a USB memory or a CD-ROM.

[0026] FIG. 7 is a schematic diagram showing an example in which a mobile terminal 50 is used as the eye tomography device 4. By using the mobile terminal 50 as the eye tomography device 4, eye tomography images can be generated with a simpler optical system configuration. In FIG. 7, for ease of explanation, the mobile terminal 50 is shown enlarged compared to its actual size. The distance sensor 40 is not particularly limited, but for example, a sensor of the mobile terminal 50 is used. The mobile terminal 50 is not particularly limited, but for example, an information processing device such as a smartphone, a tablet computer, a laptop computer, or a workstation computer can be used. Here, a terminal refers to a device that is connected to a line or network and can communicate with other devices.

[0027] 8 is a schematic diagram showing an example in which a fixed device 51 is used as the eye tomography device 4. By using the fixed device 51 as the eye tomography device 4, eye tomography images can be generated with a simpler optical system configuration. The distance measurement sensor 40 is not particularly limited, but for example, the distance measurement sensor of the fixed device 51 is used. When the fixed device 51 is used as the eye tomography device, the relative position between the subject's eye 20 and the distance measurement sensor 40 can be easily changed by the subject moving while facing the fixed device 51. Furthermore, the second step S102, which will be described later, can be performed for a certain period of time without the subject performing any operation.

[0028] The stationary device 51 is not particularly limited, and may be, for example, a smart mirror. By using a smart mirror, the subject can be photographed naturally in their daily lives without being conscious of it. Here, the smart mirror refers to a mirror-type terminal that can connect to the Internet, can reflect the subject's own image, and has a distance measurement sensor.

[0029] 9 is a schematic diagram showing an example in which a head-mounted device 60 is used as the eye tomography device 4. By using the head-mounted device 60 as the eye tomography device 4, eye tomography images can be generated with a simpler optical system configuration. The distance measurement sensor 40 is not particularly limited, but for example, a distance measurement sensor built into the head-mounted device 60 is used. When the head-mounted device 60 is used as the eye tomography device 4, as shown in FIG. 9, a first step S101 and a second step S102, which will be described later, can be easily performed regardless of the subject's movements.

[0030] 10 is a flowchart showing each step involved in implementing the eyeball tomographic image generating apparatus 4 according to one embodiment of the present invention, and each step is executed by the control unit 120 of the eyeball tomographic image generating apparatus 4. Each step will be described in detail below with reference to FIG.

[0031] 10 , the eye tomographic image generating device 4 includes a first step S101 of acquiring depth information of an intraocular structure in the subject's eye, a second step S102 of acquiring multiple pieces of depth information while changing the relative position between the subject's eye and the distance measuring sensor, a third step S103 of identifying the three-dimensional position of the depth information within the eye, and a fourth step S104 of synthesizing the multiple pieces of depth information to generate an eye tomographic image, and by performing these steps, an eye tomographic image of the subject's eye 20 is generated. The eye tomographic image generating device 4 may also include a display step S105. Furthermore, the eye tomographic image generating device 4 may include other steps as necessary.

[0032] 1 , the first step S101 is a step of acquiring depth information of the intraocular structures in the subject's eye 20 using a distance measurement sensor 40. In the first step S101, incident light 31 is made incident on the subject's eye 20 using a light source 41 and a beam splitter 42 of a depth sensor 40 of the ocular tomographic image generating device 4, and reflected light from the intraocular structures is detected by a detector 43. FIG. 1 shows that reflected light 32 from the cornea 21, reflected light 33 from the iris 22, and reflected light 34 from the retina 24 can be detected.

[0033] 1, d1 indicates the anterior chamber depth, and d2 indicates the axial length. d1 is useful information for diagnosing glaucoma, and d2 is useful information for diagnosing myopia.

[0034] Here, the distance measurement sensor refers to a sensor that measures distance. Examples of distance measurement sensors include, but are not limited to, optical distance measurement sensors (LiDAR), radio wave distance measurement sensors, and ultrasonic distance measurement sensors. Among these, LiDAR is preferred from the viewpoint of easily acquiring depth information. Examples of LiDAR include, but are not limited to, a Time-of-Flight (ToF) type and an FMCW type.

[0035] Among these, the FMCW method is preferably used in this embodiment. FMCW LiDAR emits a laser beam that continuously shifts between different frequencies. By collecting reflected light and measuring the reflection time, the detector can distinguish a specific frequency pattern from other light sources, enabling high-speed and accurate operation under all illumination conditions. Therefore, even when the distance between the subject's eye and the ranging sensor is large and light from surrounding light sources and its reflected light easily penetrates the detector, more accurate depth information tends to be obtained. Furthermore, even when the reflection intensity of the light coming from intraocular structures is very weak, as in this embodiment, more accurate depth information tends to be obtained.

[0036] The intraocular structure refers to all structures inside the eyeball, and is not particularly limited, but examples include the cornea 21, iris 22, and retina 24 shown in FIG. 1, as well as the ciliary body, Zonule of Zinn, choroid, and sclera.

[0037] The depth information means information relating to the distance from a distance measuring sensor located at a predetermined relative position with respect to the subject's eye to the intraocular structure. The depth information can be obtained from reflected light emitted by the intraocular structure after the incident light emitted from the distance measuring sensor located at a predetermined relative position with respect to the subject's eye is reflected.

[0038] In Figure 2, P1, P2, P3, P4, P5, and P6 indicate examples of depth information related to the cornea, Q1, Q2, Q3, and Q4 indicate examples of depth information related to the iris, and R1, R2, R3, R4, R5, and R6 indicate examples of depth information related to the retina.

[0039] Generally, when detecting reflected light from inside a substance, the intensity of reflected light reflected from structures near the surface of the substance is greatest, and the intensity of reflected light from internal structures tends to decrease as the light travels deeper into the substance. In Figure 1, i1 indicates the intensity of reflected light 32 from the cornea 21, i2 indicates the intensity of reflected light 33 from the iris 22, and i3 indicates the intensity of reflected light 34 from the retina 24, indicating that the intensity of reflected light from intraocular structures tends to decrease as the incident light travels deeper from the surface of the test eye.

[0040] In the first step S101, a tomographic image of the eye can be generated even when the distance measurement sensor 40 of the eye tomographic image generating device 4 is distant from the subject's eye 20. The distance between the distance measurement sensor 40 and the subject's eye 20 is not particularly limited, but from the viewpoint of easily generating a tomographic image of the eye, it is preferably 3 cm or more, more preferably 5 cm or more, even more preferably 10 cm or more, even more preferably 15 cm or more, even more preferably 20 cm or more, and particularly preferably 30 cm or more. The lower limit of the distance between the distance measurement sensor 40 and the subject's eye 20 is not particularly limited, but may be, for example, 1 mm, 3 mm, 5 mm, or 1 cm. The upper limit of the distance between the distance measurement sensor 40 and the subject's eye 20 is not particularly limited, but may be, for example, 10 m, 5 m, 3 m, 1 m, or 50 cm.

[0041] In the first step S101, resolution processing may be performed using adaptive optics. Specifically, for example, a distance measuring sensor that applies adaptive optics may be used. Here, adaptive optics refers to a technology for obtaining a high-resolution image by removing wavefront aberration.

[0042] 2.2. Second Step S102 As shown in FIG. 3, the second step S102 is a step of determining the relative position (l, θ) between the subject's eye 20 and the distance measurement sensor 40. i , θ ｒ This is a process of acquiring multiple pieces of depth information while changing the angle of the object. This will be explained in detail below.

[0043] The relative position (l, θ) between the eye 20 and the distance measuring sensor 40 i , θ ｒ ) can be changed by a conventionally known method. Such a method is not particularly limited, but for example, the orientation of the subject's eye 20 may be changed without changing the position of the distance measuring sensor 40, or the position of the distance measuring sensor 40 may be changed without changing the orientation of the subject's eye 20.

[0044] The means for changing the orientation of the subject's eye 20 is not particularly limited, but may be, for example, a fixation target projection means that presents multiple fixation targets. The fixation target projection means has a fixation lamp that emits visible light, and by turning on the fixation lamp, multiple fixation targets are presented to the subject, thereby guiding the subject's eye 20 to look in any direction.

[0045] The number of pieces of depth information to be acquired is not particularly limited because it is used in the image generation step S104 described later, but is preferably 30 or more, more preferably 100 or more, and even more preferably 300 or more. Here, the number of pieces of depth information is counted as one for each relative position (l, θi, θr) between the eye 20 to be examined and the distance measurement sensor 40.

[0046] 2.3. Third Step S103 The third step S103 is a step of identifying the three-dimensional position of the depth information within the eyeball. The third step S103 may be performed based on a plurality of pieces of depth information obtained by changing the relative position (l, θi, θr) between the subject's eye 20 and the distance measurement sensor 40. A conventionally known method can be used as a method for identifying the three-dimensional position, and is not particularly limited, but examples thereof include SfM (Structure from Motion).

[0047] In addition, in the third step S103, the three-dimensional position of the depth information may be identified based on the angle of incidence of the incident light 31 from the distance measurement sensor 40 with respect to the corneal apex of the test eye 20 and / or the thickness of the retina 24.

[0048] Furthermore, in the third step S103, as shown in Figure 4, information such as changes in the scenery 54 reflected in the pupil of the test eye 20, such as movement of the scenery reflected in the pupil of the test eye 20, changes in the corneal limbus 55 of the test eye 20, movement of the pupil center within the corneal limbus 55, or changes in the pupillary limbus may be used in combination. Specifically, the accuracy of determining the three-dimensional position of depth information can be improved by detecting changes in the scenery 54 reflected in the test eye 20 caused by the rotational movement 59 of the eyeball of the test eye 20, detecting changes 56 in the corneal limbus caused by the rotational movement 59 of the eyeball, such as the corneal limbus 55 deforming from a circular shape to an approximately elliptical shape, detecting changes 56 in the corneal limbus caused by the rotational movement 59 of the eyeball, and using these changes to determine the three-dimensional position of depth information, detecting movements 58 of the pupil center within the corneal limbus caused by the rotational movement 59 of the eyeball, and using these changes to determine the three-dimensional position of depth information, or detecting changes in the pupillary limbus 57 caused by the rotational movement 59 of the eyeball.

[0049] 2.4. Fourth Step S104 The fourth step S104 is a step of generating a tomographic image of the eyeball by combining the plurality of pieces of depth information obtained in the second step S102 and the three-dimensional positions within the eyeball identified in the three-dimensional position information identification step S103.

[0050] 5 and 6 are examples of tomographic images of an eye obtained in step 4. Fig. 5 shows a portion of the tomographic image of an eye including a cornea 21 and an iris 22, and Fig. 6 shows a portion of the tomographic image of an eye including a retina.

[0051] In the fourth step, the tomographic image of the eye may be generated using a mathematical model trained by machine learning or deep learning.

[0052] In the fourth step, the ocular tomogram may be supplemented with a standard tomogram. Here, the method for acquiring the standard tomogram may be a conventionally known method, and is not particularly limited, but may include, for example, an optical coherence tomography (OCT).

[0053] Here, the training data for the mathematical model is not particularly limited, and may be, for example, the plurality of pieces of depth information acquired in the second step. This makes it possible to generate and supplement depth information corresponding to regions not acquired in the second step S102 without using a standard tomographic image. Although this increases the number of computations by a computer, it is not necessary to prepare a standard tomographic image of the subject's eye 20, and therefore it is possible to easily generate a tomographic image of the eye.

[0054] Here, a learning model trained by machine learning (hereinafter referred to as a machine learning model) is an example of a mathematical model. A machine learning model includes a model that has a predetermined model structure and parameters that vary through a learning process, and that improves classification accuracy by optimizing the processing parameters based on experience gained from training data. In other words, a machine learning model is a model that learns optimal processing parameters through a learning process. Algorithms for machine learning models can include, for example, support vector machines, logistic regression, random forests, neural networks, etc., and the type is not particularly limited. However, from the viewpoint of generating a tomographic image of the eyeball even when there is a small amount of training data, it is preferable to use a neural network. Machine learning models that perform this learning include models that have already undergone some kind of learning using training data, as well as models that have not yet been trained.

[0055] 10 , the display step S105 is a step of displaying a tomographic image of the eye, and the eye tomographic image generating device 4 in this embodiment preferably has the display step S105. This makes it easier to check the intraocular information of the subject.

[0056] 2.6. Other Steps In addition to the steps described above, the eye tomographic image generating device 4 in this embodiment may include other steps as necessary. Examples of such other steps include, but are not limited to, a disease risk information acquisition step. The disease risk information acquisition step is a step of acquiring information regarding the presence or absence of a disease risk by inputting eye tomographic image data related to an eye disease as training data into a mathematical model trained by machine learning or deep learning. This allows for the early and simple detection of eye diseases such as glaucoma and myopia.

[0057] According to the present invention, it is possible to easily obtain tomographic images of the eye for use in ophthalmologic examinations using, for example, but not limited to, a mobile terminal such as a smartphone, etc. Therefore, it is expected that the method for obtaining tomographic images of the eye according to the present invention will be widely used throughout the world.

[0058] It also has great significance in clinical applications. Specifically, during typical ophthalmological examinations, observation and diagnosis of the subject's eye are performed using tabletop devices, but this is difficult and requires skilled techniques when examining children or bedridden elderly people. However, with the present invention, tomographic images of the eye can be generated very easily using a mobile device or other device, regardless of the subject's posture, and can be used for observation and diagnosis. Therefore, it is expected that this system will be used for remote medical consultations in rural areas and support for developing countries.

[0059] Furthermore, the present invention can be similarly used for observing and photographing the eyes of animals, and in particular for obtaining tomographic images of the eyes of pet animals and large animals kept in zoos where it is particularly difficult to bring the examined eyes close to an ophthalmic diagnostic device, thereby enabling the acquisition of ophthalmic findings of such animals.

[0060] Furthermore, it is expected that the data will be analyzed using AI as big data, which will improve the diagnostic accuracy of ophthalmologists. Ultimately, it will be used as a self-diagnosis tool for patients, which will lead to further developments in ophthalmology treatment itself.

[0061] 4...eyeball tomographic image generating device, 20...eye to be examined, 21...cornea, 22...iris, 23...crystalline lens, 24...retina, 31...incident light, 32...reflected light from cornea 21, 33...reflected light from iris 22, 34...reflected light from retina 24, 40...distance measuring sensor, 41...light source, 42...beam splitter, 43...detector, 50...mobile terminal, 51...stationary device, 60...head-mounted device, i1...reflection intensity of reflected light from cornea 21, i2...reflection intensity of reflected light from iris 22, i3...reflection intensity of reflected light from retina 24, P1, P2, P3, P4, P5, P6, Q1, Q2, Q3, Q4, R1, R2 , R3, R4, R5, R6...depth information, ■...distance from the corneal apex to the distance measuring sensor, θi, θr...azimuth angle of the distance measuring sensor when the corneal apex is used as the reference, 54...scenery reflected in the eye to be examined, 55...corneal limbus, 56...change in the corneal limbus, 57...pupil limbus, 58...movement of the pupil center within the corneal limbus, 59...rotational movement of the eyeball, 11...processor, 12...storage device, 13...communication IF, 14...input device, 15...output device, 110...storage unit, 120...control unit, S101...first step, S102...second step, S103...third step, S104...fourth step, S105...display step

Claims

1. A method for generating an eye tomographic image, comprising: a first step of acquiring depth information of an intraocular structure in a test eye using a distance measurement sensor; a second step of acquiring multiple pieces of the depth information while changing the relative position between the test eye and the distance measurement sensor; a third step of identifying a three-dimensional position within the eye of the depth information; and a fourth step of synthesizing the multiple pieces of depth information based on the position information to generate an eye tomographic image.

2. The method for generating a tomographic image of an eye described in claim 1, wherein in the third step, the three-dimensional position of the depth information is identified based on the angle of incidence of incident light from the distance measuring sensor to the corneal apex of the test eye and / or the thickness of the retina.

3. The method for generating an eye tomographic image according to claim 1, wherein in the fourth step, the eye tomographic image is generated using a mathematical model trained by machine learning or deep learning.

4. The method for generating an eye tomogram according to claim 1, wherein in the fourth step, the eye tomogram is complemented by a standard tomogram.

5. The method for generating a tomographic image of an eye according to claim 3 or 4, wherein a plurality of pieces of depth information acquired in the second step are used as training data for the mathematical model.

6. The method for generating a tomographic image of an eye according to claim 1, wherein in the first step, adaptive optics is used to perform resolution processing.

7. The method for generating an eye tomographic image as described in claim 1, further comprising a disease risk information acquisition process for acquiring information regarding the presence or absence of a disease risk by inputting the depth information into a mathematical model trained by machine learning or deep learning using eye tomographic image data related to an eye disease as training data.

8. The method for generating a tomographic image of an eye according to claim 1, further comprising a display step of displaying the depth information.

9. The eye tomographic image generating method according to claim 1, wherein the distance measuring sensor is a distance measuring unit of a mobile terminal.

10. The method for generating a tomographic image of an eye according to claim 1, wherein the distance measuring sensor is a distance measuring section of a stationary device.

11. The method for generating a tomographic image of an eye according to claim 1, wherein the distance measuring sensor is a distance measuring unit of a head-mounted device.

Images