Information processing systems, information processing methods, and programs

Abstract

The present invention makes it possible to easily estimate the condition of a subject.　Provided is an information processing system characterized by comprising: an image acquisition unit that acquires a captured image of an eye of a subject; and an anterior chamber depth estimation unit that feeds the acquired captured image into a learning model learned through machine learning using eye images and anterior chamber depths as training data to estimate the anterior chamber depth of the subject.

Description

【Technical Field】 【0001】 The present invention relates to an information processing system, an information processing method, and a program. 【Background Art】 【0002】 Patent Document 1 discloses using the result of spectral analysis of an image obtained by photographing a subject's eye for cataract diagnosis. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2002-224041 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 However, in Patent Document 1, it takes time to set the illumination light irradiated into the eye. 【0005】 The present invention has been made in view of such a background, and an object thereof is to provide a technology capable of easily estimating the state of a subject. 【Means for Solving the Problems】 【0006】 The main invention of the present invention for solving the above problems is an information processing system including an image acquisition unit that acquires a captured image obtained by photographing a subject's eye, and a learning model that has learned an eye image and an anterior chamber depth by machine learning using the training data, and giving the acquired captured image to the anterior chamber depth estimation unit that estimates the anterior chamber depth of the subject. 【0007】 Regarding other problems disclosed in the present application and methods for solving them, they will be clarified by the embodiments of the invention and the drawings. 【Effects of the Invention】 【0008】 According to the present invention, the subject's condition can be easily estimated. [Brief explanation of the drawing] 【0009】 [Figure 1] This figure shows an example of the overall configuration of an information processing system. [Figure 2] This figure shows an example of the hardware configuration of subject terminal 1. [Figure 3] This figure shows an example of the software configuration of subject terminal 1. [Figure 4] This figure shows an example of the hardware configuration of management server 2. [Figure 5] This figure shows an example of the software configuration for management server 2. [Figure 6] This is a diagram illustrating the operation of an information processing system. [Figure 7] This figure shows an example of the software configuration of the management server 2 according to the second embodiment. [Figure 8] This figure shows an example of the software configuration of the management server 2 according to the third embodiment. [Modes for carrying out the invention] 【0010】 <First Embodiment> The following describes a first embodiment of the information processing system. In the first embodiment, the anterior chamber depth (distance from the cornea to the lens) of the subject is estimated from an image of the subject's eye. A shallow anterior chamber depth increases the risk of acute glaucoma attacks and glaucoma attacks during dilated pupil examinations. Since it is possible to estimate the anterior chamber depth from an image of the subject's eye, it is also possible to understand the risk of acute glaucoma attacks and glaucoma attacks during dilated pupil examinations. 【0011】 Figure 1 shows an example of the overall configuration of an information processing system. The information processing system in this embodiment includes a management server 2. The management server 2 is connected to the subject terminal 1 via a communication network. The communication network is, for example, the internet and is constructed using public telephone lines, mobile phone lines, wireless communication channels, Ethernet (registered trademark), etc. 【0012】 Subject terminal 1 is a computer operated by the subject. Subject terminal 1 can be, for example, a smartphone, tablet computer, or personal computer. Subject terminal 1 is equipped with a camera (not shown) that can photograph the subject's face (especially the subject's eyes). It is also possible that the subject terminal 1 is operated by a test collaborator rather than by the subject themselves. 【0013】 The management server 2 may be a general-purpose computer such as a workstation or personal computer, or it may be logically implemented through cloud computing. 【0014】 <Subject terminal 1> Figure 2 shows an example of the hardware configuration of the subject terminal 1. Note that the illustrated configuration is just one example, and other configurations are also possible. The subject terminal 1 includes a CPU 101, memory 102, storage device 103, communication interface 104, touch panel display 105, and camera 106. The storage device 103 stores various data and programs, such as a hard disk drive, solid state drive, or flash memory. The communication interface 104 is an interface for connecting to a communication network, such as an adapter for connecting to Ethernet®, a modem for connecting to a public telephone network, a wireless communication device for wireless communication, or a USB (Universal Serial Bus) connector or RS232C connector for serial communication. The touch panel display 105 is an interface for inputting and outputting data, and can display images on the screen and acquire the position of touches on the screen. The camera 106 can acquire captured images. Furthermore, each functional unit of the subject terminal 1, as described later, is realized by the CPU 101 reading a program stored in the storage device 103 into the memory 102 and executing it, and each storage unit of the subject terminal 1 is realized as part of the storage area provided by the memory 102 and the storage device 103. 【0015】 Figure 3 shows an example of the software configuration of the subject terminal 1. The subject terminal 1 includes an image acquisition unit 111 and an image transmission unit 112. 【0016】 The image acquisition unit 111 acquires images (hereinafter referred to as "captured images") taken by the camera 106. The image acquisition unit 111 can control the camera 106 by known methods to acquire captured images from the camera 106. When the camera 106 takes a picture, the image acquisition unit 111 can, for example, output a message to the subject instructing them to take a picture of their eyes. The image acquisition unit 111 may, for example, be activated by the subject to acquire images, or it may acquire captured images in response to receiving a message from the management server 2 instructing it to take a picture. 【0017】 The image acquisition unit 111 may be configured to receive a specification of a captured image captured in advance. For example, the image acquisition unit 111 may be configured to receive a specification of an image of the subject's eyes captured from among the images registered in an image storage unit such as a camera roll. Alternatively, in response to a specification from the subject, the image acquisition unit 111 may be configured to read a captured image from a storage device (a storage device included in the subject terminal 1 or a storage medium connected to the subject terminal 1 or a storage device included in an external server) in which files are stored. 【0018】 It is assumed that the subject's eyes are captured in the captured image. The captured image may be an image of the subject's face, or may be an image that captures only the vicinity of the subject's eyes. The image acquisition unit 111 may determine whether the eyes are included in the captured image. For example, the image acquisition unit 111 can determine whether the eyes are included in the captured image by providing the captured image to a model for detecting eyes and determining whether the eyes can be detected from the captured image. If the eyes are not included, the image acquisition unit 111 may output a message to the subject to retake the captured image, and acquire a captured image (or a captured image captured in advance) captured again by the camera 106. 【0019】 The image transmission unit 112 transmits the captured image acquired by the image acquisition unit 111 to the management server 2. 【0020】 Figure 4 shows an example of the hardware configuration of the management server 2. Note that the illustrated configuration is just one example, and other configurations are also possible. The computer includes a CPU 201, memory 202, storage device 203, communication interface 204, input device 205, and output device 206. The storage device 203 stores various data and programs, such as a hard disk drive, solid-state drive, or flash memory. The communication interface 204 is an interface for connecting to a communication network, such as an adapter for connecting to Ethernet®, a modem for connecting to a public telephone network, a wireless communication device for wireless communication, or a USB (Universal Serial Bus) connector or RS232C connector for serial communication. The input device 205 is for inputting data, such as a keyboard, mouse, touch panel, button, or microphone. The output device 206 is for outputting data, such as a display, printer, or speaker. Furthermore, each functional unit of the management server 2, as described later, is realized by the CPU 201 reading programs stored in the storage device 203 into memory 202 and executing them, and each storage unit of the management server 2 is realized as part of the storage area provided by memory 202 and storage device 203. 【0021】 Figure 5 shows an example of the software configuration of the management server 2. The management server 2 comprises a learning model storage unit 231, a subject information storage unit 232, an image acquisition unit 211, a subject information output unit 213, a subject information acquisition unit 214, and an anterior chamber depth estimation unit 215. 【0022】 The learning model storage unit 231 stores a learning model for estimating the anterior chamber depth of the subject. The learning model stored in the learning model storage unit 231 can be created, for example, by machine learning using an eye image and anterior chamber depth as training data. The learning model can also be created by learning by machine learning using an eye image, anterior chamber depth, and at least one of age and sex as training data. The learning model may be updated by machine learning in response to feedback from the subject's eye image and the subject's anterior chamber depth (for example, the anterior chamber depth measured by the subject with another device can be received from the subject terminal 1). Note that the learning model storage unit 231 may be provided by an external server instead of the management server 2, and the learning model may be used via an API provided by the external server. 【0023】 The subject information storage unit 231 stores subject information about the subject. The subject information may include at least one of the subject's age and gender. The subject information may also include any subject attributes such as name and address. The subject information may also include an estimated value of the anterior chamber depth estimated by the anterior chamber depth estimation unit 214, which will be described later. 【0024】 The image acquisition unit 211 acquires captured images of the subject's eyes. The image acquisition unit 211 can receive captured image data transmitted from the subject terminal 1. The image acquisition unit 211 can send a message to the subject terminal 1 instructing it to take a picture of the subject's eyes. The subject terminal 1 takes a picture in response to the message and can receive the captured image of the eyes from the subject terminal 1. 【0025】 The subject information acquisition unit 214 acquires subject information. The subject information acquired by the subject information acquisition unit 214 does not need to include anterior chamber depth. For example, the subject information acquisition unit 214 can receive values ​​for each item included in the subject information, such as the subject's name, address, age, and gender, from the subject terminal 1 and register them as subject information in the subject information storage unit 231. The subject information may also include the refractive values ​​of the subject's eyes (spherical power, cylindrical power, equivalent spherical power, astigmatism axis, etc.). 【0026】 The anterior chamber depth estimation unit 215 estimates the anterior chamber depth of the subject. The anterior chamber depth estimation unit 215 can estimate the anterior chamber depth of the subject by providing the acquired images to the learning model stored in the learning model memory unit 231. 【0027】 The anterior chamber depth estimation unit 215 may estimate the anterior chamber depth of a subject by providing the learning model stored in the learning model memory unit 231 with the acquired image and at least one of the subject information items stored in the subject information memory unit 231. For example, the anterior chamber depth estimation unit 215 can estimate the anterior chamber depth of a subject by providing the learning model stored in the learning model memory unit 231 with the acquired image and at least one of the subject information's age and sex. Alternatively, for example, the anterior chamber depth estimation unit 215 can also estimate the anterior chamber depth of a subject by providing the learning model stored in the learning model memory unit 231 with the acquired image and the refractive value of the subject information. 【0028】 The subject information output unit 213 outputs information about the subject (hereinafter referred to as subject information). The subject information may include information that identifies the subject and the estimated anterior chamber depth of the subject. The subject information output unit 213 may transmit the subject information to the subject terminal 1, to an output device such as a display, or to a terminal (not shown) of a medical professional such as an ophthalmologist. 【0029】 <Operation> Figure 6 is a diagram illustrating the operation of an information processing system. 【0030】 The subject operates the subject terminal 1 to take a picture of their own eye (S301), and the subject terminal 1 transmits the captured image to the management server 2 (S302). 【0031】 The management server 2 receives the captured images from the subject terminal 1 and provides them to the learning model stored in the learning model storage unit 231 to estimate the subject's anterior chamber depth (S303). The management server 2 can then create and output subject information, including the subject's anterior chamber depth (S304). 【0032】 As described above, the information processing system according to the first embodiment can estimate the anterior chamber depth of a subject from an image of the subject's eye. This can then be used to determine the risk of glaucoma. 【0033】 Furthermore, the management server 2 may be equipped with a glaucoma attack risk determination unit that determines the risk of acute glaucoma attacks and glaucoma attacks during pupil dilation examinations based on the estimated anterior chamber depth. In this case, the subject information output unit 214 can output the glaucoma risk along with, or in lieu of, the estimated anterior chamber depth. 【0034】 <Disclosure Items> Furthermore, this disclosure also includes the following configurations. [Item 1] An image acquisition unit that acquires images of the subject's eyes, An anterior chamber depth estimation unit estimates the anterior chamber depth of the subject by providing the acquired captured images to a learning model that has been trained by machine learning using eye images and anterior chamber depth as training data. An information processing system characterized by comprising the following features. [Item 2] The information processing system described in item 1, The system includes a subject information storage unit that stores at least one of the subject's age and gender, The aforementioned learning model was trained by machine learning using the eye image, the anterior chamber depth, and at least one of the age and sex as training data. The anterior chamber depth estimation unit estimates the anterior chamber depth of the subject by providing the learning model with the acquired captured image and at least one of the subject's age and sex stored in the subject information storage unit. An information processing system characterized by the following. [Item 3] The information processing system described in item 1, The system includes a subject information storage unit that stores the refractive value of the subject's eye, The aforementioned learning model was trained using machine learning with the image of the eye, the anterior chamber depth, and the refractive value as training data. The anterior chamber depth estimation unit estimates the anterior chamber depth of the subject by providing the acquired image and the refractive value stored in the subject information storage unit to the learning model. An information processing system characterized by the following. [Item 4] The steps include: obtaining images of the subject's eyes, The process involves a step of estimating the anterior chamber depth of the subject by providing the acquired captured images to a machine learning model that has been trained using eye images and anterior chamber depth as training data, and An information processing method characterized by a computer executing the following. [Item 5] The steps include: obtaining images of the subject's eyes, The process involves a step of estimating the anterior chamber depth of the subject by providing the acquired captured images to a machine learning model that has been trained using eye images and anterior chamber depth as training data, and A program that causes a computer to execute something. 【0035】 <Second Embodiment> Next, a third embodiment of the information processing system will be described. In the third embodiment, the degree of cataracts in the subject is estimated from an image of the subject's eye. 【0036】 Figure 7 shows an example of the software configuration of the management server 2 according to the second embodiment. In the second embodiment, the management server 2 includes a learning model storage unit 231, a subject information storage unit 232, an image acquisition unit 211, a subject information output unit 213, a subject information acquisition unit 214, and a turbidity estimation unit 216. Compared to the configuration of the management server 2 in the first embodiment, the anterior chamber depth estimation unit 215 is omitted and the turbidity estimation unit 216 is added. Note that in the second embodiment as well, the management server 2 may include the anterior chamber depth estimation unit 215. The differences from the first embodiment will be mainly explained below. 【0037】 The learning model stored in the learning model memory unit 231 in the second embodiment can be created by learning through machine learning using eye images and the degree of cataracts as training data. The learning model can also be created by learning through machine learning using eye images and anterior chamber depth as training data. The learning model can also be created by learning through machine learning using eye images, anterior chamber depth, and at least one of age and gender as training data. 【0038】 The subject information stored in the subject information storage unit 231 may also include an estimated value of the degree of cataracts estimated by the turbidity estimation unit 216, which will be described later. 【0039】 The subject information output by the subject information output unit 213 includes the estimated degree of cataracts. 【0040】 The subject information acquisition unit 214 acquires subject information. The subject information acquired by the subject information acquisition unit 214 does not need to include the degree of cataracts. For example, the subject information acquisition unit 214 can receive values ​​for each item included in the subject information, such as the subject's name, address, age, and gender, from the subject terminal 1 and register them as subject information in the subject information storage unit 231. The subject information may also include the refractive values ​​of the subject's eyes (spherical power, cylindrical power, equivalent spherical power, astigmatism axis, etc.). 【0041】 The turbidity estimation unit 216 estimates the degree of cataracts (degree of turbidity) in the subject. The turbidity estimation unit 216 can estimate the degree of cataracts in the subject by providing the acquired images to the learning model stored in the learning model memory unit 231. 【0042】 The turbidity estimation unit 216 may estimate the degree of cataracts in a subject by providing the learning model stored in the learning model storage unit 231 with the acquired image and at least one of the subject information items stored in the subject information storage unit 231. For example, the turbidity estimation unit 216 can estimate the degree of cataracts in a subject by providing the learning model stored in the learning model storage unit 231 with the acquired image and at least one of the subject information, age and gender. 【0043】 As described above, the information processing system according to the second embodiment makes it possible to estimate the degree of cataracts in a subject from captured images of the subject's eyes. 【0044】 The disclosure according to the second embodiment may include the following configurations. [Item 1] An image acquisition unit that acquires images of the subject's eyes, A turbidity estimation unit estimates the degree of cataracts in the subject by providing the acquired captured images to a learning model that has been trained by machine learning using eye images and the degree of cataracts as training data. An information processing system characterized by comprising the following features. [Item 2] The information processing system described in item 1, The system includes a subject information storage unit that stores at least one of the subject's age and gender, The aforementioned learning model was trained by machine learning using the eye image, the degree of cataract, and at least one of the age and gender as training data. The anterior chamber turbidity estimation unit estimates the degree of cataract in the subject by providing the learning model with the acquired captured image and at least one of the subject's age and gender stored in the subject information storage unit. An information processing system characterized by the following. [Item 3] The steps include: obtaining images of the subject's eyes, The process involves a step of estimating the degree of cataracts in the subject by providing the acquired images to a machine learning model that has been trained using eye images and the degree of cataracts as training data, An information processing method characterized by a computer executing the following. [Item 4] The steps include: obtaining images of the subject's eyes, The process involves a step of estimating the degree of cataracts in the subject by providing the acquired images to a machine learning model that has been trained using eye images and the degree of cataracts as training data, A program that causes a computer to execute something. 【0045】 <Third Embodiment> Next, a third embodiment of the information processing system will be described. In the third embodiment, the density of corneal endothelial cells is estimated from an image of the subject's eye. 【0046】 Figure 8 shows an example of the software configuration of the management server 2 according to the third embodiment. In the third embodiment, the management server 2 includes a learning model storage unit 231, a subject information storage unit 232, an image acquisition unit 211, a subject information output unit 213, a subject information acquisition unit 214, and a corneal endothelial cell density estimation unit 217. Compared to the configuration of the management server 2 in the first embodiment, the anterior chamber depth estimation unit 215 is omitted and the corneal endothelial cell density estimation unit 217 is added. In the third embodiment as well, the management server 2 may also include an anterior chamber depth estimation unit 215 and a turbidity estimation unit 216. 【0047】 The learning model stored in the learning model storage unit 231 in the third embodiment can be created by learning through machine learning using eye images and corneal endothelial cell density (hereinafter referred to as corneal endothelial cell density) as training data. The learning model can also be created by learning through machine learning using eye images, corneal endothelial cell density, and at least one of age and sex as training data. 【0048】 The subject information stored in the subject information storage unit 231 may also include the estimated value of corneal endothelial cell density estimated by the corneal endothelial cell density estimation unit 217, which will be described later. 【0049】 The subject information output by the subject information output unit 213 includes the estimated corneal endothelial cell density. 【0050】 The subject information acquisition unit 214 acquires subject information. The subject information acquired by the subject information acquisition unit 214 does not need to include corneal endothelial cell density. For example, the subject information acquisition unit 214 can receive values ​​for each item included in the subject information, such as the subject's name, address, age, and gender, from the subject terminal 1 and register them as subject information in the subject information storage unit 231. The subject information may also include the refractive values ​​of the subject's eye (spherical power, cylindrical power, equivalent spherical power, astigmatism axis, etc.). 【0051】 The corneal endothelial cell density estimation unit 217 estimates the corneal endothelial cell density of the subject. The corneal endothelial cell density estimation unit 217 can estimate the subject's corneal endothelial cell density by providing the acquired captured images to the learning model stored in the learning model memory unit 231. 【0052】 The corneal endothelial cell density estimation unit 217 may estimate the corneal endothelial cell density of a subject by providing the learning model stored in the learning model storage unit 231 with the acquired captured image and at least one of the subject information items stored in the subject information storage unit 231. For example, the corneal endothelial cell density estimation unit 217 can estimate the corneal endothelial cell density of a subject by providing the learning model stored in the learning model storage unit 231 with the acquired captured image and at least one of the subject information's age and sex. 【0053】 As described above, the information processing system according to the third embodiment makes it possible to estimate the corneal endothelial cell density of a subject from an image of the subject's eye. 【0054】 Furthermore, the system may include information in the subject information indicating whether or not the subject wears contact lenses, and a message sending unit may be provided to send a message to subjects wearing contact lenses prompting them to undergo a corneal endothelial cell density test. The message sending unit can send the message periodically, or after a predetermined period following user registration or the last corneal endothelial cell density test, to encourage regular monitoring of the corneal endothelial cell density status. 【0055】 The disclosure according to the third embodiment may include the following configurations. [Item 1] An image acquisition unit that acquires images of the subject's eyes, A corneal endothelial cell density estimation unit estimates the corneal endothelial cell density of the subject by providing the acquired captured image to a learning model that has been trained by machine learning using eye images and corneal endothelial cell density as training data. An information processing system characterized by comprising the following features. [Item 2] The information processing system described in item 1, The system includes a subject information storage unit that stores at least one of the subject's age and gender, The aforementioned learning model was trained by machine learning using the eye image, the corneal endothelial cell density, and at least one of the age and sex as training data. The anterior chamber corneal endothelial cell density estimation unit estimates the corneal endothelial cell density of the subject by providing the learning model with the acquired captured image and at least one of the subject's age and sex stored in the subject information storage unit. An information processing system characterized by the following. [Item 3] The steps include: obtaining images of the subject's eyes, The process involves a step of estimating the corneal endothelial cell density of the subject by providing the acquired captured images to a machine learning model that has been trained using eye images and corneal endothelial cell density as training data, and An information processing method characterized by a computer executing the following. [Item 4] The steps include: obtaining images of the subject's eyes, The process involves a step of estimating the corneal endothelial cell density of the subject by providing the acquired captured images to a machine learning model that has been trained using eye images and corneal endothelial cell density as training data, and A program that causes a computer to execute something. 【0056】 Although these embodiments have been described above, they are intended to facilitate understanding of the present invention and are not intended to limit its interpretation. The present invention can be modified and improved without departing from its spirit, and equivalents thereof are also included. [Explanation of symbols] 【0057】 1. Subject's terminal 2 Management Server

Claims

[Claim 1] An image acquisition unit that acquires images of the subject's eyes, An anterior chamber depth estimation unit estimates the anterior chamber depth of the subject by providing the acquired captured images to a learning model that has been trained by machine learning using eye images and anterior chamber depth as training data. A subject information storage unit that stores at least one of the subject's age and gender, Equipped with, The aforementioned learning model was trained by machine learning using the eye image, the anterior chamber depth, and at least one of the age and sex as training data. The anterior chamber depth estimation unit estimates the anterior chamber depth of the subject by providing the learning model with the acquired captured image and at least one of the subject's age and gender stored in the subject information storage unit. An information processing system characterized by the following. [Claim 2] An image acquisition unit that acquires images of the subject's eyes, An anterior chamber depth estimation unit estimates the anterior chamber depth of the subject by providing the acquired captured images to a learning model that has been trained by machine learning using eye images and anterior chamber depth as training data. A subject information storage unit that stores the refractive value of the subject's eye, Equipped with, The aforementioned learning model was trained using machine learning with the image of the eye, the anterior chamber depth, and the refractive value as training data. The anterior chamber depth estimation unit estimates the anterior chamber depth of the subject by providing the acquired image and the refractive value stored in the subject information storage unit to the learning model. An information processing system characterized by the following. [Claim 3] The steps include: obtaining images of the subject's eyes, The process involves a step of estimating the anterior chamber depth of the subject by providing the acquired captured images to a machine learning model that has been trained using eye images and anterior chamber depth as training data, and The steps include storing at least one of the subject's age and sex in the subject information storage unit, The computer executes this, The aforementioned learning model was trained by machine learning using the eye image, the anterior chamber depth, and at least one of the age and sex as training data. An information processing method characterized in that, in the step of estimating the anterior chamber depth, the computer provides the learning model with the acquired captured image and at least one of the age and sex stored in the subject information storage unit to estimate the anterior chamber depth of the subject. [Claim 4] The steps include: obtaining images of the subject's eyes, The process involves a step of estimating the anterior chamber depth of the subject by providing the acquired captured images to a machine learning model that has been trained using eye images and anterior chamber depth as training data, and The steps include storing the refractive value of the subject's eye in the subject information storage unit, The computer executes this, The aforementioned learning model was trained using machine learning with the image of the eye, the anterior chamber depth, and the refractive value as training data. In the step of estimating the anterior chamber depth, the computer provides the learning model with the acquired image and the refractive value stored in the subject information storage unit to estimate the anterior chamber depth of the subject. An information processing method characterized by the following. [Claim 5] The steps include: obtaining images of the subject's eyes, The process involves a step of estimating the anterior chamber depth of the subject by providing the acquired captured images to a machine learning model that has been trained using eye images and anterior chamber depth as training data, and The steps include storing at least one of the subject's age and sex in the subject information storage unit, A program that causes a computer to execute, The aforementioned learning model was trained by machine learning using the eye image, the anterior chamber depth, and at least one of the age and sex as training data. In the step of estimating the anterior chamber depth, the computer is instructed to provide the learning model with the acquired captured image and at least one of the age and sex stored in the subject information storage unit to estimate the anterior chamber depth of the subject. A program characterized by the following. [Claim 6] The steps include: obtaining images of the subject's eyes, The process involves a step of estimating the anterior chamber depth of the subject by providing the acquired captured images to a machine learning model that has been trained using eye images and anterior chamber depth as training data, and The steps include storing the refractive value of the subject's eye in the subject information storage unit, A program that causes a computer to execute, The aforementioned learning model was trained using machine learning with the image of the eye, the anterior chamber depth, and the refractive value as training data. In the step of estimating the anterior chamber depth, the computer is instructed to provide the learning model with the acquired captured image and the refractive value stored in the subject information storage unit to estimate the anterior chamber depth of the subject. A program characterized by the following.

Images