JP7570229B2 - Machine learning execution program, dry eye test program, machine learning execution device, and dry eye test device - Google Patents

Description

The present invention relates to a machine learning execution program, a dry eye test program, a machine learning execution device, and a dry eye test device.

Currently, especially in developed countries, electronic devices equipped with displays, such as personal computers, smartphones, and tablets, are becoming widespread, and as a result, the number of people who are aware of eye problems is rapidly increasing. Furthermore, due to the increase in online services via the Internet and the increase in companies promoting teleworking, the number of people who are aware of eye problems is expected to increase further.

One example of an eye disorder that is relatively frequently caused by such lifestyle habits is dry eye caused by meibomian gland dysfunction. Research has also shown that approximately 70% of people over the age of 40 suffer from meibomian gland dysfunction, making care for meibomian gland dysfunction important in maintaining eye health.

For example, to check for the presence or absence and severity of meibomian gland dysfunction, an ophthalmologist must use an optical interferometer to evaluate the thickness of the tear lipid layer. Alternatively, a patient must be examined using the ophthalmic diagnostic support device disclosed in Patent Document 1.

This ophthalmological diagnosis support device includes a case data storage unit, a machine learning unit, a patient data acquisition unit, a comparison judgment unit, and a result display unit. The case data storage unit stores a plurality of case basic image data consisting of a combination of ophthalmological diagnostic image data and diagnosis results. The machine learning unit extracts characteristic image elements and classifies the case basic image data. The patient data acquisition unit acquires patient ophthalmological diagnostic image data of a patient. The comparison judgment unit compares the patient ophthalmological diagnostic image data with the case basic image data and performs a similarity judgment between the data. The result display unit displays the result of the similarity judgment.

JP 2020-036835 A

However, the above-mentioned ophthalmic diagnostic support device requires obtaining ophthalmic diagnostic data using testing equipment used in medical institutions, and therefore cannot easily test for the presence or severity of dry eye in people who are aware of eye problems.

The present invention has been made in consideration of the above-mentioned circumstances, and aims to provide a machine learning execution program, a dry eye test program, a machine learning execution device, and a dry eye test device that can predict the results of a test related to dry eye symptoms without actually conducting the test.

One aspect of the present invention is a machine learning execution program that causes a computer to execute a teacher data acquisition function that acquires teacher data in which the problem is training image data showing a training image depicting the eyes of a training subject when the eyes of the training subject are assumed to be illuminated with light having a lower color temperature than the light illuminating the eyes of the training subject, and the answer is training test result data showing the results of a test to examine the thickness of the tear lipid layer in the eyes of the training subject, and a machine learning execution function that inputs the teacher data into a machine learning program and trains the machine learning program.

One aspect of the present invention is the machine learning execution program described above, in which the training data acquisition function acquires the training data in question from training corneal image data showing a training corneal image obtained by cutting out an area depicting at least a portion of the cornea of the eye of the training subject from the training image.

One aspect of the present invention is a dry eye testing program that implements in a computer a data acquisition function for acquiring inference image data showing an inference image depicting the eyes of the inference subject when it is assumed that the eyes of the inference subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the inference subject, and a symptom estimation function for inputting the inference image data into a machine learning program trained using teacher data in which training image data showing training images depicting the eyes of the inference subject when it is assumed that the eyes of the inference subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the training subject is used as a question and training test result data showing the results of a test to examine the thickness of the tear lipid layer in the eyes of the training subject is used as an answer, causing the machine learning program to estimate the symptoms of dry eye appearing in the eyes of the inference subject, and causing the machine learning program to output symptom data showing the symptoms of dry eye appearing in the eyes of the inference subject.

One aspect of the present invention is the dry eye testing program described above, in which the data acquisition function further acquires inference corneal image data indicating an inference corneal image obtained by cutting out an area depicting at least a portion of the cornea of the eye of the inference subject from the inference image, and the symptom estimation function inputs the inference corneal image data to the machine learning program that has been trained using teacher data that targets the training corneal image data indicating a training corneal image obtained by cutting out an area depicting at least a portion of the cornea of the eye of the training subject from the training image, and causes the machine learning program to estimate the dry eye symptoms appearing in the eye of the inference subject.

One aspect of the present invention is a machine learning execution device that includes a training data acquisition unit that acquires training data in which training image data showing training images depicting the eyes of a training subject when the eyes of the training subject are assumed to be illuminated with light having a lower color temperature than the light illuminating the eyes of the training subject is used as a problem, and training test result data showing the results of a test to examine the thickness of the tear lipid layer in the eyes of the training subject is used as an answer, and a machine learning execution unit that inputs the training data into a machine learning program and trains the machine learning program.

One aspect of the present invention is a dry eye testing device that implements in a computer a data acquisition unit that acquires inference image data showing an inference image depicting the eyes of the inference subject when it is assumed that the eyes of the inference subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the inference subject, and a symptom estimation unit that inputs the inference image data into a machine learning program that has been trained using teacher data in which training image data showing training images depicting the eyes of the training subject when it is assumed that the eyes of the training subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the training subject is used as a problem and training test result data showing the results of a test to examine the thickness of the tear lipid layer in the eyes of the training subject is used as an answer, causes the machine learning program to estimate the symptoms of dry eye that are present in the eyes of the inference subject, and causes the machine learning program to output symptom data showing the symptoms of dry eye that are present in the eyes of the inference subject.

One aspect of the present invention is a machine learning execution program that causes a computer to execute a teacher data acquisition function that acquires teacher data in which training corneal image data showing a training corneal image depicting at least a portion of the cornea of the eye of a training subject is used as a question and training test result data showing the results of a test to examine the thickness of the tear lipid layer of the eye of the training subject is used as an answer, and a machine learning execution function that inputs the teacher data into a machine learning program and trains the machine learning program.

One aspect of the present invention is a dry eye testing program that implements in a computer a data acquisition function for acquiring corneal image data for inference that shows a corneal image for inference depicting at least a portion of the cornea of the eye of a subject for inference, and a symptom estimation function for inputting the corneal image data for inference into a machine learning program trained using teacher data in which the corneal image data for inference that shows a corneal image for inference depicting at least a portion of the cornea of the eye of a subject for inference is used as a question and the test result data for inference that shows the results of a test to examine the thickness of the tear lipid layer in the eye of the subject for inference is used as an answer, causing the machine learning program to estimate the symptoms of dry eye that are present in the eye of the subject for inference, and causing the machine learning program to output symptom data that shows the symptoms of dry eye that are present in the eye of the subject for inference.

One aspect of the present invention is a machine learning execution device that includes a training data acquisition unit that acquires training data in which training corneal image data showing a training corneal image depicting at least a portion of the cornea of the eye of a training subject is used as a problem and training test result data showing the results of a test to examine the thickness of the tear lipid layer of the eye of the training subject is used as an answer, and a machine learning execution unit that inputs the training data into a machine learning program and trains the machine learning program.

One aspect of the present invention is a dry eye testing device that includes a data acquisition unit that acquires corneal image data for inference that shows a corneal image for inference depicting at least a part of the cornea of the eye of an inference subject, and a symptom estimation unit that inputs the corneal image data for inference into a machine learning program that has been trained using teacher data in which the corneal image data for inference that shows a corneal image for inference depicting at least a part of the cornea of the eye of a learning subject is used as a question and the learning test result data that shows the result of a test to examine the thickness of the tear lipid layer of the eye of the learning subject is used as an answer, causes the machine learning program to estimate the symptoms of dry eye that are present in the eye of the inference subject, and causes the machine learning program to output symptom data that shows the symptoms of dry eye that are present in the eye of the inference subject.

The present invention makes it possible to predict the results of a test for dry eye symptoms without actually conducting the test.

FIG. 2 is a diagram illustrating an example of a hardware configuration of a machine learning execution device according to the first embodiment. FIG. 2 is a diagram illustrating an example of a software configuration of a machine learning execution program according to the first embodiment. A figure showing an example of a part of an image of the eye of a learning subject that is given priority when the machine learning program of the first embodiment predicts the results of a test regarding the thickness of the tear lipid layer. 4 is a flowchart illustrating an example of processing executed by a machine learning execution program according to the first embodiment. FIG. 1 is a diagram illustrating an example of a hardware configuration of a dry eye test apparatus according to a first embodiment. FIG. 4 is a diagram showing an example of a software configuration of a dry eye test program according to the first embodiment. 5 is a flowchart showing an example of processing executed by a dry eye test program according to the first embodiment. FIG. 11 is a diagram illustrating an example of a hardware configuration of a machine learning execution device according to a second embodiment. A figure showing an example of the software configuration of a machine learning execution program according to the second embodiment. 11 is a flowchart illustrating an example of processing executed by a machine learning execution program according to the second embodiment. FIG. 11 is a diagram illustrating an example of a hardware configuration of a dry eye test apparatus according to a second embodiment. FIG. 11 is a diagram showing an example of a software configuration of a dry eye test program according to the second embodiment. 13 is a flowchart showing an example of processing executed by a dry eye test program according to the second embodiment.

[First embodiment]
First, specific examples of a machine learning execution program, a machine learning execution device, and a machine learning execution method according to the first embodiment will be described with reference to FIGS. 1 to 4.

Figure 1 is a diagram showing an example of the hardware configuration of a machine learning execution device according to the first embodiment. The machine learning execution device 10a shown in Figure 1 is a device that causes the machine learning device 700a to execute machine learning in the learning phase of the machine learning device 700a, which will be described later. As shown in Figure 1, the machine learning execution device 10a also includes a processor 11a, a main memory device 12a, a communication interface 13a, an auxiliary memory device 14a, an input/output device 15a, and a bus 16a.

The processor 11a is, for example, a CPU (Central Processing Unit), and reads and executes the machine learning execution program 100a described below to realize each function of the machine learning execution program 100a. The processor 11a may also read and execute programs other than the machine learning execution program 100a to realize functions necessary to realize each function of the machine learning execution program 100a.

The main memory device 12a is, for example, a RAM (Random Access Memory), and pre-stores the machine learning execution program 100a and other programs that are read and executed by the processor 11a.

The communication interface 13a is an interface circuit for communicating with the machine learning device 700a and other devices via the network NW shown in FIG. 1. The network NW is, for example, a LAN (Local Area Network) or an intranet.

The auxiliary storage device 14a is, for example, a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or a read only memory (ROM).

The input/output device 15a is, for example, an input/output port (Input/Output Port). For example, the keyboard 811a, mouse 812a, and display 910a shown in FIG. 1 are connected to the input/output device 15a. The keyboard 811a and mouse 812a are used, for example, to input data required to operate the machine learning execution device 10a. The display 910a displays, for example, a graphical user interface (GUI) of the machine learning execution device 10a.

The bus 16a connects the processor 11a, the main memory device 12a, the communication interface 13a, the auxiliary memory device 14a, and the input/output device 15a so that they can send and receive data to each other.

Figure 2 is a diagram showing an example of the software configuration of a machine learning execution program according to the first embodiment. The machine learning execution device 10a reads and executes the machine learning execution program 100a using the processor 11a, and realizes the teacher data acquisition function 101a and the machine learning execution function 102a shown in Figure 2.

The teacher data acquisition function 101a acquires teacher data that uses one learning image data as the question and one learning test result data as the answer.

The learning image data is data showing a learning image depicting the eyes of a learning subject when the eyes of the learning subject are assumed to be illuminated with light having a lower color temperature than the light illuminating the eyes of the learning subject. Such a learning image is generated, for example, by adjusting the white balance of an image depicting the eyes of a learning subject that is actually illuminated with light having a color temperature of 4000 K, and is an image that simulates the eyes being illuminated with light having a color temperature of 3000 K. In addition, the learning image is captured, for example, using a camera mounted on a smartphone.

The learning test result data constitutes part of the answers to the training data, and is data showing the results of tests related to dry eye symptoms. Such test results include, for example, a numerical value between 0 and 1 that represents the thickness of the tear lipid layer based on a test that uses an optical interferometer to evaluate the thickness of the tear lipid layer.

If this value is greater than or equal to 0 and less than 0.5, the tear lipid layer thickness evaluated using the optical interferometer is less than 75 μm, indicating that the study subject's eyes are normal and no examination by an ophthalmologist is necessary. If this value is greater than or equal to 0.5 and less than or equal to 1, the tear lipid layer thickness evaluated using the optical interferometer is 75 μm or more, indicating that the study subject's eyes are abnormal and no examination by an ophthalmologist is necessary.

For example, the teacher data acquisition function 101a acquires 1280 pieces of teacher data. In this case, the 1280 pieces of training image data represent 1280 training images acquired by performing 4 sets of processing in which each of the two eyes of eight training subjects is photographed 20 times using a camera mounted on a smartphone. Also, in this case, the 1280 pieces of training test result data represent 1280 numerical values between 0 and 1 indicating the thickness of the tear lipid layer evaluated using an optical interferometer.

In the following explanation, an example will be given in which the 1,280 pieces of learning test result data include 600 pieces of learning test result data showing a value between 0 and less than 0.5, indicating that the learning subject's eyes are normal, and 680 pieces of learning test result data showing a value between 0.5 and 1, indicating that the learning subject's eyes are abnormal.

The machine learning execution function 102a inputs training data into the machine learning program 750a implemented in the machine learning device 700a, and trains the machine learning program 750a. For example, the machine learning execution function 102a trains the machine learning program 750a, which includes a convolutional neural network (CNN), by backpropagation.

For example, the machine learning execution function 102a inputs 520 pieces of training data, including training test result data showing values between 0 and less than 0.5, indicating that the eyes of the training subject are normal, into the machine learning program 750a. These 520 pieces of training data are training data obtained from seven people selected from the eight people mentioned above.

Also, for example, the machine learning execution function 102a inputs 600 pieces of training data, including training test result data showing a numerical value between 0.5 and 1, indicating that the training subject's eyes are abnormal, into the machine learning program 750a. These 600 pieces of training data are training data obtained from seven people selected from the eight people described above.

Then, the machine learning execution function 102a trains the machine learning program 750a using these 1,120 pieces of training data.

Also, for example, the machine learning execution function 102a may represent that the eyes of the training subject are normal, and 80 pieces of training data that were not used in the training of the machine learning program 750a may be input to the machine learning program 750a as test data. These 80 pieces of training data are training data obtained from one person who was not selected as one of the seven people mentioned above.

Also, for example, the machine learning execution function 102a may indicate that the eyes of the training subject are abnormal, and 80 pieces of training data that were not used in the training of the machine learning program 750a may be input to the machine learning program 750a as test data. These 80 pieces of training data are training data obtained from one person who was not selected as one of the seven people mentioned above.

As a result, the machine learning execution function 102a may evaluate the characteristics of the machine learning program 750a obtained by training the machine learning program 750a using the above-mentioned 1,080 pieces of teacher data.

The machine learning execution function 102a may use, for example, class activation mapping (CAM) when using test data to evaluate the characteristics of the machine learning program 750a. Class activation mapping is a technique that clarifies the part of the data input to a neural network that is the basis for the results output by the neural network. An example of class activation mapping is gradient-weighted class activation mapping. Gradient-weighted class activation mapping is a technique that uses the gradient of the classification score related to the features of the convolution executed by the convolutional neural network to identify areas of the image input to the convolutional neural network that have had a certain degree of influence on the classification.

3 is a diagram showing an example of a portion of the image of the eye of the training subject that is considered intensively when the machine learning program according to the first embodiment predicts the results of the test on the thickness of the tear film lipid layer. For example, the machine learning execution function 102a uses gradient-weighted class activation mapping to evaluate that the area surrounded by the ellipse C in FIG. 3 in the training image shown in FIG. 3 has a certain degree of influence on the prediction of the results of the test on the thickness of the tear film lipid layer by the machine learning program 750a. In addition, the three-level grayscale included in the area surrounded by the ellipse C in FIG. 3 indicates the degree of influence on the prediction of the results of the test on the thickness of the tear film lipid layer, and is displayed superimposed on the area depicting the part of the cornea of the training subject's eye close to the lower eyelid. Furthermore, this grayscale is superimposed on approximately half of the cornea of the training subject's eye on the lower eyelid side.

Next, an example of processing executed by the machine learning execution program 100a according to the first embodiment will be described with reference to FIG. 4. FIG. 4 is a flowchart showing an example of processing executed by the machine learning execution program according to the first embodiment. The machine learning execution program 100a executes the processing shown in FIG. 4 at least once.

In step S11, the teacher data acquisition function 101a acquires teacher data in which the learning image data is the question and the learning test result data is the answer.

In step S12, the machine learning execution function 102a inputs the training data into the machine learning program 750a and causes the machine learning program 750a to learn.

Next, specific examples of the dry eye test program, dry eye test device, and dry eye test method according to the first embodiment will be described with reference to Figures 5 to 7.

Figure 5 is a diagram showing an example of the hardware configuration of a dry eye test device according to the first embodiment. The dry eye test device 20a shown in Figure 5 is a device that estimates dry eye symptoms appearing in the eye of an inference subject using a machine learning device 700a in the inference phase of the machine learning device 700a that has been trained by a machine learning execution program 100a. As shown in Figure 5, the dry eye test device 20a also includes a processor 21a, a main memory device 22a, a communication interface 23a, an auxiliary memory device 24a, an input/output device 25a, and a bus 26a.

The processor 21a is, for example, a CPU, and reads and executes the dry eye test program 200a described below to realize each function of the dry eye test program 200a. The processor 21a may also read and execute a program other than the dry eye test program 200a to realize functions necessary to realize each function of the dry eye test program 200a.

The main memory device 22a is, for example, a RAM, and prestores the dry eye test program 200a and other programs that are read and executed by the processor 21a.

The communication interface 23a is an interface circuit for communicating with the machine learning device 700a and other devices via the network NW shown in FIG. 5. The network NW is, for example, a LAN or an intranet.

The auxiliary storage device 24a is, for example, a hard disk drive, a solid state drive, a flash memory, or a ROM.

The input/output device 25a is, for example, an input/output port. For example, the keyboard 821a, mouse 822a, and display 920a shown in FIG. 5 are connected to the input/output device 25a. The keyboard 821a and mouse 822a are used, for example, to input data required to operate the dry eye test device 20a. The display 920a displays, for example, a graphical user interface of the dry eye test device 20a.

The bus 26a connects the processor 21a, the main memory device 22a, the communication interface 23a, the auxiliary memory device 24a, and the input/output device 25a so that data can be sent and received among them.

Figure 6 is a diagram showing an example of the software configuration of a dry eye test program according to the first embodiment. The dry eye test device 20a reads and executes the dry eye test program 200a using the processor 21a, and realizes the data acquisition function 201a and the symptom estimation function 202a shown in Figure 6.

The data acquisition function 201a acquires image data for inference. The image data for inference is data showing an image for inference depicting the eyes of the subject for inference when it is assumed that the eyes of the subject for inference are illuminated with light having a lower color temperature than the light illuminating the eyes of the subject for inference. Such an image for inference is generated, for example, by adjusting the white balance of an image depicting the eyes of the subject for inference that are actually illuminated with light having a color temperature of 4000 K, and is an image that simulates the eyes illuminated with light having a color temperature of 3000 K. The image for inference is also captured, for example, using a camera mounted on a smartphone.

The symptom estimation function 202a inputs image data for inference to the machine learning program 750a that has been trained by the machine learning execution function 102a, and causes the machine learning program 750a to estimate the symptoms of dry eye appearing in the eye of the subject for inference. For example, the symptom estimation function 202a inputs image data for inference to the machine learning program 750a, and causes the program to estimate a numerical value representing the thickness of the tear lipid layer in the eye of the subject for inference.

The symptom estimation function 202a then causes the machine learning program 750a to output symptom data indicating the symptoms of dry eye appearing in the eye of the subject to be inferred. For example, the symptom estimation function 202a causes the machine learning program 750a to output symptom data indicating a numerical value indicating the thickness of the tear lipid layer in the eye of the subject to be inferred. In this case, the symptom data is, for example, indicated by the function itself, and is used to display a numerical value indicating the thickness of the tear lipid layer in the eye of the subject to be inferred on the display 920a.

Next, an example of processing executed by the dry eye test program 200a according to the first embodiment will be described with reference to FIG. 7. FIG. 7 is a flowchart showing an example of processing executed by the dry eye test program according to the first embodiment.

In step S21, the data acquisition function 201a acquires image data for inference.

In step S22, the symptom estimation function 202a inputs the inference image data to the trained machine learning program 750a, estimates the symptoms of dry eye appearing in the eyes of the inference subject, and causes the machine learning program 750a to output symptom data indicating the symptoms of dry eye appearing in the eyes of the inference subject.

The above describes the machine learning execution program, dry eye test program, machine learning execution device, dry eye test device, machine learning execution method, and dry eye test method according to the first embodiment.

The machine learning execution program 100a includes a teacher data acquisition function 101a and a machine learning execution function 102a.

The teacher data acquisition function 101a acquires teacher data in which the training image data is the question and the training test result data is the answer. The training image data is data showing a training image depicting the training subject's eyes when it is assumed that the training subject's eyes are illuminated with light having a lower color temperature than the light illuminating the training subject's eyes. The training test result data is data showing the results of a test to examine the thickness of the tear lipid layer in the training subject's eyes.

The machine learning execution function 102a inputs the training data into the machine learning program 750a and causes the machine learning program 750a to learn.

This allows the machine learning execution program 100a to generate a machine learning program 750a that predicts the results of a test regarding dry eye symptoms based on the learning image data.

The dry eye test program 200a includes a data acquisition function 201a and a symptom estimation function 202a.

The data acquisition function 201a acquires image data for inference. The image data for inference is data showing an image for inference depicting the eyes of the subject for inference when it is assumed that the eyes of the subject for inference are illuminated with light having a lower color temperature than the light illuminating the eyes of the subject for inference.

The symptom estimation function 202a inputs image data for inference to the machine learning program 750a that has been trained by the machine learning execution program 100a, and estimates the symptoms of dry eye appearing in the eyes of the subject for inference. The symptom estimation function 202a then causes the machine learning program 750a to output symptom data indicating the symptoms of dry eye appearing in the eyes of the subject for inference.

This allows the dry eye test program 200a to predict the results of a test regarding dry eye symptoms without actually conducting the test.

Next, we will provide an example in which the machine learning program 750a was actually trained to estimate symptoms of dry eye, and explain specific examples of the effects achieved by the machine learning execution program 100a by comparing a comparative example with an example according to the first embodiment.

In this comparative example, the problem is that the training data contains not training image data, but image data showing an image depicting the training subject's eyes when the training subject's eyes are illuminated with light having the same color temperature as the light illuminating the training subject's eyes. Also, in this comparative example, a machine learning program is trained using 520 pieces of training data representing that the training subject's eyes are normal and 600 pieces of training data representing that the training subject's eyes are abnormal.

The machine learning program trained in this way showed a prediction accuracy of 50% and a false negative rate of 50% when its characteristics were evaluated using 80 test data sets that included the image data described above and indicated that the eyes of the training subjects were normal, and 80 test data sets that included the image data described above and indicated that the eyes of the training subjects were abnormal.

On the other hand, when the characteristics of the machine learning program 750a trained by the machine learning execution program 100a were evaluated using test data containing learning image data, the prediction accuracy was 74% and the false negative rate was 26%. These characteristics exceed those of the machine learning program according to the comparative example.

The prediction accuracy is the ratio of the total number X+Y of the training images in the abnormal group that were predicted to be abnormal by the machine learning program and the number Y of the training images in the normal group that were predicted to be normal by the machine learning program to the total number of test data. Therefore, in this comparative example, the prediction accuracy is calculated as ((X+Y)/160)×100.

The false negative rate is the ratio of the number of training images in the abnormal group that are predicted to be normal by the machine learning program to the total number of training images in the abnormal group. Therefore, in this comparative example, the false negative rate is calculated as ((80-X)/80) x 100.

At least a part of the functions of the machine learning execution program 100a may be realized by hardware including a circuitry. Similarly, at least a part of the functions of the dry eye test program 200a may be realized by hardware including a circuitry. Examples of such hardware include a large scale integration (LSI), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), and a graphics processing unit (GPU).

In addition, at least some of the functions of the machine learning execution program 100a may be realized by a combination of software and hardware. Similarly, at least some of the functions of the dry eye test program 200a may be realized by a combination of software and hardware. In addition, these pieces of hardware may be integrated into one, or may be divided into multiple pieces.

In the first embodiment, the machine learning execution device 10a, the machine learning device 700a, and the dry eye test device 20a are independent devices, but this is not limiting. These devices may be realized as a single device.

[Second embodiment]
First, specific examples of a machine learning execution program, a machine learning execution device, and a machine learning execution method according to the second embodiment will be described with reference to Figures 8 to 10. Unlike the machine learning execution program, the machine learning execution device, and the machine learning execution method according to the first embodiment, the machine learning execution program, the machine learning execution device, and the machine learning execution method according to the second embodiment use teacher data including corneal image data for learning, which will be described later, as a problem, instead of image data for learning.

Figure 8 is a diagram showing an example of the hardware configuration of a machine learning execution device according to the second embodiment. The machine learning execution device 10b shown in Figure 8 is a device that causes the machine learning device 700b to execute machine learning in the learning phase of the machine learning device 700b, which will be described later. As shown in Figure 8, the machine learning execution device 10b also includes a processor 11b, a main memory device 12b, a communication interface 13b, an auxiliary memory device 14b, an input/output device 15b, and a bus 16b.

The processor 11b is, for example, a CPU, and reads and executes the machine learning execution program 100b described below to realize each function of the machine learning execution program 100b. The processor 11b may also read and execute programs other than the machine learning execution program 100b to realize functions necessary to realize each function of the machine learning execution program 100b.

The main memory device 12b is, for example, a RAM, and pre-stores the machine learning execution program 100b and other programs that are read and executed by the processor 11b.

The communication interface 13b is an interface circuit for communicating with the machine learning device 700b and other devices via the network NW shown in FIG. 8. The network NW is, for example, a LAN or an intranet.

The auxiliary storage device 14b is, for example, a hard disk drive, a solid state drive, a flash memory, or a ROM.

The input/output device 15b is, for example, an input/output port. For example, the keyboard 811b, mouse 812b, and display 910b shown in FIG. 1 are connected to the input/output device 15b. The keyboard 811b and mouse 812b are used, for example, to input data necessary to operate the machine learning execution device 10b. The display 910b displays, for example, a graphical user interface of the machine learning execution device 10b.

The bus 16b connects the processor 11b, the main memory device 12b, the communication interface 13b, the auxiliary memory device 14b, and the input/output device 15b so that data can be sent and received among them.

Figure 9 is a diagram showing an example of the software configuration of a machine learning execution program according to the second embodiment. The machine learning execution device 10b reads and executes the machine learning execution program 100b using the processor 11b, and realizes the teacher data acquisition function 101b and the machine learning execution function 102b shown in Figure 9.

The teacher data acquisition function 101b acquires teacher data that uses one piece of learning corneal image data as the question and one piece of learning test result data as the answer.

The training corneal image data is data showing a training corneal image depicting at least a portion of the cornea of the training subject's eye. The training corneal image may be an image depicting only at least a portion of the cornea of the training subject's eye, or an image depicting parts of the training subject's eye other than the cornea. The training corneal image may also be an image obtained by cutting out an area depicting at least a portion of the cornea of the training subject's eye from a training image depicting the training subject's eye.

Furthermore, the prediction accuracy of the machine learning program 750b may be improved when the training corneal image depicts only the portion of the cornea of the training subject's eye close to the lower eyelid, rather than depicting both the portion of the cornea of the training subject's eye close to the upper eyelid and the portion close to the lower eyelid. For example, when the training corneal image depicts only the half of the cornea of the training subject's eye on the lower eyelid side, the prediction accuracy of dry eye symptoms using the machine learning program 750b may be further improved. Note that the training corneal image is captured, for example, using a camera mounted on a smartphone.

The learning test result data constitutes part of the answers to the training data, and is data showing the results of tests related to dry eye symptoms. Such test results include, for example, a numerical value between 0 and 1 that represents the thickness of the tear lipid layer based on a test that uses an optical interferometer to evaluate the thickness of the tear lipid layer.

If this value is greater than or equal to 0 and less than 0.5, the tear lipid layer thickness evaluated using the optical interferometer is less than 75 μm, indicating that the study subject's eyes are normal and no examination by an ophthalmologist is necessary. If this value is greater than or equal to 0.5 and less than or equal to 1, the tear lipid layer thickness evaluated using the optical interferometer is 75 μm or more, indicating that the study subject's eyes are abnormal and no examination by an ophthalmologist is necessary.

For example, the teacher data acquisition function 101b acquires 1280 pieces of teacher data. In this case, the 1280 pieces of training corneal image data represent 1280 training images acquired by performing four sets of processing in which each of the two eyes of eight training subjects is photographed 20 times using a camera mounted on a smartphone. Also, in this case, the 1280 pieces of training test result data represent 1280 numerical values between 0 and 1 indicating the thickness of the tear lipid layer evaluated using an optical interferometer.

In the following explanation, an example will be given in which the 1,280 pieces of learning test result data include 600 pieces of learning test result data showing a value between 0 and less than 0.5, indicating that the learning subject's eyes are normal, and 680 pieces of learning test result data showing a value between 0.5 and 1, indicating that the learning subject's eyes are abnormal.

The machine learning execution function 102b inputs training data to the machine learning program 750b implemented in the machine learning device 700b, and trains the machine learning program 750b. For example, the machine learning execution function 102b trains the machine learning program 750b, which includes a convolutional neural network, by backpropagation.

For example, the machine learning execution function 102b inputs 520 pieces of training data including training test result data showing a value between 0 and less than 0.5, indicating that the eyes of the training subject are normal, into the machine learning program 750b. These 520 pieces of training data are training data obtained from seven people selected from the eight people mentioned above.

Also, for example, the machine learning execution function 102b inputs 600 pieces of training data, including training test result data showing a numerical value between 0.5 and 1, indicating that the training subject's eyes are abnormal, into the machine learning program 750b. These 600 pieces of training data are training data obtained from seven people selected from the eight people described above.

Then, the machine learning execution function 102b trains the machine learning program 750b using these 1,120 pieces of training data.

The machine learning execution function 102b may also preferentially input to the machine learning program training data that includes training corneal image data showing a training corneal image depicting a portion of the cornea of the training subject's eye that is closer to the training subject's lower eyelid. This is because, as described above, the prediction accuracy of the machine learning program 750b can be improved when the training corneal image depicts only a portion of the cornea of the training subject that is closer to the lower eyelid than when the training corneal image depicts both a portion of the cornea of the training subject's eye that is closer to the training subject's upper eyelid and a portion of the cornea of the training subject that is closer to the lower eyelid.

Also, for example, the machine learning execution function 102b may represent that the eyes of the training subject are normal, and 80 pieces of training data that were not used in the training of the machine learning program 750b may be input to the machine learning program 750b as test data. These 80 pieces of training data are training data obtained from one person who was not selected as one of the seven people mentioned above.

Also, for example, the machine learning execution function 102b may indicate that the eyes of the training subject are abnormal, and 80 pieces of training data that were not used in the training of the machine learning program 750b may be input to the machine learning program 750b as test data. These 80 pieces of training data are training data obtained from one person who was not selected as one of the seven people mentioned above.

As a result, the machine learning execution function 102b may evaluate the characteristics of the machine learning program 750b obtained by training the machine learning program 750b using the above-mentioned 1,080 pieces of teacher data.

The machine learning execution function 102b may use, for example, class activation mapping when using test data to evaluate the characteristics of the machine learning program 750b. Class activation mapping is a technique that clarifies the part of the data input to a neural network that is the basis for the results output by the neural network. An example of class activation mapping is gradient-weighted class activation mapping. Gradient-weighted class activation mapping is a technique that uses the gradient of the classification score related to the features of the convolution performed by the convolutional neural network to identify areas of the image input to the convolutional neural network that have had a certain level of influence on the classification.

Next, an example of processing executed by the machine learning execution program 100b according to the second embodiment will be described with reference to FIG. 10. FIG. 10 is a flowchart showing an example of processing executed by the machine learning execution program according to the second embodiment. The machine learning execution program 100b executes the processing shown in FIG. 10 at least once.

In step S31, the teacher data acquisition function 101b acquires teacher data in which the learning corneal image data is the question and the learning test result data is the answer.

In step S32, the machine learning execution function 102b inputs the training data into the machine learning program 750b and causes the machine learning program 750b to learn.

Next, a specific example of a dry eye testing program, a dry eye testing device, and a dry eye testing method according to the second embodiment will be described with reference to Figures 11 to 13. Unlike the dry eye testing program, the dry eye testing device, and the dry eye testing method according to the first embodiment, the dry eye testing program, the dry eye testing device, and the dry eye testing method according to the second embodiment acquires corneal image data for inference, which will be described later, instead of image data for inference.

Fig. 11 is a diagram showing an example of the hardware configuration of a dry eye test device according to the second embodiment. The dry eye test device 20b shown in Fig. 11 is a device that estimates dry eye symptoms appearing in the eye of an inference subject using a machine learning device 700b in the inference phase of the machine learning device 700b that has been trained by a machine learning execution program 100b. As shown in Fig. 11, the dry eye test device 20b also includes a processor 21b, a main memory device 22b, a communication interface 23b, an auxiliary memory device 24b, an input/output device 25b, and a bus 26b.

The processor 21b is, for example, a CPU, and reads and executes the dry eye test program 200b described below to realize each function of the dry eye test program 200b. The processor 21b may also read and execute a program other than the dry eye test program 200b to realize functions necessary to realize each function of the dry eye test program 200b.

The main memory device 22b is, for example, a RAM, and prestores the dry eye test program 200b and other programs that are read and executed by the processor 21b.

The communication interface 23b is an interface circuit for communicating with the machine learning device 700b and other devices via the network NW shown in FIG. 11. The network NW is, for example, a LAN or an intranet.

The auxiliary storage device 24b is, for example, a hard disk drive, a solid state drive, a flash memory, or a ROM.

The input/output device 25b is, for example, an input/output port. For example, the keyboard 821b, mouse 822b, and display 920b shown in FIG. 11 are connected to the input/output device 25b. The keyboard 821b and mouse 822b are used, for example, to input data required to operate the dry eye test device 20b. The display 920b displays, for example, a graphical user interface of the dry eye test device 20b.

The bus 26b connects the processor 21b, the main memory device 22b, the communication interface 23b, the auxiliary memory device 24b, and the input/output device 25b so that data can be sent and received among them.

Figure 12 is a diagram showing an example of the software configuration of a dry eye test program according to the second embodiment. The dry eye test device 20b reads and executes the dry eye test program 200b using the processor 21b, and realizes the data acquisition function 201b and the symptom estimation function 202b shown in Figure 12.

The data acquisition function 201b acquires corneal image data for inference. The corneal image data for inference is data showing an inference corneal image depicting at least a portion of the cornea of the eye of the subject for inference. The corneal image for inference may be an image depicting only at least a portion of the cornea of the eye of the subject for inference, or an image depicting parts of the eye of the subject for inference other than the cornea. The corneal image for inference may also be an image cut out of an area depicting at least a portion of the cornea of the eye of the subject for inference from an inference image depicting the eye of the subject for inference.

In addition, when the machine learning program 750b learns using training data that has as its problem training corneal image data showing a training corneal image depicting only a portion close to the lower eyelid of the training subject, it is preferable that the inference corneal image depict only a portion close to the lower eyelid of the training subject. This enables the dry eye test program 200a to predict the dry eye symptoms of the inference subject with even higher accuracy using the machine learning program 750b. For example, when the inference corneal image depicts only the half of the cornea of the inference subject's eye on the lower eyelid side, the prediction accuracy of the dry eye symptoms using the machine learning program 750b can be further improved. Note that the inference corneal image is captured, for example, using a camera mounted on a smartphone.

The symptom estimation function 202b inputs the corneal image data for inference to the machine learning program 750b that has been trained by the machine learning execution function 102b, and causes the machine learning program 750b to estimate the symptoms of dry eye appearing in the eye of the subject for inference. For example, the symptom estimation function 202b inputs the corneal image data for inference to the machine learning program 750b, and causes the program to estimate a numerical value representing the thickness of the tear lipid layer in the eye of the subject for inference.

The symptom estimation function 202b may also input the inference corneal image data to the machine learning program, which is given higher priority when the training data includes training corneal image data showing a training corneal image depicting a portion of the cornea of the training subject's eye that is closer to the training subject's lower eyelid.

Then, the symptom estimation function 202b causes the machine learning program 750b to output symptom data indicating the symptoms of dry eye appearing in the eye of the subject to be inferred. For example, the symptom estimation function 202b causes the machine learning program 750b to output symptom data indicating a numerical value indicating the thickness of the tear lipid layer in the eye of the subject to be inferred. In this case, the symptom data is, for example, indicated by itself and is used to display a numerical value indicating the thickness of the tear lipid layer in the eye of the subject to be inferred on the display 920b.

Next, an example of processing executed by the dry eye test program 200b according to the second embodiment will be described with reference to FIG. 13. FIG. 13 is a flowchart showing an example of processing executed by the dry eye test program according to the second embodiment.

In step S41, the data acquisition function 201b acquires corneal image data for inference.

In step S42, the symptom estimation function 202b inputs the corneal image data for inference into the trained machine learning program 750b, estimates the symptoms of dry eye appearing in the eye of the inference subject, and causes the machine learning program 750b to output symptom data indicating the symptoms of dry eye appearing in the eye of the inference subject.

The above describes the machine learning execution program, dry eye test program, machine learning execution device, dry eye test device, machine learning execution method, and dry eye test method according to the second embodiment.

The machine learning execution program 100b includes a teacher data acquisition function 101b and a machine learning execution function 102b.

The teacher data acquisition function 101b acquires teacher data in which the training corneal image data is the question and the training test result data is the answer. The training corneal image data is data showing a training corneal image depicting at least a portion of the cornea of the training subject's eye. The training test result data is data showing the results of a test to examine the thickness of the tear lipid layer of the training subject's eye.

The machine learning execution function 102b inputs the training data into the machine learning program 750b and causes the machine learning program 750b to learn.

This allows the machine learning execution program 100b to generate a machine learning program 750b that predicts the results of a test regarding dry eye symptoms based on the training corneal image data.

In addition, the machine learning execution program 100b may input to the machine learning program with a higher priority the more training data it contains, such as training corneal image data that shows a training corneal image depicting a portion of the cornea of the training subject's eye that is closer to the training subject's lower eyelid.

This enables the machine learning execution program 100b to generate a machine learning program 750b that predicts the results of tests related to dry eye symptoms with greater accuracy based on the training corneal image data.

The dry eye test program 200b includes a data acquisition function 201b and a symptom estimation function 202b.

The data acquisition function 201b acquires inference corneal image data. The inference corneal image data is data that represents an inference corneal image depicting at least a portion of the cornea of the eye of the inference subject.

The symptom estimation function 202b inputs the inference corneal image data to the machine learning program 750b that has been trained by the machine learning execution program 100b, and estimates the symptoms of dry eye appearing in the eye of the inference subject. The symptom estimation function 202b then causes the machine learning program 750b to output symptom data indicating the symptoms of dry eye appearing in the eye of the inference subject.

This allows the dry eye test program 200b to predict the results of a test for dry eye symptoms without actually conducting the test.

The dry eye test program 200b inputs the inference corneal image data to the machine learning program 750b, which is input with a higher priority, if the teacher data includes learning corneal image data showing a learning corneal image depicting a portion of the cornea of the learning subject's eye that is closer to the learning subject's lower eyelid.The dry eye test program 200b then causes the machine learning program 750b to estimate the dry eye symptoms appearing in the inference subject's eye.

This allows the dry eye test program 200b to more accurately predict the results of a test regarding dry eye symptoms without actually conducting the test.

Next, we will provide an example in which the machine learning program 750b is actually trained to estimate symptoms of dry eye, and explain specific examples of the effects achieved by the machine learning execution program 100b by comparing a comparative example with an example of the second embodiment.

In this comparative example, the problem is that the training data contains image data showing an image depicting the training subject's eye, rather than the training corneal image data. Also, in this comparative example, a machine learning program is trained using 520 pieces of training data representing that the training subject's eye is normal and 600 pieces of training data representing that the training subject's eye is abnormal.

The machine learning program trained in this way showed a prediction accuracy of 50% and a false negative rate of 50% when its characteristics were evaluated using 80 test data sets that included the image data described above and indicated that the eyes of the training subjects were normal, and 80 test data sets that included the image data described above and indicated that the eyes of the training subjects were abnormal.

On the other hand, the machine learning program 750b, which was trained by the machine learning execution program 100b using only training corneal image data depicting only the entire cornea of the training subject's eye, showed a prediction accuracy of 69% and a false negative rate of 31% when its characteristics were evaluated using test data containing similar training corneal image data. These characteristics exceed those of the machine learning program according to the comparative example.

Furthermore, the machine learning program 750b, which was trained by the machine learning execution program 100b using only training corneal image data depicting only the lower eyelid half of the cornea of the training subject's eye, showed a prediction accuracy of 78% and a false negative rate of 22% when its characteristics were evaluated using test data containing similar training corneal image data. These characteristics exceed those of the machine learning program according to the comparative example.

The prediction accuracy is the ratio of the total number X+Y of the training images in the abnormal group that were predicted to be abnormal by the machine learning program and the number Y of the training images in the normal group that were predicted to be normal by the machine learning program to the total number of test data. Therefore, in this comparative example, the prediction accuracy is calculated as ((X+Y)/160)×100.

The false negative rate is the ratio of the number of training images in the abnormal group that are predicted to be normal by the machine learning program to the total number of training images in the abnormal group. Therefore, in this comparative example, the false negative rate is calculated as ((80-X)/80) x 100.

At least a part of the functions of the machine learning execution program 100b may be realized by hardware including a circuit unit. Similarly, at least a part of the functions of the dry eye test program 200b may be realized by hardware including a circuit unit. Such hardware may be, for example, an LSI, an ASIC, an FPGA, or a GPU.

Furthermore, at least some of the functions of the machine learning execution program 100b may be realized by a combination of software and hardware. Similarly, at least some of the functions of the dry eye test program 200b may be realized by a combination of software and hardware. Furthermore, these pieces of hardware may be integrated into one, or may be divided into multiple pieces.

In the second embodiment, the machine learning execution device 10b, the machine learning device 700b, and the dry eye test device 20b are independent devices, but this is not limiting. These devices may be realized as a single device.

[Third embodiment]
In the first embodiment described above, the case where the teacher data acquisition function 101a acquires teacher data that does not include the learning corneal image data described in the second embodiment as a problem has been exemplified, but the present invention is not limited to this. Instead of the learning image data, the teacher data acquisition function 101a may acquire teacher data that includes, as a problem, learning corneal image data depicting the cornea of the learning subject when it is assumed that the eyes of the learning subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the learning subject. In this case, the data acquisition function 201a acquires, instead of the inference image data, inference corneal image data depicting the cornea of the inference subject when it is assumed that the eyes of the inference subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the inference subject. In this case, the symptom estimation function 202a causes the machine learning program 750a to estimate the symptoms of dry eye appearing in the eyes of the inference subject based on inference corneal image data, which depicts the cornea of the inference subject under the assumption that the eyes of the inference subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the inference subject, instead of the inference image data.

In the second embodiment described above, the teacher data acquisition function 101b acquires teacher data that does not include as a problem the learning image data depicting the eyes of the learning subject when it is assumed that the eyes of the learning subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the learning subject described in the first embodiment, but is not limited to this. Instead of the learning corneal image data, the teacher data acquisition function 101b may acquire teacher data that includes as a problem the learning corneal image data depicting the cornea of the learning subject when it is assumed that the eyes of the learning subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the learning subject. In this case, the data acquisition function 201b acquires the inference corneal image data depicting the cornea of the inference subject when it is assumed that the eyes of the inference subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the inference subject. In this case, the symptom estimation function 202b causes the machine learning program 750b to estimate the symptoms of dry eye appearing in the eyes of the inference subject based on the inference corneal image data depicting the cornea of the inference subject when it is assumed that the eyes of the inference subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the inference subject.

Next, we will explain a specific example of the effect achieved when training using teacher data that includes as a problem training corneal image data depicting the cornea of the training subject when it is assumed that the eyes of the training subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the training subject, and estimating the symptoms of dry eye appearing in the eyes of the inference subject based on the inference corneal image data depicting the cornea of the inference subject when it is assumed that the eyes of the inference subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the inference subject. In the following explanation, an example is given in which the teacher data acquisition function 101a acquires learning corneal image data depicting the cornea of the learning subject when it is assumed that the eyes of the learning subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the learning subject, and the data acquisition function 201a acquires inference corneal image data depicting the cornea of the inference subject when it is assumed that the eyes of the inference subject are illuminated with light having a lower color temperature than the light illuminating the eyes of the inference subject.

In this comparative example, the problem is that the training data contains image data showing an image depicting the cornea of the training subject when the training subject's eyes are illuminated with light having the same color temperature as the light illuminating the training subject's eyes, rather than training corneal image data depicting the cornea of the training subject when the training subject's eyes are illuminated with light having a lower color temperature than the light illuminating the training subject's eyes. Also, in this comparative example, a machine learning program is trained using 520 pieces of training data representing that the training subject's eyes are normal and 600 pieces of training data representing that the training subject's eyes are abnormal.

The machine learning program trained in this way showed a prediction accuracy of 50% and a false negative rate of 50% when its characteristics were evaluated using 80 test data sets that included the image data described above and indicated that the eyes of the training subjects were normal, and 80 test data sets that included the image data described above and indicated that the eyes of the training subjects were abnormal.

On the other hand, the machine learning program 750a, trained using training corneal image data depicting only the entire cornea of the training subject's eye when the training subject's eye is assumed to be illuminated with light having a lower color temperature than the light illuminating the training subject's eye, showed a prediction accuracy of 81% and a false negative rate of 15% when its characteristics were evaluated using test data including training corneal image data depicting the cornea of the training subject when the training subject's eye is assumed to be illuminated with light having a lower color temperature than the light illuminating the training subject's eye. This characteristic exceeds the characteristics of the machine learning program according to the comparative example.

Furthermore, the machine learning execution program 100a was trained using training corneal image data depicting only the lower eyelid side half of the cornea of the training subject's eye when it is assumed that the training subject's eye is illuminated with light having a lower color temperature than the light illuminating the training subject's eye. When the characteristics of the machine learning program 750a were evaluated using test data including training corneal image data depicting the cornea of the training subject when it is assumed that the training subject's eye is illuminated with light having a lower color temperature than the light illuminating the training subject's eye, the program showed a prediction accuracy of 89% and a false negative rate of 5%. These characteristics exceed those of the machine learning program according to the comparative example.

The prediction accuracy is the ratio of the total number X+Y of the training images in the abnormal group that were predicted to be abnormal by the machine learning program and the number Y of the training images in the normal group that were predicted to be normal by the machine learning program to the total number of test data. Therefore, in this comparative example, the prediction accuracy is calculated as ((X+Y)/160)×100.

The false negative rate is the ratio of the number of training images in the abnormal group that are predicted to be normal by the machine learning program to the total number of training images in the abnormal group. Therefore, in this comparative example, the false negative rate is calculated as ((80-X)/80) x 100.

The above-mentioned dry eye test program, dry eye test device, and dry eye test method may be used before or after the dry eye eye drops are applied to the eyes of the subject to be inferred. By using the above-mentioned dry eye test program, dry eye test device, and dry eye test method at such timing, they can also serve as a means of verifying the effectiveness of the dry eye eye drops for the dry eye symptoms suffered by the subject to be inferred.

Although an embodiment of the present invention has been described above in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and various combinations, modifications, substitutions, and/or design changes may be made without departing from the spirit of the present invention.

The effects of the above-described embodiments of the present invention are shown as examples. Therefore, in addition to the effects described above, the embodiments of the present invention may also have other effects that a person skilled in the art may recognize from the description of the above-described embodiments.

10a, 10b...machine learning execution device, 100a, 100b...machine learning execution program, 101a, 101b...teaching data acquisition function, 102a, 102b...machine learning execution function, 20a, 20b...dry eye test device, 200a, 200b...dry eye test program, 201a, 201b...data acquisition function, 202a, 202b...symptom estimation function, 700a, 700b...machine learning device, 750a, 750b...machine learning program

Claims (10)

A training data acquisition function for acquiring training data in which training image data showing a training image depicting the training subject's eyes when it is assumed that the training subject's eyes are illuminated with light having a lower color temperature than the light illuminating the training subject's eyes is used as a question, and training test result data showing the results of a test to examine the thickness of the tear lipid layer in the training subject's eyes is used as an answer;
A machine learning execution function that inputs the teacher data into a machine learning program and trains the machine learning program;
A machine learning execution program that causes a computer to execute the above. The training data acquisition function acquires the training data based on training corneal image data showing a training corneal image obtained by cutting out an area depicting at least a part of the cornea of the eye of the training subject from the training image.
The machine learning execution program according to claim 1 . A data acquisition function for acquiring image data for inference showing an image for inference depicting the eye of the subject for inference when it is assumed that the eye of the subject for inference is illuminated with light having a lower color temperature than the light illuminating the eye of the subject for inference;
a symptom estimation function that inputs the inference image data into a machine learning program trained using teacher data in which learning image data showing a learning image depicting the eyes of the learning subject when the eyes of the learning subject are assumed to be illuminated with light having a lower color temperature than the light illuminating the eyes of the learning subject is used as a problem, and learning test result data showing the results of a test to examine the thickness of the tear lipid layer in the eyes of the learning subject is used as an answer, causes the machine learning program to estimate symptoms of dry eye appearing in the eyes of the inference subject, and causes the machine learning program to output symptom data showing symptoms of dry eye appearing in the eyes of the inference subject;
A dry eye testing program that enables a computer to achieve this. The data acquisition function further acquires inference corneal image data showing an inference corneal image obtained by cutting out an area depicting at least a part of the cornea of the eye of the inference subject from the inference image;
The symptom estimation function inputs the inference corneal image data to the machine learning program trained using training data that has as its problem training corneal image data, the training corneal image being an area cut out from the training image that depicts at least a portion of the cornea of the eye of the training subject, and causes the machine learning program to estimate a symptom of dry eye appearing in the eye of the inference subject.
The dry eye test program according to claim 3. a training data acquisition unit that acquires training data having training image data showing training images depicting the training subject's eyes when the training subject's eyes are assumed to be illuminated with light having a lower color temperature than the light illuminating the training subject's eyes, and training test result data showing the results of a test to examine the thickness of the tear lipid layer in the training subject's eyes as an answer,
a machine learning execution unit that inputs the teacher data into a machine learning program and trains the machine learning program;
A machine learning execution device comprising: a data acquisition unit that acquires image data for inference showing an image for inference depicting the eye of the subject for inference when it is assumed that the eye of the subject for inference is illuminated with light having a lower color temperature than the light illuminating the eye of the subject for inference;
a symptom estimation unit that inputs the inference image data into a machine learning program trained using teacher data in which learning image data showing a learning image depicting the eyes of the learning subject when the eyes of the learning subject are assumed to be illuminated with light having a lower color temperature than the light illuminating the eyes of the learning subject is used as a problem, and learning test result data showing the results of a test to examine the thickness of the tear lipid layer in the eyes of the learning subject is used as an answer, causes the machine learning program to infer symptoms of dry eye appearing in the eyes of the inference subject, and causes the machine learning program to output symptom data showing the symptoms of dry eye appearing in the eyes of the inference subject;
A dry eye testing device that uses a computer to achieve this. A training data acquisition function for acquiring training data in which training corneal image data showing a training corneal image depicting only a half portion of the cornea of the training subject's eye on the lower eyelid side is used as a question, and training test result data showing the results of a test to examine the thickness of the tear lipid layer of the training subject's eye is used as an answer.
A machine learning execution function that inputs the teacher data into a machine learning program and trains the machine learning program;
A machine learning execution program that causes a computer to execute the above. A data acquisition function for acquiring corneal image data for inference showing a corneal image for inference depicting only a half portion of the cornea of the eye of the subject for inference on the lower eyelid side ;
a symptom estimation function that inputs the inference corneal image data into a machine learning program trained using teacher data in which learning corneal image data showing a learning corneal image depicting only the lower eyelid half of the cornea of the eye of the learning subject is used as a problem and learning test result data showing the results of a test to examine the thickness of the tear lipid layer of the eye of the learning subject is used as an answer, causes the machine learning program to estimate symptoms of dry eye appearing in the eye of the inference subject, and causes the machine learning program to output symptom data showing symptoms of dry eye appearing in the eye of the inference subject;
A dry eye testing program that enables a computer to achieve this. A training data acquisition unit acquires training data in which training corneal image data showing a training corneal image depicting only a half portion of the cornea of the training subject's eye on the lower eyelid side is used as a question, and training test result data showing the results of a test to examine the thickness of the tear lipid layer of the training subject's eye is used as an answer.
a machine learning execution unit that inputs the teacher data into a machine learning program and trains the machine learning program;
A machine learning execution device comprising: a data acquisition unit that acquires corneal image data for inference that shows a corneal image for inference depicting only a half portion of the cornea of the eye of the subject for inference on the lower eyelid side ;
a symptom estimation unit that inputs the inference corneal image data into a machine learning program trained using teacher data in which learning corneal image data showing a learning corneal image depicting only the lower eyelid half of the cornea of the eye of the learning subject is used as a problem and learning test result data showing the results of a test to examine the thickness of the tear lipid layer of the eye of the learning subject is used as an answer, causes the machine learning program to estimate a symptom of dry eye appearing in the eye of the inference subject, and causes the machine learning program to output symptom data showing the symptom of dry eye appearing in the eye of the inference subject;
A dry eye examination device comprising:

Images