Learning device and estimation device

Abstract

To provide a learning device and an estimation device for accurately measuring an activation state of a subject's brain.SOLUTION: The learning device comprises: an acquisition unit for acquiring a function image based on a result of measuring an activation state of a subject's brain by a functional near infrared spectroscopy; and a corresponding data generation unit which generates corresponding data obtained by associating the acquired function image with brain activity information indicative of the activation state of the subject's brain at the time of the measurement by the functional near infrared spectroscopy and based on information different from the result of the measurement by the functional near infrared spectroscopy.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a learning device and an estimation device. [Background technology]

[0002] Functional near-infrared spectroscopy is known as a method for measuring the brain activity of a subject (see, for example, Patent Document 1). Compared to other measurement methods such as functional magnetic resonance imaging, functional near-infrared spectroscopy does not require large-scale equipment, allowing for greater flexibility in measurement and enabling it to be implemented at low cost. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-136434 Summary of the Invention [Problem to be solved by the invention]

[0004] On the other hand, functional near-infrared spectroscopy has the problem of low spatial resolution and being easily affected by noise such as scalp blood flow, and there is a demand for improving the accuracy of measurement results.

[0005] The present invention has been made in view of the above, and has an object to provide a learning device and an estimation device for measuring the brain activity state of a subject with high accuracy. [Means for solving the problem]

[0006] The learning device of the present invention includes an acquisition unit that acquires a functional image based on measurement results obtained by measuring the activity state of a subject's brain using functional near-infrared spectroscopy, and a correspondence data generation unit that generates correspondence data that associates the acquired functional image with brain activity information that is based on information indicating the activity state of the subject's brain at the time of measurement using functional near-infrared spectroscopy and that is different from the measurement results using functional near-infrared spectroscopy.

[0007] The estimation device according to the present invention includes an acquisition unit that acquires functional images based on measurement results obtained by measuring the brain activity state of a subject using functional near-infrared spectroscopy, and an estimation unit that estimates the brain activity state of the subject based on a learning model that has been generated in advance by machine learning regarding the correlation between the functional images and brain activity information indicating the brain activity state of the subject, and the functional images acquired by the acquisition unit. [Effects of the Invention]

[0008] According to the present invention, it is possible to provide a learning device and an estimation device for measuring the brain activity state of a subject with high accuracy. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a functional block diagram showing an example of a brain function learning estimation system according to this embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a neural network. [Figure 3] FIG. 3 is a diagram illustrating an example of a learning method. [Figure 4] FIG. 4 is a diagram schematically illustrating an example of an estimation method. [Figure 5] FIG. 5 is a flowchart showing an example of the operation of the learning device. [Figure 6] FIG. 6 is a flowchart showing an example of the operation of the estimation device. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of a learning device and an estimation device according to the present invention will be described with reference to the accompanying drawings. Note that the present invention is not limited to these embodiments. Furthermore, the components in the following embodiments include those that are easily replaceable by those skilled in the art, or those that are substantially identical.

[0011] [First embodiment] 1 is a functional block diagram showing an example of a brain function learning estimation system 100 according to this embodiment. The brain function learning estimation system 100 shown in FIG. 1 includes a detection device 10, a setting device 20, a learning device 30, and an estimation device 40.

[0012] The detection device 10 detects brain activity information indicating the activity state of the subject's brain. The detection device 10 includes a measurement device 11 that measures cerebral blood flow based on the principle of fNIRS (functional Near-Infrared Spectroscopy), for example, and a measurement device 12 that is not limited to a measurement device based on the principle of fNIRS but performs measurement based on the principle of fMRI (functional Magnetic Resonance Imaging), for example, that measures brain activity amount as brain activity information.

[0013] The measuring device 11 generates a functional image showing the brain activity state of the subject from the measurement results based on the principles of fNIRS. Examples of functional images include images showing the distribution of at least one of oxyhemoglobin concentration, deoxyhemoglobin concentration, and total hemoglobin concentration at a predetermined region of the subject's brain. The functional images may be generated individually showing the distribution of oxyhemoglobin concentration, deoxyhemoglobin concentration, and total hemoglobin concentration. Alternatively, a functional image of deoxyhemoglobin concentration, which is considered to have the highest correlation with the brain activity state, may be generated. Furthermore, the functional images of oxyhemoglobin concentration, deoxyhemoglobin concentration, and total hemoglobin concentration may each be integrated into a single functional image as one channel. For example, in an RGB image, each RGB color corresponds to a channel. This allows machine learning to learn the spatial correlation between the functional images of oxyhemoglobin concentration, deoxyhemoglobin concentration, and total hemoglobin concentration.

[0014] A functional image is an image showing a cross section of a subject's brain. For example, the functional image can show a cross section of the subject's brain cut along at least one of a transverse plane, a sagittal plane, and a coronal plane. The type of cross section can be set using, for example, the setting device 20, and the setting information set by the setting device 20 is sent to the detection device 10 via the estimation device 40.

[0015] The predetermined region of the brain targeted by the functional image can be, for example, a language center such as Wernicke's area or Broca's area. When Wernicke's area or Broca's area is the predetermined region, the functional image is preferably at least one of a transverse plane and a sagittal plane suitable for observing both areas. Note that the predetermined region is not limited to the above, and may be any other region as long as it can be measured by fNIRS. fNIRS can suitably measure regions on the surface of the subject's brain, such as the cerebrum (neocortex). Therefore, the predetermined region can be, for example, at least a portion of the subject's cerebrum.

[0016] Here, a measurement device 11 that measures cerebral blood flow based on the principle of fNIRS has, for example, multiple optical fiber channels. The optical fiber channels include an output optical fiber that outputs near-infrared light from a light source to the subject's head, and a receiving optical fiber that receives near-infrared light reflected or scattered inside the subject's head. The output optical fiber and the receiving optical fiber are positioned at positions where brain activity information from the subject's Wernicke's area and Broca's area can be measured.

[0017] The measuring device 11 can generate functional images using techniques such as diffuse optical tomography based on the type of cross section (transverse, sagittal, coronal) and the specified location (Wernicke's area, Broca's area, etc.).

[0018] The measuring device 12 generates a reference image showing the brain activity of the subject from the measurement results based on the principles of fMRI. The reference image may be, for example, an image showing changes in oxyhemoglobin concentration, deoxyhemoglobin concentration, and total hemoglobin concentration at a specific location on an image of the subject's brain, or an image obtained by superimposing these images. Furthermore, it is desirable that the reference image be an image that is at least correlated with the functional image generated by the measuring device 11. For example, if the functional image generated by the measuring device 11 is a functional image of deoxyhemoglobin concentration, the reference image generated by the measuring device 12 should be an image showing changes in the deoxyhemoglobin concentration. Compared to fNIRS, fMRI has the advantages of higher spatial resolution and less susceptibility to noise. Therefore, the reference image obtained by fMRI can more accurately determine the brain activity of the subject than the functional image obtained by fNIRS.

[0019] The setting device 20 inputs setting information for the brain function learning estimation system 100. The setting device 20 may be an input device such as a keyboard or a mouse, or may be a smartphone, tablet, or the like having a touch panel.

[0020] The learning device 30 learns the detection results of the detection device 10. The learning device 30 has a processing device such as a CPU (Central Processing Unit) and a storage device such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The learning device 30 includes an acquisition unit 31, a correspondence data generation unit 32, a learning model generation unit 33, and a storage unit 34.

[0021] The acquisition unit 31 acquires functional images based on the measurement results of measuring the brain activity of the subject by fNIRS. In this embodiment, the acquisition unit 31 acquires functional images based on the measurement results of the measurement device 11. In this embodiment, the acquisition unit 31 also acquires functional images showing, for example, the Wernicke's area and Broca's area of ​​the subject's brain.

[0022] The correspondence data generation unit 32 generates correspondence data that associates the functional images acquired by the acquisition unit 31 with brain activity information corresponding to the functional images. The brain activity information is information indicating the activity state of the subject's brain during fNIRS measurement and is information based on information other than the fNIRS measurement results. Such brain activity information can be, for example, information indicating the activity state in the Wernicke's area and Broca's area of ​​the subject's brain. In this embodiment, the brain activity information is information based on the measurement results of measuring the subject's brain using fMRI. In other words, the brain activity information is an activity state that can be determined, for example, from a reference image generated by the measurement device 12. This activity state can be determined manually based on the reference image, for example. Note that the activity state may also be determined automatically using an image processing device or the like.

[0023] The activity state of each of Wernicke's area and Broca's area can be set in stages. For example, the activity state of each of Wernicke's area and Broca's area can be set in two stages: "high activity" and "low activity." Although the activity state of each area can be set in stages, it can also be set in stages according to the characteristics of each area. For example, the activity state of Wernicke's area is classified based on a predetermined threshold W1 as high activity if it is equal to or greater than the predetermined threshold W1, and as low activity if it is less than the predetermined threshold W1. Furthermore, the activity state of Broca's area is classified based on a predetermined threshold B1 as high activity if it is equal to or greater than the predetermined threshold B1, and as low activity if it is less than the predetermined threshold B1. Here, an example of setting the predetermined threshold for Wernicke's area will be described. Brain activity information is measured for a predetermined period of time while providing or not providing stimuli that stimulate the five senses, such as auditory or visual stimuli, to the subject, generating a number of reference images for the predetermined period of time. The minimum and maximum pixel values ​​(pixel values ​​converted from at least one of oxygenated hemoglobin concentration, deoxygenated hemoglobin concentration, and total hemoglobin concentration) of the region corresponding to Wernicke's area in the number of reference images for the predetermined period of time are obtained. The predetermined threshold value may be set to 50% of the maximum value, 150% of the minimum value, or the intermediate value between the maximum and minimum values. In this way, the predetermined threshold value is set based on the pixel values ​​of the reference images. A threshold value can also be set similarly for Broca's area. The activity state of each area may be set to three or more levels.

[0024] In other words, the activity of Wernicke's area and Broca's area is (1) Wernicke's area is underactive and Broca's area is underactive (hypoactivity in both areas) (2) Wernicke's area is underactive and Broca's area is overactive (Broca's area dominant) (3) Wernicke's area is highly active and Broca's area is low active (Wernicke's area dominant) (4) High activity in Wernicke's area and Broca's area (high activity in both areas) Therefore, the brain activity information can be set as four types of states: low activity state of both areas, Broca's area dominant state, Wernicke's area dominant state, and high activity state of both areas. Here, the activity states of Wernicke's area and Broca's area are set to the same level, but they may also be set to different levels, for example, two levels for Wernicke's area and four levels for Broca's area.

[0025] In this embodiment, the correspondence data generator 32 generates correspondence data that associates functional images based on measurement results obtained by simultaneously measuring the brain of the same subject using the measurement devices 11 and 12 with brain activity information. In other words, the correspondence data associates brain activity information determined based on fMRI measurement results with functional images based on fNIRS measurement results. As described above, the reference image obtained by fMRI can determine the subject's brain activity state with higher accuracy than the functional image obtained by fNIRS. Therefore, more accurate information is likely to be associated with the functional image than information obtained when the subject's brain activity state is determined based on the functional image obtained by fNIRS itself. The correspondence data generator 32 stores the generated correspondence data in the storage unit 34.

[0026] In this embodiment, the learning model generation unit 33 generates a learning model using a neural network (convolutional neural network) represented by, for example, VGG16. FIG. 2 is a diagram showing an example of a neural network. As shown in FIG. 2, the neural network NW has 13 convolutional layers S1, 5 pooling layers S2, and 3 fully connected layers S3. The neural network processes input information in the convolutional layers S1 and pooling layers S2 in order, and the processing results are combined in the fully connected layer S3 and output.

[0027] The learning model generation unit 33 inputs the correspondence data generated by the correspondence data generation unit 32 into the neural network NW, and learns the correlation between the functional images associated by the correspondence data and the brain activity information by machine learning such as deep learning. That is, the learning model generation unit 33 optimizes the neural network NW through learning to generate a learning model. For example, in supervised learning, brain activity information is treated as correct answer data, and since the brain activity information here has four types of states, learning is performed to solve a problem of classifying the brain activity information into four states. Note that in this embodiment, an example of generating a learning model using a convolutional neural network represented by VGG16 is described, but this is not limited thereto, and a learning model may be generated using other types of neural networks.

[0028] The storage unit 34 stores various types of information. The storage unit 34 has storage such as a hard disk drive or a solid state drive. Note that an external storage medium such as a removable disk may be used as the storage unit 34. The storage unit 34 stores the correspondence data generated by the data generation unit 32 and the learning model generated by the learning model generation unit 33.

[0029] The storage unit 34 stores a learning program that causes the computer to execute a process of acquiring functional images based on measurement results of the subject's brain activity state measured by fNIRS, and a process of generating correspondence data that associates the acquired functional images with brain activity information that indicates the subject's brain activity state at the time of measurement by fNIRS and is based on information different from fNIRS.The storage unit 34 also stores a learning program that causes the computer to execute a process of machine learning the correlation between the functional images and the brain activity information based on the generated correspondence data, thereby generating a learning model.

[0030] The estimation device 40 estimates the brain activity state of a subject. The estimation device 40 has a processing device such as a CPU and a storage device such as a RAM or a ROM. The estimation device 40 includes an acquisition unit 41, an estimation unit 42, and a storage unit 43.

[0031] The acquisition unit 41 acquires a functional image based on the measurement results obtained by measuring the brain activity of the subject using fNIRS. The acquisition unit 41 acquires the functional image generated by the measurement device 11.

[0032] The estimation unit 42 estimates the brain activity state of the subject based on the functional image acquired by the acquisition unit 41 and the learning model generated by the learning device 30. The estimation unit 42 inputs the functional image acquired by the acquisition unit 41 into the learning model. In this case, the learning model outputs brain activity information corresponding to the input functional image based on the learning result of the correlation between the functional image and the brain activity information. The estimation unit 42 estimates that the brain activity information, which is the output result, is the brain activity state of the subject. The estimation unit 42 outputs the estimation result. The output estimation result is transmitted to the setting device 20, for example, and displayed on the setting device 20. The estimation unit 42 may also store the estimation result in the memory unit 43.

[0033] The storage unit 43 stores various types of information. The storage unit 43 has storage such as a hard disk drive or a solid state drive. Note that an external storage medium such as a removable disk may be used as the storage unit 43. The storage unit 43 can store a learning model generated by the learning device 30.

[0034] The memory unit 43 causes the computer to execute the following processes: a process of acquiring a functional image based on the measurement results of measuring the brain activity state of the subject by fNIRS; and a process of estimating the brain activity state of the subject based on the acquired functional image and a learning model previously generated by machine learning regarding the correlation between the functional image and brain activity information indicating the brain activity state of the subject at the time of measuring the functional image.

[0035] Next, a learning method and an estimation method using the brain function learning estimation system 100 configured as described above will be described. FIG. 3 is a diagram schematically showing the flow of the learning method. In the learning method according to this embodiment, first, functional images and brain activity information that serve as materials are generated. The subject is simultaneously measured by the measuring devices 11 and 12. The measuring devices 11 and 12 generate functional images and reference images based on the measurement results.

[0036] The assessor views the reference image and judges the subject's brain activity information. Because the reference image is more accurate than the functional image, there is a higher chance of obtaining a more accurate judgment result than when determining the subject's brain activity information by looking at the functional image. The assessor views the reference image and judges the subject's brain activity state, and inputs the brain activity information that constitutes the judgment result using the setting device 20. In this case, for example, a judgment result of Broca's area dominance is input. The input brain activity information is stored, for example, in the memory of the measuring device 12. Note that the functional image and brain activity information based on the results of simultaneous measurement may include tag information such as the measurement time so that they can be associated with each other. By performing such measurements and judgments multiple times, multiple combinations of functional images and brain activity information are accumulated.

[0037] In this state, the learning process is started by inputting from the setting device 20 to cause the learning device 30 to start learning. The acquisition unit 31 acquires functional images based on the measurement results of the measuring device 11. The correspondence data generation unit 32 acquires brain activity information from the measuring device 12. The correspondence data generation unit 32 generates correspondence data that associates the acquired functional images with the brain activity information based on tag information, etc. The correspondence data generation unit 32 stores the generated correspondence data in the memory unit 34.

[0038] The learning model generation unit 33 optimizes the neural network NW and generates a learning model by performing machine learning (deep learning) on ​​the correlation between the functional image and the brain activity information based on the generated correspondence data. The learning model generation unit 33 stores the generated learning model in the storage unit 34.

[0039] FIG. 4 is a diagram schematically illustrating the flow of the estimation method. In the estimation method according to this embodiment, a subject is measured using the measurement device 11. The measurement device 11 generates a functional image based on the measurement results. In this state, the estimation process is started by inputting from the setting device 20 to cause the estimation device 40 to start estimation. The estimation device 40 acquires in advance the learning model stored in the memory unit 34 of the learning device 30 and stores it in the memory unit 43.

[0040] The acquisition unit 41 acquires a functional image based on the measurement results of the measurement device 11. The estimation unit 42 inputs the functional image into a neural network NW, which is a learning model stored in the memory unit 43, acquires brain activity information, which is the output result, and estimates the acquired brain activity information as the brain activity state of the subject. In the example shown in FIG. 4, brain activity information of "Broca's area dominance" is output from the neural network NW. The estimation unit 42 estimates that the brain activity state of the subject is "Broca's area dominance" based on the output result from the neural network NW. The estimation unit 42 outputs the estimation result. The estimation result output from the estimation unit 42 can be displayed, for example, on an external device such as the setting device 20.

[0041] 5 is a flowchart showing an example of the operation of the learning device 30. As shown in FIG. 5, in the learning device 30, the acquisition unit 31 acquires functional images based on measurement results of the brain activity state of the subject using fNIRS (step S10). Next, the correspondence data generation unit 32 generates correspondence data that associates the acquired functional images with brain activity information that indicates the brain activity state of the subject at the time of the fNIRS measurement and is based on information different from the fNIRS measurement results (step S20). Next, the learning model generation unit 33 performs machine learning of the correlation between the functional images and the brain activity information based on the correspondence data generated by the correspondence data generation unit 32, and generates a learning model (step S30).

[0042] Fig. 6 is a flowchart showing an example of the operation of the estimation device 40. As shown in Fig. 6, in the estimation device 40, the acquisition unit 41 acquires a functional image based on the measurement results obtained by measuring the brain activity state of the subject using fNIRS (step S40). Next, the estimation unit 42 estimates the brain activity state of the subject based on a learning model previously generated by machine learning regarding the correlation between the functional image and brain activity information and the functional image acquired by the acquisition unit 41 (step S50).

[0043] As described above, the learning device 30 according to this embodiment includes an acquisition unit 31 that acquires functional images based on measurement results obtained by measuring the brain activity state of a subject using fNIRS, and a correspondence data generation unit 32 that generates correspondence data that associates the acquired functional images with brain activity information that is based on information indicating the brain activity state of the subject at the time of measurement using fNIRS and that is different from the measurement results using fNIRS.

[0044] This configuration allows for the functional image based on the fNIRS measurement results to be associated with brain activity information based on information other than the fNIRS measurement results. Therefore, the functional image and brain activity information can be associated with higher accuracy than when brain activity information is determined from the functional image based on the fNIRS measurement results. This contributes to the accurate measurement of the subject's brain activity state.

[0045] The learning device 30 according to this embodiment further includes a learning model generation unit 33 that generates a learning model by machine learning the correlation between functional images and brain activity information based on the correspondence data generated by the correspondence data generation unit 32. With this configuration, the learning model is generated using correspondence data in which the functional images and brain activity information are associated with each other with high accuracy, so that a highly accurate learning model can be generated for the correlation between the functional images and brain activity information. This contributes to accurate measurement of the brain activity state of the subject.

[0046] In the learning device 30 according to this embodiment, the information different from the fNIRS measurement results is information based on the measurement results of the subject's brain obtained by fMRI at the time corresponding to the fNIRS measurement. Compared to fNIRS, fMRI has the advantage of higher spatial resolution and less susceptibility to noise. Therefore, the reference image obtained by fMRI can determine the subject's brain activity state with higher accuracy than the functional image obtained by fNIRS. Therefore, the functional image and brain activity information can be associated with higher accuracy than when brain activity information is determined from the functional image based on the fNIRS measurement results.

[0047] In the learning device 30 according to this embodiment, the functional image is an image showing the cerebrum of the subject. With this configuration, since an image of the cerebrum that can be suitably measured by fNIRS is used, highly accurate association and learning can be performed.

[0048] The estimation device 40 according to this embodiment includes an acquisition unit 41 that acquires functional images based on measurement results obtained by measuring the brain activity state of a subject using fNIRS, and an estimation unit 42 that estimates the brain activity state of the subject based on a learning model that has been generated in advance by machine learning regarding the correlation between the functional images and brain activity information that indicates the brain activity state of the subject at the time of measurement of the functional images, and the functional images acquired by the acquisition unit 41.

[0049] According to this configuration, the brain activity state of the subject can be estimated based on a functional image based on the measurement results by fNIRS and a learning model generated in advance by machine learning, making it possible to estimate the brain activity state of the subject with higher accuracy than when it is estimated manually from a functional image based on the measurement results by fNIRS.

[0050] Although the activity states of Wernicke's area and Broca's area can be set in stages, they may also be set based on the characteristics of the fNIRS optical fiber channel. Specifically, the activity states of Wernicke's area and Broca's area are set in stages based on the characteristics of the fNIRS optical fiber channel. Below, a modified example will be described in which the stages of the activity states of Wernicke's area and Broca's area are changed based on the characteristics of the fNIRS optical fiber channel.

[0051] The activity states of Wernicke's area and Broca's area are set in stages according to the number of fNIRS optical fiber channels. For example, the number of stages indicating the activity state of Wernicke's area is set in proportion to the number of light-receiving optical fibers installed to measure brain activity information in Wernicke's area. Similarly, the number of stages indicating the activity state of Broca's area is set in proportion to the number of light-receiving optical fibers installed to measure brain activity information in Broca's area. Here, the number of optical fiber channels is defined as the number of light-receiving optical fibers, but it may also be the total number of light-receiving optical fibers and light-emitting optical fibers. In this way, brain activity information can be learned and measured appropriately according to the number of optical fiber channels of the attached fNIRS.

[0052] The activity states of Wernicke's area and Broca's area are set according to the output level of the emitting optical fiber and the sensitivity of the receiving optical fiber of the fNIRS optical fiber channel. For example, the level indicating the activity state of Wernicke's area is set proportional to the sensitivity of the receiving optical fiber installed to measure brain activity information of Wernicke's area. Similarly, the level indicating the activity state of Broca's area is set proportional to the sensitivity of the receiving optical fiber installed to measure brain activity information of Broca's area. Here, the level is set proportional to the sensitivity of the receiving optical fiber, but it may also be set proportional to the output level of the emitting optical fiber, or it may take into account both the sensitivity of the receiving optical fiber and the output level of the emitting optical fiber. It may also be set proportional to the diameter of the receiving optical fiber or the diameter of the emitting optical fiber to obtain sensitivity. In this way, brain activity information can be learned and measured appropriately according to the output level and sensitivity of the attached fNIRS optical fiber channel.

[0053] The technical scope of the present invention is not limited to the above-described embodiment, and appropriate modifications can be made without departing from the spirit of the present invention. For example, in the above-described embodiment, the learning device 30 and the estimation device 40 constitute a part of the brain function learning estimation system 100, but the present invention is not limited to this. The learning device 30 and the estimation device 40 may be configured as independent devices or systems.

[0054] In the above embodiment, the learning device 30 and the estimation device 40 are provided as separate devices, but the present invention is not limited to this. For example, a processing device having the functions of the learning device 30 and the functions of the estimation device 40 may be provided. [Explanation of symbols]

[0055] S1...convolutional layer, S2...pooling layer, S3...connection layer, NW...neural network (learning model), 10...detection device, 11, 12...measuring device, 20...setting device, 30...learning device, 31, 41...acquisition unit, 32...corresponding data generation unit, 33...learning model generation unit, 34, 43...memory unit, 40...estimation device, 42...estimation unit, 100...brain function learning estimation system

Claims

1. an acquisition unit that acquires a functional image based on a measurement result of measuring the brain activity of the subject by functional near-infrared spectroscopy; a correspondence data generation unit that generates correspondence data that associates the acquired functional image with brain activity information that indicates the state of Wernicke's area and Broca's area based on information that indicates the brain activity state of the subject at the time of measurement by the functional near-infrared spectroscopy, the information being different from the measurement result by the functional near-infrared spectroscopy; and Equipped with The brain activity information indicates a state of low activity in both areas, a state of dominance in Broca's area, a state of dominance in Wernicke's area, or a state of high activity in both areas. Learning device.

2. a learning model generation unit that performs machine learning on the correlation between the functional image and the brain activity information based on the correspondence data generated by the correspondence data generation unit to generate a learning model; The learning device according to claim 1 .

3. The information different from the measurement results by functional near-infrared spectroscopy is information based on measurement results obtained by measuring the brain of the subject by functional magnetic resonance imaging at a time corresponding to the measurement by functional near-infrared spectroscopy. The learning device according to claim 1 or 2.

4. the information indicating the brain activity state of the subject is information based on the characteristics of the optical fiber during measurement by the functional near-infrared spectroscopy; The learning device according to any one of claims 1 to 3.

5. an acquisition unit that acquires a functional image based on a measurement result of measuring the brain activity of the subject by functional near-infrared spectroscopy; an estimation unit that estimates the activity state of the brain of the subject based on a learning model that has been generated in advance by machine learning regarding the correlation between the functional image and brain activity information that indicates an activity state that indicates the state of the Wernicke's area and the Broca's area of ​​the brain of the subject, and the functional image acquired by the acquisition unit; Equipped with The brain activity information indicates a state of low activity in both areas, a state of dominance in Broca's area, a state of dominance in Wernicke's area, or a state of high activity in both areas. Estimation device.

Images