# US 12,118,718 B2 · Medical information processing apparatus, medical information processing method, and non-transitory computer-readable medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,718 B2 - Document ID: US12118718B2 - Status: Granted - Kind: B2 - Application number: 17/581,036 - Filed: 2022-01-21 - Published: 2022-07-28 - Granted: 2024-10-15 - Earliest claimed: 2021-01-27 - Assignees: Canon Medical Systems Corporation - Applicants: Canon Medical Systems Corporation - Inventors: Aina Ikezaki; Yasuko Fujisawa; Chihiro Hattori; Naotaka Sakashita - Web page: https://patentgrep.com/patent/US12118718B2 ## CPC - G06F 18/00: Pattern recognition - G06T 7/0012: {Biomedical image inspection} - G06F 2218/12: Classification; Matching - G06T 2207/20081: Training; Learning - G06T 2207/30016: Brain - G06V 10/82: using neural networks - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A medical information processing apparatus according to an embodiment includes a processing circuitry. The processing circuitry is configured to: obtain first nerve activity information indicating an activity of a nerve of a subject; estimate first feeling information indicating a feeling experienced by the subject on the basis of the first nerve activity information; and determine presentation information to enable an evaluator to experience the feeling of the subject, on the basis of the first feeling information. ## Claims ### Claim 1 A medical information processing apparatus, comprising: processing circuitry configured to: obtain first nerve activity information indicating an activity of a particular nerve of a subject; generate first image data corresponding to the obtained first nerve activity information based on a visual decoder that has learned, through machine learning, a correspondence relationship between second nerve activity information indicating an activity of a nerve relevant to visual sensation and second image data corresponding to the second nerve activity information; estimate first feeling information indicating a feeling experienced by the subject based on a feeling decoder that has learned, through machine learning, a correspondence relationship between the first nerve activity information, the first image data corresponding to the first nerve activity information, and the first feeling information; and determine presentation information to enable an evaluator to experience the feeling of the subject, based on the first feeling information. ### Claim 2 (depends on 1) The medical information processing apparatus according to claim 1, wherein, based on the first nerve activity information, the processing circuitry is further configured to estimate the first feeling information that indicates the feeling experienced by the subject, the feeling experienced by the subject being related to five senses of the subject and degrees of the five senses. ### Claim 3 (depends on 1) The medical information processing apparatus according to claim 1, wherein the processing circuitry is further configured to obtain the first nerve activity information that indicates the activity of the particular nerve of the subject and is brain activity information. ### Claim 4 (depends on 1) The medical information processing apparatus according to claim 1, wherein the processing circuitry is further configured to: obtain the first nerve activity information that indicates the activity of the particular nerve of the subject and is muscle potential information, and based on the first nerve activity information, estimate the first feeling information that indicates the feeling experienced by the subject and indicates tactile sensation. ### Claim 5 (depends on 1) The medical information processing apparatus according to claim 1, wherein the processing circuitry is further configured to estimate second feeling information indicating a feeling experienced by the evaluator, based on third nerve activity information indicating an activity of a nerve of the evaluator and the image data generated by the visual decoder, and determine the presentation information for the evaluator, based on the first feeling information of the subject and the second feeling information of the evaluator. ### Claim 6 (depends on 5) The medical information processing apparatus according to claim 5, wherein the processing circuitry is further configured to determine the presentation information so that a degree of similarity between the first nerve activity information of the subject and the third nerve activity information of the evaluator is equal to or higher than a threshold value. ### Claim 7 A medical information processing method, comprising: obtaining first nerve activity information indicating an activity of a particular nerve of a subject; generating first image data corresponding to the obtained first nerve activity information based on a visual decoder that has learned, through machine learning, a correspondence relationship between second nerve activity information indicating an activity of a nerve relevant to visual sensation and second image data corresponding to the second nerve activity information; estimating first feeling information indicating a feeling experienced by the subject based on a feeling decoder that has learned, through machine learning, a correspondence relationship between the first nerve activity information, the first image data corresponding to the first nerve activity information, and the first feeling information; and determining presentation information to enable an evaluator to experience the feeling of the subject, based on the first feeling information. ### Claim 8 A non-transitory computer-readable medium comprising instructions that cause a computer to execute: obtaining first nerve activity information indicating an activity of a particular nerve of a subject; generating first image data corresponding to the obtained first nerve activity information based on a visual decoder that has learned, through machine learning, a correspondence relationship between second nerve activity information indicating an activity of a nerve relevant to visual sensation and second image data corresponding to the second nerve activity information; estimating first feeling information indicating a feeling experienced by the subject based on a feeling decoder that has learned, through machine learning, a correspondence relationship between the first nerve activity information, the first image data corresponding to the first nerve activity information, and the first feeling information; and determining presentation information to enable an evaluator to experience the feeling of the subject, based on the first feeling information.