Estimation system, estimation method, program, estimation model, brain activity training apparatus, brain activity training method, and brain activity training program
Inventors
Ogawa, Takeshi • TAMANO, RYUTA • Kawanabe, Motoaki • Kawato, Mitsuo
Assignees
ATR Advanced Telecommunications Research Institute International • Shionogi and Co Ltd
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12616389-B2
Publication Date
2026-05-05
Expiration Date
Abstract
An estimation system obtains brain wave measurement data and functional magnetic resonance imaging measurement data simultaneously measured from a subject, calculates first functional connectivity for each channel combination based on correlation between channels included in the brain wave measurement data, calculates second functional connectivity for each brain network based on correlation between regions of interest included in the functional magnetic resonance imaging measurement data, calculates a disorder-likelihood label by calculating a score representing disorder-likelihood to be estimated with the use of a plurality of second functional connectivities, and determines an estimation model for estimating disorder-likelihood based on prescribed first functional connectivity by machine learning using the first functional connectivity for each channel combination and the disorder-likelihood label.
Core Innovation
The invention provides an estimation system and associated method that simultaneously obtains brain wave measurement data from an electroencephalograph and functional magnetic resonance imaging measurement data from a functional magnetic resonance imaging device measured from a subject. The brain wave measurement data includes time waveforms for a plurality of channels corresponding to respective sensors arranged in a head of the subject, and the functional magnetic resonance imaging measurement data is used to compute functional connectivities that represent brain network activity.
The system calculates first functional connectivity for each channel combination based on correlation between channels in the brain wave measurement data, and calculates second functional connectivity for each brain network based on correlation between regions of interest in the functional magnetic resonance imaging measurement data. Based on the plurality of second functional connectivities, the system calculates a disorder-likelihood label by calculating a score representing disorder-likelihood to be estimated.
An estimation model is then determined for estimating the disorder-likelihood based on prescribed first functional connectivity by machine learning using the first functional connectivity for each channel combination and the disorder-likelihood label. A signal including the disorder-likelihood is output to a presentation apparatus, and the stored estimation model is used to calculate and present disorder-likelihood during neurofeedback based on brain wave measurement data.
Claims Coverage
The partial content includes five independent claims: clm-00001 (estimation system), clm-00013 (estimation method), clm-00014 (non-transitory storage medium), clm-00015 (trained estimation model), and clm-00016/17/18 (neurofeedback apparatus/method/storage medium variants). Across these independent claims, the inventive coverage centers on simultaneous EEG and fMRI acquisition, computation of first functional connectivity and second functional connectivity, derivation of a disorder-likelihood label from a score based on multiple second functional connectivities, and machine-learning determination of an estimation model mapping prescribed first functional connectivity to the disorder-likelihood label for output to a presentation apparatus.
Simultaneous EEG and fMRI acquisition with functional connectivity computation
Obtain, from an electroencephalograph, brain wave measurement data and, from a functional magnetic resonance imaging device, functional magnetic resonance imaging measurement data simultaneously measured from a subject, the brain wave measurement data including time waveforms for a plurality of channels corresponding to respective ones of a plurality of sensors arranged in a head; calculate first functional connectivity for each channel combination based on correlation between channels; calculate second functional connectivity for each brain network based on correlation between regions of interest.
Disorder-likelihood label from a score based on fMRI connectivities
Calculate a disorder-likelihood label by calculating a score representing disorder-likelihood to be estimated based on a plurality of second functional connectivities.
Machine-learning determination of an estimation model mapping EEG connectivity to disorder-likelihood
Determine an estimation model for estimating the disorder-likelihood based on prescribed first functional connectivity by machine learning using the first functional connectivity for each channel combination and the disorder-likelihood label.
Outputting disorder-likelihood signal to a presentation apparatus
Output a signal including the disorder-likelihood to a presentation apparatus.
Neurofeedback training using a stored estimation model and presentation of disorder-likelihood
Store an estimation model for estimating disorder-likelihood of a subject generated before neurofeedback training; measure brain wave measurement data of the subject in neurofeedback training; calculate, in the neurofeedback training, disorder-likelihood of the subject with the estimation model; output a signal for representation corresponding to the disorder-likelihood to a presentation apparatus.
Across the independent claims, the core claim set covers end-to-end estimation: simultaneous EEG and fMRI acquisition, computation of EEG-based first functional connectivity and fMRI-based second functional connectivity, derivation of a disorder-likelihood label from a score based on multiple second functional connectivities, and machine-learning determination of an estimation model mapping prescribed first functional connectivity to the disorder-likelihood label, with output to a presentation apparatus. Separate independent claims further cover a trained model and neurofeedback training apparatus/method/storage medium that uses the generated estimation model to calculate and present disorder-likelihood during neurofeedback.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?