scholarly journals Multimodal Autoencoder Predicts fNIRS Resting State From EEG Signals

2021 ◽  
Author(s):  
Parikshat Sirpal ◽  
Rafat Damseh ◽  
Ke Peng ◽  
Dang Khoa Nguyen ◽  
Frédéric Lesage
Keyword(s):  
Near Infrared ◽  
Short Term Memory ◽  
A Priori ◽  
Functional Near Infrared Spectroscopy ◽  
Neural Data ◽  
Frequency Bands ◽  
Epileptic Patients ◽  
Brain Hemodynamics ◽  
Long Short Term Memory ◽  
Trained Neural Network

AbstractIn this work, we introduce a deep learning architecture for evaluation on multimodal electroencephalographic (EEG) and functional near-infrared spectroscopy (fNIRS) recordings from 40 epileptic patients. Long short-term memory units and convolutional neural networks are integrated within a multimodal sequence-to-sequence autoencoder. The trained neural network predicts fNIRS signals from EEG, sans a priori, by hierarchically extracting deep features from EEG full spectra and specific EEG frequency bands. Results show that higher frequency EEG ranges are predictive of fNIRS signals with the gamma band inputs dominating fNIRS prediction as compared to other frequency envelopes. Seed based functional connectivity validates similar patterns between experimental fNIRS and our model’s fNIRS reconstructions. This is the first study that shows it is possible to predict brain hemodynamics (fNIRS) from encoded neural data (EEG) in the resting human epileptic brain based on power spectrum amplitude modulation of frequency oscillations in the context of specific hypotheses about how EEG frequency bands decode fNIRS signals.

scholarly journals Decoding Multiple Sound-Categories in the Auditory Cortex by Neural Networks: An fNIRS Study

2021 ◽  
Vol 15 ◽  
Author(s):  
So-Hyeon Yoo ◽  
Hendrik Santosa ◽  
Chang-Seok Kim ◽  
Keum-Shik Hong
Keyword(s):  
Auditory Cortex ◽  
Classification Accuracy ◽  
Healthy Subjects ◽  
Near Infrared ◽  
Short Term Memory ◽  
Short Term ◽  
Functional Near Infrared Spectroscopy ◽  
Concentration Changes ◽  
Long Short Term Memory ◽  
Data Subject

This study aims to decode the hemodynamic responses (HRs) evoked by multiple sound-categories using functional near-infrared spectroscopy (fNIRS). The six different sounds were given as stimuli (English, non-English, annoying, nature, music, and gunshot). The oxy-hemoglobin (HbO) concentration changes are measured in both hemispheres of the auditory cortex while 18 healthy subjects listen to 10-s blocks of six sound-categories. Long short-term memory (LSTM) networks were used as a classifier. The classification accuracy was 20.38 ± 4.63% with six class classification. Though LSTM networks’ performance was a little higher than chance levels, it is noteworthy that we could classify the data subject-wise without feature selections.

scholarly journals Complexity of Frontal Cortex fNIRS Can Support Alzheimer Disease Diagnosis in Memory and Visuo-Spatial Tests

Entropy ◽  
2019 ◽  
Vol 21 (1) ◽  
pp. 26 ◽  
Author(s):  
David Perpetuini ◽  
Antonio M. Chiarelli ◽  
Daniela Cardone ◽  
Chiara Filippini ◽  
Roberta Bucco ◽  
...  
Keyword(s):  
Frontal Cortex ◽  
Near Infrared ◽  
Short Term Memory ◽  
Functional Neuroimaging ◽  
Digit Span ◽  
Disease Diagnosis ◽  
Spatial Skills ◽  
Functional Near Infrared Spectroscopy ◽  
Experimental Conditions ◽  
Specificity And Sensitivity

Decline in visuo-spatial skills and memory failures are considered symptoms of Alzheimer’s Disease (AD) and they can be assessed at early stages employing clinical tests. However, performance in a single test is generally not indicative of AD. Functional neuroimaging, such as functional Near Infrared Spectroscopy (fNIRS), may be employed during these tests in an ecological setting to support diagnosis. Indeed, neuroimaging should not alter clinical practice allowing free doctor-patient interaction. However, block-designed paradigms, necessary for standard functional neuroimaging analysis, require tests adaptation. Novel signal analysis procedures (e.g., signal complexity evaluation) may be useful to establish brain signals differences without altering experimental conditions. In this study, we estimated fNIRS complexity (through Sample Entropy metric) in frontal cortex of early AD and controls during three tests that assess visuo-spatial and short-term-memory abilities (Clock Drawing Test, Digit Span Test, Corsi Block Tapping Test). A channel-based analysis of fNIRS complexity during the tests revealed AD-induced changes. Importantly, a multivariate analysis of fNIRS complexity provided good specificity and sensitivity to AD. This outcome was compared to cognitive tests performances that were predictive of AD in only one test. Our results demonstrated the capabilities of fNIRS and complexity metric to support early AD diagnosis.

scholarly journals The influence of prior intention on joint action: an fNIRS-based hyperscanning study

2020 ◽  
Vol 15 (12) ◽  
pp. 1351-1360
Author(s):  
Yixin Chen ◽  
Qihan Zhang ◽  
Sheng Yuan ◽  
Bingjie Zhao ◽  
Peng Zhang ◽  
...  
Keyword(s):  
Motor Performance ◽  
Near Infrared ◽  
Action Planning ◽  
Response Analysis ◽  
Functional Near Infrared Spectroscopy ◽  
Neural Data ◽  
Fast Speed ◽  
Area 6 ◽  
Supplementary Motor Cortex ◽  
Prior Intention

Abstract Motor performances of the same action are affected by prior intentions to move unintentionally, cooperatively or competitively. Here, a back-and-forth movement task combined with a motion capture system and functional near-infrared spectroscopy (fNIRS)-based hyperscanning technology was utilized to record both the behavioral and neural data of 18 dyads of participants acting in pairs [joint conditions: no-intention, cooperative (Coop) and competitive (Comp)] or alone (single conditions: self-paced and fast-speed). The results revealed that Coop or Comp intentions in the joint conditions significantly sped up motor performance compared with similar single conditions, e.g. shorter movement times (MTs) in the Coop/Comp condition than the self-paced/fast-speed condition. Hemodynamic response analysis demonstrated that stronger activities for all joint conditions than the single conditions in the premotor and the supplementary motor cortex (Brodmann area 6) were independent of variations of MTs, indicating that they might reflect more complex aspects of action planning rather than simple execution-based processes. The comparisons of joint conditions across distinct prior intentions before acting yielded significant results for both behavioral and neural measures, with the highest activation of the temporo-parietal junction (TPJ) and the shortest MTs in the Comp condition considered to be implications for the top-down influence of prior intentions on joint performance.

scholarly journals Evidence of Neurovascular Un-Coupling in Mild Alzheimer’s Disease through Multimodal EEG-fNIRS and Multivariate Analysis of Resting-State Data

Biomedicines ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 337
Author(s):  
Antonio M. Chiarelli ◽  
David Perpetuini ◽  
Pierpaolo Croce ◽  
Chiara Filippini ◽  
Daniela Cardone ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Near Infrared ◽  
Area Under The Curve ◽  
Hemoglobin Concentration ◽  
Blood Perfusion ◽  
Ambulatory Setting ◽  
Functional Near Infrared Spectroscopy ◽  
Frequency Bands ◽  
Concentration Changes

Alzheimer’s disease (AD) is associated with modifications in cerebral blood perfusion and autoregulation. Hence, neurovascular coupling (NC) alteration could become a biomarker of the disease. NC might be assessed in clinical settings through multimodal electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS). Multimodal EEG-fNIRS was recorded at rest in an ambulatory setting to assess NC and to evaluate the sensitivity and specificity of the methodology to AD. Global NC was evaluated with a general linear model (GLM) framework by regressing whole-head EEG power envelopes in three frequency bands (theta, alpha and beta) with average fNIRS oxy- and deoxy-hemoglobin concentration changes in the frontal and prefrontal cortices. NC was lower in AD compared to healthy controls (HC) with significant differences in the linkage of theta and alpha bands with oxy- and deoxy-hemoglobin, respectively (p = 0.028 and p = 0.020). Importantly, standalone EEG and fNIRS metrics did not highlight differences between AD and HC. Furthermore, a multivariate data-driven analysis of NC between the three frequency bands and the two hemoglobin species delivered a cross-validated classification performance of AD and HC with an Area Under the Curve, AUC = 0.905 (p = 2.17 × 10−5). The findings demonstrate that EEG-fNIRS may indeed represent a powerful ecological tool for clinical evaluation of NC and early identification of AD.

scholarly journals Interpersonal Agreement and Disagreement During Face-to-Face Dialogue: An fNIRS Investigation

2021 ◽  
Vol 14 ◽  
Author(s):  
Joy Hirsch ◽  
Mark Tiede ◽  
Xian Zhang ◽  
J. Adam Noah ◽  
Alexandre Salama-Manteau ◽  
...  
Keyword(s):  
Fundamental Frequency ◽  
Near Infrared ◽  
A Priori ◽  
Superior Temporal Gyrus ◽  
Acoustic Energy ◽  
Angular Gyrus ◽  
Supramarginal Gyrus ◽  
Functional Near Infrared Spectroscopy ◽  
Face To Face ◽  
Increased Activity

Although the neural systems that underlie spoken language are well-known, how they adapt to evolving social cues during natural conversations remains an unanswered question. In this work we investigate the neural correlates of face-to-face conversations between two individuals using functional near infrared spectroscopy (fNIRS) and acoustical analyses of concurrent audio recordings. Nineteen pairs of healthy adults engaged in live discussions on two controversial topics where their opinions were either in agreement or disagreement. Participants were matched according to their a priori opinions on these topics as assessed by questionnaire. Acoustic measures of the recorded speech including the fundamental frequency range, median fundamental frequency, syllable rate, and acoustic energy were elevated during disagreement relative to agreement. Consistent with both the a priori opinion ratings and the acoustic findings, neural activity associated with long-range functional networks, rather than the canonical language areas, was also differentiated by the two conditions. Specifically, the frontoparietal system including bilateral dorsolateral prefrontal cortex, left supramarginal gyrus, angular gyrus, and superior temporal gyrus showed increased activity while talking during disagreement. In contrast, talking during agreement was characterized by increased activity in a social and attention network including right supramarginal gyrus, bilateral frontal eye-fields, and left frontopolar regions. Further, these social and visual attention networks were more synchronous across brains during agreement than disagreement. Rather than localized modulation of the canonical language system, these findings are most consistent with a model of distributed and adaptive language-related processes including cross-brain neural coupling that serves dynamic verbal exchanges.

Sign in / Sign up

Export Citation Format

Share Document