Proposing a convolutional neural network for stress assessment by means of derived heart rate from functional near infrared spectroscopy

Hakimi, Naser; Jodeiri, Ata; Mirbagheri, Mahya; Setarehdan, Seyed Kamaledin

doi:10.1016/j.compbiomed.2020.103810

Cited by 25 publications

(20 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The intensity signals can be converted into concentration changes in oxygenated hemoglobin (O 2 Hb) and deoxygenated hemoglobin (HHb) [86], which can be used to determine brain hemodynamic response in different brain regions [86][87][88]. The intensity and concentration signals contain some physiological information including cardiac pulsation, respiration, and vasomotor action [89][90][91][92]. Figure 2…”

Section: Nirs-derived Intensity Signals and The Importance Of Signal Quality Assessmentmentioning

confidence: 99%

“…Several studies have shown the compatibility of the HR derived from NIRS with the HR extracted from electrocardiography and photoplethysmography [93][94][95]. Moreover, the HR derived from NIRS has shown to be a richer source of information than HR derived from PPG or ECG under physical and mental stressful conditions [92,[94][95][96]. Deriving HR from NIRS signals is highly useful in neonates as it can eliminate the need to use extra electrode for recording this information [97].…”

Section: Nirs-derived Heartbeat Patternmentioning

confidence: 99%

“…The extracted HR information can be used as a known physiologi term in a part of the model representing different physiological components in the NI The HR and brain hemodynamic information in the NIRS signals can be fused in different applications where both brain and heart functions are altered. For instance, they can be combined to accurately assess (physical) stress [92,94,97]. Furthermore, extracting the HR information from NIRS can reduce the ambiguity of the hemodynamic response model [96,[99][100][101].…”

Section: Nirs-derived Heartbeat Patternmentioning

confidence: 99%

See 2 more Smart Citations

Neuroprotection of the Perinatal Brain by Early Information of Cerebral Oxygenation and Perfusion Patterns

Costa

Hakimi

Bel

2021

IJMS

Self Cite

View full text Add to dashboard Cite

Abnormal patterns of cerebral perfusion/oxygenation are associated with neuronal damage. In preterm neonates, hypoxemia, hypo-/hypercapnia and lack of cerebral autoregulation are related to peri-intraventricular hemorrhages and white matter injury. Reperfusion damage after perinatal hypoxic ischemia in term neonates seems related with cerebral hyperoxygenation. Since biological tissue is transparent for near infrared (NIR) light, NIR-spectroscopy (NIRS) is a noninvasive bedside tool to monitor brain oxygenation and perfusion. This review focuses on early assessment and guiding abnormal cerebral oxygenation/perfusion patterns to possibly reduce brain injury. In term infants, early patterns of brain oxygenation helps to decide whether or not therapy (hypothermia) and add-on therapies should be considered. Further NIRS-related technical advances such as the use of (functional) NIRS allowing simultaneous estimation and integrating of heart rate, respiration rate and monitoring cerebral autoregulation will be discussed.

show abstract

Section: Nirs-derived Intensity Signals and The Importance Of Signal Quality Assessmentmentioning

confidence: 99%

Section: Nirs-derived Heartbeat Patternmentioning

confidence: 99%

Section: Nirs-derived Heartbeat Patternmentioning

confidence: 99%

See 1 more Smart Citation

Neuroprotection of the Perinatal Brain by Early Information of Cerebral Oxygenation and Perfusion Patterns

Costa

Hakimi

Bel

2021

IJMS

Self Cite

View full text Add to dashboard Cite

show abstract

“…While in some experimental protocols it is imperative to remove these systemic or extracerebral effects to obtain task-evoked cerebral neuronal signals, in other cases they can be treated as additional signals of interest as they may carry complementary information regarding the state of the subject 56,57 . For example, one study added time and frequency domain features of cardiac oscillations extracted from fNIRS signals to a machine learning architecture and reported increases in classification accuracy of stress by at least 10% when compared against standard model containing only the neuronal activity related information 58 . Another study reported that including end-tidal CO2 (EtCO2 -surrogate for PaCO2 measures) in the interpretation of fNIRS signals improved ability to monitor pain 59 .…”

Section: Introductionmentioning

confidence: 99%

Evaluation of fNIRS Signal Components Elicited by Cognitive and Hypercapnic Stimuli

Reddy

İzzetoğlu

Shewokis

et al. 2021

Preprint

View full text Add to dashboard Cite

Functional near infrared spectroscopy (fNIRS) measurements are confounded by signal components originating from multiple physiological causes, whose activities may vary temporally and spatially (across tissue layers, and regions of the cortex). Furthermore, the stimuli can induce evoked effects, which may lead to over or underestimation of the actual effect of interest. Here, we conducted a temporal, spectral, and spatial analysis of fNIRS signals collected during cognitive and hypercapnic stimuli to characterize effects of functional versus systemic responses. We utilized wavelet analysis to discriminate physiological causes and employed long and short source-detector separation (SDS) channels to differentiate tissue layers. Multi-channel measures were analyzed further to distinguish hemispheric differences. The results highlight cardiac, respiratory, myogenic, and very low frequency (VLF) activities within fNIRS signals. Regardless of stimuli, activity within VLF band had the largest contribution to the overall signal. The systemic activities dominated the measurements from the short SDS channels during cognitive stimulus, but not hypercapnic stimulus. Importantly, results indicate that characteristics of fNIRS signals vary with type of the stimuli administered as cognitive stimulus elicited variable responses between hemispheres in VLF band and task-evoked temporal effect in VLF, myogenic and respiratory bands, while hypercapnic stimulus induced a global response across both hemispheres.

show abstract

“…Functional near-infrared spectroscopy (fNIRS) neuroimaging technique makes it possible to non-invasively investigate brain activity in both experimental and clinical settings [1][2][3][4][5][6][7][8][9][10][11][12]. In order to guarantee a reliable estimation of the functional hemodynamics in the brain cortex, the initial task of a researcher is to collect signals with a good quality.…”

Section: Introductionmentioning

confidence: 99%

Signal quality index: an algorithm for quantitative assessment of functional near infrared spectroscopy signal quality

Sappia¹,

Hakimi²,

Colier³

et al. 2020

Biomed. Opt. Express

Self Cite

View full text Add to dashboard Cite

We propose the signal quality index (SQI) algorithm as a novel tool for quantitatively assessing the functional near infrared spectroscopy (fNIRS) signal quality in a numeric scale from 1 (very low quality) to 5 (very high quality). The algorithm comprises two preprocessing steps followed by three consecutive rating stages. The results on a dataset annotated by independent fNIRS experts showed SQI performed significantly better (p<0.05) than PHOEBE (placing headgear optodes efficiently before experimentation) and SCI (scalp coupling index), two existing algorithms, in both quantitatively rating and binary classifying the fNIRS signal quality. Employment of the proposed algorithm to estimate the signal quality before processing the fNIRS signals increases certainty in the interpretations.

show abstract

Proposing a convolutional neural network for stress assessment by means of derived heart rate from functional near infrared spectroscopy

Cited by 25 publications

References 77 publications

Neuroprotection of the Perinatal Brain by Early Information of Cerebral Oxygenation and Perfusion Patterns

Neuroprotection of the Perinatal Brain by Early Information of Cerebral Oxygenation and Perfusion Patterns

Evaluation of fNIRS Signal Components Elicited by Cognitive and Hypercapnic Stimuli

Signal quality index: an algorithm for quantitative assessment of functional near infrared spectroscopy signal quality

Contact Info

Product

Resources

About