fNIRS signal quality estimation by means of a machine learning algorithm trained on morphological and temporal features

Sappia, María Sofía; Hakimi, Naser; Svinkunaite, Liucija; Alderliesten, Thomas; Horschig, Jörn M.; Colier, Willy N.J.M.

doi:10.1117/12.2587188

Cited by 5 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concerning signals' quality estimation, a machine learning version of the SQI (MLSQI [18]) has been developed based on the training dataset described in Sappia et al [13]. However, the training dataset was collected from only 14 participants and labeled by individuals working at the company that produces the fNIRS recording device used.…”

Section: Introductionmentioning

confidence: 99%

fNIRS-QC: Crowd-Sourced Creation of a Dataset and Machine Learning Model for fNIRS Quality Control

et al. 2021

View full text Add to dashboard Cite

Despite technological advancements in functional Near Infra-Red Spectroscopy (fNIRS) and a rise in the application of the fNIRS in neuroscience experimental designs, the processing of fNIRS data remains characterized by a high number of heterogeneous approaches, implicating the scientific reproducibility and interpretability of the results. For example, a manual inspection is still necessary to assess the quality and subsequent retention of collected fNIRS signals for analysis. Machine Learning (ML) approaches are well-positioned to provide a unique contribution to fNIRS data processing by automating and standardizing methodological approaches for quality control, where ML models can produce objective and reproducible results. However, any successful ML application is grounded in a high-quality dataset of labeled training data, and unfortunately, no such dataset is currently available for fNIRS signals. In this work, we introduce fNIRS-QC, a platform designed for the crowd-sourced creation of a quality control fNIRS dataset. In particular, we (a) composed a dataset of 4385 fNIRS signals; (b) created a web interface to allow multiple users to manually label the signal quality of 510 10 s fNIRS segments. Finally, (c) a subset of the labeled dataset is used to develop a proof-of-concept ML model to automatically assess the quality of fNIRS signals. The developed ML models can serve as a more objective and efficient quality control check that minimizes error from manual inspection and the need for expertise with signal quality control.

show abstract

Section: Introductionmentioning

confidence: 99%

fNIRS-QC: Crowd-Sourced Creation of a Dataset and Machine Learning Model for fNIRS Quality Control

et al. 2021

View full text Add to dashboard Cite

show abstract

“…One advantage is that it gives the opportunity to assess the signal quality. The NIRS signal quality can be assessed by determining the strength of the heartbeat component in the signals as proposed in [35,39,40], which requires a high sampling rate in order to capture the heartbeats. Another advantage is that, compared with a low sampling rate, it provides a larger number of samples in a specified window; so, with IQR computed in sliding windows of, e.g., 1 s, a better representation of the motion artifacts in the window is achieved.…”

Section: Discussionmentioning

confidence: 99%

Respiratory Rate Extraction from Neonatal Near-Infrared Spectroscopy Signals

Hakimi

Shahbakhti²,

Horschig³

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Background: Near-infrared spectroscopy (NIRS) relative concentration signals contain ‘noise’ from physiological processes such as respiration and heart rate. Simultaneous assessment of NIRS and respiratory rate (RR) using a single sensor would facilitate a perfectly time-synced assessment of (cerebral) physiology. Our aim was to extract respiratory rate from cerebral NIRS intensity signals in neonates admitted to a neonatal intensive care unit (NICU). Methods: A novel algorithm, NRR (NIRS RR), is developed for extracting RR from NIRS signals recorded from critically ill neonates. In total, 19 measurements were recorded from ten neonates admitted to the NICU with a gestational age and birth weight of 38 ± 5 weeks and 3092 ± 990 g, respectively. We synchronously recorded NIRS and reference RR signals sampled at 100 Hz and 0.5 Hz, respectively. The performance of the NRR algorithm is assessed in terms of the agreement and linear correlation between the reference and extracted RRs, and it is compared statistically with that of two existing methods. Results: The NRR algorithm showed a mean error of 1.1 breaths per minute (BPM), a root mean square error of 3.8 BPM, and Bland–Altman limits of agreement of 6.7 BPM averaged over all measurements. In addition, a linear correlation of 84.5% (p < 0.01) was achieved between the reference and extracted RRs. The statistical analyses confirmed the significant (p < 0.05) outperformance of the NRR algorithm with respect to the existing methods. Conclusions: We showed the possibility of extracting RR from neonatal NIRS in an intensive care environment, which showed high correspondence with the reference RR recorded. Adding the NRR algorithm to a NIRS system provides the opportunity to record synchronously different physiological sources of information about cerebral perfusion and respiration by a single monitoring system. This allows for a concurrent integrated analysis of the impact of breathing (including apnea) on cerebral hemodynamics.

show abstract

“…To assess NIRS signal quality, the presence of a strong cardiac component has been often used as the main indicator of a reliable sensor-scalp coupling [105][106][107][108]. A reliable sensor-scalp coupling guarantees that NIR light travels through both intra-and extracranial layers.…”

Section: Signal Quality Assessmentmentioning

confidence: 99%

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

fNIRS signal quality estimation by means of a machine learning algorithm trained on morphological and temporal features

Cited by 5 publications

References 0 publications

fNIRS-QC: Crowd-Sourced Creation of a Dataset and Machine Learning Model for fNIRS Quality Control

fNIRS-QC: Crowd-Sourced Creation of a Dataset and Machine Learning Model for fNIRS Quality Control

Respiratory Rate Extraction from Neonatal Near-Infrared Spectroscopy Signals

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

Contact Info

Product

Resources

About