KEYWORDS: Data modeling, Image segmentation, Fourier transforms, Deep learning, Sensors, Medical research, Machine learning, Functional near infrared spectroscopy, Digital signal processing
Functional near-infrared spectroscopy (fNIRS) presents an affordable and light-weight method to monitor the cerebral hemodynamics of the brain. However, noise and artefacts hamper the analysis of fNIRS signals. Thus, the signal quality assessment is a crucial step when planning fNIRS experiments. Currently no standardized method exists for the evaluation. Commonly used visual inspection of the signals is time consuming and prone to subjective bias. Recently use of machine learning and deep learning approaches have been applied for the fNIRS signal quality assessment, showing promising results. However, currently there are only a few experiments which have investigated the use of these approaches to evaluate fNIRS signal quality. In this human brain study, we utilized previously developed deep learning approach used for the assessment of PPG signal quality with short-time Fourier transform (STFT) to evaluate the quality of raw fNIRS signals with wavelengths 690 nm, 810 nm, 830 nm and 980 nm. The data was collected from 38 subjects with a two-channel fNIRS device, measured during breath hold protocol in sitting position. A total of 10,144 segments were extracted using a window of 10 seconds length without overlap and annotated for SQA by three independent evaluators. The segments were transformed with STFT, and further processed into 2D images. The images were used as input data for CNN deep learning network, and the output further used to classify the segments as acceptable or unacceptable. The results show high potential of using DL approach for fNIRS signal quality assessment with classification accuracy of 87.89 %.
Signal quality is crucial in any signal analysis. Typically, the reason for bad signal quality is inappropriate sensor placement which is also highly dependent on the measurement location. It is usually quite easy to get a good optical signal from finger, but not from the brain. This study aims to provide a real-time signal quality assessment method to help clinical personnel in placement of the fNIRS sensors on head to ensure good signal quality. Signal was segmented for each 10 seconds and a band-pass filter at 0.5-3 Hz was applied to isolate signal in cardiac band. Each segmented signal was subject to visual quality assessment to get bad, fair, and good labels. We used maximum to mean power ratio to generate signal quality index (SQI) score. Other methods included were skewness and kurtosis of the heart rate variability (HRV). Results showed that power ratio provides better consistency and separation among three different labels. Both skewness and kurtosis failed to separate fair and good segments. Using two threshold values, indices from power ration can be transformed into red (bad), yellow (fair), and green (good) alarm to help healthcare practitioners, who have no expertise to assess signal quality, to fix sensor placement to get good or acceptable signals.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.