Prediction of epileptic seizures with convolutional neural networks and functional near-infrared spectroscopy signals

Strategic Integration: A Cross-Disciplinary Review of the fNIRS-EEG Dual-Modality Imaging System for Delivering Multimodal Neuroimaging to Applications

Background: Recent years have seen a surge of interest in dual-modality imaging systems that integrate functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG) to probe brain function. This review aims to explore the advancements and clinical applications of this technology, emphasizing the synergistic integration of fNIRS and EEG. Methods: The review begins with a detailed examination of the fundamental principles and distinctive features of fNIRS and EEG techniques. It includes critical technical specifications, data-processing methodologies, and analysis techniques, alongside an exhaustive evaluation of 30 seminal studies that highlight the strengths and weaknesses of the fNIRS-EEG bimodal system. Results: The paper presents multiple case studies across various clinical domains-such as attention-deficit hyperactivity disorder, infantile spasms, depth of anesthesia, intelligence quotient estimation, and epilepsy-demonstrating the fNIRS-EEG system's potential in uncovering disease mechanisms, evaluating treatment efficacy, and providing precise diagnostic options. Noteworthy research findings and pivotal breakthroughs further reinforce the developmental trajectory of this interdisciplinary field. Conclusions: The review addresses challenges and anticipates future directions for the fNIRS-EEG dual-modal imaging system, including improvements in hardware and software, enhanced system performance, cost reduction, real-time monitoring capabilities, and broader clinical applications. It offers researchers a comprehensive understanding of the field, highlighting the potential applications of fNIRS-EEG systems in neuroscience and clinical medicine.

Classification Algorithm for fNIRS-based Brain Signals Using Convolutional Neural Network with Spatiotemporal Feature Extraction Mechanism

Brain Computer Interface (BCI) is a highly promising human-computer interaction method that can utilize brain signals to control external devices. BCI based on functional near-infrared spectroscopy (fNIRS) is considered a relatively new and promising paradigm. fNIRS is a technique of measuring functional changes in cerebral hemodynamics. It detects changes in the hemodynamic activity of the cerebral cortex by measuring oxyhemoglobin and deoxyhemoglobin (HbR) concentrations and inversely predicts the neural activity of the brain. At the present time, Deep learning (DL) methods have not been widely used in fNIRS decoding, and there are fewer studies considering both spatial and temporal dimensions for fNIRS classification. To solve these problems, we proposed an end-to-end hybrid neural network for feature extraction of fNIRS. The method utilizes a spatial-temporal convolutional layer for automatic extraction of temporally valid information and uses a spatial attention mechanism to extract spatially localized information. A temporal convolutional network (TCN) is used to further utilize the temporal information of fNIRS before the fully connected layer. We validated our approach on a publicly available dataset including 29 subjects, including left-hand and right-hand motor imagery (MI), mental arithmetic (MA), and a baseline task. The results show that the method has few training parameters and high accuracy, providing a meaningful reference for BCI development.

Neurophotonic methods in approach to in vivo animal epileptic models: Advantages and limitations

Neurophotonic technology is a rapidly growing group of techniques that are based on the interactions of light with natural or genetically modified cells of the neural system. New optical technologies make it possible to considerably extend the tools of neurophysiological research, from the visualization of functional activity changes to control of brain tissue excitability. This opens new perspectives for studying the mechanisms underlying the development of human neurological diseases. Epilepsy is one of the most common brain disorders; it is characterized by recurrent seizures and affects >1% of the world's population. However, how seizures occur, spread, and terminate in a healthy brain is still unclear. Therefore, it is extremely important to develop appropriate models to accurately explore the causal relationship of epileptic activity. The use of neurophotonic technologies in epilepsy research falls into two broad categories: the visualization of neural epileptic activity, and the direct optical influence on neurons to induce or suppress epileptic activity. An optogenetic variant of the classical kindling model of epileptic seizures, in which activatable cells are genetically defined, is called optokindling. Research is also underway concerning the application of neurophotonic techniques for suppressing epileptic activity, aiming to bring these methods into clinical practice. This review aims to systematize and describe new approaches that use combinations of different neurophotonic methods to work with in vivo models of epilepsy. These approaches overcome many of the shortcomings associated with classical animal models of epilepsy and thus increase the effectiveness of developing new diagnostic methods and antiepileptic therapy.

Memristive Neural Networks for Predicting Seizure Activity

The aim of the study is to assess the possibilities of predicting epileptiform activity using the neuronal activity data recorded from the hippocampus and medial entorhinal cortex of mice with chronic epileptiform activity. To reach this goal, a deep artificial neural network (ANN) has been developed and its implementation based on memristive devices has been demonstrated.

Materials and Methods

The biological part of the investigation. Young healthy outbred CD1 mice were used in our study. They were divided into two groups: control (n=6) and the group with induced chronic epileptiform activity (n=6). Local field potentials (LFP) were recorded from the hippocampus and medial entorhinal cortex of the mice of both groups to register neuronal activity. The LFP recordings were used for deep ANN training. Epileptiform activity in mice was modeled by intraperitoneal injection of pilocarpine (280 mg/kg). LFP were recorded in the awake mice a month after the induction of epileptiform activity.Mathematical part of the investigation. A deep long short-term memory (LSTM) ANN capable of predicting biological signals of neuronal activity in mice has been developed. The ANN implementation is based on memristive devices, which are described by the equations of the redox processes running in the memristive thin metal-oxide-metal films, e.g., Au/ZrO2(Y)/TiN/Ti and Au/SiO2(Y)/TiN/Ti. In order to train the developed ANN to predict epileptiform activity, a supervised learning algorithm was used, which allowed us to adjust the network parameters and train LSTM on the described recordings of neuronal activity.

Results

After training on the LFP recordings from the hippocampus and medial entorhinal cortex of the mice with chronic epileptiform activity, the proposed deep ANN has demonstrated high values of evaluation metric (root-mean-square error, RMSE) and successfully predicted epileptiform activity shortly before its occurrence (40 ms). The results of the numerical experiments have shown that the RMSE value of 0.019 was reached, which indicates the efficacy of proposed approach. The accuracy of epileptiform activity prediction 40 ms before its occurrence is a significant result and shows the potential of the developed neural network architecture.

Conclusion

The proposed deep ANN can be used to predict pathological neuronal activity including epileptic seizure (focal) activity in mice before its actual occurrence. Besides, it can be applied for building a long-term prognosis of the disease course based on the LFP data. Thus, the proposed ANN based on memristive devices represents a novel approach to the prediction and analysis of pathological neuronal activity possessing a potential for improving the diagnosis and prognostication of epileptic seizures and other diseases associated with neuronal activity.

Technical feasibility of multimodal imaging in neonatal hypoxic-ischemic encephalopathy from an ovine model to a human case series

Hypoxic-ischemic encephalopathy (HIE) secondary to perinatal asphyxia occurs when the brain does not receive enough oxygen and blood. A surrogate marker for "intact survival" is necessary for the successful management of HIE. The severity of HIE can be classified based on clinical presentation, including the presence of seizures, using a clinical classification scale called Sarnat staging; however, Sarnat staging is subjective, and the score changes over time. Furthermore, seizures are difficult to detect clinically and are associated with a poor prognosis. Therefore, a tool for continuous monitoring on the cot side is necessary, for example, an electroencephalogram (EEG) that noninvasively measures the electrical activity of the brain from the scalp. Then, multimodal brain imaging, when combined with functional near-infrared spectroscopy (fNIRS), can capture the neurovascular coupling (NVC) status. In this study, we first tested the feasibility of a low-cost EEG-fNIRS imaging system to differentiate between normal, hypoxic, and ictal states in a perinatal ovine hypoxia model. Here, the objective was to evaluate a portable cot-side device and perform autoregressive with extra input (ARX) modeling to capture the perinatal ovine brain states during a simulated HIE injury. So, ARX parameters were tested with a linear classifier using a single differential channel EEG, with varying states of tissue oxygenation detected using fNIRS, to label simulated HIE states in the ovine model. Then, we showed the technical feasibility of the low-cost EEG-fNIRS device and ARX modeling with support vector machine classification for a human HIE case series with and without sepsis. The classifier trained with the ovine hypoxia data labeled ten severe HIE human cases (with and without sepsis) as the "hypoxia" group and the four moderate HIE human cases as the "control" group. Furthermore, we showed the feasibility of experimental modal analysis (EMA) based on the ARX model to investigate the NVC dynamics using EEG-fNIRS joint-imaging data that differentiated six severe HIE human cases without sepsis from four severe HIE human cases with sepsis. In conclusion, our study showed the technical feasibility of EEG-fNIRS imaging, ARX modeling of NVC for HIE classification, and EMA that may provide a biomarker of sepsis effects on the NVC in HIE.

Epilepsy seizure prediction with few-shot learning method

Epileptic seizures prediction and timely alarms allow the patient to take effective and preventive actions. In this paper, a convolutional neural network (CNN) is proposed to diagnose the preictal period. Our goal is for those epileptic patients in whom seizures occur late and it is very challenging to record the preictal signal for them. In the previous works, generalized methods were inevitably used for this group of patients which were not very accurate. Our approach to solve this problem is to provide a few-shot learning method. This method, having the previous knowledge, is trained with only a small number of samples, learns new tasks and reduces the efforts to collect more data. Evaluation results for three patients from the CHB–MIT database, for a 10-min seizure prediction horizon (SPH) and a 20-min seizure occurrence period (SOP), averaged sensitivity of 95.70% and a false prediction rate (FPR) of 0.057/h and for the 5-min prediction horizon and the 25-min seizure occurrence period averaged sensitivity of 98.52% and a false prediction rate of (FPR) of 0.045/h. The proposed few-shot learning method, based on previous knowledge gained from the generalizable method, is regulated with a few new patient samples for the patient. Our results show that the accuracy obtained in this method is higher than the generalizable methods.

Deep learning in fNIRS: a review

Significance: Optical neuroimaging has become a well-established clinical and research tool to monitor cortical activations in the human brain. It is notable that outcomes of functional near-infrared spectroscopy (fNIRS) studies depend heavily on the data processing pipeline and classification model employed. Recently, deep learning (DL) methodologies have demonstrated fast and accurate performances in data processing and classification tasks across many biomedical fields. Aim: We aim to review the emerging DL applications in fNIRS studies. Approach: We first introduce some of the commonly used DL techniques. Then, the review summarizes current DL work in some of the most active areas of this field, including brain-computer interface, neuro-impairment diagnosis, and neuroscience discovery. Results: Of the 63 papers considered in this review, 32 report a comparative study of DL techniques to traditional machine learning techniques where 26 have been shown outperforming the latter in terms of the classification accuracy. In addition, eight studies also utilize DL to reduce the amount of preprocessing typically done with fNIRS data or increase the amount of data via data augmentation. Conclusions: The application of DL techniques to fNIRS studies has shown to mitigate many of the hurdles present in fNIRS studies such as lengthy data preprocessing or small sample sizes while achieving comparable or improved classification accuracy.

Optical Monitoring in Neonatal Seizures

BACKGROUND

Neonatal seizures remain a significant cause of morbidity and mortality worldwide. The past decade has resulted in substantial progress in seizure detection and understanding the impact seizures have on the developing brain. Optical monitoring such as cerebral near-infrared spectroscopy (NIRS) and broadband NIRS can provide non-invasive continuous real-time monitoring of the changes in brain metabolism and haemodynamics.

AIM

To perform a systematic review of optical biomarkers to identify changes in cerebral haemodynamics and metabolism during the pre-ictal, ictal, and post-ictal phases of neonatal seizures.

METHOD

A systematic search was performed in eight databases. The search combined the three broad categories: (neonates) AND (NIRS) AND (seizures) using the stepwise approach following PRISMA guidance.

RESULTS

Fifteen papers described the haemodynamic and/or metabolic changes observed with NIRS during neonatal seizures. No randomised controlled trials were identified during the search. Studies reported various changes occurring in the pre-ictal, ictal, and post-ictal phases of seizures.

CONCLUSION

Clear changes in cerebral haemodynamics and metabolism were noted during the pre-ictal, ictal, and post-ictal phases of seizures in neonates. Further studies are necessary to determine whether NIRS-based methods can be used at the cot-side to provide clear pathophysiological data in real-time during neonatal seizures.

Optimizing functional near-infrared spectroscopy (fNIRS) channels for schizophrenic identification during a verbal fluency task using metaheuristic algorithms

OBJECTIVE

We aimed to reduce the complexity of the 52-channel functional near-infrared spectroscopy (fNIRS) system to facilitate its usage in discriminating schizophrenia during a verbal fluency task (VFT).

METHODS

Oxygenated hemoglobin signals obtained using 52-channel fNIRS from 100 patients with schizophrenia and 100 healthy controls during a VFT were collected and processed. Three features frequently used in the analysis of fNIRS signals, namely time average, functional connectivity, and wavelet, were extracted and optimized using various metaheuristic operators, i.e., genetic algorithm (GA), particle swarm optimization (PSO), and their parallel and serial hybrid algorithms. Support vector machine (SVM) was used as the classifier, and the performance was evaluated by ten-fold cross-validation.

RESULTS

GA and GA-dominant algorithms achieved higher accuracy compared to PSO and PSO-dominant algorithms. An optimal accuracy of 87.00% using 16 channels was obtained by GA and wavelet analysis. A parallel hybrid algorithm (the best 50% individuals assigned to GA) achieved an accuracy of 86.50% with 8 channels on the time-domain feature, comparable to the reported accuracy obtained using 52 channels.

CONCLUSION

The fNIRS system can be greatly simplified while retaining accuracy comparable to that of the 52-channel system, thus promoting its applications in the diagnosis of schizophrenia in low-resource environments. Evolutionary algorithm-dominant optimization of time-domain features is promising in this regard.

Crossing time windows optimization based on mutual information for hybrid BCI

Hybrid EEG-fNIRS brain-computer interface (HBCI) is widely employed to enhance BCI performance. EEG and fNIRS signals are combined to increase the dimensionality of the information. Time windows are used to select EEG and fNIRS singles synchronously. However, it ignores that specific modal signals have their own characteristics, when the task is stimulated, the information between the modalities will mismatch at the moment, which has a significant impact on the classification performance. Here we propose a novel crossing time windows optimization for mental arithmetic (MA) based BCI. The EEG and fNIRS signals were segmented separately by sliding time windows. Then crossing time windows (CTW) were combined with each one segment from EEG and fNIRS selected independently. Furthermore, EEG and fNIRS features were extracted using Filter Bank Common Spatial Pattern (FBCSP) and statistical methods from each sample. Mutual information was calculated for FBCSP and statistical features to characterize the discrimination of crossing time windows, and the optimal window would be selected based on the largest mutual information. Finally, a sparse structured framework of Fisher Lasso feature selection (FLFS) was designed to select the joint features, and conventional Linear Discriminant Analysis (LDA) was employed to perform classification. We used proposed method for a MA dataset. The classification accuracy of the proposed method is 92.52 ± 5.38% and higher than other methods, which shows the rationality and superiority of the proposed method.

Deep Learning in Biomedical Optics

This article reviews deep learning applications in biomedical optics with a particular emphasis on image formation. The review is organized by imaging domains within biomedical optics and includes microscopy, fluorescence lifetime imaging, in vivo microscopy, widefield endoscopy, optical coherence tomography, photoacoustic imaging, diffuse tomography, and functional optical brain imaging. For each of these domains, we summarize how deep learning has been applied and highlight methods by which deep learning can enable new capabilities for optics in medicine. Challenges and opportunities to improve translation and adoption of deep learning in biomedical optics are also summarized. Lasers Surg. Med. © 2021 Wiley Periodicals LLC.

Error Fusion of Hybrid Neural Networks for Mechanical Condition Dynamic Prediction

It is important for equipment to operate safely and reliably so that the working state of mechanical parts pushes forward an immense influence. Therefore, in order to enhance the dependability and security of mechanical equipment, to accurately predict the changing trend of mechanical components in advance plays a significant role. This paper introduces a novel condition prediction method, named error fusion of hybrid neural networks (EFHNN), by combining the error fusion of multiple sparse auto-encoders with convolutional neural networks for predicting the mechanical condition. First, to improve prediction accuracy, we can use the error fusion of multiple sparse auto-encoders to collect multi-feature information, and obtain a trend curve representing machine condition as well as a threshold line that can indicate the beginning of mechanical failure by computing the square prediction error (SPE). Then, convolutional neural networks predict the state of the machine according to the original data when the SPE value exceeds the threshold line. It can be seen from this result that the EFHNN method in the prediction of mechanical fault time series is available and superior.

Epileptic Seizures Detection Using Deep Learning Techniques: A Review

A variety of screening approaches have been proposed to diagnose epileptic seizures, using electroencephalography (EEG) and magnetic resonance imaging (MRI) modalities. Artificial intelligence encompasses a variety of areas, and one of its branches is deep learning (DL). Before the rise of DL, conventional machine learning algorithms involving feature extraction were performed. This limited their performance to the ability of those handcrafting the features. However, in DL, the extraction of features and classification are entirely automated. The advent of these techniques in many areas of medicine, such as in the diagnosis of epileptic seizures, has made significant advances. In this study, a comprehensive overview of works focused on automated epileptic seizure detection using DL techniques and neuroimaging modalities is presented. Various methods proposed to diagnose epileptic seizures automatically using EEG and MRI modalities are described. In addition, rehabilitation systems developed for epileptic seizures using DL have been analyzed, and a summary is provided. The rehabilitation tools include cloud computing techniques and hardware required for implementation of DL algorithms. The important challenges in accurate detection of automated epileptic seizures using DL with EEG and MRI modalities are discussed. The advantages and limitations in employing DL-based techniques for epileptic seizures diagnosis are presented. Finally, the most promising DL models proposed and possible future works on automated epileptic seizure detection are delineated.

Machine learning based intelligent automated neonatal epileptic seizure detection

Epilepsy is found to be the fourth most common chronic neurological disorder that tends to abnormal and unpredictable brain activity and seizure states. According to statistics, 70% of the epilepsy patients can be cured if identified and treated with anti-epileptic drugs or shock stimulations. Only about 7% to 8% need to be operated. Electroencephalogram (EEG) is a cheap and effective way to record the prolonged activities of the brain through electrical impulses between neural cells. Seizure is difficult to detect in neonates as the signal involves a lot of disturbances and the existing high accuracy system for adults can’t be used for neonates. In an attempt to build an impregnable system to detect seizure in early stages, EEG signals of neonates procured from Neonatal Intensive Care Unit (NICU) at the Helsinki University Hospital. These signals were processed and fed into three different robust algorithms –Support Vector Machine (SVM), Artificial Neural Network (ANN) and 1-Dimensional Convolutional Neural Network (1D-CNN). The experimental results were compared and the proposed CNN model with 95.99% accuracy outperforms all the state-of-art models for automated Epileptic Seizure prediction in Neonates. Deep CNN has been a powerful tool in extracting robust features from EEG signals. This generalized system can be used by medical experts for detecting Seizure in neonates with better accuracy and reliability.

Classification of epileptic seizure using feature selection based on fuzzy membership from EEG signal

BACKGROUND:

Feature selection is a technology that improves the performance result by eliminating overlapping or unrelated features.

OBJECTIVE:

To improve the performance result, this study proposes a new feature selection that uses the distance between the centers.

METHODS:

This study uses the distance between the centers of gravity (DBCG) of the bounded sum of the weighted fuzzy memberships (BSWFMs) supported by a neural network with weighted fuzzy membership (NEWFM).

RESULTS:

Using distance-based feature selection, 22 minimum features with a high performance result are selected, with the shortest DBCG of BSWFMs removed individually from the initial 24 features. The NEWFM used 22 minimum features as inputs to obtain a sensitivity, accuracy, and specificity of 99.3%, 99.5%, and 99.7%, respectively.

CONCLUSIONS:

In this study, only the mean DBCG is used to select the features; in the future, however, it will be necessary to incorporate statistical methods such as the standard deviation, maximum, and normal distribution.

Decoding Three Different Preference Levels of Consumers Using Convolutional Neural Network: A Functional Near-Infrared Spectroscopy Study

This study decodes consumers' preference levels using a convolutional neural network (CNN) in neuromarketing. The classification accuracy in neuromarketing is a critical factor in evaluating the intentions of the consumers. Functional near-infrared spectroscopy (fNIRS) is utilized as a neuroimaging modality to measure the cerebral hemodynamic responses. In this study, a specific decoding structure, called CNN-based fNIRS-data analysis, was designed to achieve a high classification accuracy. Compared to other methods, the automated characteristics, constant training of the dataset, and learning efficiency of the proposed method are the main advantages. The experimental procedure required eight healthy participants (four female and four male) to view commercial advertisement videos of different durations (15, 30, and 60 s). The cerebral hemodynamic responses of the participants were measured. To compare the preference classification performances, CNN was utilized to extract the most common features, including the mean, peak, variance, kurtosis, and skewness. Considering three video durations, the average classification accuracies of 15, 30, and 60 s videos were 84.3, 87.9, and 86.4%, respectively. Among them, the classification accuracy of 87.9% for 30 s videos was the highest. The average classification accuracies of three preferences in females and males were 86.2 and 86.3%, respectively, showing no difference in each group. By comparing the classification performances in three different combinations (like vs. so-so, like vs. dislike, and so-so vs. dislike) between two groups, male participants were observed to have targeted preferences for commercial advertising, and the classification performance 88.4% between "like" vs. "dislike" out of three categories was the highest. Finally, pairwise classification performance are shown as follows: For female, 86.1% (like vs. so-so), 87.4% (like vs. dislike), 85.2% (so-so vs. dislike), and for male 85.7, 88.4, 85.1%, respectively.

Roughness-Length-Based Characteristic Analysis of Intracranial EEG and Epileptic Seizure Prediction

To identify precursors of epileptic seizures, an EEG characteristic analysis is carried out based on a roughness-length method, where fractal dimensions and intercept values are extracted to measure the structure complexity and the amplitude roughness of EEG signals in different phases. Using the significant changes of the fractal dimension and intercept in the preictal phase with respect to those in the interictal phase, a patient-specific seizure prediction algorithm is then proposed by combining with a gradient boosting classifier. The probabilistic outputs of the trained gradient boosting classifier are further processed by threshold comparison and rule-based judgment to distinguish preictal EEG from interictal EEG and to generate seizure alerts. The prediction algorithm was evaluated on 20 patients’ intracranial EEG recordings from the Freiburg EEG database, which contains the preictal periods of 65 seizures and 499[Formula: see text]h interictal EEG. Setting the seizure prediction horizon as 2[Formula: see text]min, averaged sensitivity values of 90.42% and 91.67% with averaged false prediction rates of 0.12/h and 0.10/h were achieved for seizure occurrence periods of 30 and 50[Formula: see text]min, respectively. These results demonstrate the ability of fractal dimension and intercept metrics in predicting the occurrence of seizures.

Deep learning model for ultrafast quantification of blood flow in diffuse correlation spectroscopy

Diffuse correlation spectroscopy (DCS) is increasingly used in the optical imaging field to assess blood flow in humans due to its non-invasive, real-time characteristics and its ability to provide label-free, bedside monitoring of blood flow changes. Previous DCS studies have utilized a traditional curve fitting of the analytical or Monte Carlo models to extract the blood flow changes, which are computationally demanding and less accurate when the signal to noise ratio decreases. Here, we present a deep learning model that eliminates this bottleneck by solving the inverse problem more than 2300% faster, with equivalent or improved accuracy compared to the nonlinear fitting with an analytical method. The proposed deep learning inverse model will enable real-time and accurate tissue blood flow quantification with the DCS technique.

Transcranial photobiomodulation attenuates pentylenetetrazole-induced status epilepticus in peripubertal rats

Convulsive status epilepticus is the most common neurological emergency in children. Transcranial photobiomodulation (tPBM) reverses elevated rodent neurotransmitters after status epilepticus (SE) yet whether tPBM can attenuate seizure behaviors remains unknown. Here, we applied near-infrared laser at wavelength 808 nm transcranially to peripubertal Sprague-Dawley rats prior to pentylenetetrazole (PTZ) injection. Hematoxylin-eosin, immunofluorescence (IF) staining with anti-parvalbumin (PV) and terminal deoxynucleotidyl transferase dUTP nick-end labeling (TUNEL) assay after IF staining was performed. Behaviorally, tPBM attenuated the mean seizure score and reduced the incidence of SE and mortality. Histochemically, tPBM reduced dark neurons in the cortex, hippocampus, thalamus and hypothalamus, lessened the apoptotic ratio of parvalbumin-positive interneurons (PV-INs) and alleviated the aberrant extent of PV-positive unstained somata of PCs in the hippocampus. Conclusively, tPBM attenuated PTZ-induced seizures, SE and mortality in peripubertal rats and reduced PTZ-induced neuronal injury, apoptosis of PV-INs and preserved PV positive perisomatic inhibitory network in the hippocampus.

Cortical Tasks-Based Optimal Filter Selection: An fNIRS Study

Functional near-infrared spectroscopy (fNIRS) is one of the latest noninvasive brain function measuring technique that has been used for the purpose of brain-computer interfacing (BCI). In this paper, we compare and analyze the effect of six most commonly used filtering techniques (i.e., Gaussian, Butterworth, Kalman, hemodynamic response filter (hrf), Wiener, and finite impulse response) on classification accuracies of fNIRS-BCI. To conclude with the best optimal filter for a specific cortical task owing to a specific cortical region, we divided our experimental tasks according to the three main cortical regions: prefrontal, motor, and visual cortex. Three different experiments were performed for prefrontal and motor execution tasks while one for visual stimuli. The tasks performed for prefrontal include rest (R) vs mental arithmetic (MA), R vs object rotation (OB), and OB vs MA. Similarly, for motor execution, R vs left finger tapping (LFT), R vs right finger tapping (RFT), and LFT vs RFT. Likewise, for the visual cortex, R vs visual stimuli (VS) task. These experiments were performed for ten trials with five subjects. For consistency among extracted data, six statistical features were evaluated using oxygenated hemoglobin, namely, slope, mean, peak, kurtosis, skewness, and variance. Combination of these six features was used to classify data by the nonlinear support vector machine (SVM). The classification accuracies obtained from SVM by using hrf and Gaussian were significantly higher for R vs MA, R vs OB, R vs RFT, and R vs VS and Wiener filter for OB vs MA. Similarly, for R vs LFT and LFT vs RFT, hrf was found to be significant p<0.05. These results show the feasibility of using hrf for effective removal of noises from fNIRS data.