Using an Interpretable Amino Acid-Based Machine Learning Method to Enhance the Diagnosis of Major Depressive Disorder.

Background: Major depressive disorder (MDD) is a leading cause of disability worldwide. At present, however, there are no established biomarkers that have been validated for diagnosing and treating MDD. This study sought to assess the diagnostic and predictive potential of the differences in serum amino acid concentration levels between MDD patients and healthy controls (HCs), integrating them into interpretable machine learning models. Methods: In total, 70 MDD patients and 70 HCs matched in age, gender, and ethnicity were recruited for the study. Serum amino acid profiling was conducted by means of chromatography-mass spectrometry. A total of 21 metabolites were analysed, with 17 from a preset amino acid panel and the remaining 4 from a preset kynurenine panel. Logistic regression was applied to differentiate MDD patients from HCs. Results: The best-performing model utilised both feature selection and hyperparameter optimisation and yielded a moderate area under the receiver operating curve (AUC) classification value of 0.76 on the testing data. The top five metabolites identified as potential biomarkers for MDD were 3-hydroxy-kynurenine, valine, kynurenine, glutamic acid, and xanthurenic acid. Conclusions: Our study highlights the potential of using an interpretable machine learning analysis model based on amino acids to aid and increase the diagnostic accuracy of MDD in clinical practice.

Numerical Solution of Inverse Problem in Functional Near Infrared Spectroscopy using L1-Norm Method.

It has been more than three decades since researchers began investigating functional near-infrared spectroscopy (fNIRs) and its applications with near-infrared light for use in both clinical and pre-clinical settings. In order to increase the accuracy of fNIRs of complex tissue structures, it is necessary to create more advanced image reconstruction methods. Real fNIRs data have been used to develop an implementation of the L1-Norm approach for tackling the inverse problem in this work. The Monte Carlo (MC) simulation is used to construct the sensitivity matrix for this research. Finally, a numerical algorithm for the L1-Norm approach of image reconstruction is developed and implemented in MATLAB to aid in the process. The results showed good agreement with the actual fNIRs data.

An fNIRS investigation of novel expressed emotion stimulations in schizophrenia.

Living in high expressed emotion (EE) environments tends to increase the relapse rate in schizophrenia (SZ). At present, the neural substrates responsible for high EE in SZ remain poorly understood. Functional near-infrared spectroscopy (fNIRS) may be of great use to quantitatively assess cortical hemodynamics and elucidate the pathophysiology of psychiatric disorders. In this study, we designed novel low- (positivity and warmth) and high-EE (criticism, negative emotion, and hostility) stimulations, in the form of audio, to investigate cortical hemodynamics. We used fNIRS to measure hemodynamic signals while participants listened to the recorded audio. Healthy controls (HCs, [Formula: see text]) showed increased hemodynamic activation in the major language centers across EE stimulations, with stronger activation in Wernicke's area during the processing of negative emotional language. Compared to HCs, people with SZ ([Formula: see text]) exhibited smaller hemodynamic activation in the major language centers across EE stimulations. In addition, people with SZ showed weaker or insignificant hemodynamic deactivation in the medial prefrontal cortex. Notably, hemodynamic activation in SZ was found to be negatively correlated with the negative syndrome scale score at high EE. Our findings suggest that the neural mechanisms in SZ are altered and disrupted, especially during negative emotional language processing. This supports the feasibility of using the designed EE stimulations to assess people who are vulnerable to high-EE environments, such as SZ. Furthermore, our findings provide preliminary evidence for future research on functional neuroimaging biomarkers for people with psychiatric disorders.

Functional Near-Infrared Spectroscopy of English-Speaking Adults With Attention-Deficit/Hyperactivity Disorder During a Verbal Fluency Task.

OBJECTIVE: Functional near-infrared spectroscopy (fNIRS) provides direct and quantitative assessment of cortical hemodynamic response. It has been used to identify neurophysiological alterations in medication-naïve adults with attention-deficit/hyperactivity disorder (ADHD). Hence, this study aimed to distinguish both medication-naïve and medicated adults with ADHD from healthy controls (HC). METHOD: 75 HCs, 75 medication-naïve, and 45 medicated patients took part in this study. fNIRS signals during a verbal fluency task (VFT) were acquired using a 52-channel system and relative oxy-hemoglobin changes in the prefrontal cortex were quantified. RESULTS: Prefrontal cortex hemodynamic response was lower in patients than HCs (p ≤ ≤.001). Medication-naïve and medicated patients did not differ in hemodynamic response or symptom severity (p > .05). fNIRS measurements were not associated with any clinical variables (p > .05). 75.8% patients and 76% HCs were correctly classified using hemodynamic response. CONCLUSION: fNIRS may be a potential diagnostic tool for adult ADHD. These findings need to be replicated in larger validation studies.

Clinical outcomes and thermodynamics aspect of direct brain cooling in severe head injury.

Background: Brain cooling therapy is one of the subjects of interest, and currently, data on direct brain cooling are lacking. Hence, the objective is to investigate the clinical outcomes and discuss the thermodynamics aspect of direct brain cooling on severely injured brain patients. Methods: This pilot study recruited the severely injured brain patients who were then randomized to either a direct brain cooling therapy group using a constant cooling temperature system or a control group. All studied patients must be subjected to an emergency neurosurgical procedure of decompressive craniectomy and were monitored with intracranial pressure, brain oxygenation, and temperature. Further, comparison was made with our historical group of patients who had direct brain cooling therapy through the old technique. Results: The results disclosed the direct brain cooling treated patients through a newer technique obtained a better Extended Glasgow Outcome Score than a control group (P < 001). In addition, there is a significant outcome difference between the combined cooling treated patients (new and old technique) with the control group (P < 0.001). Focal brain oxygenation and temperature are likely factors that correlate with better outcomes. Conclusion: Direct brain cooling is feasible, safe, and affects the clinical outcomes of the severely traumatized brain, and physics of thermodynamics may play a role in its pathophysiology.

EDR-Net: Lightweight Deep Neural Network Architecture for Detecting Referable Diabetic Retinopathy.

Present architecture of convolution neural network for diabetic retinopathy (DR-Net) is based on normal convolution (NC). It incurs high computational cost as NC uses a multiplicative weight that measures a combined correlation in both cross-channel and spatial dimension of layer's inputs. This might cause the overall DR-Net architecture to be over-parameterised and computationally inefficient. This paper proposes EDR-Net - a new end-to-end, DR-Net architecture with depth-wise separable convolution module. The EDR-Net architecture was trained with DRKaggle-train dataset (35,126 images), and tested on two datasets, i.e. DRKaggle-test (53,576 images) and Messidor-2 (1,748 images). Results showed that the proposed EDR-Net achieved predictive performance comparable with current state-of-the-arts in detecting referable diabetic retinopathy (rDR) from fundus images and outperformed other light weight architectures, with at least two times less computation cost. This makes it more amenable for mobile device based computer-assisted rDR screening applications.

Wavelet-Based Fractal Analysis of rs-fMRI for Classification of Alzheimer's Disease.

The resting-state functional magnetic resonance imaging (rs-fMRI) modality has gained widespread acceptance as a promising method for analyzing a variety of neurological and psychiatric diseases. It is established that resting-state neuroimaging data exhibit fractal behavior, manifested in the form of slow-decaying auto-correlation and power-law scaling of the power spectrum across low-frequency components. With this property, the rs-fMRI signal can be broken down into fractal and nonfractal components. The fractal nature originates from several sources, such as cardiac fluctuations, respiration and system noise, and carries no information on the brain's neuronal activities. As a result, the conventional correlation of rs-fMRI signals may not accurately reflect the functional dynamic of spontaneous neuronal activities. This problem can be solved by using a better representation of neuronal activities provided by the connectivity of nonfractal components. In this work, the nonfractal connectivity of rs-fMRI is used to distinguish Alzheimer's patients from healthy controls. The automated anatomical labeling (AAL) atlas is used to extract the blood-oxygenation-level-dependent time series signals from 116 brain regions, yielding a 116 × 116 nonfractal connectivity matrix. From this matrix, significant connections evaluated using the p-value are selected as an input to a classifier for the classification of Alzheimer's vs. normal controls. The nonfractal-based approach provides a good representation of the brain's neuronal activity. It outperformed the fractal and Pearson-based connectivity approaches by 16.4% and 17.2%, respectively. The classification algorithm developed based on the nonfractal connectivity feature and support vector machine classifier has shown an excellent performance, with an accuracy of 90.3% and 83.3% for the XHSLF dataset and ADNI dataset, respectively. For further validation of our proposed work, we combined the two datasets (XHSLF+ADNI) and still received an accuracy of 90.2%. The proposed work outperformed the recently published work by a margin of 8.18% and 11.2%, respectively.

Resilience-Building for Mental Health among Early Childhood Educators: A Systematic Review and Pilot-Study towards an EEG-VR Resilience Building Intervention.

Resilience is a key factor that reflects a teacher's ability to utilize their emotional resources and working skills to provide high-quality teaching to children. Resilience-building interventions aim to promote positive psychological functioning and well-being. However, there is lack of evidence on whether these interventions improve the well-being or mental health of teachers in early childhood education (ECE) settings. This review examined the overall effectiveness of resilience-building interventions conducted on teachers working in the ECE field. A systematic approach is used to identify relevant studies that focus on resilience-building in countering work stress among early childhood educators. Findings from this review observed a preference of group approaches and varying durations of interventions. This review highlights the challenges of the group approach which can lead to lengthy interventions and attrition amongst participants. In addition to the concerns regarding response bias from self-report questionnaires, there is also a lack of physiological measures used to evaluate effects on mental health. The large efforts by 11 studies to integrate multiple centres into their intervention and the centre-based assessment performed by four studies highlight the need for a centre-focused approach to build resilience among teachers from various ECE centres. A pilot study is conducted to evaluate the feasibility of an integrated electroencephalography-virtual reality (EEG-VR) approach in building resilience in teachers, where the frontal brain activity can be monitored during a virtual classroom task. Overall, the findings of this review propose the integration of physiological measures to monitor changes in mental health throughout the resilience-building intervention and the use of VR as a tool to design a unique virtual environment.

A Standards Organization for Open and FAIR Neuroscience: the International Neuroinformatics Coordinating Facility.

There is great need for coordination around standards and best practices in neuroscience to support efforts to make neuroscience a data-centric discipline. Major brain initiatives launched around the world are poised to generate huge stores of neuroscience data. At the same time, neuroscience, like many domains in biomedicine, is confronting the issues of transparency, rigor, and reproducibility. Widely used, validated standards and best practices are key to addressing the challenges in both big and small data science, as they are essential for integrating diverse data and for developing a robust, effective, and sustainable infrastructure to support open and reproducible neuroscience. However, developing community standards and gaining their adoption is difficult. The current landscape is characterized both by a lack of robust, validated standards and a plethora of overlapping, underdeveloped, untested and underutilized standards and best practices. The International Neuroinformatics Coordinating Facility (INCF), an independent organization dedicated to promoting data sharing through the coordination of infrastructure and standards, has recently implemented a formal procedure for evaluating and endorsing community standards and best practices in support of the FAIR principles. By formally serving as a standards organization dedicated to open and FAIR neuroscience, INCF helps evaluate, promulgate, and coordinate standards and best practices across neuroscience. Here, we provide an overview of the process and discuss how neuroscience can benefit from having a dedicated standards body.

Functional near-infrared spectroscopy during the verbal fluency task of English-Speaking adults with mood disorders: A preliminary study.

Functional near-infrared spectroscopy (fNIRS) provides a direct and objective assessment of cerebral cortex function. It may be used to determine neurophysiological differences between psychiatric disorders with overlapping symptoms, such as major depressive disorder (MDD) and bipolar disorder (BD). Therefore, this preliminary study aimed to compare fNIRS signals during the verbal fluency task (VFT) of English-speaking healthy controls (HC), patients with MDD and patients with BD. Fifteen HCs, 15 patients with MDD and 15 patients with BD were recruited. Groups were matched for age, gender, ethnicity and education. Relative oxy-haemoglobin and deoxy-haemoglobin changes in the frontotemporal cortex was monitored with a 52-channel fNIRS system. Integral values of the frontal and temporal regions were derived as a measure cortical haemodynamic response magnitude. Both patient groups had lower frontal and temporal region integral values than HCs, and patients with MDD had lower frontal region integral value than patients with BD. Moreover, patients could be differentiated from HCs using the frontal and temporal integral values, and patient groups could be differentiated using the frontal region integral values. VFT performance, clinical history and symptom severity were not associated with integral values. These results suggest that prefrontal cortex haemodynamic dysfunction occurs in mood disorders, and it is more extensive in MDD than BD. The fNIRS-VFT paradigm may be a potential tool for differentiating MDD from BD in clinical settings, and these findings need to be verified in a larger sample of English-speaking patients with mood disorders.

Detection of Collaterals from Cone-Beam CT Images in Stroke.

Collateral vessels play an important role in the restoration of blood flow to the ischemic tissues of stroke patients, and the quality of collateral flow has major impact on reducing treatment delay and increasing the success rate of reperfusion. Due to high spatial resolution and rapid scan time, advance imaging using the cone-beam computed tomography (CBCT) is gaining more attention over the conventional angiography in acute stroke diagnosis. Detecting collateral vessels from CBCT images is a challenging task due to the presence of noises and artifacts, small-size and non-uniform structure of vessels. This paper presents a technique to objectively identify collateral vessels from non-collateral vessels. In our technique, several filters are used on the CBCT images of stroke patients to remove noises and artifacts, then multiscale top-hat transformation method is implemented on the pre-processed images to further enhance the vessels. Next, we applied three types of feature extraction methods which are gray level co-occurrence matrix (GLCM), moment invariant, and shape to explore which feature is best to classify the collateral vessels. These features are then used by the support vector machine (SVM), random forest, decision tree, and K-nearest neighbors (KNN) classifiers to classify vessels. Finally, the performance of these classifiers is evaluated in terms of accuracy, sensitivity, precision, recall, F-Measure, and area under the receiver operating characteristics curve. Our results show that all classifiers achieve promising classification accuracy above 90% and able to detect the collateral and non-collateral vessels from images.

Integration of the Cortical Haemodynamic Response Measured by Functional Near-Infrared Spectroscopy and Amino Acid Analysis to Aid in the Diagnosis of Major Depressive Disorder.

BACKGROUND: Major depressive disorder (MDD) is a debilitating condition with a high disease burden and medical comorbidities. There are currently few to no validated biomarkers to guide the diagnosis and treatment of MDD. In the present study, we evaluated the differences between MDD patients and healthy controls (HCs) in terms of cortical haemodynamic responses during a verbal fluency test (VFT) using functional near-infrared spectroscopy (fNIRS) and serum amino acid profiles, and ascertained if these parameters were correlated with clinical characteristics. METHODS: Twenty-five (25) patients with MDD and 25 age-, gender-, and ethnicity-matched HCs were recruited for the study. Real-time monitoring of the haemodynamic response during completion of a VFT was quantified using a 52-channel NIRS system. Serum samples were analysed and quantified by liquid chromatography-mass spectrometry for amino acid profiling. Receiver-operating characteristic (ROC) curves were used to classify potential candidate biomarkers. RESULTS: The MDD patients had lower prefrontal and temporal activation during completion of the VFT than HCs. The MDD patients had lower mean concentrations of oxy-Hb in the left orbitofrontal cortex (OFC), and lower serum histidine levels. When the oxy-haemoglobin response was combined with the histidine concentration, the sensitivity and specificity of results improved significantly from 66.7% to 73.3% and from 65.0% to 90.0% respectively, as compared to results based only on the NIRS response. CONCLUSIONS: These findings demonstrate the use of combination biomarkers to aid in the diagnosis of MDD. This technique could be a useful approach to detect MDD with greater precision, but additional studies are required to validate the methodology.

Working Memory Performance under a Negative Affect Is More Susceptible to Higher Cognitive Workloads with Different Neural Haemodynamic Correlates.

The effect of stress on task performance is complex, too much or too little stress negatively affects performance and there exists an optimal level of stress to drive optimal performance. Task difficulty and external affective factors are distinct stressors that impact cognitive performance. Neuroimaging studies showed that mood affects working memory performance and the correlates are changes in haemodynamic activity in the prefrontal cortex (PFC). We investigate the interactive effects of affective states and working memory load (WML) on working memory task performance and haemodynamic activity using functional near-infrared spectroscopy (fNIRS) neuroimaging on the PFC of healthy participants. We seek to understand if haemodynamic responses could tell apart workload-related stress from situational stress arising from external affective distraction. We found that the haemodynamic changes towards affective stressor- and workload-related stress were more dominant in the medial and lateral PFC, respectively. Our study reveals distinct affective state-dependent modulations of haemodynamic activity with increasing WML in n-back tasks, which correlate with decreasing performance. The influence of a negative effect on performance is greater at higher WML, and haemodynamic activity showed evident changes in temporal, and both spatial and strength of activation differently with WML.

Automatic Polyp Segmentation in Colonoscopy Images Using a Modified Deep Convolutional Encoder-Decoder Architecture.

Colorectal cancer has become the third most commonly diagnosed form of cancer, and has the second highest fatality rate of cancers worldwide. Currently, optical colonoscopy is the preferred tool of choice for the diagnosis of polyps and to avert colorectal cancer. Colon screening is time-consuming and highly operator dependent. In view of this, a computer-aided diagnosis (CAD) method needs to be developed for the automatic segmentation of polyps in colonoscopy images. This paper proposes a modified SegNet Visual Geometry Group-19 (VGG-19), a form of convolutional neural network, as a CAD method for polyp segmentation. The modifications include skip connections, 5 × 5 convolutional filters, and the concatenation of four dilated convolutions applied in parallel form. The CVC-ClinicDB, CVC-ColonDB, and ETIS-LaribPolypDB databases were used to evaluate the model, and it was found that our proposed polyp segmentation model achieved an accuracy, sensitivity, specificity, precision, mean intersection over union, and dice coefficient of 96.06%, 94.55%, 97.56%, 97.48%, 92.3%, and 95.99%, respectively. These results indicate that our model performs as well as or better than previous schemes in the literature. We believe that this study will offer benefits in terms of the future development of CAD tools for polyp segmentation for colorectal cancer diagnosis and management. In the future, we intend to embed our proposed network into a medical capsule robot for practical usage and try it in a hospital setting with clinicians.

Bimodal Data Fusion of Simultaneous Measurements of EEG and fNIRS during Lower Limb Movements.

Electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) have temporal and spatial characteristics that may complement each other and, therefore, pose an intriguing approach for brain-computer interaction (BCI). In this work, the relationship between the hemodynamic response and brain oscillation activity was investigated using the concurrent recording of fNIRS and EEG during ankle joint movements. Twenty subjects participated in this experiment. The EEG was recorded using 20 electrodes and hemodynamic responses were recorded using 32 optodes positioned over the motor cortex areas. The event-related desynchronization (ERD) feature was extracted from the EEG signal in the alpha band (8-11) Hz, and the concentration change of the oxy-hemoglobin (oxyHb) was evaluated from the hemodynamics response. During the motor execution of the ankle joint movements, a decrease in the alpha (8-11) Hz amplitude (desynchronization) was found to be correlated with an increase of the oxyHb (r = -0.64061, p < 0.00001) observed on the Cz electrode and the average of the fNIRS channels (ch28, ch25, ch32, ch35) close to the foot area representation. Then, the correlated channels in both modalities were used for ankle joint movement classification. The result demonstrates that the integrated modality based on the correlated channels provides a substantial enhancement in ankle joint classification accuracy of 93.01 ± 5.60% (p < 0.01) compared with single modality. These results highlight the potential of the bimodal fNIR-EEG approach for the development of future BCI for lower limb rehabilitation.

Detection of Emotional Sensitivity Using fNIRS Based Dynamic Functional Connectivity.

In this study, we proposed an analytical framework to identify dynamic task-based functional connectivity (FC) features as new biomarkers of emotional sensitivity in nursing students, by using a combination of unsupervised and supervised machine learning techniques. The dynamic FC was measured by functional Near-Infrared Spectroscopy (fNIRS), and computed using a sliding window correlation (SWC) analysis. A k -means clustering technique was applied to derive four recurring connectivity states. The states were characterized by both graph theory and semi-metric analysis. Occurrence probability and state transition were extracted as dynamic FC network features, and a Random Forest (RF) classifier was implemented to detect emotional sensitivity. The proposed method was trialled on 39 nursing students and 19 registered nurses during decision-making, where we assumed registered nurses have developed strategies to cope with emotional sensitivity. Emotional stimuli were selected from International Affective Digitized Sound System (IADS) database. Experiment results showed that registered nurses demonstrated single dominant connectivity state of task-relevance, while nursing students displayed in two states and had higher level of task-irrelevant state connectivity. The results also showed that students were more susceptive to emotional stimuli, and the derived dynamic FC features provided a stronger discriminating power than heart rate variability (accuracy of 81.65% vs 71.03%) as biomarkers of emotional sensitivity. This work forms the first study to demonstrate the stability of fNIRS based dynamic FC states as a biomarker. In conclusion, the results support that the state distribution of dynamic FC could help reveal the differentiating factors between the nursing students and registered nurses during decision making, and it is anticipated that the biomarkers might be used as indicators when developing professional training related to emotional sensitivity.

Automatic colonic polyp detection using integration of modified deep residual convolutional neural network and ensemble learning approaches.

BACKGROUND AND OBJECTIVE: The increased incidence of colorectal cancer (CRC) and its mortality rate have attracted interest in the use of artificial intelligence (AI) based computer-aided diagnosis (CAD) tools to detect polyps at an early stage. Although these CAD tools have thus far achieved a good accuracy level to detect polyps, they still have room to improve further (e.g. sensitivity). Therefore, a new CAD tool is developed in this study to detect colonic polyps accurately. METHODS: In this paper, we propose a novel approach to distinguish colonic polyps by integrating several techniques, including a modified deep residual network, principal component analysis and AdaBoost ensemble learning. A powerful deep residual network architecture, ResNet-50, was investigated to reduce the computational time by altering its architecture. To keep the interference to a minimum, median filter, image thresholding, contrast enhancement, and normalisation techniques were exploited on the endoscopic images to train the classification model. Three publicly available datasets, i.e., Kvasir, ETIS-LaribPolypDB, and CVC-ClinicDB, were merged to train the model, which included images with and without polyps. RESULTS: The proposed approach trained with a combination of three datasets achieved Matthews Correlation Coefficient (MCC) of 0.9819 with accuracy, sensitivity, precision, and specificity of 99.10%, 98.82%, 99.37%, and 99.38%, respectively. CONCLUSIONS: These results show that our method could repeatedly classify endoscopic images automatically and could be used to effectively develop computer-aided diagnostic tools for early CRC detection.

Cortical haemodynamic response during the verbal fluency task in patients with bipolar disorder and borderline personality disorder: a preliminary functional near-infrared spectroscopy study.

BACKGROUND: Functional near-infrared spectroscopy (fNIRS) is an emerging neuroimaging modality that provides a direct and quantitative assessment of cortical haemodynamic response during a cognitive task. It may be used to identify neurophysiological differences between psychiatric disorders with overlapping symptoms, such as bipolar disorder (BD) and borderline personality disorder (BPD). Hence, this preliminary study aimed to compare the cerebral haemodynamic function of healthy controls (HC), patients with BD and patients with BPD. METHODS: Twenty-seven participants (9 HCs, 9 patients with BD and 9 patients with BPD) matched for age, gender, ethnicity and education were recruited. Relative oxy-haemoglobin and deoxy-haemoglobin changes in the frontotemporal cortex was monitored with a 52-channel fNIRS system during a verbal fluency task (VFT). VFT performance, clinical history and symptom severity were also noted. RESULTS: Compared to HCs, both patient groups had lower mean oxy-haemoglobin in the frontotemporal cortex during the VFT. Moreover, mean oxy-haemoglobin in the left inferior frontal region is markedly lower in patients with BPD compared to patients with BD. Task performance, clinical history and symptom severity were not associated with mean oxy-haemoglobin levels. CONCLUSIONS: Prefrontal cortex activity is disrupted in patients with BD and BPD, but it is more extensive in BPD. These results provide further neurophysiological evidence for the separation of BPD from the bipolar spectrum. fNIRS could be a potential tool for assessing the frontal lobe function of patients who present with symptoms that are common to BD and BPD.

Optimizing Mental Workload Estimation by Detecting Baseline State Using Vector Phase Analysis Approach.

Improper baseline return from the previous task-evoked hemodynamic response (HR) can contribute to a large variation in the subsequent HR, affecting the estimation of mental workload in brain-computer interface systems. In this study, we proposed a method using vector phase analysis to detect the baseline state as being optimal or suboptimal. We hypothesize that selecting neuronal-related HR as observed in the optimal-baseline blocks can lead to an improvement in estimating mental workload. Oxygenated and deoxygenated hemoglobin concentration changes were integrated as parts of the vector phase. The proposed method was applied to a block-design functional near-infrared spectroscopy dataset (total blocks = 1384), measured on 24 subjects performing multiple difficulty levels of mental arithmetic task. Significant differences in hemodynamic signal change were observed between the optimal- and suboptimal-baseline blocks detected using the proposed method. This supports the effectiveness of the proposed method in detecting baseline state for better estimation of mental workload. The results further highlight the need of customized recovery duration. In short, the proposed method offers a practical approach to detect task-evoked signals, without the need of extra probes.