A Novel Approach to Surface EMG-based Gesture Classification Using a Vision Transformer Integrated with Convolutive Blind Source Separation.

A robust pattern recognition framework is required for ideal real-time human-machine interface (HMI) applications. Convolutional neural networks and recurrent neural networks have been widely used for the classification of gestures based on electromyography (EMG), but few studies have demonstrated the effectiveness of using a vision transformer for this purpose. Additionally, the accuracy achieved is influenced by the efficacy of the preprocessing pipeline. This study assessed ViT with and without an attention mechanism for precise motor intent decoding by investigating various input features and integrating convolutive blind source separation (BSS) preprocessing. All investigations were carried out with two open-access high-density surface EMG datasets of 34 and 21 hand gestures recorded from 20 and 5 healthy subjects respectively. Integration of centering and optimal extension factors resulted in better performance with raw input. However, spatial whitening increased the model's sensitivity to noise. The best-performing BSS-integrated convolution vision transformer model (BSS-CViT) model yielded an accuracy of 96.61% and 91.98% on test datasets one and two. This is a promising result for future studies in real-time HMI applications. The code implementation results reported in this study are available on GitHub. https://github.com/deremustapha/BSS-ViT.

Beyond the Microscope: A Technological Overture for Cervical Cancer Detection.

Cervical cancer is a common and preventable disease that poses a significant threat to women's health and well-being. It is the fourth most prevalent cancer among women worldwide, with approximately 604,000 new cases and 342,000 deaths in 2020, according to the World Health Organization. Early detection and diagnosis of cervical cancer are crucial for reducing mortality and morbidity rates. The Papanicolaou smear test is a widely used screening method that involves the examination of cervical cells under a microscope to identify any abnormalities. However, this method is time-consuming, labor-intensive, subjective, and prone to human errors. Artificial intelligence techniques have emerged as a promising alternative to improve the accuracy and efficiency of Papanicolaou smear diagnosis. Artificial intelligence techniques can automatically analyze Papanicolaou smear images and classify them into normal or abnormal categories, as well as detect the severity and type of lesions. This paper provides a comprehensive review of the recent advances in artificial intelligence diagnostics of the Papanicolaou smear, focusing on the methods, datasets, performance metrics, and challenges. The paper also discusses the potential applications and future directions of artificial intelligence diagnostics of the Papanicolaou smear.

Multiclass classification of imagined speech EEG using noise-assisted multivariate empirical mode decomposition and multireceptive field convolutional neural network.

Introduction: In this study, we classified electroencephalography (EEG) data of imagined speech using signal decomposition and multireceptive convolutional neural network. The imagined speech EEG with five vowels /a/, /e/, /i/, /o/, and /u/, and mute (rest) sounds were obtained from ten study participants. Materials and methods: First, two different signal decomposition methods were applied for comparison: noise-assisted multivariate empirical mode decomposition and wavelet packet decomposition. Six statistical features were calculated from the decomposed eight sub-frequency bands EEG. Next, all features obtained from each channel of the trial were vectorized and used as the input vector of classifiers. Lastly, EEG was classified using multireceptive field convolutional neural network and several other classifiers for comparison. Results: We achieved an average classification rate of 73.09 and up to 80.41% in a multiclass (six classes) setup (Chance: 16.67%). In comparison with various other classifiers, significant improvements for other classifiers were achieved (p-value < 0.05). From the frequency sub-band analysis, high-frequency band regions and the lowest-frequency band region contain more information about imagined vowel EEG data. The misclassification and classification rate of each vowel imaginary EEG was analyzed through a confusion matrix. Discussion: Imagined speech EEG can be classified successfully using the proposed signal decomposition method and a convolutional neural network. The proposed classification method for imagined speech EEG can contribute to developing a practical imagined speech-based brain-computer interfaces system.

CervixFormer: A Multi-scale swin transformer-Based cervical pap-Smear WSI classification framework.

BACKGROUND AND OBJECTIVES: Cervical cancer affects around 0.5 million women per year, resulting in over 0.3 million fatalities. Therefore, repetitive screening for cervical cancer is of utmost importance. Computer-assisted diagnosis is key for scaling up cervical cancer screening. Current recognition algorithms, however, perform poorly on the whole-slide image (WSI) analysis, fail to generalize for different staining methods and on uneven distribution for subtype imaging, and provide sub-optimal clinical-level interpretations. Herein, we developed CervixFormer-an end-to-end, multi-scale swin transformer-based adversarial ensemble learning framework to assess pre-cancerous and cancer-specific cervical malignant lesions on WSIs. METHODS: The proposed framework consists of (1) a self-attention generative adversarial network (SAGAN) for generating synthetic images during patch-level training to address the class imbalanced problems; (2) a multi-scale transformer-based ensemble learning method for cell identification at various stages, including atypical squamous cells (ASC) and atypical squamous cells of undetermined significance (ASCUS), which have not been demonstrated in previous studies; and (3) a fusion model for concatenating ensemble-based results and producing final outcomes. RESULTS: In the evaluation, the proposed method is first evaluated on a private dataset of 717 annotated samples from six classes, obtaining a high recall and precision of 0.940 and 0.934, respectively, in roughly 1.2 minutes. To further examine the generalizability of CervixFormer, we evaluated it on four independent, publicly available datasets, namely, the CRIC cervix, Mendeley LBC, SIPaKMeD Pap Smear, and Cervix93 Extended Depth of Field image datasets. CervixFormer obtained a fairly better performance on two-, three-, four-, and six-class classification of smear- and cell-level datasets. For clinical interpretation, we used GradCAM to visualize a coarse localization map, highlighting important regions in the WSI. Notably, CervixFormer extracts feature mostly from the cell nucleus and partially from the cytoplasm. CONCLUSIONS: In comparison with the existing state-of-the-art benchmark methods, the CervixFormer outperforms them in terms of recall, accuracy, and computing time.

Differential relationship of observer-rated and self-rated depression and anxiety scales with heart rate variability features.

Heart rate variability (HRV) is a known psychophysiological marker for diverse psychiatric symptoms. In this study, we aimed to explore the potential for clinical use of HRV by investigating the interrelationship between HRV indices and clinical measures mainly used to assess depressive and anxious symptoms. Participants who reported depressive and anxious symptoms were designated into the following groups: group 1, clinician-rated and self-rated depression; group 2, only self-rated depression; group 3, clinician-rated and self-rated anxiety; group 4, only self-rated anxiety. Statistical comparisons were performed between these groups to investigate the association between HRV and clinical measures. As a result, HRV variables showed significant correlations only with the clinician-rated assessments. Moreover, both time and frequency domain HRV indices were significantly different between groups 1 and 2, but groups 3 and 4 showed significant differences only in frequency domain HRV indices. Our study showed that HRV is an objective indicator for depressive or anxious symptoms. Additionally, it is considered a potential indicator for predicting the severity or state of depressive symptoms rather than of anxious symptoms. This study will contribute to increasing the diagnostic utility of discriminating those symptoms based on HRV in the future.

Vowel speech recognition from rat electroencephalography using long short-term memory neural network.

Over the years, considerable research has been conducted to investigate the mechanisms of speech perception and recognition. Electroencephalography (EEG) is a powerful tool for identifying brain activity; therefore, it has been widely used to determine the neural basis of speech recognition. In particular, for the classification of speech recognition, deep learning-based approaches are in the spotlight because they can automatically learn and extract representative features through end-to-end learning. This study aimed to identify particular components that are potentially related to phoneme representation in the rat brain and to discriminate brain activity for each vowel stimulus on a single-trial basis using a bidirectional long short-term memory (BiLSTM) network and classical machine learning methods. Nineteen male Sprague-Dawley rats subjected to microelectrode implantation surgery to record EEG signals from the bilateral anterior auditory fields were used. Five different vowel speech stimuli were chosen, /a/, /e/, /i/, /o/, and /u/, which have highly different formant frequencies. EEG recorded under randomly given vowel stimuli was minimally preprocessed and normalized by a z-score transformation to be used as input for the classification of speech recognition. The BiLSTM network showed the best performance among the classifiers by achieving an overall accuracy, f1-score, and Cohen's κ values of 75.18%, 0.75, and 0.68, respectively, using a 10-fold cross-validation approach. These results indicate that LSTM layers can effectively model sequential data, such as EEG; hence, informative features can be derived through BiLSTM trained with end-to-end learning without any additional hand-crafted feature extraction methods.

An effective modular approach for crowd counting in an image using convolutional neural networks.

Abrupt and continuous nature of scale variation in a crowded scene is a challenging task to enhance crowd counting accuracy in an image. Existing crowd counting techniques generally used multi-column or single-column dilated convolution to tackle scale variation due to perspective distortion. However, due to multi-column nature, they obtain identical features, whereas, the standard dilated convolution (SDC) with expanded receptive field size has sparse pixel sampling rate. Due to sparse nature of SDC, it is highly challenging to obtain relevant contextual information. Further, features at multiple scale are not extracted despite some inception-based model is not used (which is cost effective). To mitigate theses drawbacks in SDC, we therefore, propose a hierarchical dense dilated deep pyramid feature extraction through convolution neural network (CNN) for single image crowd counting (HDPF). It comprises of three modules: general feature extraction module (GFEM), deep pyramid feature extraction module (PFEM) and fusion module (FM). The GFEM is responsible to obtain task independent general features. Whereas, PFEM plays a vital role to obtain the relevant contextual information due to dense pixel sampling rate caused by densely connected dense stacked dilated convolutional modules (DSDCs). Further, due to dense connections among DSDCs, the final feature map acquires multi-scale information with expanded receptive field as compared to SDC. Due to dense pyramid nature, it is very effective to propagate the extracted feature from lower dilated convolutional layers (DCLs) to middle and higher DCLs, which result in better estimation accuracy. The FM is used to fuse the incoming features extracted by other modules. The proposed technique is tested through simulations on three well known datasets: Shanghaitech (Part-A), Shanghaitech (Part-B) and Venice. Results justify its relative effectiveness in terms of selected performance.

HADF-Crowd: A Hierarchical Attention-Based Dense Feature Extraction Network for Single-Image Crowd Counting.

Crowd counting is a challenging task due to large perspective, density, and scale variations. CNN-based crowd counting techniques have achieved significant performance in sparse to dense environments. However, crowd counting in high perspective-varying scenes (images) is getting harder due to different density levels occupied by the same number of pixels. In this way large variations for objects in the same spatial area make it difficult to count accurately. Further, existing CNN-based crowd counting methods are used to extract rich deep features; however, these features are used locally and disseminated while propagating through intermediate layers. This results in high counting errors, especially in dense and high perspective-variation scenes. Further, class-specific responses along channel dimensions are underestimated. To address these above mentioned issues, we therefore propose a CNN-based dense feature extraction network for accurate crowd counting. Our proposed model comprises three main modules: (1) backbone network, (2) dense feature extraction modules (DFEMs), and (3) channel attention module (CAM). The backbone network is used to obtain general features with strong transfer learning ability. The DFEM is composed of multiple sub-modules called dense stacked convolution modules (DSCMs), densely connected with each other. In this way features extracted from lower and middle-lower layers are propagated to higher layers through dense connections. In addition, combinations of task independent general features obtained by the former modules and task-specific features obtained by later ones are incorporated to obtain high counting accuracy in large perspective-varying scenes. Further, to exploit the class-specific response between background and foreground, CAM is incorporated at the end to obtain high-level features along channel dimensions for better counting accuracy. Moreover, we have evaluated the proposed method on three well known datasets: Shanghaitech (Part-A), Shanghaitech (Part-B), and Venice. The performance of the proposed technique justifies its relative effectiveness in terms of selected performance compared to state-of-the-art techniques.

EEG microstate features for schizophrenia classification.

Electroencephalography (EEG) microstate analysis is a method wherein spontaneous EEG activity is segmented at sub-second levels to analyze quasi-stable states. In particular, four archetype microstates and their features are known to reflect changes in brain state in neuropsychiatric diseases. However, previous studies have only reported differences in each microstate feature and have not determined whether microstate features are suitable for schizophrenia classification. Therefore, it is necessary to validate microstate features for schizophrenia classification. Nineteen microstate features, including duration, occurrence, and coverage as well as thirty-one conventional EEG features, including statistical, frequency, and temporal characteristics were obtained from resting-state EEG recordings of 14 patients diagnosed with schizophrenia and from 14 healthy (control) subjects. Machine-learning based multivariate analysis was used to evaluate classification performance. EEG recordings of patients and controls showed different microstate features. More importantly, when differentiating among patients and controls, EEG microstate features outperformed conventional EEG ones. The performance of the microstate features exceeded that of conventional EEG, even after optimization using recursive feature elimination. EEG microstate features applied with conventional EEG features also showed better classification performance than conventional EEG features alone. The current study is the first to validate the use of microstate features to discriminate schizophrenia, suggesting that EEG microstate features are useful for schizophrenia classification.

EEG microstate features according to performance on a mental arithmetic task.

In this study, we hypothesized that task performance could be evaluated applying EEG microstate to mental arithmetic task. This pilot study also aimed at evaluating the efficacy of microstates as novel features to discriminate task performance. Thirty-six subjects were divided into good and poor performers, depending on how well they performed the task. Microstate features were derived from EEG recordings during resting and task states. In the good performers, there was a decrease in type C and an increase in type D features during the task compared to the resting state. Mean duration and occurrence decreased and increased, respectively. In the poor performers, occurrence of type D feature, mean duration and occurrence showed greater changes. We investigated whether microstate features were suitable for task performance classification and eleven features including four archetypes were selected by recursive feature elimination (RFE). The model that implemented them showed the highest classification performance for differentiating between groups. Our pilot findings showed that the highest mean Area Under Curve (AUC) was 0.831. This study is the first to apply EEG microstate features to specific cognitive tasks in healthy subjects, suggesting that EEG microstate features can reflect task achievement.

Quantification of stroke lesion volume using epidural EEG in a cerebral ischaemic rat model.

Precise monitoring of the brain after a stroke is essential for clinical decision making. Due to the non-invasive nature and high temporal resolution of electroencephalography (EEG), it is widely used to evaluate real-time cortical activity. In this study, we investigated the stroke-related EEG biomarkers and developed a predictive model for quantifying the structural brain damage in a focal cerebral ischaemic rat model. We enrolled 31 male Sprague-Dawley rats and randomly assigned them to mild stroke, moderate stroke, severe stroke, and control groups. We induced photothrombotic stroke targeting the right auditory cortex. We then acquired EEG signal responses to sound stimuli (frequency linearly increasing from 8 to 12 kHz with 750 ms duration). Power spectral analysis revealed a significant correlation of the relative powers of alpha, theta, delta, delta/alpha ratio, and (delta + theta)/(alpha + beta) ratio with the stroke lesion volume. The auditory evoked potential analysis revealed a significant association of amplitude and latency with stroke lesion volume. Finally, we developed a multiple regression model combining EEG predictors for quantifying the ischaemic lesion (R2 = 0.938, p value < 0.001). These findings demonstrate the potential application of EEG as a valid modality for monitoring the brain after a stroke.

Susceptibility of pentylenetetrazole-induced seizures in mice with Cereblon gene knockout.

Epilepsy is a neurological disorder characterized by unpredictable seizures, which are bursts of electrical activity that temporarily affect the brain. Cereblon (CRBN), a DCAFs (DDB1 and CUL4-associated factors), is a well-established protein associated with human mental retardation. Being a substrate receptor of the cullin-RING E3 ubiquitin ligase (CRL) 4 complex, CRBN mediates ubiquitination of several substrates and conducts multiple biological processes. In the central nervous system, the largeconductance Ca2+-activated K+ (BKCa) channel, which is the substrate of CRBN, is an important regulator of epilepsy. Despite the functional role and importance of CRBN in the brain, direct injection of pentylenetetrazole (PTZ) to induce seizures in CRBN knock-out mice has not been challenged. In this study, we investigated the effect of PTZ in CRBN knock-out mice. Here, we demonstrate that, compared with WT mice, CRBN knock-out mice do not show the intensification of seizures by PTZ induction. Moreover, electroencephalography recordings were also performed in the brains of both WT and CRBN knockout mice to identify the absence of significant differences in the pattern of seizure activities. Consistently, immunoblot analysis for validating the protein level of the CRL4 complex containing CRBN (CRL4Crbn) in the mouse brain was carried out. Taken together, we found that the deficiency of CRBN does not affect PTZ-induced seizure. [BMB Reports 2020; 53(9): 484-489].

Performance of the nasal photoplethysmographic index as an analgesic index during surgery under general anaesthesia.

In a previous study, we developed a new analgesic index using nasal photoplethysmography (nasal photoplethysmographic index, NPI) and showed that the NPI was superior to the surgical pleth index (SPI) in distinguishing pain above numerical rating scale 3. Because the NPI was developed using data obtained from conscious patients with pain, we evaluated the performance of NPI in comparison with the SPI and the analgesia nociception index (ANI) in patients under general anaesthesia with target-controlled infusion of propofol and remifentanil. The time of nociception occurrence was defined as when the signs of inadequate anaesthesia occurred. The median values of NPI, SPI, and ANI for 1 minute from the time of the sign of inadequate anaesthesia were determined as the value of each analgesic index that represents inadequate anaesthesia. The time of no nociception was determined as 2 minutes before the onset of skin incision, and the median value for 1 minute from that time was defined as the baseline value. In total, 81 patients were included in the analysis. NPI showed good performance in distinguishing inadequate anaesthesia during propofol-remifentanil based general anaesthesia. NPI had the highest value in terms of area under the receiver operating characteristic curve, albeit without statistical significance (NPI: 0.733, SPI: 0.722, ANI: 0.668). The coefficient of variations of baseline values of NPI, SPI, and ANI were 27.5, 47.2, and 26.1, respectively. Thus, the NPI was effective for detecting inadequate anaesthesia, showing similar performance with both indices and less baseline inter-individual variability than the SPI.

3D-Deep Learning Based Automatic Diagnosis of Alzheimer's Disease with Joint MMSE Prediction Using Resting-State fMRI.

We performed this research to 1) evaluate a novel deep learning method for the diagnosis of Alzheimer's disease (AD) and 2) jointly predict the Mini Mental State Examination (MMSE) scores of South Korean patients with AD. Using resting-state functional Magnetic Resonance Imaging (rs-fMRI) scans of 331 participants, we obtained functional 3-dimensional (3-D) independent component spatial maps for use as features in classification and regression tasks. A 3-D convolutional neural network (CNN) architecture was developed for the classification task. MMSE scores were predicted using: linear least square regression (LLSR), support vector regression, bagging-based ensemble regression, and tree regression with group independent component analysis (gICA) features. To improve MMSE regression performance, we applied feature optimization methods including least absolute shrinkage and selection operator and support vector machine-based recursive feature elimination (SVM-RFE). The mean balanced test accuracy was 85.27% for the classification of AD versus healthy controls. The medial visual, default mode, dorsal attention, executive, and auditory related networks were mainly associated with AD. The maximum clinical MMSE score prediction accuracy with the LLSR method applied on gICA combined with SVM-RFE features had the lowest root mean square error (3.27 ± 0.58) and the highest R2 value (0.63 ± 0.02). Classification of AD and healthy controls can be successfully achieved using only rs-fMRI and MMSE scores can be accurately predicted using functional independent component features. In the absence of trained clinicians, AD disease status and clinical MMSE scores can be jointly predicted using 3-D deep learning and regression learning approaches with rs-fMRI data.

3D-CNN based discrimination of schizophrenia using resting-state fMRI.

MOTIVATION: This study reports a framework to discriminate patients with schizophrenia and normal healthy control subjects, based on magnetic resonance imaging (MRI) of the brain. Resting-state functional MRI data from a total of 144 subjects (72 patients with schizophrenia and 72 healthy controls) was obtained from a publicly available dataset using a three-dimensional convolution neural network 3D-CNN based deep learning classification framework and ICA based features. RESULTS: We achieved 98.09 ± 1.01% ten-fold cross-validated classification accuracy with a p-value < 0.001 and an area under the curve (AUC) of 0.9982 ± 0.015. In addition, differences in functional connectivity between the two groups were statistically analyzed across multiple resting-state networks. The disconnection between the visual and frontal network was prominent in patients, while they showed higher connectivity between the default mode network and other task-positive/ cerebellar networks. These ICA functional network maps served as highly discriminative three-dimensional imaging features for the discrimination of schizophrenia in this study. CONCLUSION: Due to the very high AUC, this research with more validation on the cross diagnosis and publicly available dataset, may be translated in future as an adjunct tool to assist clinicians in the initial screening of schizophrenia.

Real-Time Noninvasive Intracranial State Estimation Using Unscented Kalman Filter.

Intracranial pressure (ICP) monitoring is desirable as a first-line measure to assist decision-making in cases of increased ICP. Clinically, non-invasive ICP monitoring is also required to avoid infection and hemorrhage in patients. The relationships among the arterial blood pressure (ABP), ICP, cerebral blood flow, and its velocity ( [Formula: see text]) measured by transcranial Doppler ultrasound measurement have been reported. However, real-time non-invasive ICP estimation using these modalities is less well documented. This paper presents a novel algorithm for real-time and non-invasive ICP monitoring with [Formula: see text] and ABP, called direct-current (DC)-ICP. The technique was compared with invasive ICP for 10 acute-brain-injury patients admitted to Cheju Halla Hospital and Gangnam Severance Hospital from July 2017 to June 2018. The inter-subject correlation coefficient between true and estimate was 0.75 and the AUCs of the ROCs for prediction of increased ICP for the DC-ICP methods were 0.83. Thus, [Formula: see text] monitoring can facilitate reliable real-time ICP tracking with our novel DC-ICP algorithm, which can provide valuable information under clinical conditions.

The Effects of Transcranial Direct Current Stimulation on the Cognitive and Behavioral Changes After Electrode Implantation Surgery in Rats.

Postoperative delirium can lead to increased morbidity and mortality, and may even be a potentially life-threatening clinical syndrome. However, the neural mechanism underlying this condition has not been fully understood and there is little knowledge regarding potential preventive strategies. To date, investigation of transcranial direct current stimulation (tDCS) for the relief of symptoms caused by neuropsychiatric disorders and the enhancement of cognitive performance has led to promising results. In this study, we demonstrated that tDCS has a possible effect on the fast recovery from delirium in rats after microelectrode implant surgery, as demonstrated by postoperative behavior and neurophysiology compared with sham stimulation. This is the first study to describe the possible effects of tDCS for the fast recovery from delirium based on the study of both electroencephalography and behavioral changes. Postoperative rats showed decreased attention, which is the core symptom of delirium. However, anodal tDCS over the right frontal area immediately after surgery exhibited positive effects on acute attentional deficit. It was found that relative power of theta was lower in the tDCS group than in the sham group after surgery, suggesting that the decrease might be the underlying reason for the positive effects of tDCS. Connectivity analysis revealed that tDCS could modulate effective connectivity and synchronization of brain activity among different brain areas, including the frontal cortex, parietal cortex, and thalamus. It was concluded that anodal tDCS on the right frontal regions may have the potential to help patients recover quickly from delirium.

Myoelectric Signal Classification of Targeted Muscles Using Dictionary Learning.

Surface electromyography (sEMG) signals comprise electrophysiological information related to muscle activity. As this signal is easy to record, it is utilized to control several myoelectric prostheses devices. Several studies have been conducted to process sEMG signals more efficiently. However, research on optimal algorithms and electrode placements for the processing of sEMG signals is still inconclusive. In addition, very few studies have focused on minimizing the number of electrodes. In this study, we investigated the most effective method for myoelectric signal classification with a small number of electrodes. A total of 23 subjects participated in the study, and the sEMG data of 14 different hand movements of the subjects were acquired from targeted muscles and untargeted muscles. Furthermore, the study compared the classification accuracy of the sEMG data using discriminative feature-oriented dictionary learning (DFDL) and other conventional classifiers. DFDL demonstrated the highest classification accuracy among the classifiers, and its higher quality performance became more apparent as the number of channels decreased. The targeted method was superior to the untargeted method, particularly when classifying sEMG signals with DFDL. Therefore, it was concluded that the combination of the targeted method and the DFDL algorithm could classify myoelectric signals more effectively with a minimal number of channels.

Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer's dementia diagnosis using multi-measure rs-fMRI spatial patterns.

BACKGROUND: Early diagnosis of Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) is essential for timely treatment. Machine learning and multivariate pattern analysis (MVPA) for the diagnosis of brain disorders are explicitly attracting attention in the neuroimaging community. In this paper, we propose a voxel-wise discriminative framework applied to multi-measure resting-state fMRI (rs-fMRI) that integrates hybrid MVPA and extreme learning machine (ELM) for the automated discrimination of AD and MCI from the cognitive normal (CN) state. MATERIALS AND METHODS: We used two rs-fMRI cohorts: the public Alzheimer's disease Neuroimaging Initiative database (ADNI2) and an in-house Alzheimer's disease cohort from South Korea, both including individuals with AD, MCI, and normal controls. After extracting three-dimensional (3-D) patterns measuring regional coherence and functional connectivity during the resting state, we performed univariate statistical t-tests to generate a 3-D mask that retained only voxels showing significant changes. Given the initial univariate features, to enhance discriminative patterns, we implemented MVPA feature reduction using support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage and selection operator (LASSO), in combination with the univariate t-test. Classifications were performed by an ELM, and its efficiency was compared to linear and nonlinear (radial basis function) SVMs. RESULTS: The maximal accuracies achieved by the method in the ADNI2 cohort were 98.86% (p<0.001) and 98.57% (p<0.001) for AD and MCI vs. CN, respectively. In the in-house cohort, the same accuracies were 98.70% (p<0.001) and 94.16% (p<0.001). CONCLUSION: From a clinical perspective, combining extreme learning machine and hybrid MVPA applied on concatenations of multiple rs-fMRI biomarkers can potentially assist the clinicians in AD and MCI diagnosis.