Combining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns

Motor Intentions Decoded from fMRI Signals

Motor intention is a high-level brain function related to planning for movement. Although studies have shown that motor intentions can be decoded from brain signals before movement execution, it is unclear whether intentions relating to mental imagery of movement can be decoded. Here, we investigated whether differences in spatial and temporal patterns of brain activation were elicited by intentions to perform different types of motor imagery and whether the patterns could be used by a multivariate pattern classifier to detect such differential intentions. The results showed that it is possible to decode intentions before the onset of different types of motor imagery from functional MR signals obtained from fronto-parietal brain regions, such as the premotor cortex and posterior parietal cortex, while controlling for eye movements and for muscular activity of the hands. These results highlight the critical role played by the aforementioned brain regions in covert motor intentions. Moreover, they have substantial implications for rehabilitating patients with motor disabilities.

Decoding N400m Evoked Component: A Tutorial on Multivariate Pattern Analysis for OP-MEG Data

Multivariate pattern analysis (MVPA) has played an extensive role in interpreting brain activity, which has been applied in studies with modalities such as functional Magnetic Resonance Imaging (fMRI), Magnetoencephalography (MEG) and Electroencephalography (EEG). The advent of wearable MEG systems based on optically pumped magnetometers (OPMs), i.e., OP-MEG, has broadened the application of bio-magnetism in the realm of neuroscience. Nonetheless, it also raises challenges in temporal decoding analysis due to the unique attributes of OP-MEG itself. The efficacy of decoding performance utilizing multimodal fusion, such as MEG-EEG, also remains to be elucidated. In this regard, we investigated the impact of several factors, such as processing methods, models and modalities, on the decoding outcomes of OP-MEG. Our findings indicate that the number of averaged trials, dimensionality reduction (DR) methods, and the number of cross-validation folds significantly affect the decoding performance of OP-MEG data. Additionally, decoding results vary across modalities and fusion strategy. In contrast, decoder type, resampling frequency, and sliding window length exert marginal effects. Furthermore, we introduced mutual information (MI) to investigate how information loss due to OP-MEG data processing affect decoding accuracy. Our study offers insights for linear decoding research using OP-MEG and expand its application in the fields of cognitive neuroscience.

Anti-phasic oscillatory development for speech and noise processing in cochlear implanted toddlers

Human brain demonstrates amazing readiness for speech and language learning at birth, but the auditory development preceding such readiness remains unknown. Cochlear implanted (CI) children (n = 67; mean age 2.77 year ± 1.31 SD; 28 females) with prelingual deafness provide a unique opportunity to study this stage. Using functional near-infrared spectroscopy, it was revealed that the brain of CI children was irresponsive to sounds at CI hearing onset. With increasing CI experiences up to 32 months, the brain demonstrated function, region and hemisphere specific development. Most strikingly, the left anterior temporal lobe showed an oscillatory trajectory, changing in opposite phases for speech and noise. The study provides the first longitudinal brain imaging evidence for early auditory development preceding speech acquisition.

Quantifying noise effects in optical measures of excited state transport

Time-resolved microscopy is a widely used approach for imaging and quantifying charge and energy transport in functional materials. While it is generally recognized that resolving small diffusion lengths is limited by measurement noise, the impacts of noise have not been systematically assessed or quantified. This article reports modeling efforts to elucidate the impact of noise on optical probes of transport. Excited state population distributions, modeled as Gaussians with additive white noise typical of experimental conditions, are subject to decay and diffusive evolution. Using a conventional composite least-squares fitting algorithm, the resulting diffusion constant estimates are compared with the model input parameter. The results show that heteroscedasticity (i.e., time-varying noise levels), insufficient spatial and/or temporal resolution, and small diffusion lengths relative to the magnitude of noise lead to a surprising degree of imprecision under moderate experimental parameters. Moreover, the compounding influence of low initial contrast and small diffusion length leads to systematic overestimation of diffusion coefficients. Each of these issues is quantitatively analyzed herein, and experimental approaches to mitigate them are proposed. General guidelines for experimentalists to rapidly assess measurement precision are provided, as is an open-source tool for customizable evaluation of noise effects on time-resolved microscopy transport measurements.

Unsupervised Joint Domain Adaptation for Decoding Brain Cognitive States From tfMRI Images

Recent advances in large model and neuroscience have enabled exploration of the mechanism of brain activity by using neuroimaging data. Brain decoding is one of the most promising researches to further understand the human cognitive function. However, current methods excessively depends on high-quality labeled data, which brings enormous expense of collection and annotation of neural images by experts. Besides, the performance of cross-individual decoding suffers from inconsistency in data distribution caused by individual variation and different collection equipments. To address mentioned above issues, a Join Domain Adapative Decoding (JDAD) framework is proposed for unsupervised decoding specific brain cognitive state related to behavioral task. Based on the volumetric feature extraction from task-based functional Magnetic Resonance Imaging (tfMRI) data, a novel objective loss function is designed by the combination of joint distribution regularizer, which aims to restrict the distance of both the conditional and marginal probability distribution of labeled and unlabeled samples. Experimental results on the public Human Connectome Project (HCP) S1200 dataset show that JDAD achieves superior performance than other prevalent methods, especially for fine-grained task with 11.5%-21.6% improvements of decoding accuracy. The learned 3D features are visualized by Grad-CAM to build a combination with brain functional regions, which provides a novel path to learn the function of brain cortex regions related to specific cognitive task in group level.

Neuroimaging and artificial intelligence for assessment of chronic painful temporomandibular disorders-a comprehensive review

Chronic Painful Temporomandibular Disorders (TMD) are challenging to diagnose and manage due to their complexity and lack of understanding of brain mechanism. In the past few decades' neural mechanisms of pain regulation and perception have been clarified by neuroimaging research. Advances in the neuroimaging have bridged the gap between brain activity and the subjective experience of pain. Neuroimaging has also made strides toward separating the neural mechanisms underlying the chronic painful TMD. Recently, Artificial Intelligence (AI) is transforming various sectors by automating tasks that previously required humans' intelligence to complete. AI has started to contribute to the recognition, assessment, and understanding of painful TMD. The application of AI and neuroimaging in understanding the pathophysiology and diagnosis of chronic painful TMD are still in its early stages. The objective of the present review is to identify the contemporary neuroimaging approaches such as structural, functional, and molecular techniques that have been used to investigate the brain of chronic painful TMD individuals. Furthermore, this review guides practitioners on relevant aspects of AI and how AI and neuroimaging methods can revolutionize our understanding on the mechanisms of painful TMD and aid in both diagnosis and management to enhance patient outcomes.

The diagnostic performance of machine learning based on resting-state functional magnetic resonance imaging data for major depressive disorders: a systematic review and meta-analysis

Objective

Machine learning (ML) has been widely used to detect and evaluate major depressive disorder (MDD) using neuroimaging data, i.e., resting-state functional magnetic resonance imaging (rs-fMRI). However, the diagnostic efficiency is unknown. The aim of the study is to conduct an updated meta-analysis to evaluate the diagnostic performance of ML based on rs-fMRI data for MDD.

Methods

English databases were searched for relevant studies. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) was used to assess the methodological quality of the included studies. A random-effects meta-analytic model was implemented to investigate the diagnostic efficiency, including sensitivity, specificity, diagnostic odds ratio (DOR), and area under the curve (AUC). Regression meta-analysis and subgroup analysis were performed to investigate the cause of heterogeneity.

Results

Thirty-one studies were included in this meta-analysis. The pooled sensitivity, specificity, DOR, and AUC with 95% confidence intervals were 0.80 (0.75, 0.83), 0.83 (0.74, 0.82), 14.00 (9, 22.00), and 0.86 (0.83, 0.89), respectively. Substantial heterogeneity was observed among the studies included. The meta-regression showed that the leave-one-out cross-validation (loocv) (sensitivity: p < 0.01, specificity: p < 0.001), graph theory (sensitivity: p < 0.05, specificity: p < 0.01), n > 100 (sensitivity: p < 0.001, specificity: p < 0.001), simens equipment (sensitivity: p < 0.01, specificity: p < 0.001), 3.0T field strength (Sensitivity: p < 0.001, specificity: p = 0.04), and Beck Depression Inventory (BDI) (sensitivity: p = 0.04, specificity: p = 0.06) might be the sources of heterogeneity. Furthermore, the subgroup analysis showed that the sample size (n > 100: sensitivity: 0.71, specificity: 0.72, n < 100: sensitivity: 0.81, specificity: 0.79), the different levels of disease evaluated by the Hamilton Depression Rating Scale (HDRS/HAMD) (mild vs. moderate vs. severe: sensitivity: 0.52 vs. 0.86 vs. 0.89, specificity: 0.62 vs. 0.78 vs. 0.82, respectively), the depression scales in patients with comparable levels of severity. (BDI vs. HDRS/HAMD: sensitivity: 0.86 vs. 0.87, specificity: 0.78 vs. 0.80, respectively), and the features (graph vs. functional connectivity: sensitivity: 0.84 vs. 0.86, specificity: 0.76 vs. 0.78, respectively) selected might be the causes of heterogeneity.

Conclusion

ML showed high accuracy for the automatic diagnosis of MDD. Future studies are warranted to promote the potential use of these classification algorithms in clinical settings.

Dynamic neural reconstructions of attended object location and features using EEG

Attention allows us to select relevant and ignore irrelevant information from our complex environments. What happens when attention shifts from one item to another? To answer this question, it is critical to have tools that accurately recover neural representations of both feature and location information with high temporal resolution. In the present study, we used human electroencephalography (EEG) and machine learning to explore how neural representations of object features and locations update across dynamic shifts of attention. We demonstrate that EEG can be used to create simultaneous time courses of neural representations of attended features (time point-by-time point inverted encoding model reconstructions) and attended location (time point-by-time point decoding) during both stable periods and across dynamic shifts of attention. Each trial presented two oriented gratings that flickered at the same frequency but had different orientations; participants were cued to attend one of them and on half of trials received a shift cue midtrial. We trained models on a stable period from Hold attention trials and then reconstructed/decoded the attended orientation/location at each time point on Shift attention trials. Our results showed that both feature reconstruction and location decoding dynamically track the shift of attention and that there may be time points during the shifting of attention when 1) feature and location representations become uncoupled and 2) both the previously attended and currently attended orientations are represented with roughly equal strength. The results offer insight into our understanding of attentional shifts, and the noninvasive techniques developed in the present study lend themselves well to a wide variety of future applications.NEW & NOTEWORTHY We used human EEG and machine learning to reconstruct neural response profiles during dynamic shifts of attention. Specifically, we demonstrated that we could simultaneously read out both location and feature information from an attended item in a multistimulus display. Moreover, we examined how that readout evolves over time during the dynamic process of attentional shifts. These results provide insight into our understanding of attention, and this technique carries substantial potential for versatile extensions and applications.

BolT: Fused window transformers for fMRI time series analysis

Deep-learning models have enabled performance leaps in analysis of high-dimensional functional MRI (fMRI) data. Yet, many previous methods are suboptimally sensitive for contextual representations across diverse time scales. Here, we present BolT, a blood-oxygen-level-dependent transformer model, for analyzing multi-variate fMRI time series. BolT leverages a cascade of transformer encoders equipped with a novel fused window attention mechanism. Encoding is performed on temporally-overlapped windows within the time series to capture local representations. To integrate information temporally, cross-window attention is computed between base tokens in each window and fringe tokens from neighboring windows. To gradually transition from local to global representations, the extent of window overlap and thereby number of fringe tokens are progressively increased across the cascade. Finally, a novel cross-window regularization is employed to align high-level classification features across the time series. Comprehensive experiments on large-scale public datasets demonstrate the superior performance of BolT against state-of-the-art methods. Furthermore, explanatory analyses to identify landmark time points and regions that contribute most significantly to model decisions corroborate prominent neuroscientific findings in the literature.

Multi-model order spatially constrained ICA reveals highly replicable group differences and consistent predictive results from resting data: A large N fMRI schizophrenia study

Brain functional networks identified from resting functional magnetic resonance imaging (fMRI) data have the potential to reveal biomarkers for brain disorders, but studies of complex mental illnesses such as schizophrenia (SZ) often yield mixed results across replication studies. This is likely due in part to the complexity of the disorder, the short data acquisition time, and the limited ability of the approaches for brain imaging data mining. Therefore, the use of analytic approaches which can both capture individual variability while offering comparability across analyses is highly preferred. Fully blind data-driven approaches such as independent component analysis (ICA) are hard to compare across studies, and approaches that use fixed atlas-based regions can have limited sensitivity to individual sensitivity. By contrast, spatially constrained ICA (scICA) provides a hybrid, fully automated solution that can incorporate spatial network priors while also adapting to new subjects. However, scICA has thus far only been used with a single spatial scale (ICA dimensionality, i.e., ICA model order). In this work, we present an approach using multi-objective optimization scICA with reference algorithm (MOO-ICAR) to extract subject-specific intrinsic connectivity networks (ICNs) from fMRI data at multiple spatial scales, which also enables us to study interactions across spatial scales. We evaluate this approach using a large N (N > 1,600) study of schizophrenia divided into separate validation and replication sets. A multi-scale ICN template was estimated and labeled, then used as input into scICA which was computed on an individual subject level. We then performed a subsequent analysis of multiscale functional network connectivity (msFNC) to evaluate the patient data, including group differences and classification. Results showed highly consistent group differences in msFNC in regions including cerebellum, thalamus, and motor/auditory networks. Importantly, multiple msFNC pairs linking different spatial scales were implicated. The classification model built on the msFNC features obtained up to 85% F1 score, 83% precision, and 88% recall, indicating the strength of the proposed framework in detecting group differences between schizophrenia and the control group. Finally, we evaluated the relationship of the identified patterns to positive symptoms and found consistent results across datasets. The results verified the robustness of our framework in evaluating brain functional connectivity of schizophrenia at multiple spatial scales, implicated consistent and replicable brain networks, and highlighted a promising approach for leveraging resting fMRI data for brain biomarker development.

Right Posterior Temporal Cortex Supports Integration of Phonetic and Talker Information

Though the right hemisphere has been implicated in talker processing, it is thought to play a minimal role in phonetic processing, at least relative to the left hemisphere. Recent evidence suggests that the right posterior temporal cortex may support learning of phonetic variation associated with a specific talker. In the current study, listeners heard a male talker and a female talker, one of whom produced an ambiguous fricative in /s/-biased lexical contexts (e.g., epi?ode) and one who produced it in /∫/-biased contexts (e.g., friend?ip). Listeners in a behavioral experiment (Experiment 1) showed evidence of lexically guided perceptual learning, categorizing ambiguous fricatives in line with their previous experience. Listeners in an fMRI experiment (Experiment 2) showed differential phonetic categorization as a function of talker, allowing for an investigation of the neural basis of talker-specific phonetic processing, though they did not exhibit perceptual learning (likely due to characteristics of our in-scanner headphones). Searchlight analyses revealed that the patterns of activation in the right superior temporal sulcus (STS) contained information about who was talking and what phoneme they produced. We take this as evidence that talker information and phonetic information are integrated in the right STS. Functional connectivity analyses suggested that the process of conditioning phonetic identity on talker information depends on the coordinated activity of a left-lateralized phonetic processing system and a right-lateralized talker processing system. Overall, these results clarify the mechanisms through which the right hemisphere supports talker-specific phonetic processing.

Brain Network Analysis: A Review on Multivariate Analytical Methods

Despite the explosive growth of neuroimaging studies aimed at analyzing the brain as a complex system, critical methodological gaps remain to be addressed. Most tools currently used for analyzing network data of the brain are univariate in nature and are based on assumptions borne out of previous techniques not directly related to the big and complex data of the brain. Although graph-based methods have shown great promise, the development of principled multivariate models to address inherent limitations of graph-based methods, such as their dependence on network size and degree distributions, and to allow assessing the effects of multiple phenotypes on the brain and simulating brain networks has largely lagged behind. Although some studies have been made in developing multivariate frameworks to fill this gap, in the absence of a "gold-standard" method or guidelines, choosing the most appropriate method for each study can be another critical challenge for investigators in this multidisciplinary field. Here, we briefly introduce important multivariate methods for brain network analyses in two main categories: data-driven and model-based methods. We discuss whether/how such methods are suited for examining connectivity (edge-level), topology (system-level), or both. This review will aid in choosing an appropriate multivariate method with respect to variables such as network type, number of subjects and brain regions included, and the interest in connectivity, topology, or both. This review is aimed to be accessible to investigators from different backgrounds, with a focus on applications in brain network studies, though the methods may be applicable in other areas too. Impact statement As the U.S. National Institute of Health notes, the rich biomedical data can greatly improve our knowledge of human health if new analytical tools are developed, and their applications are broadly disseminated. A major challenge in analyzing the brain as a complex system is about developing parsimonious multivariate methods, and particularly choosing the most appropriate one among the existing methods with respect to the study variables in this multidisciplinary field. This study provides a review on the most important multivariate methods to aid in helping the most appropriate ones with respect to the desired variables for each study.

Optimizing multivariate pattern classification in rapid event-related designs

BACKGROUND

Multivariate pattern analysis (MVPA or pattern decoding) has attracted considerable attention as a sensitive analytic tool for investigations using functional magnetic resonance imaging (fMRI) data. With the introduction of MVPA, however, has come a proliferation of methodological choices confronting the researcher, with few studies to date offering guidance from the vantage point of controlled datasets detached from specific experimental hypotheses.

NEW METHOD

We investigated the impact of four data processing steps on support vector machine (SVM) classification performance aimed at maximizing information capture in the presence of common noise sources. The four techniques included: trial averaging (classifying on separate trial estimates versus condition-based averages), within-run mean centering (centering the data or not), method of cost selection (using a fixed or tuned cost value), and motion-related denoising approach (comparing no denoising versus a variety of nuisance regressions capturing motion-related reference signals). The impact of these approaches was evaluated on real fMRI data from two control ROIs, as well as on simulated pattern data constructed with carefully controlled voxel- and trial-level noise components.

RESULTS

We find significant improvements in classification performance across both real and simulated datasets with run-wise trial averaging and mean centering. When averaging trials within conditions of each run, we note a simultaneous increase in the between-subject variability of SVM classification accuracies which we attribute to the reduced size of the test set used to assess the classifier's prediction error. Therefore, we propose a hybrid technique whereby randomly sampled subsets of trials are averaged per run and demonstrate that it helps mitigate the tradeoff between improving signal-to-noise ratio by averaging and losing exemplars in the test set.

COMPARISON WITH EXISTING METHODS

Though a handful of empirical studies have employed run-based trial averaging, mean centering, or their combination, such studies have done so without theoretical justification or rigorous testing using control ROIs.

CONCLUSIONS

Therefore, we intend this study to serve as a practical guide for researchers wishing to optimize pattern decoding without risk of introducing spurious results.

Impact of blindness onset on the representation of sound categories in occipital and temporal cortices

The ventral occipito-temporal cortex (VOTC) reliably encodes auditory categories in people born blind using a representational structure partially similar to the one found in vision (Mattioni et al.,2020). Here, using a combination of uni- and multivoxel analyses applied to fMRI data, we extend our previous findings, comprehensively investigating how early and late acquired blindness impact on the cortical regions coding for the deprived and the remaining senses. First, we show enhanced univariate response to sounds in part of the occipital cortex of both blind groups that is concomitant to reduced auditory responses in temporal regions. We then reveal that the representation of the sound categories in the occipital and temporal regions is more similar in blind subjects compared to sighted subjects. What could drive this enhanced similarity? The multivoxel encoding of the ‘human voice’ category that we observed in the temporal cortex of all sighted and blind groups is enhanced in occipital regions in blind groups , suggesting that the representation of vocal information is more similar between the occipital and temporal regions in blind compared to sighted individuals. We additionally show that blindness does not affect the encoding of the acoustic properties of our sounds (e.g. pitch, harmonicity) in occipital and in temporal regions but instead selectively alter the categorical coding of the voice category itself. These results suggest a functionally congruent interplay between the reorganization of occipital and temporal regions following visual deprivation, across the lifespan.

Multimodel Order Independent Component Analysis: A Data-Driven Method for Evaluating Brain Functional Network Connectivity Within and Between Multiple Spatial Scales

Background: While functional connectivity is widely studied, there has been little work studying functional connectivity at different spatial scales. Likewise, the relationship of functional connectivity between spatial scales is unknown. Methods: We proposed an independent component analysis (ICA)-based approach to capture information at multiple-model orders (component numbers), and to evaluate functional network connectivity (FNC) both within and between model orders. We evaluated the approach by studying group differences in the context of a study of resting-state functional magnetic resonance imaging (rsfMRI) data collected from schizophrenia (SZ) individuals and healthy controls (HC). The predictive ability of FNC at multiple spatial scales was assessed using support vector machine-based classification. Results: In addition to consistent predictive patterns at both multiple-model orders and single-model orders, unique predictive information was seen at multiple-model orders and in the interaction between model orders. We observed that the FNC between model orders 25 and 50 maintained the highest predictive information between HC and SZ. Results highlighted the predictive ability of the somatomotor and visual domains both within and between model orders compared with other functional domains. Also, subcortical-somatomotor, temporal-somatomotor, and temporal-subcortical FNCs had relatively high weights in predicting SZ. Conclusions: In sum, multimodel order ICA provides a more comprehensive way to study FNC, produces meaningful and interesting results, which are applicable to future studies. We shared the spatial templates from this work at different model orders to provide a reference for the community, which can be leveraged in regression-based or fully automated (spatially constrained) ICA approaches. Impact statement Multimodel order independent component analysis (ICA) provides a comprehensive way to study brain functional network connectivity within and between multiple spatial scales, highlighting findings that would have been ignored in single-model order analysis. This work expands upon and adds to the relatively new literature on resting functional magnetic resonance imaging-based classification and prediction. Results highlighted the differentiating power of specific intrinsic connectivity networks on classifying brain disorders of schizophrenia patients and healthy participants, at different spatial scales. The spatial templates from this work provide a reference for the community, which can be leveraged in regression-based or fully automated ICA approaches.

Sound-modulations of visual motion perception implicate the cortico-vestibular brain

A widely used example of the intricate (yet poorly understood) intertwining of multisensory signals in the brain is the audiovisual bounce inducing effect (ABE). This effect presents two identical objects moving along the azimuth with uniform motion and towards opposite directions. The perceptual interpretation of the motion is ambiguous and is modulated if a transient (sound) is presented in coincidence with the point of overlap of the two objects' motion trajectories. This phenomenon has long been written-off to simple attentional or decision-making mechanisms, although the neurological underpinnings for the effect are not well understood. Using behavioural metrics concurrently with event-related fMRI, we show that sound-induced modulations of motion perception can be further modulated by changing motion dynamics of the visual targets. The phenomenon engages the posterior parietal cortex and the parieto-insular-vestibular cortical complex, with a close correspondence of activity in these regions with behaviour. These findings suggest that the insular cortex is engaged in deriving a probabilistic perceptual solution through the integration of multisensory data.

Evaluation of Feature Selection for Alzheimer’s Disease Diagnosis

Accurate recognition of patients with Alzheimer’s disease (AD) or mild cognitive impairment (MCI) is important for the subsequent treatment and rehabilitation. Recently, with the fast development of artificial intelligence (AI), AI-assisted diagnosis has been widely used. Feature selection as a key component is very important in AI-assisted diagnosis. So far, many feature selection methods have been developed. However, few studies consider the stability of a feature selection method. Therefore, in this study, we introduce a frequency-based criterion to evaluate the stability of feature selection and design a pipeline to select feature selection methods considering both stability and discriminability. There are two main contributions of this study: (1) It designs a bootstrap sampling-based workflow to simulate real-world scenario of feature selection. (2) It develops a decision graph to determine the optimal combination of supervised and unsupervised feature selection both considering feature stability and discriminability. Experimental results on the ADNI dataset have demonstrated the feasibility of our method.

GPU-accelerated connectome discovery at scale

Diffusion magnetic resonance imaging and tractography enable the estimation of anatomical connectivity in the human brain, in vivo. Yet, without ground-truth validation, different tractography algorithms can yield widely varying connectivity estimates. Although streamline pruning techniques mitigate this challenge, slow compute times preclude their use in big-data applications. We present 'Regularized, Accelerated, Linear Fascicle Evaluation' (ReAl-LiFE), a GPU-based implementation of a state-of-the-art streamline pruning algorithm (LiFE), which achieves >100× speedups over previous CPU-based implementations. Leveraging these speedups, we overcome key limitations with LiFE's algorithm to generate sparser and more accurate connectomes. We showcase ReAl-LiFE's ability to estimate connections with superlative test-retest reliability, while outperforming competing approaches. Moreover, we predicted inter-individual variations in multiple cognitive scores with ReAl-LiFE connectome features. We propose ReAl-LiFE as a timely tool, surpassing the state of the art, for accurate discovery of individualized brain connectomes at scale. Finally, our GPU-accelerated implementation of a popular non-negative least-squares optimization algorithm is widely applicable to many real-world problems.

Neural decoding of semantic concepts: A systematic literature review

Objective Semantic concepts are coherent entities within our minds. They underpin our thought processes and are a part of the basis for our understanding of the world. Modern neuroscience research is increasingly exploring how individual semantic concepts are encoded within our brains and a number of studies are beginning to reveal key patterns of neural activity that underpin specific concepts. Building upon this basic understanding of the process of semantic neural encoding, neural engineers are beginning to explore tools and methods for semantic decoding: identifying which semantic concepts an individual is focused on at a given moment in time from recordings of their neural activity. In this paper we review the current literature on semantic neural decoding. Approach We conducted this review according to the Preferred Reporting Items for Systematic reviews and Meta-Analysis (PRISMA) guidelines. Specifically, we assess the eligibility of published peer-reviewed reports via a search of PubMed and Google Scholar. We identify a total of 74 studies in which semantic neural decoding is used to attempt to identify individual semantic concepts from neural activity. Results Our review reveals how modern neuroscientific tools have been developed to allow decoding of individual concepts from a range of neuroimaging modalities. We discuss specific neuroimaging methods, experimental designs, and machine learning pipelines that are employed to aid the decoding of semantic concepts. We quantify the efficacy of semantic decoders by measuring information transfer rates. We also discuss current challenges presented by this research area and present some possible solutions. Finally, we discuss some possible emerging and speculative future directions for this research area. Significance Semantic decoding is a rapidly growing area of research. However, despite its increasingly widespread popularity and use in neuroscientific research this is the first literature review focusing on this topic across neuroimaging modalities and with a focus on quantifying the efficacy of semantic decoders.

Blood SSR1: A Possible Biomarker for Early Prediction of Parkinson’s Disease

Parkinson’s disease (PD) is the second most common neurodegenerative disease associated with age. Early diagnosis of PD is key to preventing the loss of dopamine neurons. Peripheral-blood biomarkers have shown their value in recent years because of their easy access and long-term monitoring advantages. However, few peripheral-blood biomarkers have proven useful. This study aims to explore potential peripheral-blood biomarkers for the early diagnosis of PD. Three substantia nigra (SN) transcriptome datasets from the Gene Expression Omnibus (GEO) database were divided into a training cohort and a test cohort. We constructed a protein–protein interaction (PPI) network and a weighted gene co-expression network analysis (WGCNA) network, found their overlapping differentially expressed genes and studied them as the key genes. Analysis of the peripheral-blood transcriptome datasets of PD patients from GEO showed that three key genes were upregulated in PD over healthy participants. Analysis of the relationship between their expression and survival and analysis of their brain expression suggested that these key genes could become biomarkers. Then, animal models were studied to validate the expression of the key genes, and only SSR1 (the signal sequence receptor subunit1) was significantly upregulated in both animal models in peripheral blood. Correlation analysis and logistic regression analysis were used to analyze the correlation between brain dopaminergic neurons and SSR1 expression, and it was found that SSR1 expression was negatively correlated with dopaminergic neuron survival. The upregulation of SSR1 expression in peripheral blood was also found to precede the abnormal behavior of animals. In addition, the application of artificial intelligence technology further showed the value of SSR1 in clinical PD prediction. The three classifiers all showed that SSR1 had high predictability for PD. The classifier with the best prediction accuracy was selected through AUC and MCC to construct a prediction model. In short, this research not only provides potential biomarkers for the early diagnosis of PD but also establishes a possible artificial intelligence model for predicting PD.

Intelligibility of audiovisual sentences drives multivoxel response patterns in human superior temporal cortex

Regions of the human posterior superior temporal gyrus and sulcus (pSTG/S) respond to the visual mouth movements that constitute visual speech and the auditory vocalizations that constitute auditory speech, and neural responses in pSTG/S may underlie the perceptual benefit of visual speech for the comprehension of noisy auditory speech. We examined this possibility through the lens of multivoxel pattern responses in pSTG/S. BOLD fMRI data was collected from 22 participants presented with speech consisting of English sentences presented in five different formats: visual-only; auditory with and without added auditory noise; and audiovisual with and without auditory noise. Participants reported the intelligibility of each sentence with a button press and trials were sorted post-hoc into those that were more or less intelligible. Response patterns were measured in regions of the pSTG/S identified with an independent localizer. Noisy audiovisual sentences with very similar physical properties evoked very different response patterns depending on their intelligibility. When a noisy audiovisual sentence was reported as intelligible, the pattern was nearly identical to that elicited by clear audiovisual sentences. In contrast, an unintelligible noisy audiovisual sentence evoked a pattern like that of visual-only sentences. This effect was less pronounced for noisy auditory-only sentences, which evoked similar response patterns regardless of intelligibility. The successful integration of visual and auditory speech produces a characteristic neural signature in pSTG/S, highlighting the importance of this region in generating the perceptual benefit of visual speech.

Machine learning in neuroimaging: from research to clinical practice

Neuroimaging is critical in clinical care and research, enabling us to investigate the brain in health and disease. There is a complex link between the brain's morphological structure, physiological architecture, and the corresponding imaging characteristics. The shape, function, and relationships between various brain areas change during development and throughout life, disease, and recovery. Like few other areas, neuroimaging benefits from advanced analysis techniques to fully exploit imaging data for studying the brain and its function. Recently, machine learning has started to contribute (a) to anatomical measurements, detection, segmentation, and quantification of lesions and disease patterns, (b) to the rapid identification of acute conditions such as stroke, or (c) to the tracking of imaging changes over time. As our ability to image and analyze the brain advances, so does our understanding of its intricate relationships and their role in therapeutic decision-making. Here, we review the current state of the art in using machine learning techniques to exploit neuroimaging data for clinical care and research, providing an overview of clinical applications and their contribution to fundamental computational neuroscience.

Visual adaptation and 7T fMRI reveal facial identity processing in the human brain under shallow interocular suppression

Face identity is represented at a high level of the visual hierarchy. Whether the human brain can process facial identity information in the absence of visual awareness remains unclear. In this study, we investigated potential face identity representation through face-identity adaptation with the adapting faces interocularly suppressed by Continuous Flash Suppression (CFS) noise, a modified binocular rivalry paradigm. The strength of interocular suppression was manipulated by varying the contrast of CFS noise. While obeservers reported the face images subjectively unperceived and the face identity objectively unrecognizable, a significant face identity aftereffect was observed under low but not high contrast CFS noise. In addition, the identity of face images under shallow interocular suppression can be decoded from multi-voxel patterns in the right fusiform face area (FFA) obtained with high-resolution 7T fMRI. Thus the comined evidence from visual adaptation and 7T fMRI suggest that face identity can be represented in the human brain without explicit perceptual recognition. The processing of interocularly suppressed faces could occur at different levels depending on how "deep" the information is suppressed.

Aberrant Cerebello-Cortical Connectivity in Pianists With Focal Task-Specific Dystonia

Musician's dystonia is a type of focal task-specific dystonia (FTSD) characterized by abnormal muscle hypercontraction and loss of fine motor control specifically during instrument playing. Although the neuropathophysiology of musician's dystonia remains unclear, it has been suggested that maladaptive functional abnormalities in subcortical and cortical regions may be involved. Here, we hypothesized that aberrant effective connectivity between the cerebellum (subcortical) and motor/somatosensory cortex may underlie the neuropathophysiology of musician's dystonia. Using functional magnetic resonance imaging, we measured the brain activity of 30 pianists with or without FTSD as they played a magnetic resonance imaging-compatible piano-like keyboard, which elicited dystonic symptoms in many but not all pianists with FTSD. Pianists with FTSD showed greater activation of the right cerebellum during the task than healthy pianists. Furthermore, patients who reported dystonic symptoms during the task demonstrated greater cerebellar activation than those who did not, establishing a link between cerebellar activity and overt dystonic symptoms. Using multivoxel pattern analysis, moreover, we found that dystonic and healthy pianists differed in the task-related effective connectivity between the right cerebellum and left premotor/somatosensory cortex. The present study indicates that abnormal cerebellar activity and cerebello-cortical connectivity may underlie the pathophysiology of FTSD in musicians.

Combined Support Vector Machine Classifier and Brain Structural Network Features for the Individual Classification of Amnestic Mild Cognitive Impairment and Subjective Cognitive Decline Patients

OBJECTIVE

Individuals with subjective cognitive decline (SCD) or amnestic mild cognitive impairment (aMCI) represent important targets for the early detection and intervention of Alzheimer's disease (AD). In this study, we employed a multi-kernel support vector machine (SVM) to examine whether white matter (WM) structural networks can be used for screening SCD and aMCI.

METHODS

A total of 138 right-handed participants [51 normal controls (NC), 36 SCD, 51 aMCI] underwent MRI brain scans. For each participant, three types of WM networks with different edge weights were constructed with diffusion MRI data: fiber number-weighted networks, mean fractional anisotropy-weighted networks, and mean diffusivity (MD)-weighted networks. By employing a multiple-kernel SVM, we seek to integrate information from three weighted networks to improve classification performance. The accuracy of classification between each pair of groups was evaluated via leave-one-out cross-validation.

RESULTS

For the discrimination between SCD and NC, an area under the curve (AUC) value of 0.89 was obtained, with an accuracy of 83.9%. Further analysis revealed that the methods using three types of WM networks outperformed other methods using single WM network. Moreover, we found that most of discriminative features were from MD-weighted networks, which distributed among frontal lobes. Similar classification performance was also reported in the differentiation between subjects with aMCI and NCs (accuracy = 83.3%). Between SCD and aMCI, an AUC value of 0.72 was obtained, with an accuracy of 72.4%, sensitivity of 74.5% and specificity of 69.4%. The highest accuracy was achieved with features only selected from MD-weighted networks.

CONCLUSION

White matter structural network features help machine learning algorithms accurately identify individuals with SCD and aMCI from NCs. Our findings have significant implications for the development of potential brain imaging markers for the early detection of AD.

An integrative prediction algorithm of drug-refractory epilepsy based on combined clinical-EEG functional connectivity features

OBJECTIVE

Although the use of antiepileptic drugs (AEDs) is routine, 30-40% of patients with epilepsy (PWEs) experience drug resistance. Thus, early identification of AED resistance will help optimize treatment regimens and improve patients' prognoses. However, there have been few studies on this topic to date. Here, we try to establish an integrative prediction model of AED resistance for drug-naive PWEs, and to identify the clinical and Electroencephalogram (EEG) factors that affect their outcomes.

METHODS

One hundred sixty-four PWEs naive to AEDs treated at a tertiary care center from January 2014 to June 2020 were retrospectively analyzed. A total of 113 of these patients were well controlled and 53 were drug refractory with regular AED treatment for more than one year. Eighty clinical characteristics and 684 EEG functional connectivity variables based on phase lag index before drug initiation were identified. Overall, 80% of each group was chosen to establish a support vector machine (SVM) model with ten-fold cross validation, and the other 20% were used to evaluate the model's performance. Absolute weight value was used to rank the features that had impacts on classification.

RESULTS

An integrative algorithm was modeled to predict AED resistance for drug-naive PWEs by SVM based on clinical characteristics and EEG functional connectivity values. The model had an accuracy of 94% [95% confidence interval (CI) 0.85-1.0], sensitivity of 95% [95% CI 0.82-1.0], specificity of 93% [95% CI 0.77-1.0], and an area under the curve (AUC) of 0.98 [95% CI 0.91-1.0]. The p values of accuracy, sensitivity specificity and AUC were calculated as 0.001, 0.001, 0.01 and 0.001, respectively. The δ band fromT4-FZ and T3-PZ, α band from T3-T6 and β band from F7-CZ and FP2-F3 were the top five EEG features that impacted the SVM classifier.

CONCLUSION

We constructed an integrative prediction algorithm of AED resistance for drug-naive PWEs. Its utility in clinical settings should be evaluated in the future.

Modulations of depth responses in the human brain by object context: Does biological relevance matter?

Depth sensitivity has been shown to be modulated by object context (plausibility). It is possible that it is behavioural relevance rather than object plausibility per se which drives this effect. Here, we manipulated the biological relevance of objects (face or a non-face) and tested whether object relevance affects behavioural sensitivity and neural responses to depth-position. In a first experiment, we presented human observers with disparity-defined faces and non-faces, and observers were asked to judge the depth position of the target under signal-noise and clear (fine) task conditions. In the second experiment, we concurrently measured behavioural and fMRI responses to depth. We found that behavioural performance varied across stimulus conditions such that they were significantly worse for the upright face than the inverted face and the random shape in the SNR task, but worse for the random shape than the upright face in the feature task. Pattern analysis of fMRI responses revealed that activity of FFA was distinctly different during depth judgments of the upright face versus the other two stimuli, with its responses (and to a stronger extent, those of V3) appearing functionally-relevant to behavioural performance. We speculate that FFA is not only involved in object analysis, but exerts considerable influence on stereoscopic mechanisms as early as in V3 based on a broader appreciation of the stimulus' behavioural relevance.Significance StatementWe asked how disparity sensitivity is modulated by object (biological) relevance using behavioural and neuroimaging paradigms. We show that behavioural sensitivity to depth-position changes in biological (face) vs non-biological (random surface) contexts, and that these changes are task-dependent. Imaging results highlight a potentially key role of the fusiform region for governing the modulation of stereo encoding by object relevance. These findings highlight powerful interactions between object recognition mechanisms and stereoencoding, such that the utility of disparity information may be up/down weighed depending on the biological relevance of the object.

Neural Representations of Task Context and Temporal Order During Action Sequence Execution

Routine action sequences can share a great deal of similarity in terms of their stimulus response mappings. As a consequence, their correct execution relies crucially on the ability to preserve contextual and temporal information. However, there are few empirical studies on the neural mechanism and the brain areas maintaining such information. To address this gap in the literature, we recently recorded the blood-oxygen level dependent (BOLD) response in a newly developed coffee-tea making task. The task involves the execution of four action sequences that each comprise six consecutive decision states, which allows for examining the maintenance of contextual and temporal information. Here, we report a reanalysis of this dataset using a data-driven approach, namely multivariate pattern analysis, that examines context-dependent neural activity across several predefined regions of interest. Results highlight involvement of the inferior-temporal gyrus and lateral prefrontal cortex in maintaining temporal and contextual information for the execution of hierarchically organized action sequences. Furthermore, temporal information seems to be more strongly encoded in areas over the left hemisphere.

Support vector machine based classification of smokers and nonsmokers using diffusion tensor imaging

Despite significant progress in treatments for smoking cessation, smoking continues to be a significant public health concern, especially in young adulthood. Thus, developing a predictive model that can classify and characterize the brain-based biomarkers predicting smoking status would be imperative to improving treatment development. In this study, we applied a support vector machine-based classification method to discriminate 70 young male smokers and 70 matched nonsmokers using their diffusion tensor imaging (DTI) data. The classification procedure achieved an average accuracy of 88.6% and an average area under the curve of 0.95. The most discriminative features that contributed to the classification were primarily located in the sagittal stratum (SS), external capsule (EC), superior longitudinal fasciculus (SLF), anterior corona radiata (ACR) and inferior front-occipital fasciculus (IFOF). The following regression analysis showed a significant negatively correlation between the average RD values of the left ACR (r = -0.247, p = 0.039) and FTND. The average MD values in the right EC (r = -0.254, p = 0.034) and RD values in the right IFOF (r = -0.240, p = 0.046) were inversely associated with pack-years. Our findings indicate that the discriminative white matter (WM) features as brain biomarkers provide great predictive power for smoking status and suggest that machine learning techniques can reveal underlying smoking-related neurobiology.

Musical Expertise Shapes Functional and Structural Brain Networks Independent of Absolute Pitch Ability

Professional musicians are a popular model for investigating experience-dependent plasticity in human large-scale brain networks. A minority of musicians possess absolute pitch, the ability to name a tone without reference. The study of absolute pitch musicians provides insights into how a very specific talent is reflected in brain networks. Previous studies of the effects of musicianship and absolute pitch on large-scale brain networks have yielded highly heterogeneous findings regarding the localization and direction of the effects. This heterogeneity was likely influenced by small samples and vastly different methodological approaches. Here, we conducted a comprehensive multimodal assessment of effects of musicianship and absolute pitch on intrinsic functional and structural connectivity using a variety of commonly used and state-of-the-art multivariate methods in the largest sample to date (n = 153 female and male human participants; 52 absolute pitch musicians, 51 non-absolute pitch musicians, and 50 non-musicians). Our results show robust effects of musicianship in interhemispheric and intrahemispheric connectivity in both structural and functional networks. Crucially, most of the effects were replicable in both musicians with and without absolute pitch compared with non-musicians. However, we did not find evidence for an effect of absolute pitch on intrinsic functional or structural connectivity in our data: The two musician groups showed strikingly similar networks across all analyses. Our results suggest that long-term musical training is associated with robust changes in large-scale brain networks. The effects of absolute pitch on neural networks might be subtle, requiring very large samples or task-based experiments to be detected.SIGNIFICANCE STATEMENT A question that has fascinated neuroscientists, psychologists, and musicologists for a long time is how musicianship and absolute pitch, the rare talent to name a tone without reference, are reflected in large-scale networks of the human brain. Much is still unknown as previous studies have reported widely inconsistent results based on small samples. Here, we investigate the largest sample of musicians and non-musicians to date (n = 153) using a multitude of established and novel analysis methods. Results provide evidence for robust effects of musicianship on functional and structural networks that were replicable in two separate groups of musicians and independent of absolute pitch ability.

Decoding with confidence: Statistical control on decoder maps

In brain imaging, decoding is widely used to infer relationships between brain and cognition, or to craft brain-imaging biomarkers of pathologies. Yet, standard decoding procedures do not come with statistical guarantees, and thus do not give confidence bounds to interpret the pattern maps that they produce. Indeed, in whole-brain decoding settings, the number of explanatory variables is much greater than the number of samples, hence classical statistical inference methodology cannot be applied. Specifically, the standard practice that consists in thresholding decoding maps is not a correct inference procedure. We contribute a new statistical-testing framework for this type of inference. To overcome the statistical inefficiency of voxel-level control, we generalize the Family Wise Error Rate (FWER) to account for a spatial tolerance δ, introducing the δ-Family Wise Error Rate (δ-FWER). Then, we present a decoding procedure that can control the δ-FWER: the Ensemble of Clustered Desparsified Lasso (EnCluDL), a procedure for multivariate statistical inference on high-dimensional structured data. We evaluate the statistical properties of EnCluDL with a thorough empirical study, along with three alternative procedures including decoder map thresholding. We show that EnCluDL exhibits the best recovery properties while ensuring the expected statistical control.

Deep-Learning-Based Multivariate Pattern Analysis (dMVPA): A Tutorial and a Toolbox

In recent years, multivariate pattern analysis (MVPA) has been hugely beneficial for cognitive neuroscience by making new experiment designs possible and by increasing the inferential power of functional magnetic resonance imaging (fMRI), electroencephalography (EEG), and other neuroimaging methodologies. In a similar time frame, “deep learning” (a term for the use of artificial neural networks with convolutional, recurrent, or similarly sophisticated architectures) has produced a parallel revolution in the field of machine learning and has been employed across a wide variety of applications. Traditional MVPA also uses a form of machine learning, but most commonly with much simpler techniques based on linear calculations; a number of studies have applied deep learning techniques to neuroimaging data, but we believe that those have barely scratched the surface of the potential deep learning holds for the field. In this paper, we provide a brief introduction to deep learning for those new to the technique, explore the logistical pros and cons of using deep learning to analyze neuroimaging data – which we term “deep MVPA,” or dMVPA – and introduce a new software toolbox (the “Deep Learning In Neuroimaging: Exploration, Analysis, Tools, and Education” package, DeLINEATE for short) intended to facilitate dMVPA for neuroscientists (and indeed, scientists more broadly) everywhere.

Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability

Variation in cognitive ability arises from subtle differences in underlying neural architecture. Understanding and predicting individual variability in cognition from the differences in brain networks requires harnessing the unique variance captured by different neuroimaging modalities. Here we adopted a multi-level machine learning approach that combines diffusion, functional, and structural MRI data from the Human Connectome Project (N = 1050) to provide unitary prediction models of various cognitive abilities: global cognitive function, fluid intelligence, crystallized intelligence, impulsivity, spatial orientation, verbal episodic memory and sustained attention. Out-of-sample predictions of each cognitive score were first generated using a sparsity-constrained principal component regression on individual neuroimaging modalities. These individual predictions were then aggregated and submitted to a LASSO estimator that removed redundant variability across channels. This stacked prediction led to a significant improvement in accuracy, relative to the best single modality predictions (approximately 1% to more than 3% boost in variance explained), across a majority of the cognitive abilities tested. Further analysis found that diffusion and brain surface properties contribute the most to the predictive power. Our findings establish a lower bound to predict individual differences in cognition using multiple neuroimaging measures of brain architecture, both structural and functional, quantify the relative predictive power of the different imaging modalities, and reveal how each modality provides unique and complementary information about individual differences in cognitive function.

Chinese-English bilinguals show linguistic-perceptual links in the brain associating short spoken phrases with corresponding real-world natural action sounds by semantic category

Higher cognitive functions such as linguistic comprehension must ultimately relate to perceptual systems in the brain, though how and why this forms remains unclear. Different brain networks that mediate perception when hearing real-world natural sounds has recently been proposed to respect a taxonomic model of acoustic-semantic categories. Using functional magnetic resonance imaging (fMRI) with Chinese/English bilingual listeners, the present study explored whether reception of short spoken phrases, in both Chinese (Mandarin) and English, describing corresponding sound-producing events would engage overlapping brain regions at a semantic category level. The results revealed a double-dissociation of cortical regions that were preferential for representing knowledge of human versus environmental action events, whether conveyed through natural sounds or the corresponding spoken phrases depicted by either language. These findings of cortical hubs exhibiting linguistic-perceptual knowledge links at a semantic category level should help to advance neurocomputational models of the neurodevelopment of language systems.

Multivariate spatial feature selection in fMRI

Multivariate neuroimaging analyses constitute a powerful class of techniques to identify psychological representations. However, not all psychological processes are represented at the same spatial scale throughout the brain. This heterogeneity is apparent when comparing hierarchically organized local representations of perceptual processes to flexible transmodal representations of more abstract cognitive processes such as social and affective operations. An open question is how the spatial scale of analytic approaches interacts with the spatial scale of the representations under investigation. In this article, we describe how multivariate analyses can be viewed as existing on a spatial spectrum, anchored by searchlights used to identify locally distributed patterns of information on one end, whole brain approach used to identify diffuse neural representations at the other and region-based approaches in between. We describe how these distinctions are an important and often overlooked analytic consideration and provide heuristics to compare these different techniques to choose based on the analyst’s inferential goals.

The human posterior cingulate and the stress-response benefits of viewing green urban landscapes

The mechanistic and neural bases of why green environments drive positive mental health outcomes remain poorly understood. We show that viewing green urban landscapes that vary in terms of green-space density elicits corresponding changes in the activity of the human ventral posterior cingulate cortex that is correlated to behavioural stress-related responses. We further show that cingulate responses are engaged early in the processing cascade, influencing attentional and executive regions in a predominantly feedforward manner. Our data suggest a key role for this region in regulating (nature) dose-dependent changes in stress responses, potentially through its extensive connections to the prefrontal and hippocampal regions which in turn project towards the neuroendocrine system. As the posterior cingulate cortex is implicated in a variety of neurological diseases and disorders, these findings raise a therapeutic potential for natural environmental exposure, highlighting green-cover as a modifiable element that links to changes in limbic responses, and has health consequences for practitioners and city-planners alike.

Lexical Information Guides Retuning of Neural Patterns in Perceptual Learning for Speech

A listener's interpretation of a given speech sound can vary probabilistically from moment to moment. Previous experience (i.e., the contexts in which one has encountered an ambiguous sound) can further influence the interpretation of speech, a phenomenon known as perceptual learning for speech. This study used multivoxel pattern analysis to query how neural patterns reflect perceptual learning, leveraging archival fMRI data from a lexically guided perceptual learning study conducted by Myers and Mesite [Myers, E. B., & Mesite, L. M. Neural systems underlying perceptual adjustment to non-standard speech tokens. Journal of Memory and Language, 76, 80-93, 2014]. In that study, participants first heard ambiguous /s/-/∫/ blends in either /s/-biased lexical contexts (epi_ode) or /∫/-biased contexts (refre_ing); subsequently, they performed a phonetic categorization task on tokens from an /asi/-/a∫i/ continuum. In the current work, a classifier was trained to distinguish between phonetic categorization trials in which participants heard unambiguous productions of /s/ and those in which they heard unambiguous productions of /∫/. The classifier was able to generalize this training to ambiguous tokens from the middle of the continuum on the basis of individual participants' trial-by-trial perception. We take these findings as evidence that perceptual learning for speech involves neural recalibration, such that the pattern of activation approximates the perceived category. Exploratory analyses showed that left parietal regions (supramarginal and angular gyri) and right temporal regions (superior, middle, and transverse temporal gyri) were most informative for categorization. Overall, our results inform an understanding of how moment-to-moment variability in speech perception is encoded in the brain.

Risk gene identification and support vector machine learning to construct an early diagnosis model of myocardial infarction

The present study aimed to identify genes associated with increased risk of myocardial infarction (MI) and construct an early diagnosis model based on support vector machine (SVM) learning. The gene expression profile data of GSE34198, containing 97 human blood samples including 49 patients with MI and 48 healthy individuals, were obtained from the Gene Expression Omnibus database. Differentially expressed gene (DEG) screening, DEG enrichment analysis, protein-protein interaction (PPI) network investigation and clustering analysis were performed. The feature genes were identified using the neighboring score algorithm. Furthermore, a recursive feature elimination (RFE) algorithm was employed to screen risk factors among feature genes. The SVM prediction model was constructed and validated using the dataset GSE61144. A total of 1,207 DEGs (724 downregulated, 483 upregulated) between the two groups were identified. PPI analysis investigated 1,083 DEGs and 46,363 edges. In total, 87 genes were selected as candidate genes, and were primarily enriched in functions including ‘G-protein coupled receptor signaling’ or pathways such as ‘focal adhesion’. Furthermore, 15 genes with a high RFE score were selected to construct an SVM prediction model. The model's average accuracy was 86%. Data set verification showed that the predictive precision reached 0.92. High expression of the genes vascular endothelial growth factor A, A-kinase anchoring protein 12 and olfactory receptor 8D2 were potential risk factors for MI. The SVM early diagnosis model constructed by candidate genes could not only predict early MI, but also provide risk probability according to the severity of MI.

Dynamics reconstruction and classification via Koopman features

Knowledge discovery and information extraction of large and complex datasets has attracted great attention in wide-ranging areas from statistics and biology to medicine. Tools from machine learning, data mining, and neurocomputing have been extensively explored and utilized to accomplish such compelling data analytics tasks. However, for time-series data presenting active dynamic characteristics, many of the state-of-the-art techniques may not perform well in capturing the inherited temporal structures in these data. In this paper, integrating the Koopman operator and linear dynamical systems theory with support vector machines, we develop an ovel dynamic data mining framework to construct low-dimensional linear models that approximate the nonlinear flow of high-dimensional time-series data generated by unknown nonlinear dynamical systems. This framework then immediately enables pattern recognition, e.g., classification, of complex time-series data to distinguish their dynamic behaviors by using the trajectories generated by the reduced linear systems. Moreover, we demonstrate the applicability and efficiency of this framework through the problems of time-series classification in bioinformatics and healthcare, including cognitive classification and seizure detection with fMRI and EEG data, respectively. The developed Koopman dynamic learning framework then lays a solid foundation for effective dynamic data mining and promises a mathematically justified method for extracting the dynamics and significant temporal structures of nonlinear dynamical systems.

Shared Numerosity Representations Across Formats and Tasks Revealed with 7 Tesla fMRI: Decoding, Generalization, and Individual Differences in Behavior

Debate continues on whether encoding of symbolic number is grounded in nonsymbolic numerical magnitudes. Nevertheless, fluency of perceiving both number formats, and translating between them, predicts math skills across the life span. Therefore, this study asked if numbers share cortical activation patterns across formats and tasks, and whether neural response to number predicts math-related behaviors. We analyzed patterns of neural activation using 7 Tesla functional magnetic resonance imaging in a sample of 39 healthy adults. Discrimination was successful between numerosities 2, 4, 6, and 8 dots and generalized to activation patterns of the same numerosities represented as Arabic digits in the bilateral parietal lobes and left inferior frontal gyrus (IFG) (and vice versa). This indicates that numerosity-specific neural resources are shared between formats. Generalization was also successful across tasks where participants either identified or compared numerosities in bilateral parietal lobes and IFG. Individual differences in decoding did not relate to performance on a number comparison task completed outside of the scanner, but generalization between formats and across tasks negatively related to math achievement in the parietal lobes. Together, these findings suggest that individual differences in representational specificity within format and task contexts relate to mathematical expertise.

Machine Learning Detects Pattern of Differences in Functional Magnetic Resonance Imaging (fMRI) Data between Chronic Fatigue Syndrome (CFS) and Gulf War Illness (GWI)

BACKGROUND

Gulf War Illness (GWI) and Chronic Fatigue Syndrome (CFS) are two debilitating disorders that share similar symptoms of chronic pain, fatigue, and exertional exhaustion after exercise. Many physicians continue to believe that both are psychosomatic disorders and to date no underlying etiology has been discovered. As such, uncovering objective biomarkers is important to lend credibility to criteria for diagnosis and to help differentiate the two disorders.

METHODS

We assessed cognitive differences in 80 subjects with GWI and 38 with CFS by comparing corresponding fMRI scans during 2-back working memory tasks before and after exercise to model brain activation during normal activity and after exertional exhaustion, respectively. Voxels were grouped by the count of total activity into the Automated Anatomical Labeling (AAL) atlas and used in an "ensemble" series of machine learning algorithms to assess if a multi-regional pattern of differences in the fMRI scans could be detected.

RESULTS

A K-Nearest Neighbor (70%/81%), Linear Support Vector Machine (SVM) (70%/77%), Decision Tree (82%/82%), Random Forest (77%/78%), AdaBoost (69%/81%), Naïve Bayes (74%/78%), Quadratic Discriminant Analysis (QDA) (73%/75%), Logistic Regression model (82%/82%), and Neural Net (76%/77%) were able to differentiate CFS from GWI before and after exercise with an average of 75% accuracy in predictions across all models before exercise and 79% after exercise. An iterative feature selection and removal process based on Recursive Feature Elimination (RFE) and Random Forest importance selected 30 regions before exercise and 33 regions after exercise that differentiated CFS from GWI across all models, and produced the ultimate best accuracies of 82% before exercise and 82% after exercise by Logistic Regression or Decision Tree by a single model, and 100% before and after exercise when selected by any six or more models. Differential activation on both days included the right anterior insula, left putamen, and bilateral orbital frontal, ventrolateral prefrontal cortex, superior, inferior, and precuneus (medial) parietal, and lateral temporal regions. Day 2 had the cerebellum, left supplementary motor area and bilateral pre- and post-central gyri. Changes between days included the right Rolandic operculum switching to the left on Day 2, and the bilateral midcingulum switching to the left anterior cingulum.

CONCLUSION

We concluded that CFS and GWI are significantly differentiable using a pattern of fMRI activity based on an ensemble machine learning model.

Using a Data-Driven Approach to Estimate Second-Language Proficiency From Brain Activation: A Functional Near-Infrared Spectroscopy Study

While non-invasive brain imaging has made substantial contributions to advance human brain science, estimation of individual state is becoming important to realize its applications in society. Brain activations were used to classify second-language proficiencies. Participants in functional near-infrared spectroscopy (fNIRS) experiment were 20/20 native Japanese speakers with high/low English abilities and 19/19 native English speakers with high/low Japanese abilities. Their cortical activities were measured by functional near-infrared spectroscopy while they were conducting Japanese/English listening comprehension tests. The data-driven method achieved classification accuracy of 77.5% in the case of Japanese speakers and 81.9% in the case of English speakers. The informative features predominantly originated from regions associated with language function. These results bring an insight of fNIRS neuroscience and its applications in society.

Tools of the Trade Multivoxel pattern analysis in fMRI: a practical introduction for social and affective neuroscientists

The family of neuroimaging analytical techniques known as multivoxel pattern analysis (MVPA) has dramatically increased in popularity over the past decade, particularly in social and affective neuroscience research using functional magnetic resonance imaging (fMRI). MVPA examines patterns of neural responses, rather than analyzing single voxel- or region-based values, as is customary in conventional univariate analyses. Here, we provide a practical introduction to MVPA and its most popular variants (namely, representational similarity analysis (RSA) and decoding analyses, such as classification using machine learning) for social and affective neuroscientists of all levels, particularly those new to such methods. We discuss how MVPA differs from traditional mass-univariate analyses, the benefits MVPA offers to social neuroscientists, experimental design and analysis considerations, step-by-step instructions for how to implement specific analyses in one's own dataset and issues that are currently facing research using MVPA methods.

Stable biomarker identification for predicting schizophrenia in the human connectome

Schizophrenia, as a psychiatric disorder, has recognized brain alterations both at the structural and at the functional magnetic resonance imaging level. The developing field of connectomics has attracted much attention as it allows researchers to take advantage of powerful tools of network analysis in order to study structural and functional connectivity abnormalities in schizophrenia. Many methods have been proposed to identify biomarkers in schizophrenia, focusing mainly on improving the classification performance or performing statistical comparisons between groups. However, the stability of biomarkers selection has been for long overlooked in the connectomics field. In this study, we follow a machine learning approach where the identification of biomarkers is addressed as a feature selection problem for a classification task. We perform a recursive feature elimination and support vector machines (RFE-SVM) approach to identify the most meaningful biomarkers from the structural, functional, and multi-modal connectomes of healthy controls and patients. Furthermore, the stability of the retrieved biomarkers is assessed across different subsamplings of the dataset, allowing us to identify the affected core of the pathology. Considering our technique altogether, it demonstrates a principled way to achieve both accurate and stable biomarkers while highlighting the importance of multi-modal approaches to brain pathology as they tend to reveal complementary information.

Support Vector Machines and Affective Science

Support vector machines (SVMs) are being used increasingly in affective science as a data-driven classification method and feature reduction technique. Whereas traditional statistical methods typically compare group averages on selected variables, SVMs use a predictive algorithm to learn multivariate patterns that optimally discriminate between groups. In this review, we provide a framework for understanding the methods of SVM-based analyses and summarize the findings of seminal studies that use SVMs for classification or data reduction in the behavioral and neural study of emotion and affective disorders. We conclude by discussing promising directions and potential applications of SVMs in future research in affective science.

Logistic Regression Algorithm Differentiates Gulf War Illness (GWI) Functional Magnetic Resonance Imaging (fMRI) Data from a Sedentary Control

Gulf War Illness (GWI) is a debilitating condition characterized by dysfunction of cognition, pain, fatigue, sleep, and diverse somatic symptoms with no known underlying pathology. As such, uncovering objective biomarkers such as differential regions of activity within a Functional Magnetic Resonance Imaging (fMRI) scan is important to enhance validity of the criteria for diagnosis. Symptoms are exacerbated by mild activity, and exertional exhaustion is a key complaint amongst sufferers. We modeled this exertional exhaustion by having GWI (n = 80) and sedentary control (n = 31) subjects perform submaximal exercise stress tests on two consecutive days. Cognitive differences were assessed by comparing fMRI scans performed during 2-Back working memory tasks before and after the exercise. Machine learning algorithms were used to identify differences in brain activation patterns between the two groups on Day 1 (before exercise) and Day 2 (after exercise). The numbers of voxels with t > 3.17 (corresponding to p < 0.001 uncorrected) were determined for brain regions defined by the Automated Anatomical Labeling (AAL) atlas. Data were divided 70:30 into training and test sets. Recursive feature selection identified twenty-nine regions of interest (ROIs) that significantly distinguished GWI from control on Day 1 and 28 ROIs on Day 2. Ten regions were present in both models between the two days, including right anterior insula, orbital frontal cortex, thalamus, bilateral temporal poles, and left supramarginal gyrus and cerebellar Crus 1. The models had 70% accuracy before exercise on Day 1 and 85% accuracy after exercise on Day 2, indicating the logistic regression model significantly differentiated subjects with GWI from the sedentary control group. Exercise caused changes in these patterns that may indicate the cognitive differences caused by exertional exhaustion. A second set of predictive models was able to classify previously identified GWI exercise subgroups START, STOPP, and POTS for both Days 1 and Days 2 with 67% and 69% accuracy respectively. This study was the first of its kind to differentiate GWI and the three sub-phenotypes START, STOPP, and POTS from a sedentary control using a logistic regression estimation method.