RESUMO
Watching a speaker's face improves speech perception accuracy. This benefit is enabled, in part, by implicit lipreading abilities present in the general population. While it is established that lipreading can alter the perception of a heard word, it is unknown how these visual signals are represented in the auditory system or how they interact with auditory speech representations. One influential, but untested, hypothesis is that visual speech modulates the population-coded representations of phonetic and phonemic features in the auditory system. This model is largely supported by data showing that silent lipreading evokes activity in the auditory cortex, but these activations could alternatively reflect general effects of arousal or attention or the encoding of non-linguistic features such as visual timing information. This gap limits our understanding of how vision supports speech perception. To test the hypothesis that the auditory system encodes visual speech information, we acquired functional magnetic resonance imaging (fMRI) data from healthy adults and intracranial recordings from electrodes implanted in patients with epilepsy during auditory and visual speech perception tasks. Across both datasets, linear classifiers successfully decoded the identity of silently lipread words using the spatial pattern of auditory cortex responses. Examining the time course of classification using intracranial recordings, lipread words were classified at earlier time points relative to heard words, suggesting a predictive mechanism for facilitating speech. These results support a model in which the auditory system combines the joint neural distributions evoked by heard and lipread words to generate a more precise estimate of what was said.
RESUMO
The study of human working memory (WM) holds significant importance in neuroscience; yet, exploring the role of the medial temporal lobe (MTL) in WM has been limited by the technological constraints of noninvasive methods. Recent advancements in human intracranial neural recordings have indicated the involvement of the MTL in WM processes. These recordings show that different regions of the MTL are involved in distinct aspects of WM processing and also dynamically interact with each other and the broader brain network. These findings support incorporating the MTL into models of the neural basis of WM. This integration can better reflect the complex neural mechanisms underlying WM and enhance our understanding of WM's flexibility, adaptability, and precision.
RESUMO
OBJECTIVE: Many patients pursue epilepsy surgery with the hope of reducing or stopping anti-seizure medications (ASMs), in addition to reducing their seizure frequency and severity. While ASM decrease is primarily driven by surgical outcomes and patient preferences, preoperative estimates of meaningful ASM reduction or discontinuation are uncertain, especially when accounting for the various forking paths possible following intracranial EEG (iEEG), including resection, neuromodulation, or even the absence of further surgery. Here, we characterize in detail the ASM reduction in a large cohort of patients who underwent iEEG, facilitating proactive, early counseling for a complicated cohort considering surgical treatment. METHODS: We identified a multi-institutional cohort of patients who underwent iEEG between 2001 and 2022, with a minimum of two years follow-up. The total number of ASMs prescribed immediately prior to surgery, choice of investigation modality, and subsequent surgical treatment were extracted for each patient. Primary endpoints included decreases in ASM counts from preoperative baseline to various follow-up intervals. RESULTS: A total of 284 patients were followed for a median of 6.0 (range 2,22) years after iEEG surgery. Patients undergoing resection saw an average reduction of â¼ 0.5 ASMs. Patients undergoing neuromodulation saw no decrease and trended towards requiring increased ASM usage during long-term follow-up. Only patients undergoing resection were likely to completely discontinue all ASMs, with an increasing probability over time approaching â¼ 10 %. Up to half of resection patients saw ASM decreases, which was largely stable during long-term follow-up, whereas only a quarter of neuromodulation patients saw a reduction, though their ASM reduction decreased over time. CONCLUSIONS: With the increasing use of stereotactic EEG and non-curative neuromodulation procedures, realistic estimates of ASM reduction and discontinuation should be considered preoperatively. Almost half of patients undergoing resective surgery can expect to reduce their ASMs, though only a tenth can expect to discontinue ASMs completely. If reduction is not seen early, it likely does not occur later during long-term follow-up. Less than a third of patients undergoing neuromodulation can expect ASM reduction, and instead most may require increased usage during long-term follow-up.
Assuntos
Anticonvulsivantes , Epilepsia , Humanos , Feminino , Masculino , Adulto , Anticonvulsivantes/uso terapêutico , Pessoa de Meia-Idade , Adulto Jovem , Epilepsia/cirurgia , Adolescente , Eletrocorticografia , Convulsões/cirurgia , Seguimentos , Procedimentos Neurocirúrgicos , Idoso , Estudos de Coortes , Criança , Resultado do TratamentoRESUMO
Scale-free brain activity, linked with learning, the integration of different time scales, and the formation of mental models, is correlated with a metastable cognitive basis. The spectral slope, a key aspect of scale-free dynamics, was proposed as a potential indicator to distinguish between different sleep stages. Studies suggest that brain networks maintain a consistent scale-free structure across wakefulness, anesthesia, and recovery. Although differences in anesthetic sensitivity between the sexes are recognized, these variations are not evident in clinical electroencephalographic recordings of the cortex. Recently, changes in the slope of the power law exponent of neural activity were found to correlate with changes in Rényi entropy, an extended concept of Shannon's information entropy. These findings establish quantifiers as a promising tool for the study of scale-free dynamics in the brain. Our study presents a novel visual representation called the Rényi entropy-complexity causality space, which encapsulates complexity, permutation entropy, and the Rényi parameter q. The main goal of this study is to define this space for classical dynamical systems within theoretical bounds. In addition, the study aims to investigate how well different time series mimicking scale-free activity can be discriminated. Finally, this tool is used to detect dynamic features in intracranial electroencephalography (iEEG) signals. To achieve these goals, the study implementse the Bandt and Pompe method for ordinal patterns. In this process, each signal is associated with a probability distribution, and the causal measures of Rényi entropy and complexity are computed based on the parameter q. This method is a valuable tool for analyzing simulated time series. It effectively distinguishes elements of correlated noise and provides a straightforward means of examining differences in behaviors, characteristics, and classifications. For the iEEG experimental data, the REM state showed a greater number of significant sex-based differences, while the supramarginal gyrus region showed the most variation across different modes and analyzes. Exploring scale-free brain activity with this framework could provide valuable insights into cognition and neurological disorders. The results may have implications for understanding differences in brain function between the sexes and their possible relevance to neurological disorders.
RESUMO
Epilepsy is characterized by recurrent, unprovoked seizures. Accurate prediction of seizure occurrence has long been a clinical goal since this would allow to optimize patient treatment, prevent injuries due to seizures, and alleviate the patient burden of unpredictability. Advances in implantable electroencephalographic (EEG) devices, allowing for long-term interictal EEG recordings, have facilitated major progress in this field. Recently, it has been discovered that interictal brain activity demonstrates circadian and multi-dien cycles that are strongly aligned, or phase locked, with seizure risk. Thus, cyclical brain activity patterns have been used to forecast seizures. However, in the effort to develop a clinically useful EEG based seizure forecasting system, challenges remain. Firstly, multiple EEG features demonstrate cyclical patterns, but it remains unclear which feature is best suited for predicting seizures. Secondly, the technology for long-term EEG recording is currently limited in both spatial and temporal sampling resolution. In this study, we compare five established EEG metrics:synchrony, spatial correlation, temporal correlation, signal variance which have been motivated from critical dynamics theory, and interictal epileptiform discharge (IED) which are a traditional marker of seizure propensity. We assess their effectiveness in detecting 24-h and seizure cycles as well as their robustness under spatial and temporal subsampling. Analyzing intracranial EEG data from 23 patients, we report that all examined features exhibit 24-h cycles. Spatial correlation, signal variance, and synchrony showed the highest phase locking with seizures, while IED rates were the lowest. Notably, spatial and temporal correlation were also found to be highly correlated to each other, as were signal variance and IED-suggesting some features may reflect similar aspects of cortical dynamics, whereas others provide complementary information. All features proved robust under subsampling, indicating that the dynamic properties of interictal activity evolve slowly and are not confined to specific brain regions. Our results may aid future translational research by assisting in design and testing of EEG based seizure forecasting systems.
RESUMO
How is information processed in the cerebral cortex? In most cases, recorded brain activity is averaged over many (stimulus) repetitions, which erases the fine-structure of the neural signal. However, the brain is obviously a single-trial processor. Thus, we here demonstrate that an unsupervised machine learning approach can be used to extract meaningful information from electro-physiological recordings on a single-trial basis. We use an auto-encoder network to reduce the dimensions of single local field potential (LFP) events to create interpretable clusters of different neural activity patterns. Strikingly, certain LFP shapes correspond to latency differences in different recording channels. Hence, LFP shapes can be used to determine the direction of information flux in the cerebral cortex. Furthermore, after clustering, we decoded the cluster centroids to reverse-engineer the underlying prototypical LFP event shapes. To evaluate our approach, we applied it to both extra-cellular neural recordings in rodents, and intra-cranial EEG recordings in humans. Finally, we find that single channel LFP event shapes during spontaneous activity sample from the realm of possible stimulus evoked event shapes. A finding which so far has only been demonstrated for multi-channel population coding.
Assuntos
Aprendizado Profundo , Eletroencefalografia , Humanos , Animais , Eletroencefalografia/métodos , Córtex Cerebral/fisiologia , Masculino , Aprendizado de Máquina não Supervisionado , Ratos , Adulto , FemininoRESUMO
BACKGROUND: Accurate identification of abnormal electroencephalographic (EEG) activity is pivotal for diagnosing and treating epilepsy. Recent studies indicate that decomposing brain activity into periodic (oscillatory) and aperiodic (trend across all frequencies) components can illuminate the drivers of spectral activity changes. NEW METHODS: We analysed intracranial EEG (iEEG) data from 234 subjects, creating a normative map. This map was compared to a cohort of 63 patients with refractory focal epilepsy under consideration for neurosurgery. The normative map was computed using three approaches: (i) relative complete band power, (ii) relative band power with the aperiodic component removed, and (iii) the aperiodic exponent. Abnormalities were calculated for each approach in the patient cohort. We evaluated the spatial profiles, assessed their ability to localize abnormalities, and replicated the findings using magnetoencephalography (MEG). RESULTS: Normative maps of relative complete band power and relative periodic band power exhibited similar spatial profiles, while the aperiodic normative map revealed higher exponent values in the temporal lobe. Abnormalities estimated through complete band power effectively distinguished between good and bad outcome patients. Combining periodic and aperiodic abnormalities enhanced performance, like the complete band power approach. COMPARISON WITH EXISTING METHODS AND CONCLUSIONS: Sparing cerebral tissue with abnormalities in both periodic and aperiodic activity may result in poor surgical outcomes. Both periodic and aperiodic components do not carry sufficient information in isolation. The relative complete band power solution proved to be the most reliable method for this purpose. Future studies could investigate how cerebral location or pathology influences periodic or aperiodic abnormalities.
Assuntos
Encéfalo , Eletrocorticografia , Magnetoencefalografia , Humanos , Magnetoencefalografia/métodos , Masculino , Feminino , Adulto , Eletrocorticografia/métodos , Adulto Jovem , Encéfalo/fisiopatologia , Mapeamento Encefálico/métodos , Pessoa de Meia-Idade , Adolescente , Processamento de Sinais Assistido por Computador , Epilepsia Resistente a Medicamentos/fisiopatologia , Epilepsia Resistente a Medicamentos/diagnóstico , Epilepsia Resistente a Medicamentos/cirurgia , Epilepsias Parciais/fisiopatologia , Epilepsias Parciais/diagnóstico , Epilepsias Parciais/cirurgia , Epilepsia/fisiopatologia , Epilepsia/diagnóstico , Estudos de Coortes , Eletroencefalografia/métodos , Ondas Encefálicas/fisiologiaRESUMO
Simultaneous noninvasive and invasive electrophysiological recordings provide a unique opportunity to achieve a comprehensive understanding of human brain activity, much like a Rosetta stone for human neuroscience. In this review we focus on the increasingly-used powerful combination of intracranial electroencephalography (iEEG) with scalp electroencephalography (EEG) or magnetoencephalography (MEG). We first provide practical insight on how to achieve these technically challenging recordings. We then provide examples from clinical research on how simultaneous recordings are advancing our understanding of epilepsy. This is followed by the illustration of how human neuroscience and methodological advances could benefit from these simultaneous recordings. We conclude with a call for open data sharing and collaboration, while ensuring neuroethical approaches and argue that only with a true collaborative approach the promises of simultaneous recordings will be fulfilled.
Assuntos
Encéfalo , Magnetoencefalografia , Humanos , Magnetoencefalografia/métodos , Encéfalo/fisiologia , Eletroencefalografia/métodos , Epilepsia/fisiopatologia , Eletrocorticografia/métodosRESUMO
Brain activity may manifest itself as oscillations which are repetitive rhythms of neuronal firing. These local field potentials can be measured via intracranial electroencephalography (iEEG). This review focuses on iEEG used to map human brain structures involved in olfaction. After presenting the methodology of the review, a summary of the brain structures involved in olfaction is given, followed by a review of the literature on human olfactory oscillations in different contexts. A single case is provided as an illustration of the olfactory oscillations. Overall, the timing and sequence of oscillations found in the different structures of the olfactory system seem to play an important role for olfactory perception.
Assuntos
Percepção Olfatória , Olfato , Humanos , Olfato/fisiologia , Encéfalo/fisiologia , Percepção Olfatória/fisiologia , Eletroencefalografia/métodosRESUMO
Humans have the remarkable ability to vividly retrieve sensory details of past events. According to the theory of sensory reinstatement, during remembering, brain regions specialized for processing specific sensory stimuli are reactivated to support content-specific retrieval. Recently, several studies have emphasized transformations in the spatial organization of these reinstated activity patterns. Specifically, studies of scene stimuli suggest a clear anterior shift in the location of retrieval activations compared with the activity observed during perception. However, it is not clear that such transformations occur universally, with inconsistent evidence for other important stimulus categories, particularly faces. One challenge in addressing this question is the careful delineation of face-selective cortices, which are interdigitated with other selective regions, in configurations that spatially differ across individuals. Therefore, we conducted a multisession neuroimaging study to first carefully map individual participants' (nine males and seven females) face-selective regions within ventral temporal cortex (VTC), followed by a second session to examine the activity patterns within these regions during face memory encoding and retrieval. While face-selective regions were expectedly engaged during face perception at encoding, memory retrieval engagement exhibited a more selective and constricted reinstatement pattern within these regions, but did not show any consistent direction of spatial transformation (e.g., anteriorization). We also report on unique human intracranial recordings from VTC under the same experimental conditions. These findings highlight the importance of considering the complex configuration of category-selective cortex in elucidating principles shaping the neural transformations that occur from perception to memory.
Assuntos
Mapeamento Encefálico , Reconhecimento Facial , Imageamento por Ressonância Magnética , Lobo Temporal , Humanos , Masculino , Feminino , Lobo Temporal/fisiologia , Lobo Temporal/diagnóstico por imagem , Adulto , Reconhecimento Facial/fisiologia , Adulto Jovem , Memória/fisiologia , Estimulação Luminosa/métodos , Rememoração Mental/fisiologiaRESUMO
Deep brain stimulation (DBS) is a viable treatment for a variety of neurological conditions, however, the mechanisms through which DBS modulates large-scale brain networks are unresolved. Clinical effects of DBS are observed over multiple timescales. In some conditions, such as Parkinson's disease and essential tremor, clinical improvement is observed within seconds. In many other conditions, such as epilepsy, central pain, dystonia, neuropsychiatric conditions or Tourette syndrome, the DBS related effects are believed to require neuroplasticity or reorganization and often take hours to months to observe. To optimize DBS parameters, it is therefore essential to develop electrophysiological biomarkers that characterize whether DBS settings are successfully engaging and modulating the network involved in the disease of interest. In this study, 10 individuals with drug resistant epilepsy undergoing intracranial stereotactic EEG including a thalamus electrode underwent a trial of repetitive thalamic stimulation. We evaluated thalamocortical effective connectivity using single pulse electrical stimulation, both at baseline and following a 145 Hz stimulation treatment trial. We found that when high frequency stimulation was delivered for >1.5 hours, the evoked potentials measured from remote regions were significantly reduced in amplitude and the degree of modulation was proportional to the strength of baseline connectivity. When stimulation was delivered for shorter time periods, results were more variable. These findings suggest that changes in effective connectivity in the network targeted with DBS accumulate over hours of DBS. Stimulation evoked potentials provide an electrophysiological biomarker that allows for efficient data-driven characterization of neuromodulation effects, which could enable new objective approaches for individualized DBS optimization.
RESUMO
OBJECTIVE: Interictal biomarkers of the epileptogenic zone (EZ) and their use in machine learning models open promising avenues for improvement of epilepsy surgery evaluation. Currently, most studies restrict their analysis to short segments of intracranial EEG (iEEG). METHODS: We used 2381 hours of iEEG data from 25 patients to systematically select 5-minute segments across various interictal conditions. Then, we tested machine learning models for EZ localization using iEEG features calculated within these individual segments or across them and evaluated the performance by the area under the precision-recall curve (PRAUC). RESULTS: On average, models achieved a score of 0.421 (the result of the chance classifier was 0.062). However, the PRAUC varied significantly across the segments (0.323-0.493). Overall, NREM sleep achieved the highest scores, with the best results of 0.493 in N2. When using data from all segments, the model performed significantly better than single segments, except NREM sleep segments. CONCLUSIONS: The model based on a short segment of iEEG recording can achieve similar results as a model based on prolonged recordings. The analyzed segment should, however, be carefully and systematically selected, preferably from NREM sleep. SIGNIFICANCE: Random selection of short iEEG segments may give rise to inaccurate localization of the EZ.
Assuntos
Eletroencefalografia , Epilepsia , Aprendizado de Máquina , Humanos , Feminino , Masculino , Adulto , Epilepsia/fisiopatologia , Epilepsia/diagnóstico , Eletroencefalografia/métodos , Pessoa de Meia-Idade , Fatores de Tempo , Adulto Jovem , Eletrocorticografia/métodos , Eletrocorticografia/normas , Adolescente , Encéfalo/fisiopatologia , Fases do Sono/fisiologiaRESUMO
The hippocampus is generally considered to have relatively late involvement in recognition memory, its main electrophysiological signature being between 400 and 800â ms after stimulus onset. However, most electrophysiological studies have analyzed the hippocampus as a single responsive area, selecting only a single-site signal exhibiting the strongest effect in terms of amplitude. These classical approaches may not capture all the dynamics of this structure, hindering the contribution of other hippocampal sources that are not located in the vicinity of the selected site. We combined intracerebral electroencephalogram recordings from epileptic patients with independent component analysis during a recognition memory task involving the recognition of old and new images. We identified two sources with different responses emerging from the hippocampus: a fast one (maximal amplitude at â¼250â ms) that could not be directly identified from raw recordings and a latter one, peaking at â¼400â ms. The former component presented different amplitudes between old and new items in 6 out of 10 patients. The latter component had different delays for each condition, with a faster activation (â¼290â ms after stimulus onset) for recognized items. We hypothesize that both sources represent two steps of hippocampal recognition memory, the faster reflecting the input from other structures and the latter the hippocampal internal processing. Recognized images evoking early activations would facilitate neural computation in the hippocampus, accelerating memory retrieval of complementary information. Overall, our results suggest that the hippocampal activity is composed of several sources with an early activation related to recognition memory.
Assuntos
Epilepsia , Reconhecimento Psicológico , Humanos , Reconhecimento Psicológico/fisiologia , Memória/fisiologia , Hipocampo/fisiologia , EletroencefalografiaRESUMO
The amygdala might support an attentional bias for emotional faces. However, whether and how selective attention toward a specific valence modulates this bias is not fully understood. Likewise, it is unclear whether amygdala and cortical signals respond to emotion and attention in a similar way. We recorded gamma-band activity (GBA, > 30 Hz) intracranially in the amygdalae of 11 patients with epilepsy and collected scalp recordings from 19 healthy participants. We presented angry, neutral, and happy faces randomly, and we denoted one valence as the target. Participants detected happy targets most quickly and accurately. In the amygdala, during attention to negative faces, low gamma-band activity (LGBA, < 90 Hz) increased for angry compared with happy faces from 160 ms. From 220 ms onward, amygdala high gamma-band activity (HGBA, > 90 Hz) was higher for angry and neutral faces than for happy ones. Monitoring neutral faces increased amygdala HGBA for emotions compared with neutral faces from 40 ms. Expressions were not differentiated in GBA while monitoring positive faces. On the scalp, only threat monitoring resulted in expression differentiation. Here, posterior LGBA was increased selectively for angry targets from 60 ms. The data show that GBA differentiation of emotional expressions is modulated by attention to valence: Top-down-controlled threat vigilance coordinates widespread GBA in favor of angry faces. Stimulus-driven emotion differentiation in amygdala GBA occurs during a neutral attentional focus. These findings align with a multi-pathway model of emotion processing and specify the role of GBA in this process.
Assuntos
Tonsila do Cerebelo , Emoções , Humanos , Emoções/fisiologia , Ira , Felicidade , Expressão FacialRESUMO
Exploring the neural mechanisms of awareness is a fundamental task of cognitive neuroscience. There is an ongoing dispute regarding the role of the prefrontal cortex (PFC) in the emergence of awareness, which is partially raised by the confound between report- and awareness-related activity. To address this problem, we designed a visual awareness task that can minimize report-related motor confounding. Our results show that saccadic latency is significantly shorter in the aware trials than in the unaware trials. Local field potential (LFP) data from six patients consistently show early (200-300ms) awareness-related activity in the PFC, including event-related potential and high-gamma activity. Moreover, the awareness state can be reliably decoded by the neural activity in the PFC since the early stage, and the neural pattern is dynamically changed rather than being stable during the representation of awareness. Furthermore, the enhancement of dynamic functional connectivity, through the phase modulation at low frequency, between the PFC and other brain regions in the early stage of the awareness trials may explain the mechanism of conscious access. These results indicate that the PFC is critically involved in the emergence of awareness.
Assuntos
Neurociência Cognitiva , Córtex Pré-Frontal , Humanos , Estado de Consciência , Movimentos SacádicosRESUMO
Intracranial electrical stimulation (iES) of auditory cortex can elicit sound experiences with a variety of perceived contents (hallucination or illusion) and locations (contralateral or bilateral side), independent of actual acoustic inputs. However, the neural mechanisms underlying this elicitation heterogeneity remain undiscovered. Here, we collected subjective reports following iES at 3062 intracranial sites in 28 patients (both sexes) and identified 113 auditory cortical sites with iES-elicited sound experiences. We then decomposed the sound-induced intracranial electroencephalogram (iEEG) signals recorded from all 113 sites into time-frequency features. We found that the iES-elicited perceived contents can be predicted by the early high-γ features extracted from sound-induced iEEG. In contrast, the perceived locations elicited by stimulating hallucination sites and illusion sites are determined by the late high-γ and long-lasting α features, respectively. Our study unveils the crucial neural signatures of iES-elicited sound experiences in human and presents a new strategy to hearing restoration for individuals suffering from deafness.
Assuntos
Córtex Auditivo , Ilusões , Masculino , Feminino , Humanos , Córtex Auditivo/fisiologia , Ilusões/fisiologia , Estimulação Acústica , Mapeamento Encefálico , Estimulação Elétrica , AlucinaçõesRESUMO
BACKGROUND: Intracranial electrodes are typically localized from post-implantation CT artifacts. Automatic algorithms localizing low signal-to-noise ratio artifacts and high-density electrode arrays are missing. Additionally, implantation of grids/strips introduces brain deformations, resulting in registration errors when fusing post-implantation CT and pre-implantation MR images. Brain-shift compensation methods project electrode coordinates to cortex, but either fail to produce smooth solutions or do not account for brain deformations. NEW METHODS: We first introduce GridFit, a model-based fitting approach that simultaneously localizes all electrodes' CT artifacts in grids, strips, or depth arrays. Second, we present CEPA, a brain-shift compensation algorithm combining orthogonal-based projections, spring-mesh models, and spatial regularization constraints. RESULTS: We tested GridFit on â¼6000 simulated scenarios. The localization of CT artifacts showed robust performance under difficult scenarios, such as noise, overlaps, and high-density implants (<1 mm errors). Validation with data from 20 challenging patients showed 99% accurate localization of the electrodes (3160/3192). We tested CEPA brain-shift compensation with data from 15 patients. Projections accounted for simple mechanical deformation principles with < 0.4 mm errors. The inter-electrode distances smoothly changed across neighbor electrodes, while changes in inter-electrode distances linearly increased with projection distance. COMPARISON WITH EXISTING METHODS: GridFit succeeded in difficult scenarios that challenged available methods and outperformed visual localization by preserving the inter-electrode distance. CEPA registration errors were smaller than those obtained for well-established alternatives. Additionally, modeling resting-state high-frequency activity in five patients further supported CEPA. CONCLUSION: GridFit and CEPA are versatile tools for registering intracranial electrode coordinates, providing highly accurate results even in the most challenging implantation scenarios. The methods are implemented in the iElectrodes open-source toolbox.
Assuntos
Eletroencefalografia , Imageamento por Ressonância Magnética , Humanos , Eletroencefalografia/métodos , Eletrodos Implantados , Imageamento por Ressonância Magnética/métodos , Encéfalo/diagnóstico por imagem , Córtex Cerebral/diagnóstico por imagem , EletrodosRESUMO
OBJECTIVES: The present study is designed to explore the process of epileptic patterns' automatic detection, specifically, epileptic spikes and high-frequency oscillations (HFOs), via a selection of machine learning (ML) techniques. The primary motivation for conducting such a research lies mainly in the need to investigate the long-term electroencephalography (EEG) recordings' visual examination process, often considered as a time-consuming and potentially error-prone procedure, requiring a great deal of mental focus and highly experimented neurologists. On attempting to resolve such a challenge, a number of state-of-the-art ML algorithms have been evaluated and compare in terms of performance, to pinpoint the most effective algorithm fit for accurately extracting epileptic EEG patterns. CONTENT: Based on intracranial as well as simulated EEG data, the attained findings turn out to reveal that the randomforest (RF) method proved to be the most consistently effective approach, significantly outperforming the entirety of examined methods in terms of EEG recordings epileptic-pattern identification. Indeed, the RF classifier appeared to record an average balanced classification rate (BCR) of 92.38â¯% in regard to spikes recognition process, and 78.77â¯% in terms of HFOs detection. SUMMARY: Compared to other approaches, our results provide valuable insights into the RF classifier's effectiveness as a powerful ML technique, fit for detecting EEG signals born epileptic bursts. OUTLOOK: As a potential future work, we envisage to further validate and sustain our major reached findings through incorporating a larger EEG dataset. We also aim to explore the generative adversarial networks (GANs) application so as to generate synthetic EEG signals or combine signal generation techniques with deep learning approaches. Through this new vein of thought, we actually preconize to enhance and boost the automated detection methods' performance even more, thereby, noticeably enhancing the epileptic EEG pattern recognition area.
Assuntos
Epilepsia , Humanos , Epilepsia/diagnóstico , Eletroencefalografia/métodos , Algoritmos , Aprendizado de Máquina , Processamento de Sinais Assistido por ComputadorRESUMO
Brain interictal epileptiform discharges (IEDs), as one of the hallmarks of epileptic brain, are transient events captured by electroencephalogram (EEG). IEDs are generated by seizure networks, and they occur between seizures (interictal periods). The development of a robust method for IED detection could be highly informative for clinical treatment procedures and epileptic patient management. Since 1972, different machine learning techniques, from template matching to deep learning, have been developed to automatically detect IEDs from scalp EEG (scEEG) and intracranial EEG (iEEG). While the scEEG signals suffer from low information details and high attenuation of IEDs due to the high skull electrical impedance, the iEEG signals recorded using implanted electrodes enjoy higher details and are more suitable for identifying the IEDs. In this review paper, we group IED detection techniques into six categories: (1) template matching, (2) feature representation (mimetic, time-frequency, and nonlinear features), (3) matrix decomposition, (4) tensor factorization, (5) neural networks, and (6) estimation of the iEEG from the concurrent scEEG followed by detection and classification. The methods are compared quantitatively (e.g., in terms of accuracy, sensitivity, and specificity), and their general advantages and limitations are described. Finally, current limitations and possible future research paths related to this field are mentioned.
Assuntos
Eletroencefalografia , Epilepsia , Humanos , Eletroencefalografia/métodos , Epilepsia/diagnóstico , Encéfalo , Convulsões , Aprendizado de Máquina , Couro CabeludoRESUMO
Epilepsy surgery is a potentially curative treatment of drug-resistant epilepsy that has remained underutilized both due to inadequate referrals and incomplete localization hypotheses. The complexity of patients evaluated for epilepsy surgery has increased, thus new approaches are necessary to treat these patients. The paradigm of epilepsy surgery has evolved to match this challenge, now considering the entire seizure network with the goal of disrupting it through resection, ablation, neuromodulation, or a combination. The network paradigm has the potential to aid in identification of the seizure network as well as treatment selection.