Automatic classification of ICA components from infant EEG using MARA
Ontology highlight
ABSTRACT:
SUBMITTER: Marriott Haresign I
PROVIDER: S-EPMC8556604 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundArtifacts contained in EEG recordings hamper both, the visual interpretation by experts as well as the algorithmic processing and analysis (e.g. for Brain-Computer Interfaces (BCI) or for Mental State Monitoring). While hand-optimized selection of source components derived from Independent Component Analysis (ICA) to clean EEG data is widespread, the field could greatly profit from automated solutions based on Machine Learning methods. Existing ICA-based removal strategies depend on explicit recordings of an individual's artifacts or have not been shown to reliably identify muscle artifacts.MethodsWe propose an automatic method for the classification of general artifactual source components. They are estimated by TDSEP, an ICA method that takes temporal correlations into account. The linear classifier is based on an optimized feature subset determined by a Linear Programming Machine (LPM). The subset is composed of features from the frequency-, the spatial- and temporal domain. A subject independent classifier was trained on 640 TDSEP components (reaction time (RT) study, n = 12) that were hand labeled by experts as artifactual or brain sources and tested on 1080 new components of RT data of the same study. Generalization was tested on new data from two studies (auditory Event Related Potential (ERP) paradigm, n = 18; motor imagery BCI paradigm, n = 80) that used data with different channel setups and from new subjects.ResultsBased on six features only, the optimized linear classifier performed on level with the inter-expert disagreement (<10% Mean Squared Error (MSE)) on the RT data. On data of the auditory ERP study, the same pre-calculated classifier generalized well and achieved 15% MSE. On data of the motor imagery paradigm, we demonstrate that the discriminant information used for BCI is preserved when removing up to 60% of the most artifactual source components.ConclusionsWe propose a universal and efficient classifier of ICA components for the subject independent removal of artifacts from EEG data. Based on linear methods, it is applicable for different electrode placements and supports the introspection of results. Trained on expert ratings of large data sets, it is not restricted to the detection of eye- and muscle artifacts. Its performance and generalization ability is demonstrated on data of different EEG studies.
| S-EPMC3175453 | biostudies-literature
Project description:We present a practical "how-to" guide to help determine whether single-subject fMRI independent components (ICs) characterise structured noise or not. Manual identification of signal and noise after ICA decomposition is required for efficient data denoising: to train supervised algorithms, to check the results of unsupervised ones or to manually clean the data. In this paper we describe the main spatial and temporal features of ICs and provide general guidelines on how to evaluate these. Examples of signal and noise components are provided from a wide range of datasets (3T data, including examples from the UK Biobank and the Human Connectome Project, and 7T data), together with practical guidelines for their identification. Finally, we discuss how the data quality, data type and preprocessing can influence the characteristics of the ICs and present examples of particularly challenging datasets.
| S-EPMC5489418 | biostudies-literature
Project description:Reliable markers measuring disease progression in Huntington's disease (HD), before and after disease manifestation, may guide a therapy aimed at slowing or halting disease progression. Quantitative electroencephalography (qEEG) may provide a quantification method for possible (sub)cortical dysfunction occurring prior to or concomitant with motor or cognitive disturbances observed in HD. In this pilot study we construct an automatic classifier distinguishing healthy controls from HD gene carriers using qEEG and derive qEEG features that correlate with clinical markers known to change with disease progression in HD, with the aim of exploring biomarker potential. We included twenty-six HD gene carriers (49.7?±?8.5 years) and 25 healthy controls (52.7?±?8.7 years). EEG was recorded for three minutes with subjects at rest. An EEG index was created by applying statistical pattern recognition to a large set of EEG features, which was subsequently tested using 10-fold cross-validation. The index resulted in a continuous variable ranging from 0 to 1: a low value indicating a state close to normal and a high value pointing to HD. qEEG features that correlate specifically with commonly used clinical markers in HD research were derived. The classification index had a specificity of 83%, a sensitivity of 83% and an accuracy of 83%. The area under the curve of the receiver operator characteristic curve was 0.9. qEEG analysis on subsets of electrophysiological features resulted in two highly significant correlations with clinical scores. The results of this pilot study suggest that qEEG may serve as a biomarker in HD. The indices correlating with modalities changing with the progression of the disease may lead to tools based on qEEG that help monitor efficacy in intervention studies.
| S-EPMC6208376 | biostudies-literature
Project description:We developed a real-time sleep stage classification system with a convolutional neural network using only a one-channel electro-encephalogram source from mice and universally available features in any time-series data: raw signal, spectrum, and zeitgeber time. To accommodate historical information from each subject, we included a long short-term memory recurrent neural network in combination with the universal features. The resulting system (UTSN-L) achieved 90% overall accuracy and 81% multi-class Matthews Correlation Coefficient, with particularly high-quality judgements for rapid eye movement sleep (91% sensitivity and 98% specificity). This system can enable automatic real-time interventions during rapid eye movement sleep, which has been difficult due to its relatively low abundance and short duration. Further, it eliminates the need for ordinal pre-calibration, electromyogram recording, and manual classification and thus is scalable. The code is open-source with a graphical user interface and closed feedback loop capability, making it easily adaptable to a wide variety of end-user needs. By allowing large-scale, automatic, and real-time sleep stage-specific interventions, this system can aid further investigations of the functions of sleep and the development of new therapeutic strategies for sleep-related disorders.
| S-EPMC8160151 | biostudies-literature
Project description:BackgroundEEG may be affected by artefacts hindering the analysis of brain signals. Data-driven methods like independent component analysis (ICA) are successful approaches to remove artefacts from the EEG. However, the ICA-based methods developed so far are often affected by limitations, such as: the need for visual inspection of the separated independent components (subjectivity problem) and, in some cases, for the independent and simultaneous recording of the inspected artefacts to identify the artefactual independent components; a potentially heavy manipulation of the EEG signals; the use of linear classification methods; the use of simulated artefacts to validate the methods; no testing in dry electrode or high-density EEG datasets; applications limited to specific conditions and electrode layouts.MethodsOur fingerprint method automatically identifies EEG ICs containing eyeblinks, eye movements, myogenic artefacts and cardiac interference by evaluating 14 temporal, spatial, spectral, and statistical features composing the IC fingerprint. Sixty-two real EEG datasets containing cued artefacts are recorded with wet and dry electrodes (128 wet and 97 dry channels). For each artefact, 10 nonlinear SVM classifiers are trained on fingerprints of expert-classified ICs. Training groups include randomly chosen wet and dry datasets decomposed in 80 ICs. The classifiers are tested on the IC-fingerprints of different datasets decomposed into 20, 50, or 80 ICs. The SVM performance is assessed in terms of accuracy, False Omission Rate (FOR), Hit Rate (HR), False Alarm Rate (FAR), and sensitivity (p). For each artefact, the quality of the artefact-free EEG reconstructed using the classification of the best SVM is assessed by visual inspection and SNR.ResultsThe best SVM classifier for each artefact type achieved average accuracy of 1 (eyeblink), 0.98 (cardiac interference), and 0.97 (eye movement and myogenic artefact). Average classification sensitivity (p) was 1 (eyeblink), 0.997 (myogenic artefact), 0.98 (eye movement), and 0.48 (cardiac interference). Average artefact reduction ranged from a maximum of 82% for eyeblinks to a minimum of 33% for cardiac interference, depending on the effectiveness of the proposed method and the amplitude of the removed artefact. The performance of the SVM classifiers did not depend on the electrode type, whereas it was better for lower decomposition levels (50 and 20 ICs).DiscussionApart from cardiac interference, SVM performance and average artefact reduction indicate that the fingerprint method has an excellent overall performance in the automatic detection of eyeblinks, eye movements and myogenic artefacts, which is comparable to that of existing methods. Being also independent from simultaneous artefact recording, electrode number, type and layout, and decomposition level, the proposed fingerprint method can have useful applications in clinical and experimental EEG settings.
| S-EPMC5826009 | biostudies-literature
Project description:Due to its millisecond-scale temporal resolution, EEG allows to assess neural correlates with precisely defined temporal relationship relative to a given event. This knowledge is generally lacking in data from functional magnetic resonance imaging (fMRI) which has a temporal resolution on the scale of seconds so that possibilities to combine the two modalities are sought. Previous applications combining event-related potentials (ERPs) with simultaneous fMRI BOLD generally aimed at measuring known ERP components in single trials and correlate the resulting time series with the fMRI BOLD signal. While it is a valuable first step, this procedure cannot guarantee that variability of the chosen ERP component is specific for the targeted neurophysiological process on the group and single subject level. Here we introduce a newly developed data-driven analysis procedure that automatically selects task-specific electrophysiological independent components (ICs). We used single-trial simultaneous EEG/fMRI analysis of a visual Go/Nogo task to assess inhibition-related EEG components, their trial-to-trial amplitude variability, and the relationship between this variability and the fMRI. Single-trial EEG/fMRI analysis within a subgroup of 22 participants revealed positive correlations of fMRI BOLD signal with EEG-derived regressors in fronto-striatal regions which were more pronounced in an early compared to a late phase of task execution. In sum, selecting Nogo-related ICs in an automated, single subject procedure reveals fMRI-BOLD responses correlated to different phases of task execution. Furthermore, to illustrate utility and generalizability of the method beyond detecting the presence or absence of reliable inhibitory components in the EEG, we show that the IC selection can be extended to other events in the same dataset, e.g., the visual responses.
| S-EPMC4077017 | biostudies-literature
Project description:We respond to a critique of our temporal Independent Components Analysis (ICA) method for separating global noise from global signal in fMRI data that focuses on the signal versus noise classification of several components. While we agree with several of Power's comments, we provide evidence and analysis to rebut his major criticisms and to reassure readers that temporal ICA remains a powerful and promising denoising approach.
| S-EPMC6591096 | biostudies-literature
Project description:BACKGROUND:The interplay between sleep structure and seizure probability has previously been studied using electroencephalography (EEG). Combining sleep assessment and detection of epileptic activity in ultralong-term EEG could potentially optimize seizure treatment and sleep quality of patients with epilepsy. However, the current gold standard polysomnography (PSG) limits sleep recording to a few nights. A novel subcutaneous device was developed to record ultralong-term EEG, and has been shown to measure events of clinical relevance for patients with epilepsy. We investigated whether subcutaneous EEG recordings can also be used to automatically assess the sleep architecture of epilepsy patients. METHOD:Four adult inpatients with probable or definite temporal lobe epilepsy were monitored simultaneously with long-term video scalp EEG (LTV EEG) and subcutaneous EEG. In total, 11 nights with concurrent recordings were obtained. The sleep EEG in the two modalities was scored independently by a trained expert according to the American Academy of Sleep Medicine (AASM) rules. By using the sleep stage labels from the LTV EEG as ground truth, an automatic sleep stage classifier based on 30 descriptive features computed from the subcutaneous EEG was trained and tested. RESULTS:An average Cohen's kappa of [Formula: see text] was achieved using patient specific leave-one-night-out cross validation. When merging all sleep stages into a single class and thereby evaluating an awake-sleep classifier, we achieved a sensitivity of 94.8% and a specificity of 96.6%. Compared to manually labeled video-EEG, the model underestimated total sleep time and sleep efficiency by 8.6 and 1.8 min, respectively, and overestimated wakefulness after sleep onset by 13.6 min. CONCLUSION:This proof-of-concept study shows that it is possible to automatically sleep score patients with epilepsy based on two-channel subcutaneous EEG. The results are comparable with the methods currently used in clinical practice. In contrast to comparable studies with wearable EEG devices, several nights were recorded per patient, allowing for the training of patient specific algorithms that can account for the individual brain dynamics of each patient. Clinical trial registered at ClinicalTrial.gov on 19 October 2016 (ID:NCT02946151).
| S-EPMC6822424 | biostudies-literature
Project description:Different machine learning algorithms have recently been used for assisting automated classification of independent component analysis (ICA) results from resting-state fMRI data. The success of this approach relies on identification of artifact components and meaningful functional networks. A limiting factor of ICA is the uncertainty of the number of independent components (NIC). We aim to develop a framework based on support vector machines (SVM) and optimized feature-selection for automated classification of independent components (ICs) and use the framework to investigate the effects of input NIC on the ICA results. Seven different resting-state fMRI datasets were studied. 18 features were devised by mimicking the empirical criteria for manual evaluation. The five most significant (p < 0.01) features were identified by general linear modeling and used to generate a classification model for the framework. This feature-optimized classification of ICs with SVM (FOCIS) framework was used to classify both group and single subject ICA results. The classification results obtained using FOCIS and previously published FSL-FIX were compared against manually evaluated results. On average the false negative rate in identifying artifact contaminated ICs for FOCIS and FSL-FIX were 98.27 and 92.34%, respectively. The number of artifact and functional network components increased almost linearly with the input NIC. Through tracking, we demonstrate that incrementing NIC affects most ICs when NIC < 33, whereas only a few limited ICs are affected by direct splitting when NIC is incremented beyond NIC > 40. For a given IC, its changes with increasing NIC are individually specific irrespective whether the component is a potential resting-state functional network or an artifact component. Using FOCIS, we investigated experimentally the ICA dimensionality of resting-state fMRI datasets and found that the input NIC can critically affect the ICA results of resting-state fMRI data.
| S-EPMC4424860 | biostudies-literature
Project description:BACKGROUND: Random forest, an ensemble based supervised machine learning algorithm, is used to predict the SCOP structural classification for a target structure, based on the similarity of its structural descriptors to those of a template structure with an equal number of secondary structure elements (SSEs). An initial assessment of random forest is carried out for domains consisting of three SSEs. The usability of random forest in classifying larger domains is demonstrated by applying it to domains consisting of four, five and six SSEs. RESULTS: Random forest, trained on SCOP version 1.69, achieves a predictive accuracy of up to 94% on an independent and non-overlapping test set derived from SCOP version 1.73. For classification to the SCOP Class, Fold, Super-family or Family levels, the predictive quality of the model in terms of Matthew's correlation coefficient (MCC) ranged from 0.61 to 0.83. As the number of constituent SSEs increases the MCC for classification to different structural levels decreases. CONCLUSIONS: The utility of random forest in classifying domains from the place-holder classes of SCOP to the true Class, Fold, Super-family or Family levels is demonstrated. Issues such as introduction of a new structural level in SCOP and the merger of singleton levels can also be addressed using random forest. A real-world scenario is mimicked by predicting the classification for those protein structures from the PDB, which are yet to be assigned to the SCOP classification hierarchy.
| S-EPMC2916923 | biostudies-literature