Author name cluster

Maarten De Vos

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

23 papers

1 author row

JBHI Journal 2026 Journal Article

Non-Direct Contact ECG Signal Classification Using a Hybrid Deep Learning Framework With Validation in Bedside Heart Rate Variability Analysis

Zhijun Xiao
Maarten De Vos
Christos Chatzichristos
Yunyi Jiang
Minghui Zhao
Fei Ding
Chenxi Yang
Jianqing Li

In recent years, the demand for smart healthcare solutions have heightened the need for accuracy, reliability, and comfort in bedside ECG recording and analysis. This study presents a bedside non-direct contact ECG recording system based on capacitive coupling electrocardiography (cECG) and verifies its performance in accurately capturing Heart Rate Variability (HRV) during the night. Firstly, cECG collects ECG data through clothing, avoiding skin irritation from conventional wet electrodes. Secondly, leveraging the unique characteristics of cECG signals, a deep learning framework assesses the quality of cECG, filtering noise and identifying off-bed information, enhancing HRV analysis precision. Subsequently, the system was employed to recording sleep data from 6 subjects overnight, with our proposed algorithm utilized for signal quality assessment (SQA) and HRV analysis. Finally, HRV features were compared with synchronously collected wet electrode ECG signals, encompassing time domain features, frequency domain features, and nonlinear features, totaling 13 HRV features. Experimental findings demonstrate that for the SQA task, the model achieved a classification accuracy of 94. 7%, with a Recall of 0. 941, Precision of 0. 940, F1 score of 0. 941, and Cohen’s Kappa of 0. 927. The accuracy of on/off-bed monitoring reached 99. 79%. Additionally, HRV features showed a strong correlation with the reference ECG. In the time-domain metrics, the largest mean absolute percentage error (MAPE) is for PNN50, with a value of 8. 148%. In the frequency-domain features, the largest MAPE is for HF, with a value of 13. 253%. For nonlinear features, the largest MAPE is for SD1, with a value of 5. 182%. Generally, the system exhibited a reliable solution for cECG recording, on/off-bed status detection, and bedside HRV analysis.

JBHI Journal 2025 Journal Article

A Human-in-the-Loop Method for Annotation of Events in Biomedical Signals

Nick Seeuws
Maarten De Vos
Alexander Bertrand

Objective: Building large-scale data bases of biomedical signal recordings for training artificial-intelligence systems involves substantial human effort in data processing and annotation. In the case of event detection, experts need to exhaustively scroll through the recordings and highlight events of interest. Methods: We propose an iterative annotation support algorithm with a human in the loop to improve the efficiency of the annotation process. Our algorithm generates proposal events based on an event detection model trained on incomplete annotations. The human only needs to verify candidate events proposed by the tool instead of scrolling through the entire data set. Our algorithm iterates between proposal generation and verification to leverage the human-in-the-loop feedback to obtain a growing set of event annotations. Results: Our algorithm finds a substantial amount of events at a fraction of the human time spent when comparing with a benchmark method and the normal manual process, finding all events in one data set and 70% of events in another with the human-in-the-loop only viewing 20% of the data. Conclusion: Our results show that combining human and computer effort can substantially speed up the annotation process for events in biomedical signal processing. Significance: Due to its simplicity and minimal reliance on task-specific information, our algorithm is broadly applicable, unlocking substantial improvements in the scalability and efficiency of biomedical signal annotation.

NeurIPS Conference 2025 Conference Paper

Balancing Multimodal Training Through Game-Theoretic Regularization

Konstantinos Kontras
Thomas Strypsteen
Christos Chatzichristos
Paul Liang
Matthew Blaschko
Maarten De Vos

Multimodal learning holds the promise for richer information extraction by capturing dependencies across data sources. Yet, current training methods often underperform due to modality competition, a phenomenon where modalities contend for training resources, leaving some underoptimized. This raises a pivotal question: how can we address training imbalances, ensure adequate optimization across all modalities, and achieve consistent performance improvements as we transition from unimodal to multimodal data? This paper proposes the Multimodal Competition Regularizer (MCR), inspired by a mutual information (MI) decomposition designed to prevent the adverse effects of competition in multimodal training. Our key contributions are: 1) A game-theoretic framework that adaptively balances modality contributions by encouraging each to maximize its informative role in the final prediction. 2) Refining lower and upper bounds for each MI term to enhance the extraction of both task-relevant unique and shared information across modalities. 3) Proposing latent space permutations for conditional MI estimation, significantly improving computational efficiency. MCR outperforms all previously suggested training strategies and simple baselines, demonstrating that training modalities jointly lead to important performance gains on synthetic and large real-world datasets. We release our code and models at https: //github. com/kkontras/MCR.

JBHI Journal 2024 Journal Article

Learning Robust Representations of Tonic-Clonic Seizures With Cyclic Transformer

Jingwei Zhang
Lauren Swinnen
Christos Chatzichristos
Wim Van Paesschen
Maarten De Vos

Tonic-clonic seizures (TCSs) pose a significant risk for sudden unexpected death in epilepsy (SUDEP). Previous research has highlighted the potential of multimodal wearable seizure detection systems in accurately detecting TCSs through continuous monitoring, enabling timely alarms and potentially preventing SUDEP. However, such multimodal systems carry a higher risk of sensor malfunction. In this paper, we propose a cyclic transformer approach to address these challenges. The cyclic transformer learns a robust representation by performing circular modal translations between the source and target modalities. It leverages back-translation as regularization technique to enhance the discriminative power of the learned representation. Notably, the proposed cyclic transformer is trained on paired multimodal data but requires only a single source modality during deployment. This characteristic ensures the robustness of the cyclic transformer to perturbations or missing information in the target modality. Experimental results demonstrate that the proposed cyclic transformer achieves competitive performance compared with existing multimodal systems. While both approaches were trained using EEG and EMG data, the cyclic transformer exclusively employs EEG data for testing, diverging from the state-of-the-art's utilization of both EEG and EMG data during test. This showcases the effectiveness of the cyclic transformer in multimodal TCSs detection, offering a promising approach for enhancing the accuracy and robustness of seizure detection systems while mitigating the risks associated with sensor malfunction.

JBHI Journal 2024 Journal Article

Personalization of Automatic Sleep Scoring: How Best to Adapt Models to Personal Domains in Wearable EEG

Kristian P. Lorenzen
Elisabeth R. M. Heremans
Maarten De Vos
Kaare B. Mikkelsen

Wearable EEG enables us to capture large amounts of high-quality sleep data for diagnostic purposes. To make full use of this capacity we need high-performance automatic sleep scoring models. To this end, it has been noted that domain mismatch between recording equipment can be considerable, e. g. PSG to wearable EEG, but a previously observed benefit from personalizing models to individual subjects further indicates a personal domain in sleep EEG. In this work, we have investigated the extent of such a personal domain in wearable EEG, and review supervised and unsupervised approaches to personalization as found in the literature. We investigated the personalization effect of the unsupervised Adversarial Domain Adaptation and implemented an unsupervised method based on statistics alignment. No beneficial personalization effect was observed using these unsupervised methods. We find that supervised personalization leads to a substantial performance improvement on the target subject ranging from 15% Cohen's Kappa for subjects with poor performance ( $\kappa < 0. 70$ ) to roughly 2% on subjects with high performance ( $\kappa > 0. 80$ ). This improvement was present for models trained on both small and large data sets, indicating that even high-performance models benefit from supervised personalization. We found that this personalization can be beneficially regularized using Kullback-Leibler regularization, leading to lower variance with negligible cost to improvement. Based on the experiments, we recommend model personalization using Kullback-Leibler regularization.

JBHI Journal 2024 Journal Article

Position Paper From the Digital Twins in Healthcare to the Virtual Human Twin: A Moon-Shot Project for Digital Health Research

Marco Viceconti
Maarten De Vos
Sabato Mellone
Liesbet Geris

The idea of a systematic digital representation of the entire known human pathophysiology, which we could call the Virtual Human Twin, has been around for decades. To date, most research groups focused instead on developing highly specialised, highly focused patient-specific models able to predict specific quantities of clinical relevance. While it has facilitated harvesting the low-hanging fruits, this narrow focus is, in the long run, leaving some significant challenges that slow the adoption of digital twins in healthcare. This position paper lays the conceptual foundations for developing the Virtual Human Twin (VHT). The VHT is intended as a distributed and collaborative infrastructure, a collection of technologies and resources (data, models) that enable it, and a collection of Standard Operating Procedures (SOP) that regulate its use. The VHT infrastructure aims to facilitate academic researchers, public organisations, and the biomedical industry in developing and validating new digital twins in healthcare solutions with the possibility of integrating multiple resources if required by the specific context of use. Healthcare professionals and patients can also use the VHT infrastructure for clinical decision support or personalised health forecasting. As the European Commission launched the EDITH coordination and support action to develop a roadmap for the development of the Virtual Human Twin, this position paper is intended as a starting point for the consensus process and a call to arms for all stakeholders.

JBHI Journal 2023 Journal Article

L-SeqSleepNet: Whole-cycle Long Sequence Modeling for Automatic Sleep Staging

Huy Phan
Kristian P. Lorenzen
Elisabeth Heremans
Oliver Y. Chén
Minh C. Tran
Philipp Koch
Alfred Mertins
Mathias Baumert

Human sleep is cyclical with a period of approximately 90 minutes, implying long temporal dependency in the sleep data. Yet, exploring this long-term dependency when developing sleep staging models has remained untouched. In this work, we show that while encoding the logic of a whole sleep cycle is crucial to improve sleep staging performance, the sequential modelling approach in existing state-of-the-art deep learning models are inefficient for that purpose. We thus introduce a method for efficient long sequence modelling and propose a new deep learning model, L-SeqSleepNet, which takes into account whole-cycle sleep information for sleep staging. Evaluating L-SeqSleepNet on four distinct databases of various sizes, we demonstrate state-of-the-art performance obtained by the model over three different EEG setups, including scalp EEG in conventional Polysomnography (PSG), in-ear EEG, and around-the-ear EEG (cEEGrid), even with a single EEG channel input. Our analyses also show that L-SeqSleepNet is able to alleviate the predominance of N2 sleep (the major class in terms of classification) to bring down errors in other sleep stages. Moreover the network becomes much more robust, meaning that for all subjects where the baseline method had exceptionally poor performance, their performance are improved significantly. Finally, the computation time only grows at a sub-linear rate when the sequence length increases.

JBHI Journal 2023 Journal Article

Personalized Longitudinal Assessment of Multiple Sclerosis Using Smartphones

Oliver Y. Chén
Florian Lipsmeier
Huy Phan
Frank Dondelinger
Andrew Creagh
Christian Gossens
Michael Lindemann
Maarten De Vos

Personalized longitudinal disease assessment is central to quickly diagnosing, appropriately managing, and optimally adapting the therapeutic strategy of multiple sclerosis (MS). It is also important for identifying idiosyncratic subject-specific disease profiles. Here, we design a novel longitudinal model to map individual disease trajectories in an automated way using smartphone sensor data that may contain missing values. First, we collect digital measurements related to gait and balance, and upper extremity functions using sensor-based assessments administered on a smartphone. Next, we treat missing data via imputation. We then discover potential markers of MS by employing a generalized estimation equation. Subsequently, parameters learned from multiple training datasets are ensembled to form a simple, unified longitudinal predictive model to forecast MS over time in previously unseen people with MS. To mitigate potential underestimation for individuals with severe disease scores, the final model incorporates additional subject-specific fine-tuning using data from the first day. The results show that the proposed model is promising to achieve personalized longitudinal MS assessment; they also suggest that features related to gait and balance as well as upper extremity function, remotely collected from sensor-based assessments, may be useful digital markers for predicting MS over time.

JBHI Journal 2022 Journal Article

A Deep Shared Multi-Scale Inception Network Enables Accurate Neonatal Quiet Sleep Detection With Limited EEG Channels

Amir H. Ansari
Kirubin Pillay
Anneleen Dereymaeker
Katrien Jansen
Sabine Van Huffel
Gunnar Naulaers
Maarten De Vos

In this paper, we introduce a new variation of the Convolutional Neural Network Inception block, called Sinc, for sleep stage classification in premature newborn babies using electroencephalogram (EEG). In practice, there are many medical centres where only a limited number of EEG channels are recorded. Existing automated algorithms mainly use multi-channel EEGs which perform poorly when fewer numbers of channels are available. The proposed Sinc utilizes multi-scale analysis to place emphasis on the temporal EEG information to be less dependent on the number of EEG channels. In Sinc, we increase the receptive fields through Inception while by additionally sharing the filters that have similar receptive fields, overfitting is controlled and the number of trainable parameters dramatically reduced. To train and test this model, 96 longitudinal EEG recordings from 26 premature infants are used. The Sinc-based model significantly outperforms state-of-the-art neonatal quiet sleep detection algorithms, with mean Kappa 0. 77 ± 0. 01 (with 8-channel EEG) and 0. 75 ± 0. 01 (with a single bipolar channel EEG). This is the first study using Inception-based networks for EEG analysis that utilizes filter sharing to improve efficiency and trainability. The suggested network can successfully detect quiet sleep stages with even a single EEG channel making it more practical especially in the hospital setting where cerebral function monitoring is predominantly used.

JBHI Journal 2022 Journal Article

CMS2-Net: Semi-Supervised Sleep Staging for Diverse Obstructive Sleep Apnea Severity

Chuanhao Zhang
Wenwen Yu
Yamei Li
Hongqiang Sun
Yuan Zhang
Maarten De Vos

Although the development of computer-aided algorithms for sleep staging is integrated into automatic detection of sleep disorders, most supervised deep learning-based models might suffer from insufficient labeled data. While the adoption of semi-supervised learning (SSL) can mitigate the issue, the SSL models are still limited to the lack of discriminative feature extraction for diverse obstructive sleep apnea (OSA) severity. This model deterioration might be exacerbated during the domain adaptation. Such exploration on the alleviation of domain-shift of SSL model between different OSA conditions has attracted more and more attentions from the clinic. In this work, a co-attention meta sleep staging network (CMS2-net) is proposed to simultaneously deal with two issues: the inter-class disparity problem and the intra-class selection problem. Within CMS2-net, a co-attention module and a triple-classifier are designed to explicitly refine the coarse feature representations by identifying the class boundary inconsistency. Moreover, the mutual information with meta contrastive variance is introduced to supervise the gradient stream from a multi-scale view. The performance of the proposed framework is demonstrated on both public and local datasets. Furthermore, our approach achieves the state-of-the-art SSL results on both datasets.

YNIMG Journal 2021 Journal Article

Identifying neural signatures mediating behavioral symptoms and psychosis onset: High-dimensional whole brain functional mediation analysis

Oliver Y. Chén
Hengyi Cao
Huy Phan
Guy Nagels
Jenna M. Reinen
Jiangtao Gou
Tianchen Qian
Junrui Di

Along the pathway from behavioral symptoms to the development of psychotic disorders sits the multivariate mediating brain. The functional organization and structural topography of large-scale multivariate neural mediators among patients with brain disorders, however, are not well understood. Here, we design a high-dimensional brain-wide functional mediation framework to investigate brain regions that intermediate between baseline behavioral symptoms and future conversion to full psychosis among individuals at clinical high risk (CHR). Using resting-state functional magnetic resonance imaging (fMRI) data from 263 CHR subjects, we extract an α brain atlas and a β brain atlas: the former underlines brain areas associated with prodromal symptoms and the latter highlights brain areas associated with disease onset. In parallel, we identify and separate mediators that potentially positively and negatively mediate symptoms and psychosis, respectively, and quantify the effect of each neural mediator on disease development. Taken together, these results paint a brain-wide picture of neural markers that are potentially mediating behavioral symptoms and the development of psychotic disorders; additionally, they underscore a statistical framework that is useful to uncover large-scale intermediating variables in a regulatory biological system.

JBHI Journal 2021 Journal Article

Smartphone- and Smartwatch-Based Remote Characterisation of Ambulation in Multiple Sclerosis During the Two-Minute Walk Test

Andrew P. Creagh
Cedric Simillion
Alan K. Bourke
Alf Scotland
Florian Lipsmeier
Corrado Bernasconi
Johan van Beek
Mike Baker

Leveraging consumer technology such as smartphone and smartwatch devices to objectively assess people with multiple sclerosis (PwMS) remotely could capture unique aspects of disease progression. This study explores the feasibility of assessing PwMS and Healthy Control's (HC) physical function by characterising gaitrelated features, which can be modelled using machine learning (ML) techniques to correctly distinguish subgroups of PwMS from healthy controls. A total of 97 subjects (24 HC subjects, 52 mildly disabled (PwMSmild, EDSS [0-3]) and 21 moderately disabled (PwMSmod, EDSS [3. 5- 5. 5]) contributed data which was recorded from a TwoMinute Walk Test (2MWT) performed out-of-clinic and daily over a 24-week period. Signal-based features relating to movement were extracted from sensors in smartphone and smartwatch devices. A large number of features (n = 156) showed fair-to-strong (R > 0. 3) correlations with clinical outcomes. LASSO feature selection was applied to select and rank subsets of features used for dichotomous classification between subject groups, which were compared using Logistic Regression (LR), Support Vector Machines (SVM) and Random Forest (RF) models. Classifications of subject types were compared using data obtained from smartphone, smartwatch and the fusion of features from both devices. Models built on smartphone features alone achieved the highest classification performance, indicating that accurate and remote measurement of the ambulatory characteristics of HC and PwMS can be achieved with only one device. It was observed however that smartphonebased performance was affected by inconsistent placement location (running belt versus pocket). Results show that PwMSmod could be distinguished from HC subjects (Acc. 82. 2 ± 2. 9%, Sen. 80. 1 ± 3. 9%, Spec. 87. 2 ± 4. 2%, F 1 84. 3 ± 3. 8), and PwMSmild (Acc. 82. 3 ± 1. 9%, Sen. 71. 6 ± 4. 2%, Spec. 87. 0 ± 3. 2%, F1 75. 1 ± 2. 2) using an SVM classifier with a Radial Basis Function (RBF). PwMSmild were shown to exhibit HC-like behaviour and were thus less distinguishable from HC (Acc. 66. 4 ± 4. 5%, Sen. 67. 5 ± 5. 7%, Spec. 60. 3 ± 6. 7%, F 1 58. 6 ± 5. 8). Finally, it was observed that subjects in this study demonstrated low intraand high inter-subject variability which was representative of subject-specific gait characteristics.

JBHI Journal 2018 Journal Article

Weighted Performance Metrics for Automatic Neonatal Seizure Detection Using Multiscored EEG Data

Amir Hossein Ansari
Perumpillichira Joseph Cherian
Alexander Caicedo Dorado
Katrien Jansen
Anneleen Dereymaeker
Leen De Wispelaere
Charlotte Dielman
Jan Vervisch

In neonatal intensive care units, there is a need for around the clock monitoring of electroencephalogram (EEG), especially for recognizing seizures. An automated seizure detector with an acceptable performance can partly fill this need. In order to develop a detector, an extensive dataset labeled by experts is needed. However, accurately defining neonatal seizures on EEG is a challenge, especially when seizure discharges do not meet exact definitions of repetitiveness or evolution in amplitude and frequency. When several readers score seizures independently, disagreement can be high. Commonly used metrics such as good detection rate (GDR) and false alarm rate (FAR) derived from data scored by multiple raters have their limitations. Therefore, new metrics are needed to measure the performance with respect to the different labels. In this paper, instead of defining the labels by consensus or majority voting, popular metrics including GDR, FAR, positive predictive value, sensitivity, specificity, and selectivity are modified such that they can take different scores into account. To this end, 353 hours of EEG data containing seizures from 81 neonates were visually scored by a clinical neurophysiologist, and then processed by an automated seizure detector. The scored seizures were mixed with false detections of an automated seizure detector and were relabeled by three independent EEG readers. Then, all labels were used in the proposed performance metrics and the result was compared with the majority voting technique and showed higher accuracy and robustness for the proposed metrics. Results were confirmed using a bootstrapping test.

YNIMG Journal 2015 Journal Article

A prospective fMRI-based technique for localising the epileptogenic zone in presurgical evaluation of epilepsy

Borbála Hunyadi
Simon Tousseyn
Patrick Dupont
Sabine Van Huffel
Maarten De Vos
Wim Van Paesschen

There is growing evidence for the benefits of simultaneous EEG-fMRI as a non-invasive localising tool in the presurgical evaluation of epilepsy. However, many EEG-fMRI studies fail due to the absence of interictal epileptic discharges (IEDs) on EEG. Here we present an algorithm which makes use of fMRI as sole modality to localise the epileptogenic zone (EZ). Recent studies using various model-based or data-driven fMRI analysis techniques showed that it is feasible to find activation maps which are helpful in the detection of the EZ. However, there is lack of evidence that these techniques can be used prospectively, due to (a) their low specificity, (b) selecting multiple activation maps, or (c) a widespread epileptic network indicated by the selected maps. In the current study we present a method based on independent component analysis and a cascade of classifiers that exclusively detects a single map related to interictal epileptic brain activity. In order to establish the sensitivity and specificity of the proposed method, it was evaluated on a group of 18 EEG-negative patients with a single well-defined EZ and 13 healthy controls. The results show that our method provides maps which correctly indicate the EZ in several (N =4) EEG-negative cases but at the same time maintaining a high specificity (92%). We conclude that our fMRI-based approach can be used in a prospective manner, and can extend the applicability of fMRI to EEG-negative cases.

YNIMG Journal 2015 Journal Article

Cross-modal reorganization in cochlear implant users: Auditory cortex contributes to visual face processing

Maren Stropahl
Karsten Plotz
Rüdiger Schönfeld
Thomas Lenarz
Pascale Sandmann
Galit Yovel
Maarten De Vos
Stefan Debener

There is converging evidence that the auditory cortex takes over visual functions during a period of auditory deprivation. A residual pattern of cross-modal take-over may prevent the auditory cortex to adapt to restored sensory input as delivered by a cochlear implant (CI) and limit speech intelligibility with a CI. The aim of the present study was to investigate whether visual face processing in CI users activates auditory cortex and whether this has adaptive or maladaptive consequences. High-density electroencephalogram data were recorded from CI users (n=21) and age-matched normal hearing controls (n=21) performing a face versus house discrimination task. Lip reading and face recognition abilities were measured as well as speech intelligibility. Evaluation of event-related potential (ERP) topographies revealed significant group differences over occipito-temporal scalp regions. Distributed source analysis identified significantly higher activation in the right auditory cortex for CI users compared to NH controls, confirming visual take-over. Lip reading skills were significantly enhanced in the CI group and appeared to be particularly better after a longer duration of deafness, while face recognition was not significantly different between groups. However, auditory cortex activation in CI users was positively related to face recognition abilities. Our results confirm a cross-modal reorganization for ecologically valid visual stimuli in CI users. Furthermore, they suggest that residual takeover, which can persist even after adaptation to a CI is not necessarily maladaptive.

YNIMG Journal 2015 Journal Article

Lateralization patterns of covert but not overt movements change with age: An EEG neurofeedback study

Catharina Zich
Stefan Debener
Maarten De Vos
Stella Frerichs
Stefanie Maurer
Cornelia Kranczioch

The mental practice of movements has been suggested as a promising add-on therapy to facilitate motor recovery after stroke. In the case of mentally practised movements, electroencephalogram (EEG) can be utilized to provide feedback about an otherwise covert act. The main target group for such an intervention are elderly patients, though research so far is largely focused on young populations (<30years). The present study therefore aimed to examine the influence of age on the neural correlates of covert movements (CMs) in a real-time EEG neurofeedback framework. CM-induced event-related desynchronization (ERD) was studied in young (mean age: 23. 6years) and elderly (mean age: 62. 7years) healthy adults. Participants performed covert and overt hand movements. CMs were based on kinesthetic motor imagery (MI) or quasi-movements (QM). Based on previous studies investigating QM in the mu frequency range (8–13Hz) QM were expected to result in more lateralized ERD% patterns and accordingly higher classification accuracies. Independent of CM strategy the elderly were characterized by a significantly reduced lateralization of ERD%, due to stronger ipsilateral ERD%, and in consequence, reduced classification accuracies. QM were generally perceived as more vivid, but no differences were evident between MI and QM in ERD% or classification accuracies. EEG feedback enhanced task-related activity independently of strategy and age. ERD% measures of overt and covert movements were strongly related in young adults, whereas in the elderly ERD% lateralization is dissociated. In summary, we did not find evidence in support of more pronounced ERD% lateralization patterns in QM. Our finding of a less lateralized activation pattern in the elderly is in accordance to previous research and with the idea that compensatory processes help to overcome neurodegenerative changes related to normal ageing. Importantly, it indicates that EEG neurofeedback studies should place more emphasis on the age of the potential end-users.

YNIMG Journal 2015 Journal Article

Real-time EEG feedback during simultaneous EEG–fMRI identifies the cortical signature of motor imagery

Catharina Zich
Stefan Debener
Cornelia Kranczioch
Martin G. Bleichner
Ingmar Gutberlet
Maarten De Vos

Motor imagery (MI) combined with real-time electroencephalogram (EEG) feedback is a popular approach for steering brain–computer interfaces (BCI). MI BCI has been considered promising as add-on therapy to support motor recovery after stroke. Yet whether EEG neurofeedback indeed targets specific sensorimotor activation patterns cannot be unambiguously inferred from EEG alone. We combined MI EEG neurofeedback with concurrent and continuous functional magnetic resonance imaging (fMRI) to characterize the relationship between MI EEG neurofeedback and activation in cortical sensorimotor areas. EEG signals were corrected online from interfering MRI gradient and ballistocardiogram artifacts, enabling the delivery of real-time EEG feedback. Significantly enhanced task-specific brain activity during feedback compared to no feedback blocks was present in EEG and fMRI. Moreover, the contralateral MI related decrease in EEG sensorimotor rhythm amplitude correlated inversely with fMRI activation in the contralateral sensorimotor areas, whereas a lateralized fMRI pattern did not necessarily go along with a lateralized EEG pattern. Together, the findings indicate a complex relationship between MI EEG signals and sensorimotor cortical activity, whereby both are similarly modulated by EEG neurofeedback. This finding supports the potential of MI EEG neurofeedback for motor rehabilitation and helps to better understand individual differences in MI BCI performance.

YNIMG Journal 2014 Journal Article

Bayesian model selection of template forward models for EEG source reconstruction

Gregor Strobbe
Pieter van Mierlo
Maarten De Vos
Bogdan Mijović
Hans Hallez
Sabine Van Huffel
José David López
Stefaan Vandenberghe

Several EEG source reconstruction techniques have been proposed to identify the generating neuronal sources of electrical activity measured on the scalp. The solution of these techniques depends directly on the accuracy of the forward model that is inverted. Recently, a parametric empirical Bayesian (PEB) framework for distributed source reconstruction in EEG/MEG was introduced and implemented in the Statistical Parametric Mapping (SPM) software. The framework allows us to compare different forward modeling approaches, using real data, instead of using more traditional simulated data from an assumed true forward model. In the absence of a subject specific MR image, a 3-layered boundary element method (BEM) template head model is currently used including a scalp, skull and brain compartment. In this study, we introduced volumetric template head models based on the finite difference method (FDM). We constructed a FDM head model equivalent to the BEM model and an extended FDM model including CSF. These models were compared within the context of three different types of source priors related to the type of inversion used in the PEB framework: independent and identically distributed (IID) sources, equivalent to classical minimum norm approaches, coherence (COH) priors similar to methods such as LORETA, and multiple sparse priors (MSP). The resulting models were compared based on ERP data of 20 subjects using Bayesian model selection for group studies. The reconstructed activity was also compared with the findings of previous studies using functional magnetic resonance imaging. We found very strong evidence in favor of the extended FDM head model with CSF and assuming MSP. These results suggest that the use of realistic volumetric forward models can improve PEB EEG source reconstruction.

YNIMG Journal 2014 Journal Article

Multiple sparse volumetric priors for distributed EEG source reconstruction

Gregor Strobbe
Pieter van Mierlo
Maarten De Vos
Bogdan Mijović
Hans Hallez
Sabine Van Huffel
José David López
Stefaan Vandenberghe

We revisit the multiple sparse priors (MSP) algorithm implemented in the statistical parametric mapping software (SPM) for distributed EEG source reconstruction (Friston et al. , 2008). In the present implementation, multiple cortical patches are introduced as source priors based on a dipole source space restricted to a cortical surface mesh. In this note, we present a technique to construct volumetric cortical regions to introduce as source priors by restricting the dipole source space to a segmented gray matter layer and using a region growing approach. This extension allows to reconstruct brain structures besides the cortical surface and facilitates the use of more realistic volumetric head models including more layers, such as cerebrospinal fluid (CSF), compared to the standard 3-layered scalp-skull-brain head models. We illustrated the technique with ERP data and anatomical MR images in 12 subjects. Based on the segmented gray matter for each of the subjects, cortical regions were created and introduced as source priors for MSP-inversion assuming two types of head models. The standard 3-layered scalp–skull–brain head models and extended 4-layered head models including CSF. We compared these models with the current implementation by assessing the free energy corresponding with each of the reconstructions using Bayesian model selection for group studies. Strong evidence was found in favor of the volumetric MSP approach compared to the MSP approach based on cortical patches for both types of head models. Overall, the strongest evidence was found in favor of the volumetric MSP reconstructions based on the extended head models including CSF. These results were verified by comparing the reconstructed activity. The use of volumetric cortical regions as source priors is a useful complement to the present implementation as it allows to introduce more complex head models and volumetric source priors in future studies.

YNIMG Journal 2014 Journal Article

The dynamics of contour integration: A simultaneous EEG–fMRI study

Bogdan Mijović
Maarten De Vos
Katrien Vanderperren
Bart Machilsen
Stefan Sunaert
Sabine Van Huffel
Johan Wagemans

To study the dynamics of contour integration in the human brain, we simultaneously acquired EEG and fMRI data while participants were engaged in a passive viewing task. The stimuli were Gabor arrays with some Gabor elements positioned on the contour of an embedded shape, in three conditions: with local and global structure (perfect contour alignment), with global structure only (orthogonal orientations interrupting the alignment), or without contour. By applying JointICA to the EEG and fMRI responses of the subjects, new insights could be obtained that cannot be derived from unimodal recordings. In particular, only in the global structure condition, an ERP peak around 300ms was identified that involved a loop from LOC to the early visual areas. This component can be interpreted as being related to the verification of the consistency of the different local elements with the globally defined shape, which is necessary when perfect local-to-global alignment is absent. By modifying JointICA, a quantitative comparison of brain regions and the time-course of their interplay were obtained between different conditions. More generally, we provide additional support for the presence of feedback loops from higher areas to lower level sensory regions.

YNIMG Journal 2012 Journal Article

Let's face it, from trial to trial: Comparing procedures for N170 single-trial estimation

Maarten De Vos
Jeremy D. Thorne
Galit Yovel
Stefan Debener

The estimation of event-related single trial EEG activity is notoriously difficult but is of growing interest in various areas of cognitive neuroscience, such as multimodal neuroimaging and EEG-based brain computer interfaces. However, an objective evaluation of different approaches is lacking. The present study therefore compared four frequently-used single-trial data filtering procedures: raw sensor amplitudes, regression-based estimation, bandpass filtering, and independent component analysis (ICA). High-density EEG data were recorded from 20 healthy participants in a face recognition task and were analyzed with a focus on the face-selective N170 single-trial event-related potential. Linear discriminant analysis revealed significantly better single-trial estimation for ICA compared to raw sensor amplitudes, whereas the other two approaches did not improve classification accuracy. Further analyses suggested that ICA enabled extraction of a face-sensitive independent component in each participant, which led to the superior performance in single trial estimation. Additionally, we show that the face-sensitive component does not directly represent activity from a neuronal population exclusively involved in face-processing, but rather the activity of a network involved in general visual processing. We conclude that ICA effectively facilitates the separation of physiological trial-by-trial fluctuations from measurement noise, in particular when the process of interest is reliably reflected in components representing the neural signature of interest.

YNIMG Journal 2012 Journal Article

The “why” and “how” of JointICA: Results from a visual detection task

Bogdan Mijović
Katrien Vanderperren
Nikolay Novitskiy
Bart Vanrumste
Peter Stiers
Bea Van den Bergh
Lieven Lagae
Stefan Sunaert

Since several years, neuroscience research started to focus on multimodal approaches. One such multimodal approach is the combination of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI). However, no standard integration procedure has been established so far. One promising data-driven approach consists of a joint decomposition of event-related potentials (ERPs) and fMRI maps derived from the response to a particular stimulus. Such an algorithm (joint independent component analysis or JointICA) has recently been proposed by Calhoun et al. (2006). This method provides sources with both a fine spatial and temporal resolution, and has shown to provide meaningful results. However, the algorithm's performance has not been fully characterized yet, and no procedure has been proposed to assess the quality of the decomposition. In this paper, we therefore try to answer why and how JointICA works. We show the performance of the algorithm on data obtained in a visual detection task, and compare the performance for EEG recorded simultaneously with fMRI data and for EEG recorded in a separate session (outside the scanner room). We perform several analyses in order to set the necessary conditions that lead to a sound decomposition, and to give additional insights for exploration in future studies. In that respect, we show how the algorithm behaves when different EEG electrodes are used and we test the robustness with respect to the number of subjects in the study. The performance of the algorithm in all the experiments is validated based on results from previous studies.

YNIMG Journal 2010 Journal Article

Removal of BCG artifacts from EEG recordings inside the MR scanner: A comparison of methodological and validation-related aspects

Katrien Vanderperren
Maarten De Vos
Jennifer R. Ramautar
Nikolay Novitskiy
Maarten Mennes
Sara Assecondi
Bart Vanrumste
Peter Stiers

Multimodal approaches are of growing interest in the study of neural processes. To this end much attention has been paid to the integration of electroencephalographic (EEG) and functional magnetic resonance imaging (fMRI) data because of their complementary properties. However, the simultaneous acquisition of both types of data causes serious artifacts in the EEG, with amplitudes that may be much larger than those of EEG signals themselves. The most challenging of these artifacts is the ballistocardiogram (BCG) artifact, caused by pulse-related electrode movements inside the magnetic field. Despite numerous efforts to find a suitable approach to remove this artifact, still a considerable discrepancy exists between current EEG-fMRI studies. This paper attempts to clarify several methodological issues regarding the different approaches with an extensive validation based on event-related potentials (ERPs). More specifically, Optimal Basis Set (OBS) and Independent Component Analysis (ICA) based methods were investigated. Their validation was not only performed with measures known from previous studies on the average ERPs, but most attention was focused on task-related measures, including their use on trial-to-trial information. These more detailed validation criteria enabled us to find a clearer distinction between the most widely used cleaning methods. Both OBS and ICA proved to be able to yield equally good results. However, ICA methods needed more parameter tuning, thereby making OBS more robust and easy to use. Moreover, applying OBS prior to ICA can optimize the data quality even more, but caution is recommended since the effect of the additional ICA step may be strongly subject-dependent.