Epileptic Focus Localization via Brain Network Analysis on Riemannian Manifolds

Qi, Yu; Kang, Lin; Wang, Yueming; Ren, Feixiao; Lian, Qi; Wang, Shuang; Jiang, Haojie; Wang, Yiwen; Wu, Zhaohui; Pan, Gang

doi:10.1109/tnsre.2019.2939010

Cited by 9 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But the phase synchronization connectivity matrix is relatively simple, a more advanced and auto‐learning algorithmic model should also be applied. Regarding the multiple‐channel iEEG signals as matrices on a Riemannian manifold, Qi et al 73 successfully localized the SOZ by brain network connectivity analysis with an average area under the curve (AUC) score of 87.5%. Subsequently, Han et al constructed EEG segment as a brain functional network stacking into dynamic epileptic brain functional networks as the time axis for seizure prediction 54 .…”

Section: Computerized Application In Epileptic Eeg Analysis: Dynamica...mentioning

confidence: 99%

Computerized application for epilepsy in China: Does the era of artificial intelligence comes?

Gong

Wang

et al. 2022

Acta Neuro Scandinavica

Self Cite

View full text Add to dashboard Cite

Epilepsy, one of the most common neurological diseases in China, is notorious for its spontaneous, unprovoked and recurrent seizures. The etiology of epilepsy varies among individual patients, including congenital gene mutation, traumatic injury, infections, etc. This heterogeneity partly hampered the accurate diagnosis and choice of appropriate treatments. Encouragingly, great achievements have been achieved in computational science, making it become a key player in medical fields gradually and bringing new hope for rapid and accurate diagnosis as well as targeted therapies in epilepsy. Here, we historically review the advances of computerized applications in epilepsy—especially those tremendous findings achieved in China—for different purposes including seizure prediction, localization of epileptogenic zone, post‐surgical prognosis, etc. Special attentions are paid to the great progress based on artificial intelligence (AI), which is more “sensitive”, “smart” and “in‐depth” than human capacities. At last, we give a comprehensive discussion about the disadvantages and limitations of current computerized applications for epilepsy and propose some future directions as further stepping stones to embrace “the era of AI” in epilepsy.

show abstract

Section: Computerized Application In Epileptic Eeg Analysis: Dynamica...mentioning

confidence: 99%

Computerized application for epilepsy in China: Does the era of artificial intelligence comes?

Gong

Wang

et al. 2022

Acta Neuro Scandinavica

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, the aforementioned Euclidean machine learning methods for emotion recognition are not directly suitable for handling EEG network connectivity matrices. Considering the Riemannian properties, prior studies have proposed knearest neighbor (kNN) methods [32] for classifying motor imagery (MI) [33], steady-state visually evoked potentials (SSVEP) [34], and epileptic states [35] from EEG covariance or coherence matrices on Riemannian manifolds. However, using EEG network connectivity matrices to recognize emotional states on Riemannian manifolds has not been achieved so far (see section II for detailed explanation).…”

Section: Introductionmentioning

confidence: 99%

“…Third, existing R-kNN methods have exclusively focused on real-valued EEG covariance and coherence matrices [31]- [35], which has limited ability to capture phase information in EEG functional networks. However, phase also contains critical information in EEG signals [38], [39].…”

Section: Introductionmentioning

confidence: 99%

Emotion Recognition from EEG Network Connectivity Using Low-Dimensional Discriminant Analysis on Riemannian Manifolds

Fang,

Wang,

Wang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In iBCI systems, neural decoding algorithm plays an important role. Many algorithms have been proposed to decode motor information from neural signals [5][6][7], including population vector [8], linear estimators [9], deep neural networks [10], recursive Bayesian decoders [11]. Among these approaches, Kalman filter is considered to provide more accurate trajectory estimation by incorporating the process of trajectory evolution as a prior knowledge [12], which has been successfully applied to online cursor and prosthetic control, achieving the state-of-the-art performance [5,13].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces

Qi,

Liu,

Wang

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Brain-computer interfaces (BCIs) have enabled prosthetic device control by decoding motor movements from neural activities. Neural signals recorded from cortex exhibit nonstationary property due to abrupt noises and neuroplastic changes in brain activities during motor control. Current state-of-the-art neural signal decoders such as Kalman filter assume fixed relationship between neural activities and motor movements, thus will fail if this assumption is not satisfied. We propose a dynamic ensemble modeling (DyEnsemble) approach that is capable of adapting to changes in neural signals by employing a proper combination of decoding functions. The DyEnsemble method firstly learns a set of diverse candidate models. Then, it dynamically selects and combines these models online according to Bayesian updating mechanism. Our method can mitigate the effect of noises and cope with different task behaviors by automatic model switching, thus gives more accurate predictions. Experiments with neural data demonstrate that the DyEnsemble method outperforms Kalman filters remarkably, and its advantage is more obvious with noisy signals.

show abstract

Epileptic Focus Localization via Brain Network Analysis on Riemannian Manifolds

Cited by 9 publications

References 34 publications

Computerized application for epilepsy in China: Does the era of artificial intelligence comes?

Computerized application for epilepsy in China: Does the era of artificial intelligence comes?

Emotion Recognition from EEG Network Connectivity Using Low-Dimensional Discriminant Analysis on Riemannian Manifolds

Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces

Contact Info

Product

Resources

About