Topological inference and correlation of signals with application to electroencephalography in epilepsy

Yin, Jian; Wang, Yuan

doi:10.1016/j.bspc.2022.104396

Cited by 1 publication

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stereotactic EEG (SEEG) is a high-resolution imaging modality that records signal data from multi-contact electrodes implanted directly in brain structures 6 . In epilepsy, the changes in SEEG signals provide insight into how local network variations affect global changes in brain activity 28 , and these signals are widely regarded as the gold standard in pre-surgical evaluation for identifying the critical area for surgical resection in epilepsy patients 29 . SEEG records interactions between electrodes; these interactions can be characterized via signal coupling in various brain regions 14 .…”

Section: Introductionmentioning

confidence: 99%

“…The NIC tool allows users to derive this signal coupling from raw EEG using various correlation metrics, storing this information in a correlation matrix 14 . Persistent homology, a topological data analysis method that tracks the formation (birth) and termination (death) of topological features across a filtration, can be applied to matrices of signal coupling to identify multidimensional interactions and reveal changes in topological structures underpinning the breakdown of normal dynamic brain networks 22,28,30 . In this process, a filtration is applied to a correlation matrix representing the signal coupling in SEEG data, gradually varying the scale or threshold to extract topological features at different levels of connectivity 13,22 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MaTiLDA: An Integrated Machine Learning and Topological Data Analysis Platform for Brain Network Dynamics

Prantzalos

Upadhyaya

Shafiabadi

et al. 2023

Preprint

View full text Add to dashboard Cite

Topological data analysis (TDA) is a powerful approach for investigating complex relationships in brain networks; however, its application requires substantial domain knowledge in programming, mathematics, and data science, especially in the context of data-driven approaches like machine learning (ML). To address this educational barrier, we introduce MaTiLDA, a graphical user interface that enables exploration of common representations of TDA features and their efficacy in various classical machine learning models. This user-friendly tool is the first graphical user interface built to explore TDA representations in machine learning applications. MaTiLDA provides a user-centric method for characterizing complex neural relationships using TDA techniques. To demonstrate the utility of MaTiLDA in characterizing brain network dynamics, we apply this workflow to a cohort of 4 refractory epilepsy patients and evaluate the predictive performance of various TDA feature representations in a series of ML models. The MaTiLDA application can be accessed through https://bmhinformatics.case.edu/nicworkflow/MaTiLDA

show abstract

Section: Introductionmentioning

confidence: 99%