EEG-Based Brain Network Biomarkers in Alzheimer's Disease Progression Brain Network Functional Analysis for Alzheimer's Disease Progression
-
- Einzelkauf Download ausgewählt
-
Sprache:Englisch
Fr. 36.90
inkl. gesetzl. MwSt.Beschreibung
Produktdetails
Format
Kopierschutz
Nein
Family Sharing
Nein
Text-to-Speech
Nein
Erscheinungsdatum
02.12.2025
Verlag
GRINSeitenzahl
(Printausgabe)
Dateigröße
6170 KB
Sprache
Englisch
EAN
9783389168554
Document from the year 2025 in the subject Medicine - Neurology, Psychiatry, Addiction, , language: English, abstract: Dementia, particularly Alzheimer's disease and its prodromal stage, mild cognitive impairment (MCI), is a major global health challenge. Early detection of MCI is crucial because it often precedes irreversible neurodegeneration, yet distinguishing it from later-stage dementia remains difficult due to overlapping symptoms and subtle early changes in brain function.
This book, "Graph Convolution Networks for EEG-Based Brain Network Biomarkers in Alzheimer's Disease Progression", addresses this challenge by proposing analytical frameworks that reveal the underlying pathophysiological mechanisms of dementia-related disorders. Electroencephalography (EEG), with its accessibility and high temporal resolution, offers a practical window into neural activity, but its full potential emerges only when interpreted from a network-centric perspective.
Adopting a complex network approach, this work investigates EEG-derived brain functional networks (BFNs) in dementia. Using the Phase Lag Index (PLI) as the core connectivity metric, it constructs frequency-specific functional networks and applies a data-driven thresholding technique for robust, unbiased topology estimation. Quantitative and statistical network analyses show that graph-theoretic measures such as rich-club organization, transitivity, and assortativity provide effective biomarkers for differentiating MCI, Alzheimer's disease, and vascular dementia.
Building on these insights, the BFNs are then used as structured graph inputs to a Graph Convolution Network (GCN) model. Integrating network neuroscience with deep learning, the proposed GCN framework achieves high classification accuracy (around 95%), highlighting the power of graph-learning methods for dementia staging.
Combining methodological rigor, theoretical depth, and practical evaluation, this book presents a unified framework for EEG-based brain network biomarker discovery. It is intended for researchers, clinicians, and students in computational neuroscience, biomedical signal processing, machine learning, and neurodegenerative disease research, and aims to contribute to earlier detection, better tracking, and deeper understanding of Alzheimer's disease progression.
This book, "Graph Convolution Networks for EEG-Based Brain Network Biomarkers in Alzheimer's Disease Progression", addresses this challenge by proposing analytical frameworks that reveal the underlying pathophysiological mechanisms of dementia-related disorders. Electroencephalography (EEG), with its accessibility and high temporal resolution, offers a practical window into neural activity, but its full potential emerges only when interpreted from a network-centric perspective.
Adopting a complex network approach, this work investigates EEG-derived brain functional networks (BFNs) in dementia. Using the Phase Lag Index (PLI) as the core connectivity metric, it constructs frequency-specific functional networks and applies a data-driven thresholding technique for robust, unbiased topology estimation. Quantitative and statistical network analyses show that graph-theoretic measures such as rich-club organization, transitivity, and assortativity provide effective biomarkers for differentiating MCI, Alzheimer's disease, and vascular dementia.
Building on these insights, the BFNs are then used as structured graph inputs to a Graph Convolution Network (GCN) model. Integrating network neuroscience with deep learning, the proposed GCN framework achieves high classification accuracy (around 95%), highlighting the power of graph-learning methods for dementia staging.
Combining methodological rigor, theoretical depth, and practical evaluation, this book presents a unified framework for EEG-based brain network biomarker discovery. It is intended for researchers, clinicians, and students in computational neuroscience, biomedical signal processing, machine learning, and neurodegenerative disease research, and aims to contribute to earlier detection, better tracking, and deeper understanding of Alzheimer's disease progression.
Kundinnen und Kunden meinen
Verfassen Sie die erste Bewertung zu diesem Artikel
Helfen Sie anderen Kund*innen durch Ihre Meinung