Two-Dimensional Latent Space Manifold of Brain Connectomes Across the Spectrum of Clinical Cognitive Decline

Sábháilte in:
Sonraí bibleagrafaíochta
Foilsithe in:Bioengineering vol. 12, no. 8 (2025), p. 819-839
Príomhchruthaitheoir: Güneş, Bayır
Rannpháirtithe: Yüksel Dal Demet, Harı Emre, Ay Ulaş, Gurvit Hakan, Alkan, Kabakçıoğlu, Acar Burak
Foilsithe / Cruthaithe:
MDPI AG
Ábhair:
Rochtain ar líne:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Clibeanna: Cuir clib leis
Níl clibeanna ann, Bí ar an gcéad duine le clib a chur leis an taifead seo!

MARC

LEADER 00000nab a2200000uu 4500
001 3243983851
003 UK-CbPIL
022 |a 2306-5354 
024 7 |a 10.3390/bioengineering12080819  |2 doi 
035 |a 3243983851 
045 2 |b d20250101  |b d20251231 
100 1 |a Güneş, Bayır  |u VAVlab, Department of Electrical & Electronics Engineering, Boğaziçi University, Istanbul 34342, Türkiye 
245 1 |a Two-Dimensional Latent Space Manifold of Brain Connectomes Across the Spectrum of Clinical Cognitive Decline 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a Alzheimer’s Disease and Dementia (ADD) progresses along a continuum of cognitive decline, typically from Subjective Cognitive Impairment (SCI) to Mild Cognitive Impairment (MCI) and eventually to dementia. While many studies have focused on classifying these clinical stages, fewer have examined whether brain connectomes encode this continuum in a low-dimensional, interpretable form. Motivated by the hypothesis that structural brain connectomes undergo complex yet compact changes across cognitive decline, we propose a Graph Neural Network (GNN)-based framework that embeds these connectomes into a two-dimensional manifold to capture the evolving patterns of structural connectivity associated with cognitive deterioration. Using attention-based graph aggregation and Principal Component Analysis (PCA), we find that MCI subjects consistently occupy an intermediate position between SCI and ADD, and that the observed transitions align with known clinical biomarkers of ADD pathology. This hypothesis-driven analysis is further supported by the model’s robust separation performance, with ROC-AUC scores of 0.93 for ADD vs. SCI and 0.81 for ADD vs. MCI. These findings offer an interpretable and neurologically grounded representation of dementia progression, emphasizing structural connectome alterations as potential markers of cognitive decline. 
653 |a Alzheimer's disease 
653 |a Deep learning 
653 |a Principal components analysis 
653 |a Hypotheses 
653 |a Brain research 
653 |a Graph neural networks 
653 |a Dementia 
653 |a Neural networks 
653 |a Dementia disorders 
653 |a Classification 
653 |a Regions 
653 |a Biomarkers 
653 |a Brain 
653 |a Cognitive ability 
653 |a Neurodegenerative diseases 
653 |a Survival analysis 
653 |a Impairment 
700 1 |a Yüksel Dal Demet  |u Department of Electrical & Electronics Engineering, Fatih Sultan Mehmet Vakıf University, Istanbul 34015, Türkiye; dyukseldal@fsm.edu.tr 
700 1 |a Harı Emre  |u Hulusi Behçet Life Sciences Research Laboratory, Neuroimaging Unit, Istanbul University, Istanbul 34093, Türkiye; emre.hari@istanbul.edu.tr (E.H.); psk.ulasay@gmail.com (U.A.) 
700 1 |a Ay Ulaş  |u Hulusi Behçet Life Sciences Research Laboratory, Neuroimaging Unit, Istanbul University, Istanbul 34093, Türkiye; emre.hari@istanbul.edu.tr (E.H.); psk.ulasay@gmail.com (U.A.) 
700 1 |a Gurvit Hakan  |u Behavioral Neurology and Movement Disorders Unit, Department of Neurology, Faculty of Medicine, Istanbul University, Istanbul 34093, Türkiye; gurvit@istanbul.edu.tr 
700 1 |a Alkan, Kabakçıoğlu  |u Department of Physics, Koç University, Istanbul 34450, Türkiye; akabakcioglu@ku.edu.tr 
700 1 |a Acar Burak  |u VAVlab, Department of Electrical & Electronics Engineering, Boğaziçi University, Istanbul 34342, Türkiye 
773 0 |t Bioengineering  |g vol. 12, no. 8 (2025), p. 819-839 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3243983851/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3243983851/fulltextwithgraphics/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3243983851/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch