EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Benchmarking Synolitic Graphs for Autism Classification from Multisite Resting-State fMRI

Alexey Zaikin iD, Daniil Vlasenko iD, Denis Zakharov iD, Janna G Oganezova iD, Mikhail I Krivonosov iD, Mikhail Ivanchenko, Oleg Blyuss iD

Diagnostics · 27.08.2026 · 16 (17) · 2746

DOI: 10.3390/diagnostics16172746 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 27.08.2026. Verfasst von Alexey Zaikin und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics and Women's Cancer, University College London, London WC1E 6BT, UK. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Russian Federation Ministry for Science and Higher Education, Barts Charity.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Synolitic graphs (SGs) were developed for task-based fMRI, where edge weights encode the discriminative power of pairwise regional features; whether similar information can be recovered from resting-state data was untested. We benchmarked SGs for autism spectrum disorder (ASD) classification using the multisite ABIDE-I dataset (871 subjects: 403 subjects with ASD, 468 typical controls; 17 sites; CC200 atlas).

Methods

Using 5-fold cross-validation with 10 repeats and balanced accuracy as the primary metric, we compared SGs with eight baselines including correlation matrices, tangent space connectivity, elastic net logistic regression, SVM, and XGBoost.

Results

The vectorised correlation matrix achieved 67.9% balanced accuracy (AUC = 0.743), the combined model 68.0% (AUC = 0.744), and SGs 57.0% (AUC = 0.598). SGs performed above chance (permutation p = 0.001), but their performance was not significantly different from that of direct logistic regression (Nadeau–Bengio p = 0.82). After covariate residualisation, correlation-based methods retained 66.9–67.1% balanced accuracy, while SGs achieved 55.6%. Leave-one-site-out validation yielded 66.0–66.2% for correlation-based models and 55.0% for SGs, with similar declines of approximately 2 percentage points from standard cross-validation. SG-derived ROI rankings were unstable, and ADOS severity prediction among 193 ASD participants was underpowered and inconclusive.

Conclusions

Conventional connectivity representations substantially outperformed SGs for resting-state ASD classification, contrasting with previously reported task-fMRI advantages. No evaluated method achieved performance suitable for stand-alone clinical screening or diagnosis; this study should therefore be interpreted as a methodological benchmark rather than a validation of a clinically deployable tool.

Schlagwörter

Stichwörter der Autor:innen

ABIDEautism spectrum disorderbenchmark studyfunctional connectivitymultisite classificationresting-state fMRIsynolitic graphs

Autor:innen und Institutionen

  • Department of Mathematics and Women's Cancer, University College London, London WC1E 6BT, UK.
  • Institute of Biogerontology, Lobachevsky State University, Nizhny Novgorod 603022, Russia.
  • Institute for Cognitive Neuroscience, University Higher School of Economics, Moscow 101000, Russia.
  • Academician A.P. Nesterov Department of Ophthalmology of the Institute of Clinical Medicine, Pirogov Russian National Research Medical University, Moscow 117437, Russia.
  • Centre for Cancer Screening, Prevention and Early Diagnosis, Wolfson Institute of Population Health, Queen Mary University of London, London EC1M 6BQ, UK.
  • Department of Paediatrics and Paediatric Infectious Diseases, Institute of Child's Health, I.M. Sechenov First Moscow State Medical University (Sechenov University), Moscow 119991, Russia.

ORCID-Profile: Alexey Zaikin, Daniil Vlasenko, Denis Zakharov, Janna G Oganezova, Mikhail I Krivonosov, Oleg Blyuss

Förderung

  • Russian Federation Ministry for Science and Higher Education
  • Barts Charity

Zitieren

APA

Zaikin, A., Vlasenko, D., Zakharov, D., Oganezova, J. G., Krivonosov, M. I., Ivanchenko, M., & Blyuss, O. (2026). Benchmarking Synolitic Graphs for Autism Classification from Multisite Resting-State fMRI. Diagnostics, 16(17), 2746. https://doi.org/10.3390/diagnostics16172746

Vancouver

Zaikin A, Vlasenko D, Zakharov D, Oganezova JG, Krivonosov MI, Ivanchenko M, et al. Benchmarking Synolitic Graphs for Autism Classification from Multisite Resting-State fMRI. Diagnostics. 2026;16(17):2746. doi:10.3390/diagnostics16172746

BibTeX
@article{Zaikin2026,
  author = {Zaikin, Alexey and Vlasenko, Daniil and Zakharov, Denis and Oganezova, Janna G and Krivonosov, Mikhail I and Ivanchenko, Mikhail and Blyuss, Oleg},
  title = {Benchmarking Synolitic Graphs for Autism Classification from Multisite Resting-State fMRI},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {17},
  pages = {2746},
  doi = {10.3390/diagnostics16172746}
}
Kostenlos starten →