EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Site Classification of Autism Spectrum Disorder Using Spatially Constrained ICA on Resting-State fMRI Networks

Talha Imtiaz Baig iD, Junlin Jing, Peng Hu, Bochao Niu, Zhenzhen Yang, Bharat B Biswal, Benjamin Klugah-Brown

Brain Sciences · 31.01.2026 · 16 (2) · 181

DOI: 10.3390/brainsci16020181 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Brain Sciences, online erschienen am 31.01.2026. Verfasst von Talha Imtiaz Baig und 6 weiteren Autor:innen. Beteiligte Einrichtung: The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University …. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 89 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China MOST2030 Brain Project, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by differences in social communications and restricted, repetitive patterns of behaviors and interests, affecting approximately 1% of children globally. While functional magnetic resonance imaging (fMRI) has provided insights into altered brain connectivity patterns in ASD, classification based on neuroimaging remains a challenging due to the heterogeneity of the disorder and variability in imaging data across sites. This study employs a network-based approach using large-scale, multi-site rs-fMRI dataset from the Autism Brain Imaging Data Exchange (ABIDE I and II) to classify ASD and healthy controls using machine learning.

Methods

A semi-blind Independent Component Analysis method, specifically the spatial constraint reference ICA, is applied to identify functional brain networks, and the ComBat harmonization technique is used to address site-specific variability across 11 independent datasets, ensuring consistency in feature representation. Support Vector Machines (SVMs) are employed for classification, focusing on three key networks: the Default Mode Network (DMN), Sensorimotor Network (SMN), and Visual Sensory Network (VSN).

Results

The results demonstrate high classification accuracy, with the VSN achieving the highest performance (83.23% accuracy, 87.90% AUC), followed by the DMN (81.43% accuracy, 84.53% AUC) and the SMN (80.52% accuracy, 84.96% AUC), positioned with their recognized roles in social cognition and sensory–motor processing, respectively.

Conclusions

The integration of ICA-based feature extraction with ComBat harmonization significantly improved classification accuracy compared to previous studies. These findings point out the potential of network-based approaches in ASD classification and point out the importance of integrating multi-site neuroimaging data for identifying reproduceable network-level features.

Schlagwörter

Stichwörter der Autor:innen

Autism Spectrum Disorder (ASD)brain connectivityclassificationfeature extractionmachine learningmulti-site neuroimagingnetwork analysisspatial constraint ICAsupport vector machinevariability reduction

Autor:innen und Institutionen

  • The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, No. 2006, Xiyuan Avenue…
  • Department of Radiology, Ludwig-Maximilians-University Munich, Marchioninistr. 15, 81377 Munich, Germany.
  • Department of Biomedical Engineering, New Jersey Institute of Technology, 619 Fenster Hall, Newark, NJ 07102, USA.

ORCID-Profile: Talha Imtiaz Baig

Förderung

  • China MOST2030 Brain Project
  • National Natural Science Foundation of China

Zitieren

APA

Baig, T. I., Jing, J., Hu, P., Niu, B., Yang, Z., Biswal, B. B., & Klugah-Brown, B. (2026). Multi-Site Classification of Autism Spectrum Disorder Using Spatially Constrained ICA on Resting-State fMRI Networks. Brain Sciences, 16(2), 181. https://doi.org/10.3390/brainsci16020181

Vancouver

Baig TI, Jing J, Hu P, Niu B, Yang Z, Biswal BB, et al. Multi-Site Classification of Autism Spectrum Disorder Using Spatially Constrained ICA on Resting-State fMRI Networks. Brain Sciences. 2026;16(2):181. doi:10.3390/brainsci16020181

BibTeX
@article{Baig2026,
  author = {Baig, Talha Imtiaz and Jing, Junlin and Hu, Peng and Niu, Bochao and Yang, Zhenzhen and Biswal, Bharat B and Klugah-Brown, Benjamin},
  title = {Multi-Site Classification of Autism Spectrum Disorder Using Spatially Constrained ICA on Resting-State fMRI Networks},
  journal = {Brain Sciences},
  year = {2026},
  volume = {16},
  number = {2},
  pages = {181},
  doi = {10.3390/brainsci16020181}
}
Kostenlos starten →