EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Contrastive and Transfer Learning for Aligned Multimodal Neuroimaging Classification of Autism Spectrum Disorder

Raja Vavekanand iD, Ganesh Kumar iD, Muhammad Moazzam Jawaid iD, Shafiya Qadeer Memon, Teerath Kumar iD

Journal of Imaging · 20.07.2026 · 12 (7) · 328

DOI: 10.3390/jimaging12070328 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 20.07.2026. Verfasst von Raja Vavekanand und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Technology, Benazir Bhutto Shaheed University Lyari, Karachi 75660, Sindh, Pakistan. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Autism Spectrum Disorder (ASD) assessment remains challenging because behavioural instruments are partly observer-dependent and neuroimaging data are heterogeneous. This paper presents FAA (Fuse After Aligned), which is a multimodal classification framework that combines transfer learning for structural MRI (sMRI) representation learning with a contrastive objective for the pre-fusion alignment of sMRI and resting-state functional MRI-derived functional connectivity (FC) features. Evaluation was restricted to the single-site ABIDE-I New York University subset comprising 75 participants with ASD and 98 typically developing controls. Under the reported five-fold internal cross-validation protocol, FAA achieved a mean accuracy of 92.6% compared with 87.4% for naive fusion and 90.9% for the sMRI-only baseline. Ablation analyses indicate that adding the contrastive objective is associated with improved classification performance and that ResNet-18 outperforms the evaluated ViT-16 configurations in this small-sample setting. These findings support the methodological value of pre-fusion feature alignment within the evaluated cohort. The framework offers a robust, computationally efficient, and clinically viable approach for objective ASD diagnosis with strong potential for generalisation to multi-site neuroimaging applications.

Schlagwörter

Stichwörter der Autor:innen

Autism Spectrum Disordercontrastive learningmultimodal classificationneuroimagingtransfer learning

Autor:innen und Institutionen

  • Department of Information Technology, Benazir Bhutto Shaheed University Lyari, Karachi 75660, Sindh, Pakistan.
  • Department of Computing, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Malaysia.
  • School of Computer Science and Informatics, De Montfort University, Leicester LE1 9BH, UK.
  • Department of Software Engineering, Mehran University of Engineering and Technology, Jamshoro 76062, Sindh, Pakistan.
  • School of Computing, Atlantic Technological University, F94 DV52 Letterkenny, Ireland.

ORCID-Profile: Raja Vavekanand, Ganesh Kumar, Muhammad Moazzam Jawaid, Teerath Kumar

Zitieren

APA

Vavekanand, R., Kumar, G., Jawaid, M. M., Memon, S. Q., & Kumar, T. (2026). Contrastive and Transfer Learning for Aligned Multimodal Neuroimaging Classification of Autism Spectrum Disorder. Journal of Imaging, 12(7), 328. https://doi.org/10.3390/jimaging12070328

Vancouver

Vavekanand R, Kumar G, Jawaid MM, Memon SQ, Kumar T. Contrastive and Transfer Learning for Aligned Multimodal Neuroimaging Classification of Autism Spectrum Disorder. Journal of Imaging. 2026;12(7):328. doi:10.3390/jimaging12070328

BibTeX
@article{Vavekanand2026,
  author = {Vavekanand, Raja and Kumar, Ganesh and Jawaid, Muhammad Moazzam and Memon, Shafiya Qadeer and Kumar, Teerath},
  title = {Contrastive and Transfer Learning for Aligned Multimodal Neuroimaging Classification of Autism Spectrum Disorder},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {7},
  pages = {328},
  doi = {10.3390/jimaging12070328}
}
Kostenlos starten →