EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient Deep Learning Models for Predicting Individualized Task Activation From Resting‐State Functional Connectivity

Soren J Madsen, Young-Eun Lee iD, Shaun K L Quah, Lucina Q Uddin, Jeanette A Mumford, Deanna M Barch, Damien A Fair, Ian H Gotlib iD, Russell A Poldrack, Amy Kuceyeski, Manish Saggar iD

Human Brain Mapping · 15.06.2026 · 47 (9)

DOI: 10.1002/hbm.70557 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Human Brain Mapping, online erschienen am 18.06.2026. Verfasst von Soren J Madsen und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry, Stanford University, Stanford, California, USA. Hauptthemen laut MEDLINE: Deep Learning, Connectome, Magnetic Resonance Imaging, Nerve Net. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIMH NIH HHS, Stanford Maternal and Child Health Research Institute, National Institute of Mental Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning models have demonstrated the potential to predict task‐evoked brain activation from resting‐state functional magnetic resonance imaging, offering a pathway toward individualized brain mapping without requiring task‐based data. In this study, we systematically evaluate architectural strategies for improving the efficiency and scalability of such models. Using data from the Human Connectome Project, we replicate the BrainSurfCNN framework and introduce two extensions: BrainSERF, which incorporates channel‐wise attention through squeeze‐and‐excitation modules, and BrainSurfGCN, a graph‐based model that leverages cortical mesh topology for efficient message passing. Across multiple evaluation metrics, including spatial correlation, Dice score, Dice AUC, and subject identification accuracy, all models achieve comparable predictive performance. Despite similar accuracy, the proposed models offer distinct advantages. BrainSERF provides modest improvements in capturing individual‐specific features, while BrainSurfGCN achieves substantial reductions in model size and training time, highlighting a favorable trade‐off between performance and computational efficiency. Beyond architectural comparisons, we investigate factors driving variability in prediction accuracy. We find that behavioral task performance, resting‐state data quality, and inter‐subject variability in task activation jointly constrain prediction fidelity. In particular, contrasts with lower signal reliability and higher variability exhibit reduced predictability across all models. Together, these findings demonstrate that incorporating topological and functional structural priors can improve the efficiency of deep learning models without sacrificing accuracy, while also emphasizing that prediction performance is fundamentally limited by the reliability of the underlying neural signals.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningConnectomeMagnetic Resonance ImagingNerve NetBrainCerebral CortexHumansPredictive Learning ModelsAdultMaleFemale

Stichwörter der Autor:innen

deep learningfunctional MRIresting‐statetask contrast

Autor:innen und Institutionen

  • Department of Psychiatry, Stanford University, Stanford, California, USA.
  • Department of Psychiatry, University of California, Los Angeles, California, USA.
  • Department of Psychology, Stanford University, Stanford, California, USA.
  • Department of Psychology, Washington University in St. Louis, St. Louis, Missouri, USA.
  • Department of Pediatrics, University of Minnesota, Minneapolis, Minnesota, USA.
  • Department of Radiology, Weill Cornell Medicine, New York, New York, USA.

ORCID-Profile: Young-Eun Lee, Ian H Gotlib, Manish Saggar

Förderung

  • NIMH NIH HHS
  • Stanford Maternal and Child Health Research Institute
  • National Institute of Mental Health

Zitieren

APA

Madsen, S. J., Lee, Y. E., Quah, S. K. L., Uddin, L. Q., Mumford, J. A., Barch, D. M., Fair, D. A., Gotlib, I. H., Poldrack, R. A., Kuceyeski, A., & Saggar, M. (2026). Efficient Deep Learning Models for Predicting Individualized Task Activation From Resting‐State Functional Connectivity. Human Brain Mapping, 47(9). https://doi.org/10.1002/hbm.70557

Vancouver

Madsen SJ, Lee YE, Quah SKL, Uddin LQ, Mumford JA, Barch DM, et al. Efficient Deep Learning Models for Predicting Individualized Task Activation From Resting‐State Functional Connectivity. Human Brain Mapping. 2026;47(9). doi:10.1002/hbm.70557

BibTeX
@article{Madsen2026,
  author = {Madsen, Soren J and Lee, Young-Eun and Quah, Shaun K L and Uddin, Lucina Q and Mumford, Jeanette A and Barch, Deanna M and Fair, Damien A and Gotlib, Ian H and Poldrack, Russell A and Kuceyeski, Amy and Saggar, Manish},
  title = {Efficient Deep Learning Models for Predicting Individualized Task Activation From Resting‐State Functional Connectivity},
  journal = {Human Brain Mapping},
  year = {2026},
  volume = {47},
  number = {9},
  doi = {10.1002/hbm.70557}
}
Kostenlos starten →