EUVIMEDEUVIMED entdecken
Crossref

A Parameter-free unsupervised framework for fMRI data analysis using batch learning growing neural gas and spatial-temporal false positive control

Tania Hossein Khani, Amir Hossein Tajarrod, Mousa Shamsi, Asghar Zarei

Computer Methods and Programs in Biomedicine · 2026-07 · 281 · 109338

DOI: 10.1016/j.cmpb.2026.109338 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2026-07. Verfasst von Tania Hossein Khani und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Biomedical Engineering, Sahand University of Technology, Tabriz, Iran. Electronic address: tania.thk@gmail.com. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Unsupervised Machine Learning. Die Arbeit nennt 43 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND OBJECTIVE: Clustering methods are essential for analyzing functional magnetic resonance imaging (fMRI) time-series data to identify active brain regions and elucidate functional neural patterns. Despite recent advancements in enhancing the stability and automation of cluster number selection, many methods still rely on user-defined parameters, which complicates their application. METHODS: To deal with these issues, this study introduces a novel parameter-free hierarchical topological structure learning clustering algorithm, Batch Learning Growing Neural Gas (BL-GNG), which builds on the Growing Neural Gas (GNG) model to improve convergence speed and eliminate the need for manual parameter tuning. Then, a two-stage false positive rate control mechanism, based on randomization inference and three-dimensional neighborhood criteria, further enhances the algorithm's robustness is proffered. RESULTS: The performance of BL-GNG was evaluated on real fMRI data targeting auditory cortex activity, using the General Linear Model in SPM with a Family-Wise Error-corrected threshold of p < 0.05 as the ground truth. Compared to K-means, Fuzzy C-means (FCM), Neural Gas (NG), and GNG. BL-GNG achieved a Jaccard Coefficient of 0.99 and an Area Under the ROC Curve of 0.97, demonstrating superior exactitude and stability across 50 iterative runs. With an average execution time of 26 s, the algorithm also offers significant computational efficiency. CONCLUSIONS: These results highlight BL-GNG's potential as a powerful tool for fMRI analysis, with applications in diagnosing brain disorders, investigating neural subnetworks, and advancing cognitive neuroscience research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingUnsupervised Machine LearningHumansAlgorithmsCluster AnalysisClustering AlgorithmsFuzzy LogicFalse Positive ReactionsBrainAuditory CortexROC Curve

Stichwörter der Autor:innen

Batch learning growing neural gasClustering techniqueFalse positive controllingfMRI time series analysis

Autor:innen und Institutionen

  • Faculty of Biomedical Engineering, Sahand University of Technology, Tabriz, Iran. Electronic address: tania.thk@gmail.com.
  • Faculty of Biomedical Engineering, Sahand University of Technology, Tabriz, Iran.
  • Faculty of Biomedical Engineering, Sahand University of Technology, Tabriz, Iran. Electronic address: shamsi@sut.ac.ir.
  • Faculty of Biomedical Engineering, Sahand University of Technology, Tabriz, Iran. Electronic address: a.zarei@sut.ac.ir.

Zitieren

APA

Khani, T. H., Tajarrod, A. H., Shamsi, M., & Zarei, A. (2026). A Parameter-free unsupervised framework for fMRI data analysis using batch learning growing neural gas and spatial-temporal false positive control. Computer Methods and Programs in Biomedicine, 281, 109338. https://doi.org/10.1016/j.cmpb.2026.109338

Vancouver

Khani TH, Tajarrod AH, Shamsi M, Zarei A. A Parameter-free unsupervised framework for fMRI data analysis using batch learning growing neural gas and spatial-temporal false positive control. Computer Methods and Programs in Biomedicine. 2026;281:109338. doi:10.1016/j.cmpb.2026.109338

BibTeX
@article{Khani2026,
  author = {Khani, Tania Hossein and Tajarrod, Amir Hossein and Shamsi, Mousa and Zarei, Asghar},
  title = {A Parameter-free unsupervised framework for fMRI data analysis using batch learning growing neural gas and spatial-temporal false positive control},
  journal = {Computer Methods and Programs in Biomedicine},
  year = {2026},
  volume = {281},
  pages = {109338},
  doi = {10.1016/j.cmpb.2026.109338}
}
Kostenlos starten →