EUVIMEDEUVIMED entdecken
Crossref

Learning discriminative functional connectivity networks for identifying Autism spectrum disorder

Mengxue Pang, Lei Liu, Feng Zhao, Bin Fu, Limei Zhang, Lishan Qiao

Biomedical Signal Processing and Control · 2025-06 · 104 · 107466

DOI: 10.1016/j.bspc.2024.107466 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Signal Processing and Control, 2025-06. Verfasst von Mengxue Pang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Functional connectivity networks (FCNs) have been widely used in the analysis and diagnosis of brain diseases, such as Autism spectrum disorder (ASD), and how to construct high-quality FCNs, generally based on resting-state functional magnetic resonance imaging (rs-fMRI), has become a growing concern in the neuroscience community. Currently, many ways have been developed to build FCNs, such as Pearson’s correlation and sparse representation. Despite their popularity and effectiveness in some scenarios, such FCNs are estimated in an unsupervised way, ignoring the label information of the samples/subjects. Therefore, it is hard to guarantee that these FCNs can lead to an optimal result (e.g., the accuracy of brain disorder classification task). To address this issue, in this paper, we propose a new method to learn FCNs by integrating the classification loss into the FCN learning framework. In particular, the supervised information is encoded by a projection matrix that maps the rs-fMRI from the original space into a new space where we expect to learn more discriminative FCNs. To evaluate our proposed method, we conduct experiments on ABIDE database to identify subjects with ASD from normal controls. Experimental results show that the proposed scheme performs better than the baseline and state-of-the-art methods.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province

Zitieren

APA

Pang, M., Liu, L., Zhao, F., Fu, B., Zhang, L., & Qiao, L. (2025). Learning discriminative functional connectivity networks for identifying Autism spectrum disorder. Biomedical Signal Processing and Control, 104, 107466. https://doi.org/10.1016/j.bspc.2024.107466

Vancouver

Pang M, Liu L, Zhao F, Fu B, Zhang L, Qiao L. Learning discriminative functional connectivity networks for identifying Autism spectrum disorder. Biomedical Signal Processing and Control. 2025;104:107466. doi:10.1016/j.bspc.2024.107466

BibTeX
@article{Pang2025,
  author = {Pang, Mengxue and Liu, Lei and Zhao, Feng and Fu, Bin and Zhang, Limei and Qiao, Lishan},
  title = {Learning discriminative functional connectivity networks for identifying Autism spectrum disorder},
  journal = {Biomedical Signal Processing and Control},
  year = {2025},
  volume = {104},
  pages = {107466},
  doi = {10.1016/j.bspc.2024.107466}
}
Kostenlos starten →