EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SAD: semi-supervised automatic detection of BOLD activations in high temporal resolution fMRI data

Tim Schmidt, Zoltán Nagy

Magnetic Resonance Materials in Physics, Biology and Medicine · 2024

DOI: 10.1007/s10334-024-01197-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Materials in Physics, Biology and Medicine, 2024. Verfasst von Tim Schmidt und 1 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory for Social and Neural Systems Research, SNS-Lab, University of Zurich, Rämistrasse 100, CH-8091, Zurich, Switzerland. tim.schmidt@econ.uzh…. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Brain, Brain Mapping, Hemodynamics. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Zurich.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Despite the prevalent use of the general linear model (GLM) in fMRI data analysis, assuming a pre-defined hemodynamic response function (HRF) for all voxels can lead to reduced reliability and may distort the inferences derived from it. To overcome the necessity of presuming a specific model for the hemodynamic response, we introduce a semi-supervised automatic detection (SAD) method. Materials and methods The proposed SAD method employs a Bi-LSTM neural network to classify high temporal resolution fMRI data. Network training utilized an fMRI dataset with 75-ms temporal resolution in an iterative scheme. Classification performance was evaluated on a second fMRI dataset from the same participant, collected on a different day. Comparative analysis with the standard GLM approach was conducted to evaluate the cooperative effectiveness of the SAD method.

Results

The SAD method performed well based on the classification scores: true-positive rate = 0.961, area under the receiver operating curve = 0.998, true-negative rate = 0.99, F1-score = 0.979, False-negative rate = 0.038, false-discovery rate = 0.002, false-positive rate = 0.002 at 75-ms temporal resolution.

Conclusion

SAD can detect hemodynamic responses at 75-ms temporal resolution without relying on a specific shape of an HRF. Future work could expand the use cases to include more participants and different fMRI paradigms.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingBrainBrain MappingHemodynamicsAlgorithmsNeural Networks, ComputerHumansReproducibility of ResultsLinear ModelsImage Processing, Computer-AssistedROC CurveMaleAdultFemale

Stichwörter der Autor:innen

AutocorrelationBOLDLSTMNeural networksfMRI

Autor:innen und Institutionen

  • Laboratory for Social and Neural Systems Research, SNS-Lab, University of Zurich, Rämistrasse 100, CH-8091, Zurich, Switzerland. tim.schmidt@econ.uzh.ch.
  • Institute for Biomedical Engineering, ETH Zurich and University of Zurich, Zurich, Switzerland. tim.schmidt@econ.uzh.ch.
  • Laboratory for Social and Neural Systems Research, SNS-Lab, University of Zurich, Rämistrasse 100, CH-8091, Zurich, Switzerland.

Förderung

  • University of Zurich

Zitieren

APA

Schmidt, T., & Nagy, Z. (2024). SAD: semi-supervised automatic detection of BOLD activations in high temporal resolution fMRI data. Magnetic Resonance Materials in Physics, Biology and Medicine. https://doi.org/10.1007/s10334-024-01197-0

Vancouver

Schmidt T, Nagy Z. SAD: semi-supervised automatic detection of BOLD activations in high temporal resolution fMRI data. Magnetic Resonance Materials in Physics, Biology and Medicine. 2024. doi:10.1007/s10334-024-01197-0

BibTeX
@article{Schmidt2024,
  author = {Schmidt, Tim and Nagy, Zoltán},
  title = {SAD: semi-supervised automatic detection of BOLD activations in high temporal resolution fMRI data},
  journal = {Magnetic Resonance Materials in Physics, Biology and Medicine},
  year = {2024},
  doi = {10.1007/s10334-024-01197-0}
}
Kostenlos starten →