EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DrSVision: A Machine Learning Tool for Cortical Region-Specific fNIRS Calibration Based on Cadaveric Head MRI

Serhat Ilgaz Yöner iD, Mehmet Emin Aksoy iD, Hayrettin Can Südor iD, Kurtuluş İzzetoğlu iD, Baran Bozkurt, Alp Dinçer iD

Sensors · 2025

DOI: 10.3390/s25206340 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Serhat Ilgaz Yöner und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Equipment Technology, Junior College, Acıbadem Mehmet Ali Aydınlar University, Istanbul 34752, Türkiye. Hauptthemen laut MEDLINE: Machine Learning, Magnetic Resonance Imaging, Head. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Acıbadem University, Acıbadem Mehmet Ali Aydınlar University General Research Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Functional Near-Infrared Spectroscopy is (fNIRS) a non-invasive neuroimaging technique that monitors cerebral hemodynamic responses by measuring near-infrared (NIR) light absorption caused by changes in oxygenated and deoxygenated hemoglobin concentrations. While fNIRS has been widely used in cognitive and clinical neuroscience, a key challenge persists: the lack of practical tools required for calibrating source-detector separation (SDS) to maximize sensitivity at depth (SAD) for monitoring specific cortical regions of interest to neuroscience and neuroimaging studies. This study presents DrSVision version 1.0, a standalone software developed to address this limitation. Monte Carlo (MC) simulations were performed using segmented magnetic resonance imaging (MRI) data from eight cadaveric heads to realistically model light attenuation across anatomical layers. SAD of 10–20 mm with SDS of 19–39 mm was computed. The dataset was used to train a Gaussian Process Regression (GPR)-based machine learning (ML) model that recommends optimal SDS for achieving maximal sensitivity at targeted depths. The software operates independently of any third-party platforms and provides users with region-specific calibration outputs tailored for experimental goals, supporting more precise application of fNIRS. Future developments aim to incorporate subject-specific calibration using anatomical data and broaden support for diverse and personalized experimental setups. DrSVision represents a step forward in fNIRS experimentation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningMagnetic Resonance ImagingHeadHumansSpectroscopy, Near-InfraredCalibrationCadaverSoftwareMonte Carlo Method

Stichwörter der Autor:innen

MRIMonte Carlo simulationscalibration toolfNIRSfunctional near-infrared spectroscopygaussian process regressionmachine learningmagnetic resonance imagingsensitivity at depthsource-detector separation

Autor:innen und Institutionen

  • Department of Biomedical Equipment Technology, Junior College, Acıbadem Mehmet Ali Aydınlar University, Istanbul 34752, Türkiye.
  • CASE (Center of Advanced Simulation and Education), Acıbadem Mehmet Ali Aydınlar University, Istanbul 34752, Türkiye.
  • School of Biomedical Engineering, Science and Health Systems, Drexel University, Philadelphia, PA 19104, USA.
  • Department of Neurosurgery, School of Medicine, Acıbadem Mehmet Ali Aydınlar University, Istanbul 34752, Türkiye.
  • Neuroanatomy Laboratory, School of Medicine, Acıbadem Mehmet Ali Aydınlar University, Istanbul 34752, Türkiye.
  • Center for Neuroradiological Applications and Research, Acıbadem Mehmet Ali Aydınlar University, Istanbul 34752, Türkiye.

ORCID-Profile: Serhat Ilgaz Yöner, Mehmet Emin Aksoy, Hayrettin Can Südor, Kurtuluş İzzetoğlu, Alp Dinçer

Förderung

  • Acıbadem University
  • Acıbadem Mehmet Ali Aydınlar University General Research Fund

Zitieren

APA

Yöner, S. I., Aksoy, M. E., Südor, H. C., İzzetoğlu, K., Bozkurt, B., & Dinçer, A. (2025). DrSVision: A Machine Learning Tool for Cortical Region-Specific fNIRS Calibration Based on Cadaveric Head MRI. Sensors. https://doi.org/10.3390/s25206340

Vancouver

Yöner SI, Aksoy ME, Südor HC, İzzetoğlu K, Bozkurt B, Dinçer A. DrSVision: A Machine Learning Tool for Cortical Region-Specific fNIRS Calibration Based on Cadaveric Head MRI. Sensors. 2025. doi:10.3390/s25206340

BibTeX
@article{Yner2025,
  author = {Yöner, Serhat Ilgaz and Aksoy, Mehmet Emin and Südor, Hayrettin Can and İzzetoğlu, Kurtuluş and Bozkurt, Baran and Dinçer, Alp},
  title = {DrSVision: A Machine Learning Tool for Cortical Region-Specific fNIRS Calibration Based on Cadaveric Head MRI},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25206340}
}
Kostenlos starten →