Multispectral snapshot imaging of skin microcirculatory hemoglobin oxygen saturation using artificial neural networks trained on in vivo data.

Journal: Journal of biomedical optics
PMID: 35340134

Abstract

SIGNIFICANCE: Developing algorithms for estimating blood oxygenation from snapshot multispectral imaging (MSI) data is challenging due to the complexity of sensor characteristics and photon transport modeling in tissue. We circumvent this using a method where artificial neural networks (ANNs) are trained on in vivo MSI data with target values from a point-measuring reference method.

Authors

  • Maria Ewerlöf
    Linköping University, Department of Biomedical Engineering, Linköping, Sweden.
  • Tomas Strömberg
    Linköping University, Department of Biomedical Engineering, Linköping, Sweden.
  • Marcus Larsson
    Linköping University, Department of Biomedical Engineering, Linköping, Sweden.
  • E Göran Salerud
    Linköping University, Department of Biomedical Engineering, Linköping, Sweden.

Keywords

External Resources

Popular Topics
Recent Journals