Restoration of metabolic functional metrics from label-free, two-photon human tissue images using multiscale deep-learning-based denoising algorithms.

Journal: Journal of biomedical optics
Published Date:

Abstract

SIGNIFICANCE: Label-free, two-photon excited fluorescence (TPEF) imaging captures morphological and functional metabolic tissue changes and enables enhanced understanding of numerous diseases. However, noise and other artifacts present in these images severely complicate the extraction of biologically useful information.

Authors

  • Nilay Vora
    Tufts University, Department of Biomedical Engineering, Medford, Massachusetts, United States.
  • Christopher M Polleys
    Tufts University, Department of Biomedical Engineering, Medford, Massachusetts, United States.
  • Filippos Sakellariou
    Anatolia College, Thessaloniki, Greece.
  • Georgios Georgalis
    Tufts University, Data Intensive Studies Center, Medford, Massachusetts, United States.
  • Hong-Thao Thieu
    Tufts University School of Medicine, Tufts Medical Center, Department of Obstetrics and Gynecology, Boston, Massachusetts, United States.
  • Elizabeth M Genega
    Tufts University School of Medicine, Tufts Medical Center, Department of Pathology and Laboratory Medicine, Boston, Massachusetts, United States.
  • Narges Jahanseir
    Tufts University School of Medicine, Tufts Medical Center, Department of Pathology and Laboratory Medicine, Boston, Massachusetts, United States.
  • Abani Patra
    Tufts University, Data Intensive Studies Center, Medford, Massachusetts, United States.
  • Eric Miller
    Tufts University, Department of Electrical and Computer Engineering, Medford, Massachusetts, United States.
  • Irene Georgakoudi
    Department of Biomedical Engineering, Tufts University, Medford, MA, 02155, USA. Electronic address: Irene.Georgakoudi@tufts.edu.