Deep learning-enabled realistic virtual histology with ultraviolet photoacoustic remote sensing microscopy.

Journal: Nature communications
PMID: 37749108

Abstract

The goal of oncologic surgeries is complete tumor resection, yet positive margins are frequently found postoperatively using gold standard H&E-stained histology methods. Frozen section analysis is sometimes performed for rapid intraoperative margin evaluation, albeit with known inaccuracies. Here, we introduce a label-free histological imaging method based on an ultraviolet photoacoustic remote sensing and scattering microscope, combined with unsupervised deep learning using a cycle-consistent generative adversarial network for realistic virtual staining. Unstained tissues are scanned at rates of up to 7 mins/cm, at resolution equivalent to 400x digital histopathology. Quantitative validation suggests strong concordance with conventional histology in benign and malignant prostate and breast tissues. In diagnostic utility studies we demonstrate a mean sensitivity and specificity of 0.96 and 0.91 in breast specimens, and respectively 0.87 and 0.94 in prostate specimens. We also find virtual stain quality is preferred (P = 0.03) compared to frozen section analysis in a blinded survey of pathologists.

Authors

  • Matthew T Martell
    Department of Electrical and Computer Engineering, University of Alberta, 116 Street & 85 Avenue, Edmonton, AB, T6G 2R3, Canada.
  • Nathaniel J M Haven
    Department of Electrical and Computer Engineering, University of Alberta, 116 Street & 85 Avenue, Edmonton, AB, T6G 2R3, Canada.
  • Brendyn D Cikaluk
    Department of Electrical and Computer Engineering, University of Alberta, 116 Street & 85 Avenue, Edmonton, AB, T6G 2R3, Canada.
  • Brendon S Restall
    Department of Electrical and Computer Engineering, University of Alberta, 116 Street & 85 Avenue, Edmonton, AB, T6G 2R3, Canada.
  • Ewan A McAlister
    Department of Electrical and Computer Engineering, University of Alberta, 116 Street & 85 Avenue, Edmonton, AB, T6G 2R3, Canada.
  • Rohan Mittal
    Department of Laboratory Medicine and Pathology, University of Alberta, 11405 87 Avenue NW, Edmonton, AB, T6G 1C9, Canada.
  • Benjamin A Adam
    Department of Laboratory Medicine and Pathology, University of Alberta, 11405 87 Avenue NW, Edmonton, AB, T6G 1C9, Canada.
  • Nadia Giannakopoulos
    Department of Laboratory Medicine and Pathology, University of Alberta, 11405 87 Avenue NW, Edmonton, AB, T6G 1C9, Canada.
  • Lashan Peiris
    Department of Surgery, University of Alberta, 8440 - 112 Street, Edmonton, AB, T6G 2B7, Canada.
  • Sveta Silverman
    Department of Laboratory Medicine and Pathology, University of Alberta, 11405 87 Avenue NW, Edmonton, AB, T6G 1C9, Canada.
  • Jean Deschenes
    Department of Laboratory Medicine and Pathology, University of Alberta, 11405 87 Avenue NW, Edmonton, AB, T6G 1C9, Canada.
  • Xingyu Li
    State Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing 400044, China.
  • Roger J Zemp
    Department of Electrical and Computer Engineering, University of Alberta, 116 Street & 85 Avenue, Edmonton, AB, T6G 2R3, Canada. rzemp@ualberta.ca.

Keywords

External Resources

Popular Topics
Recent Journals