EUVIMEDEUVIMED entdecken
Open Access

Noninvasive virtual biopsy using micro-registered optical coherence tomography (OCT) in human subjects

Yonatan Winetraub iD, Aidan Van Vleck iD, Edwin Yuan iD, Itamar Terem, Jinjing Zhao, Caroline Yu, Warren Chan, Hanh Do iD, Saba Shevidi, Maiya Mao, Jacqueline Yu, Megan Hong und 6 weitere

Science Advances · 12.04.2024 · 10 (15)

DOI: 10.1126/sciadv.adi5794 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 12.04.2024. Verfasst von Yonatan Winetraub und 17 weiteren Autor:innen. Beteiligte Einrichtung: Department of Structural Biology, Stanford University, Stanford, CA 94305, USA. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Neural Networks, Computer. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, NCI NIH HHS, NIGMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Histological hematoxylin and eosin–stained (H&E) tissue sections are used as the gold standard for pathologic detection of cancer, tumor margin detection, and disease diagnosis. Producing H&E sections, however, is invasive and time-consuming. While deep learning has shown promise in virtual staining of unstained tissue slides, true virtual biopsy requires staining of images taken from intact tissue. In this work, we developed a micron-accuracy coregistration method [micro-registered optical coherence tomography (OCT)] that can take a two-dimensional (2D) H&E slide and find the exact corresponding section in a 3D OCT image taken from the original fresh tissue. We trained a conditional generative adversarial network using the paired dataset and showed high-fidelity conversion of noninvasive OCT images to virtually stained H&E slices in both 2D and 3D. Applying these trained neural networks to in vivo OCT images should enable physicians to readily incorporate OCT imaging into their clinical practice, reducing the number of unnecessary biopsy procedures.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, Optical CoherenceNeural Networks, ComputerHumansBiopsyImaging, Three-Dimensional

Autor:innen und Institutionen

  • Department of Structural Biology, Stanford University, Stanford, CA 94305, USA.
  • Molecular Imaging Program at Stanford, Stanford, CA 94305, USA.
  • The Bio-X Program, Stanford, CA 94305, USA.
  • Biophysics Program at Stanford, Stanford, CA 94305, USA.
  • Department of Applied Physics, Stanford University, Stanford, CA 94305, USA.
  • Department of Electrical Engineering, Stanford University, Stanford, CA 94305, USA.

ORCID-Profile: Yonatan Winetraub, Aidan Van Vleck, Edwin Yuan, Hanh Do, Kerri E Rieger, Steven Chu, Sumaira Aasi, Kavita Y Sarin, Adam de la Zerda

Förderung

  • NIH HHS
  • NCI NIH HHS
  • NIGMS NIH HHS

Zitieren

APA

Winetraub, Y., Van Vleck, A., Yuan, E., Terem, I., Zhao, J., Yu, C., Chan, W., Do, H., Shevidi, S., Mao, M., Yu, J., Hong, M., Blankenberg, E., Rieger, K. E., Chu, S., Aasi, S., Sarin, K. Y., & de la Zerda, A. (2024). Noninvasive virtual biopsy using micro-registered optical coherence tomography (OCT) in human subjects. Science Advances, 10(15). https://doi.org/10.1126/sciadv.adi5794

Vancouver

Winetraub Y, Van Vleck A, Yuan E, Terem I, Zhao J, Yu C, et al. Noninvasive virtual biopsy using micro-registered optical coherence tomography (OCT) in human subjects. Science Advances. 2024;10(15). doi:10.1126/sciadv.adi5794

BibTeX
@article{Winetraub2024,
  author = {Winetraub, Yonatan and Van Vleck, Aidan and Yuan, Edwin and Terem, Itamar and Zhao, Jinjing and Yu, Caroline and Chan, Warren and Do, Hanh and Shevidi, Saba and Mao, Maiya and Yu, Jacqueline and Hong, Megan and Blankenberg, Erick and Rieger, Kerri E and Chu, Steven and Aasi, Sumaira and Sarin, Kavita Y and de la Zerda, Adam},
  title = {Noninvasive virtual biopsy using micro-registered optical coherence tomography (OCT) in human subjects},
  journal = {Science Advances},
  year = {2024},
  volume = {10},
  number = {15},
  doi = {10.1126/sciadv.adi5794}
}
Kostenlos starten →