Your browser doesn't support javascript.
loading
Virtual histological staining of unlabeled autopsy tissue.
Li, Yuzhu; Pillar, Nir; Li, Jingxi; Liu, Tairan; Wu, Di; Sun, Songyu; Ma, Guangdong; de Haan, Kevin; Huang, Luzhe; Zhang, Yijie; Hamidi, Sepehr; Urisman, Anatoly; Keidar Haran, Tal; Wallace, William Dean; Zuckerman, Jonathan E; Ozcan, Aydogan.
Afiliação
  • Li Y; Electrical and Computer Engineering Department, University of California, Los Angeles, CA, 90095, USA.
  • Pillar N; Bioengineering Department, University of California, Los Angeles, CA, 90095, USA.
  • Li J; California NanoSystems Institute (CNSI), University of California, Los Angeles, CA, 90095, USA.
  • Liu T; Electrical and Computer Engineering Department, University of California, Los Angeles, CA, 90095, USA.
  • Wu D; Bioengineering Department, University of California, Los Angeles, CA, 90095, USA.
  • Sun S; California NanoSystems Institute (CNSI), University of California, Los Angeles, CA, 90095, USA.
  • Ma G; Electrical and Computer Engineering Department, University of California, Los Angeles, CA, 90095, USA.
  • de Haan K; Bioengineering Department, University of California, Los Angeles, CA, 90095, USA.
  • Huang L; California NanoSystems Institute (CNSI), University of California, Los Angeles, CA, 90095, USA.
  • Zhang Y; Electrical and Computer Engineering Department, University of California, Los Angeles, CA, 90095, USA.
  • Hamidi S; Bioengineering Department, University of California, Los Angeles, CA, 90095, USA.
  • Urisman A; California NanoSystems Institute (CNSI), University of California, Los Angeles, CA, 90095, USA.
  • Keidar Haran T; Computer Science Department, University of California, Los Angeles, CA, 90095, USA.
  • Wallace WD; Computer Science Department, University of California, Los Angeles, CA, 90095, USA.
  • Zuckerman JE; Electrical and Computer Engineering Department, University of California, Los Angeles, CA, 90095, USA.
  • Ozcan A; School of Physics, Xi'an Jiaotong University, Xi'an, Shaanxi, 710049, China.
Nat Commun ; 15(1): 1684, 2024 Feb 23.
Article em En | MEDLINE | ID: mdl-38396004
ABSTRACT
Traditional histochemical staining of post-mortem samples often confronts inferior staining quality due to autolysis caused by delayed fixation of cadaver tissue, and such chemical staining procedures covering large tissue areas demand substantial labor, cost and time. Here, we demonstrate virtual staining of autopsy tissue using a trained neural network to rapidly transform autofluorescence images of label-free autopsy tissue sections into brightfield equivalent images, matching hematoxylin and eosin (H&E) stained versions of the same samples. The trained model can effectively accentuate nuclear, cytoplasmic and extracellular features in new autopsy tissue samples that experienced severe autolysis, such as COVID-19 samples never seen before, where the traditional histochemical staining fails to provide consistent staining quality. This virtual autopsy staining technique provides a rapid and resource-efficient solution to generate artifact-free H&E stains despite severe autolysis and cell death, also reducing labor, cost and infrastructure requirements associated with the standard histochemical staining.
Assuntos

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Redes Neurais de Computação Idioma: En Ano de publicação: 2024 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Redes Neurais de Computação Idioma: En Ano de publicação: 2024 Tipo de documento: Article