Cargando…

A generative adversarial approach to facilitate archival-quality histopathologic diagnoses from frozen tissue sections

In clinical diagnostics and research involving histopathology, formalin fixed paraffin embedded (FFPE) tissue is almost universally favored for its superb image quality. However, tissue processing time (>24 hours) can slow decision-making. In contrast, fresh frozen (FF) processing (<1 hour) ca...

Descripción completa

Detalles Bibliográficos
Autores principales: Falahkheirkhah, Kianoush, Guo, Tao, Hwang, Michael, Tamboli, Pheroze, Wood, Christopher G, Karam, Jose A, Sircar, Kanishka, Bhargava, Rohit
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9050807/
https://www.ncbi.nlm.nih.gov/pubmed/34963688
http://dx.doi.org/10.1038/s41374-021-00718-y
_version_ 1784696448988741632
author Falahkheirkhah, Kianoush
Guo, Tao
Hwang, Michael
Tamboli, Pheroze
Wood, Christopher G
Karam, Jose A
Sircar, Kanishka
Bhargava, Rohit
author_facet Falahkheirkhah, Kianoush
Guo, Tao
Hwang, Michael
Tamboli, Pheroze
Wood, Christopher G
Karam, Jose A
Sircar, Kanishka
Bhargava, Rohit
author_sort Falahkheirkhah, Kianoush
collection PubMed
description In clinical diagnostics and research involving histopathology, formalin fixed paraffin embedded (FFPE) tissue is almost universally favored for its superb image quality. However, tissue processing time (>24 hours) can slow decision-making. In contrast, fresh frozen (FF) processing (<1 hour) can yield rapid information but diagnostic accuracy is suboptimal due to lack of clearing, morphologic deformation and more frequent artifacts. Here, we bridge this gap using artificial intelligence. We synthesize FFPE-like images (“virtual FFPE”) from FF images using a generative adversarial network (GAN) from 98 paired kidney samples derived from 40 patients. Five board-certified pathologists evaluated the results in a blinded test. Image quality of the virtual FFPE data was assessed to be high and showed a close resemblance to real FFPE images. Clinical assessments of disease on the virtual FFPE images showed a higher inter-observer agreement compared to FF images. The nearly instantaneously generated virtual FFPE images can not only reduce time to information but can facilitate more precise diagnosis from routine FF images without extraneous costs and effort.
format Online
Article
Text
id pubmed-9050807
institution National Center for Biotechnology Information
language English
publishDate 2022
record_format MEDLINE/PubMed
spelling pubmed-90508072022-06-28 A generative adversarial approach to facilitate archival-quality histopathologic diagnoses from frozen tissue sections Falahkheirkhah, Kianoush Guo, Tao Hwang, Michael Tamboli, Pheroze Wood, Christopher G Karam, Jose A Sircar, Kanishka Bhargava, Rohit Lab Invest Article In clinical diagnostics and research involving histopathology, formalin fixed paraffin embedded (FFPE) tissue is almost universally favored for its superb image quality. However, tissue processing time (>24 hours) can slow decision-making. In contrast, fresh frozen (FF) processing (<1 hour) can yield rapid information but diagnostic accuracy is suboptimal due to lack of clearing, morphologic deformation and more frequent artifacts. Here, we bridge this gap using artificial intelligence. We synthesize FFPE-like images (“virtual FFPE”) from FF images using a generative adversarial network (GAN) from 98 paired kidney samples derived from 40 patients. Five board-certified pathologists evaluated the results in a blinded test. Image quality of the virtual FFPE data was assessed to be high and showed a close resemblance to real FFPE images. Clinical assessments of disease on the virtual FFPE images showed a higher inter-observer agreement compared to FF images. The nearly instantaneously generated virtual FFPE images can not only reduce time to information but can facilitate more precise diagnosis from routine FF images without extraneous costs and effort. 2022-05 2021-12-28 /pmc/articles/PMC9050807/ /pubmed/34963688 http://dx.doi.org/10.1038/s41374-021-00718-y Text en Users may view, print, copy, and download text and data-mine the content in such documents, for the purposes of academic research, subject always to the full Conditions of use: https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms
spellingShingle Article
Falahkheirkhah, Kianoush
Guo, Tao
Hwang, Michael
Tamboli, Pheroze
Wood, Christopher G
Karam, Jose A
Sircar, Kanishka
Bhargava, Rohit
A generative adversarial approach to facilitate archival-quality histopathologic diagnoses from frozen tissue sections
title A generative adversarial approach to facilitate archival-quality histopathologic diagnoses from frozen tissue sections
title_full A generative adversarial approach to facilitate archival-quality histopathologic diagnoses from frozen tissue sections
title_fullStr A generative adversarial approach to facilitate archival-quality histopathologic diagnoses from frozen tissue sections
title_full_unstemmed A generative adversarial approach to facilitate archival-quality histopathologic diagnoses from frozen tissue sections
title_short A generative adversarial approach to facilitate archival-quality histopathologic diagnoses from frozen tissue sections
title_sort generative adversarial approach to facilitate archival-quality histopathologic diagnoses from frozen tissue sections
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9050807/
https://www.ncbi.nlm.nih.gov/pubmed/34963688
http://dx.doi.org/10.1038/s41374-021-00718-y
work_keys_str_mv AT falahkheirkhahkianoush agenerativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT guotao agenerativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT hwangmichael agenerativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT tambolipheroze agenerativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT woodchristopherg agenerativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT karamjosea agenerativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT sircarkanishka agenerativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT bhargavarohit agenerativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT falahkheirkhahkianoush generativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT guotao generativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT hwangmichael generativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT tambolipheroze generativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT woodchristopherg generativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT karamjosea generativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT sircarkanishka generativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections
AT bhargavarohit generativeadversarialapproachtofacilitatearchivalqualityhistopathologicdiagnosesfromfrozentissuesections