Abstract

Deep neural networks have been used to map multi-modal, multi-photon microscopy measurements of a label-free tissue sample to its corresponding histologically stained brightfield microscope colour image. It is shown that the extra structural and functional contrasts provided by using two source modes, namely two-photon excitation microscopy and fluorescence lifetime imaging, result in a more faithful reconstruction of the target haematoxylin and eosin stained mode. This modal mapping procedure can aid histopathologists, since it provides access to unobserved imaging modalities, and translates the high-dimensional numerical data generated by multi-modal, multi-photon microscopy into traditionally accepted visual forms. Furthermore, by combining the strengths of traditional chemical staining and modern multi-photon microscopy techniques, modal mapping enables label-free, non-invasive studies of in vivo tissue samples or intravital microscopic imaging inside living animals. The results show that modal co-registration and the inclusion of spatial variations increase the visual accuracy of the mapped results.

Original languageEnglish (US)
Article number355205
Pages (from-to)1339-1350
Number of pages12
JournalBiomedical Optics Express
Volume10
Issue number3
DOIs
StatePublished - Mar 1 2019

Fingerprint

staining
Photons
Microscopy
Staining and Labeling
microscopy
photons
Optical Imaging
Hematoxylin
Eosine Yellowish-(YS)
animals
Color
microscopes
inclusions
color
life (durability)
fluorescence
excitation

ASJC Scopus subject areas

  • Biotechnology
  • Atomic and Molecular Physics, and Optics

Cite this

Digital staining through the application of deep neural networks to multi-modal multi-photon microscopy. / Borhani, Navid; Bower, Andrew J.; Boppart, Stephen Allen; Psaltis, Demetri.

In: Biomedical Optics Express, Vol. 10, No. 3, 355205, 01.03.2019, p. 1339-1350.

Research output: Contribution to journalArticle

@article{0236c2c00b994334b9a6e63e89f9d567,
title = "Digital staining through the application of deep neural networks to multi-modal multi-photon microscopy",
abstract = "Deep neural networks have been used to map multi-modal, multi-photon microscopy measurements of a label-free tissue sample to its corresponding histologically stained brightfield microscope colour image. It is shown that the extra structural and functional contrasts provided by using two source modes, namely two-photon excitation microscopy and fluorescence lifetime imaging, result in a more faithful reconstruction of the target haematoxylin and eosin stained mode. This modal mapping procedure can aid histopathologists, since it provides access to unobserved imaging modalities, and translates the high-dimensional numerical data generated by multi-modal, multi-photon microscopy into traditionally accepted visual forms. Furthermore, by combining the strengths of traditional chemical staining and modern multi-photon microscopy techniques, modal mapping enables label-free, non-invasive studies of in vivo tissue samples or intravital microscopic imaging inside living animals. The results show that modal co-registration and the inclusion of spatial variations increase the visual accuracy of the mapped results.",
author = "Navid Borhani and Bower, {Andrew J.} and Boppart, {Stephen Allen} and Demetri Psaltis",
year = "2019",
month = "3",
day = "1",
doi = "10.1364/BOE.10.001339",
language = "English (US)",
volume = "10",
pages = "1339--1350",
journal = "Biomedical Optics Express",
issn = "2156-7085",
publisher = "The Optical Society",
number = "3",

}

TY - JOUR

T1 - Digital staining through the application of deep neural networks to multi-modal multi-photon microscopy

AU - Borhani, Navid

AU - Bower, Andrew J.

AU - Boppart, Stephen Allen

AU - Psaltis, Demetri

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Deep neural networks have been used to map multi-modal, multi-photon microscopy measurements of a label-free tissue sample to its corresponding histologically stained brightfield microscope colour image. It is shown that the extra structural and functional contrasts provided by using two source modes, namely two-photon excitation microscopy and fluorescence lifetime imaging, result in a more faithful reconstruction of the target haematoxylin and eosin stained mode. This modal mapping procedure can aid histopathologists, since it provides access to unobserved imaging modalities, and translates the high-dimensional numerical data generated by multi-modal, multi-photon microscopy into traditionally accepted visual forms. Furthermore, by combining the strengths of traditional chemical staining and modern multi-photon microscopy techniques, modal mapping enables label-free, non-invasive studies of in vivo tissue samples or intravital microscopic imaging inside living animals. The results show that modal co-registration and the inclusion of spatial variations increase the visual accuracy of the mapped results.

AB - Deep neural networks have been used to map multi-modal, multi-photon microscopy measurements of a label-free tissue sample to its corresponding histologically stained brightfield microscope colour image. It is shown that the extra structural and functional contrasts provided by using two source modes, namely two-photon excitation microscopy and fluorescence lifetime imaging, result in a more faithful reconstruction of the target haematoxylin and eosin stained mode. This modal mapping procedure can aid histopathologists, since it provides access to unobserved imaging modalities, and translates the high-dimensional numerical data generated by multi-modal, multi-photon microscopy into traditionally accepted visual forms. Furthermore, by combining the strengths of traditional chemical staining and modern multi-photon microscopy techniques, modal mapping enables label-free, non-invasive studies of in vivo tissue samples or intravital microscopic imaging inside living animals. The results show that modal co-registration and the inclusion of spatial variations increase the visual accuracy of the mapped results.

UR - http://www.scopus.com/inward/record.url?scp=85063935319&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063935319&partnerID=8YFLogxK

U2 - 10.1364/BOE.10.001339

DO - 10.1364/BOE.10.001339

M3 - Article

AN - SCOPUS:85063935319

VL - 10

SP - 1339

EP - 1350

JO - Biomedical Optics Express

JF - Biomedical Optics Express

SN - 2156-7085

IS - 3

M1 - 355205

ER -