Evaluating virtual staining for high-throughput screening

Samuel Tonks; Chih Hsu; Steve Hood; Ryan Musso; Ceriden Hopely; Minh Doan; Erin Edwards; Alexander Krull; Iain Styles

doi:10.1109/ISBI53787.2023.10230501

Evaluating virtual staining for high-throughput screening

Samuel Tonks
, Chih Hsu
, Steve Hood
, Ryan Musso
, Ceriden Hopely
, Minh Doan
, Erin Edwards
, Alexander Krull
, Iain Styles

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

238 Downloads (Pure)

Abstract

Little is known about the feasibility of virtual staining for industry applications such as high-throughput screening (HTS). We provide a thorough analysis of the usability of image-to-image translation for the virtual staining of label-free bright-field microscopy images of live cells, using a pool of more than 1.6 million images across six lung, six ovarian and six breast cell lines consisting of paired bright-field, cytoplasm, nuclei and DNA-damage stains. To our knowledge this is the first time an analysis of virtual staining has been performed on three levels; pixel-based, biological-feature based, and determining if virtual staining can reproduce drug-effect. Our results reveal that while virtually stained nuclei and cytoplasm images often consistently and faithfully reproduce the information found in fluorescence microscopy, virtually stained images of DNA-damage are usually less accurate.

Original language	English
Title of host publication	2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)
Publisher	IEEE
Number of pages	5
ISBN (Electronic)	9781665473583
ISBN (Print)	9781665473590 (PoD)
DOIs	https://doi.org/10.1109/ISBI53787.2023.10230501
Publication status	Published - 1 Sept 2023
Event	20th IEEE International Symposium on Biomedical Imaging - Cartagena , Colombia Duration: 18 Apr 2023 → 21 Apr 2023

Publication series

Name	ISBI
Publisher	IEEE
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	20th IEEE International Symposium on Biomedical Imaging
Abbreviated title	ISBI 2023
Country/Territory	Colombia
City	Cartagena
Period	18/04/23 → 21/04/23

Bibliographical note

Acknowledgments:
This work was funded by GSK and a studentship from the Engineering and Physical Sciences Research Council (project reference 2457518).

Keywords

High-temperature superconductors
Microscopy
Industry applications
Lung
Fluorescence
Breast
Biology

Access to Document

10.1109/ISBI53787.2023.10230501

TonksS2023Evaluating
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. S. Tonks et al., "Evaluating virtual staining for high-throughput screening," 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), Cartagena, Colombia, 2023, pp. 1-5, doi: 10.1109/ISBI53787.2023.10230501.
Accepted author manuscript, 750 KBLicence: Other (please specify with Rights Statement)

Cite this

@inproceedings{9dbac4f77c3941d39e8dfee721185388,

title = "Evaluating virtual staining for high-throughput screening",

abstract = "Little is known about the feasibility of virtual staining for industry applications such as high-throughput screening (HTS). We provide a thorough analysis of the usability of image-to-image translation for the virtual staining of label-free bright-field microscopy images of live cells, using a pool of more than 1.6 million images across six lung, six ovarian and six breast cell lines consisting of paired bright-field, cytoplasm, nuclei and DNA-damage stains. To our knowledge this is the first time an analysis of virtual staining has been performed on three levels; pixel-based, biological-feature based, and determining if virtual staining can reproduce drug-effect. Our results reveal that while virtually stained nuclei and cytoplasm images often consistently and faithfully reproduce the information found in fluorescence microscopy, virtually stained images of DNA-damage are usually less accurate.",

keywords = "High-temperature superconductors, Microscopy, Industry applications, Lung, Fluorescence, Breast, Biology",

author = "Samuel Tonks and Chih Hsu and Steve Hood and Ryan Musso and Ceriden Hopely and Minh Doan and Erin Edwards and Alexander Krull and Iain Styles",

note = "Acknowledgments: This work was funded by GSK and a studentship from the Engineering and Physical Sciences Research Council (project reference 2457518).; 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023 ; Conference date: 18-04-2023 Through 21-04-2023",

year = "2023",

month = sep,

day = "1",

doi = "10.1109/ISBI53787.2023.10230501",

language = "English",

isbn = "9781665473590 (PoD)",

series = "ISBI",

publisher = "IEEE",

booktitle = "2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)",

}

Tonks, S, Hsu, C, Hood, S, Musso, R, Hopely, C, Doan, M, Edwards, E, Krull, A & Styles, I 2023, Evaluating virtual staining for high-throughput screening. in 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)., 10230501, ISBI, IEEE, 20th IEEE International Symposium on Biomedical Imaging, Cartagena , Colombia, 18/04/23. https://doi.org/10.1109/ISBI53787.2023.10230501

TY - GEN

T1 - Evaluating virtual staining for high-throughput screening

AU - Tonks, Samuel

AU - Hsu, Chih

AU - Hood, Steve

AU - Musso, Ryan

AU - Hopely, Ceriden

AU - Doan, Minh

AU - Edwards, Erin

AU - Krull, Alexander

AU - Styles, Iain

N1 - Acknowledgments: This work was funded by GSK and a studentship from the Engineering and Physical Sciences Research Council (project reference 2457518).

PY - 2023/9/1

Y1 - 2023/9/1

N2 - Little is known about the feasibility of virtual staining for industry applications such as high-throughput screening (HTS). We provide a thorough analysis of the usability of image-to-image translation for the virtual staining of label-free bright-field microscopy images of live cells, using a pool of more than 1.6 million images across six lung, six ovarian and six breast cell lines consisting of paired bright-field, cytoplasm, nuclei and DNA-damage stains. To our knowledge this is the first time an analysis of virtual staining has been performed on three levels; pixel-based, biological-feature based, and determining if virtual staining can reproduce drug-effect. Our results reveal that while virtually stained nuclei and cytoplasm images often consistently and faithfully reproduce the information found in fluorescence microscopy, virtually stained images of DNA-damage are usually less accurate.

AB - Little is known about the feasibility of virtual staining for industry applications such as high-throughput screening (HTS). We provide a thorough analysis of the usability of image-to-image translation for the virtual staining of label-free bright-field microscopy images of live cells, using a pool of more than 1.6 million images across six lung, six ovarian and six breast cell lines consisting of paired bright-field, cytoplasm, nuclei and DNA-damage stains. To our knowledge this is the first time an analysis of virtual staining has been performed on three levels; pixel-based, biological-feature based, and determining if virtual staining can reproduce drug-effect. Our results reveal that while virtually stained nuclei and cytoplasm images often consistently and faithfully reproduce the information found in fluorescence microscopy, virtually stained images of DNA-damage are usually less accurate.

KW - High-temperature superconductors

KW - Microscopy

KW - Industry applications

KW - Lung

KW - Fluorescence

KW - Breast

KW - Biology

U2 - 10.1109/ISBI53787.2023.10230501

DO - 10.1109/ISBI53787.2023.10230501

M3 - Conference contribution

SN - 9781665473590 (PoD)

T3 - ISBI

BT - 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)

PB - IEEE

T2 - 20th IEEE International Symposium on Biomedical Imaging

Y2 - 18 April 2023 through 21 April 2023

ER -

Evaluating virtual staining for high-throughput screening

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this