Deep Learning Identifies Cardiomyocyte Nuclei in Murine Tissue with High Precision

Shah R. Ali; Dan Nguyen; Brandon Wang; Steven Jiang; Hesham A. Sadek

doi:10.1101/2020.01.10.900936

Deep Learning Identifies Cardiomyocyte Nuclei in Murine Tissue with High Precision

Shah R. Ali, Dan Nguyen, Brandon Wang, Steven Jiang, Hesham A. Sadek

Research output: Contribution to journal › Article › peer-review

Abstract

Proper identification and annotation of cells in mammalian tissues is of paramount importance to biological research. Various approaches are currently used to identify and label cell types of interest in complex tissues. In this report, we generated an artificial intelligence (AI) deep learning model that uses image segmentation to predict cardiomyocyte nuclei in mouse heart sections without a specific cardiomyocyte nuclear label. This tool can annotate cardiomyocytes highly sensitively and specifically (AUC 0.94) using only cardiomyocyte structural protein immunostaining and a global nuclear stain. We speculate that our method is generalizable to other tissues to annotate specific cell types and organelles in a label-free way.

Original language	English (US)
Journal	Unknown Journal
DOIs	https://doi.org/10.1101/2020.01.10.900936
State	Published - Jan 10 2020

ASJC Scopus subject areas

Biochemistry, Genetics and Molecular Biology(all)
Agricultural and Biological Sciences(all)
Immunology and Microbiology(all)
Neuroscience(all)
Pharmacology, Toxicology and Pharmaceutics(all)

Access to Document

10.1101/2020.01.10.900936

Fingerprint Dive into the research topics of 'Deep Learning Identifies Cardiomyocyte Nuclei in Murine Tissue with High Precision'. Together they form a unique fingerprint.

Cite this

@article{297b727d10b841f99d53bcbe488bbf6c,

title = "Deep Learning Identifies Cardiomyocyte Nuclei in Murine Tissue with High Precision",

abstract = "Proper identification and annotation of cells in mammalian tissues is of paramount importance to biological research. Various approaches are currently used to identify and label cell types of interest in complex tissues. In this report, we generated an artificial intelligence (AI) deep learning model that uses image segmentation to predict cardiomyocyte nuclei in mouse heart sections without a specific cardiomyocyte nuclear label. This tool can annotate cardiomyocytes highly sensitively and specifically (AUC 0.94) using only cardiomyocyte structural protein immunostaining and a global nuclear stain. We speculate that our method is generalizable to other tissues to annotate specific cell types and organelles in a label-free way.",

author = "Ali, {Shah R.} and Dan Nguyen and Brandon Wang and Steven Jiang and Sadek, {Hesham A.}",

note = "Publisher Copyright: The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. All rights reserved. No reuse allowed without permission. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.",

year = "2020",

month = jan,

day = "10",

doi = "10.1101/2020.01.10.900936",

language = "English (US)",

journal = "Seminars in Fetal and Neonatal Medicine",

issn = "1744-165X",

publisher = "W.B. Saunders Ltd",

}

TY - JOUR

T1 - Deep Learning Identifies Cardiomyocyte Nuclei in Murine Tissue with High Precision

AU - Ali, Shah R.

AU - Nguyen, Dan

AU - Wang, Brandon

AU - Jiang, Steven

AU - Sadek, Hesham A.

N1 - Publisher Copyright: The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. All rights reserved. No reuse allowed without permission. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/1/10

Y1 - 2020/1/10

N2 - Proper identification and annotation of cells in mammalian tissues is of paramount importance to biological research. Various approaches are currently used to identify and label cell types of interest in complex tissues. In this report, we generated an artificial intelligence (AI) deep learning model that uses image segmentation to predict cardiomyocyte nuclei in mouse heart sections without a specific cardiomyocyte nuclear label. This tool can annotate cardiomyocytes highly sensitively and specifically (AUC 0.94) using only cardiomyocyte structural protein immunostaining and a global nuclear stain. We speculate that our method is generalizable to other tissues to annotate specific cell types and organelles in a label-free way.

AB - Proper identification and annotation of cells in mammalian tissues is of paramount importance to biological research. Various approaches are currently used to identify and label cell types of interest in complex tissues. In this report, we generated an artificial intelligence (AI) deep learning model that uses image segmentation to predict cardiomyocyte nuclei in mouse heart sections without a specific cardiomyocyte nuclear label. This tool can annotate cardiomyocytes highly sensitively and specifically (AUC 0.94) using only cardiomyocyte structural protein immunostaining and a global nuclear stain. We speculate that our method is generalizable to other tissues to annotate specific cell types and organelles in a label-free way.

UR - http://www.scopus.com/inward/record.url?scp=85095504031&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85095504031&partnerID=8YFLogxK

U2 - 10.1101/2020.01.10.900936

DO - 10.1101/2020.01.10.900936

M3 - Article

AN - SCOPUS:85095504031

JO - Seminars in Fetal and Neonatal Medicine

JF - Seminars in Fetal and Neonatal Medicine

SN - 1744-165X

ER -