Automatic microscopic cell counting by use of unsupervised adversarial domain adaptation and supervised density regression

Shenghua He, Kyaw T. Minn, Lilianna Solnica-krezel, Hua Li, Mark Anastasio

Research output: Contribution to conferencePaper

Abstract

Accurate cell counting in microscopic images is important for medical diagnoses and biological studies. However, manual cell counting is very time-consuming, tedious, and prone to subjective errors. We propose a new density regression-based method for automatic cell counting that reduces the need to manually annotate experimental images. A supervised learning-based density regression model (DRM) is trained with annotated synthetic images (the source domain) and their corresponding ground truth density maps. A domain adaptation model (DAM) is built to map experimental images (the target domain) to the feature space of the source domain. By use of the unsupervised learning-based DAM and supervised learning-based DRM, a cell density map of a given target image can be estimated, from which the number of cells can be counted. Results from experimental immunofluorescent microscopic images of human embryonic stem cells demonstrate the promising performance of the proposed counting method.
Original languageEnglish (US)
Pages2
DOIs
StatePublished - Mar 18 2019
Externally publishedYes
EventDigital Pathology - San Diego, United States
Duration: Feb 16 2019Feb 21 2019

Conference

ConferenceDigital Pathology
Period2/16/192/21/19

Fingerprint

learning
stem
supervised learning
method

Cite this

Automatic microscopic cell counting by use of unsupervised adversarial domain adaptation and supervised density regression. / He, Shenghua; Minn, Kyaw T.; Solnica-krezel, Lilianna; Li, Hua; Anastasio, Mark.

2019. 2 Paper presented at Digital Pathology, .

Research output: Contribution to conferencePaper

He, S, Minn, KT, Solnica-krezel, L, Li, H & Anastasio, M 2019, 'Automatic microscopic cell counting by use of unsupervised adversarial domain adaptation and supervised density regression' Paper presented at Digital Pathology, 2/16/19 - 2/21/19, pp. 2. https://doi.org/10.1117/12.2513058
He, Shenghua ; Minn, Kyaw T. ; Solnica-krezel, Lilianna ; Li, Hua ; Anastasio, Mark. / Automatic microscopic cell counting by use of unsupervised adversarial domain adaptation and supervised density regression. Paper presented at Digital Pathology, .
@conference{37890e2c462444b9a65ab880f752e2a6,
title = "Automatic microscopic cell counting by use of unsupervised adversarial domain adaptation and supervised density regression",
abstract = "Accurate cell counting in microscopic images is important for medical diagnoses and biological studies. However, manual cell counting is very time-consuming, tedious, and prone to subjective errors. We propose a new density regression-based method for automatic cell counting that reduces the need to manually annotate experimental images. A supervised learning-based density regression model (DRM) is trained with annotated synthetic images (the source domain) and their corresponding ground truth density maps. A domain adaptation model (DAM) is built to map experimental images (the target domain) to the feature space of the source domain. By use of the unsupervised learning-based DAM and supervised learning-based DRM, a cell density map of a given target image can be estimated, from which the number of cells can be counted. Results from experimental immunofluorescent microscopic images of human embryonic stem cells demonstrate the promising performance of the proposed counting method.",
author = "Shenghua He and Minn, {Kyaw T.} and Lilianna Solnica-krezel and Hua Li and Mark Anastasio",
year = "2019",
month = "3",
day = "18",
doi = "10.1117/12.2513058",
language = "English (US)",
pages = "2",
note = "Digital Pathology ; Conference date: 16-02-2019 Through 21-02-2019",

}

TY - CONF

T1 - Automatic microscopic cell counting by use of unsupervised adversarial domain adaptation and supervised density regression

AU - He, Shenghua

AU - Minn, Kyaw T.

AU - Solnica-krezel, Lilianna

AU - Li, Hua

AU - Anastasio, Mark

PY - 2019/3/18

Y1 - 2019/3/18

N2 - Accurate cell counting in microscopic images is important for medical diagnoses and biological studies. However, manual cell counting is very time-consuming, tedious, and prone to subjective errors. We propose a new density regression-based method for automatic cell counting that reduces the need to manually annotate experimental images. A supervised learning-based density regression model (DRM) is trained with annotated synthetic images (the source domain) and their corresponding ground truth density maps. A domain adaptation model (DAM) is built to map experimental images (the target domain) to the feature space of the source domain. By use of the unsupervised learning-based DAM and supervised learning-based DRM, a cell density map of a given target image can be estimated, from which the number of cells can be counted. Results from experimental immunofluorescent microscopic images of human embryonic stem cells demonstrate the promising performance of the proposed counting method.

AB - Accurate cell counting in microscopic images is important for medical diagnoses and biological studies. However, manual cell counting is very time-consuming, tedious, and prone to subjective errors. We propose a new density regression-based method for automatic cell counting that reduces the need to manually annotate experimental images. A supervised learning-based density regression model (DRM) is trained with annotated synthetic images (the source domain) and their corresponding ground truth density maps. A domain adaptation model (DAM) is built to map experimental images (the target domain) to the feature space of the source domain. By use of the unsupervised learning-based DAM and supervised learning-based DRM, a cell density map of a given target image can be estimated, from which the number of cells can be counted. Results from experimental immunofluorescent microscopic images of human embryonic stem cells demonstrate the promising performance of the proposed counting method.

U2 - 10.1117/12.2513058

DO - 10.1117/12.2513058

M3 - Paper

SP - 2

ER -