Automatic segmentation of intravital fluorescence microscopy images by K-means clustering of FLIM phasors

Yide Zhang, Takashi Hato, Pierre Dagher, Evan L. Nichols, Cody J. Smith, Kenneth Dunn, Scott S. Howard

Research output: Contribution to journalArticle

Abstract

Fluorescence lifetime imaging microscopy (FLIM) provides additional contrast for fluorophores with overlapping emission spectra. The phasor approach to FLIM greatly reduces the complexity of FLIM analysis and enables a useful image segmentation technique by selecting adjacent phasor points and labeling their corresponding pixels with different colors. This phasor labeling process, however, is empirical and could lead to biased results. In this Letter, we present a novel and unbiased approach to automate the phasor labeling process using an unsupervised machine learning technique, i.e., K-means clustering. In addition, we provide an open-source, user-friendly program that enables users to easily employ the proposed approach. We demonstrate successful image segmentation on 2D and 3D FLIM images of fixed cells and living animals acquired with two different FLIM systems. Finally, we evaluate how different parameters affect the segmentation result and provide a guideline for users to achieve optimal performance.

Original languageEnglish (US)
Pages (from-to)3928-3931
Number of pages4
JournalOptics Letters
Volume44
Issue number16
DOIs
StatePublished - Aug 15 2019

Fingerprint

microscopy
life (durability)
fluorescence
marking
machine learning
animals
emission spectra
pixels
color
cells

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics

Cite this

Automatic segmentation of intravital fluorescence microscopy images by K-means clustering of FLIM phasors. / Zhang, Yide; Hato, Takashi; Dagher, Pierre; Nichols, Evan L.; Smith, Cody J.; Dunn, Kenneth; Howard, Scott S.

In: Optics Letters, Vol. 44, No. 16, 15.08.2019, p. 3928-3931.

Research output: Contribution to journalArticle

Zhang, Yide ; Hato, Takashi ; Dagher, Pierre ; Nichols, Evan L. ; Smith, Cody J. ; Dunn, Kenneth ; Howard, Scott S. / Automatic segmentation of intravital fluorescence microscopy images by K-means clustering of FLIM phasors. In: Optics Letters. 2019 ; Vol. 44, No. 16. pp. 3928-3931.
@article{a5a45b0caad34f88b2c787e161b00f14,
title = "Automatic segmentation of intravital fluorescence microscopy images by K-means clustering of FLIM phasors",
abstract = "Fluorescence lifetime imaging microscopy (FLIM) provides additional contrast for fluorophores with overlapping emission spectra. The phasor approach to FLIM greatly reduces the complexity of FLIM analysis and enables a useful image segmentation technique by selecting adjacent phasor points and labeling their corresponding pixels with different colors. This phasor labeling process, however, is empirical and could lead to biased results. In this Letter, we present a novel and unbiased approach to automate the phasor labeling process using an unsupervised machine learning technique, i.e., K-means clustering. In addition, we provide an open-source, user-friendly program that enables users to easily employ the proposed approach. We demonstrate successful image segmentation on 2D and 3D FLIM images of fixed cells and living animals acquired with two different FLIM systems. Finally, we evaluate how different parameters affect the segmentation result and provide a guideline for users to achieve optimal performance.",
author = "Yide Zhang and Takashi Hato and Pierre Dagher and Nichols, {Evan L.} and Smith, {Cody J.} and Kenneth Dunn and Howard, {Scott S.}",
year = "2019",
month = "8",
day = "15",
doi = "10.1364/OL.44.003928",
language = "English (US)",
volume = "44",
pages = "3928--3931",
journal = "Optics Letters",
issn = "0146-9592",
publisher = "The Optical Society",
number = "16",

}

TY - JOUR

T1 - Automatic segmentation of intravital fluorescence microscopy images by K-means clustering of FLIM phasors

AU - Zhang, Yide

AU - Hato, Takashi

AU - Dagher, Pierre

AU - Nichols, Evan L.

AU - Smith, Cody J.

AU - Dunn, Kenneth

AU - Howard, Scott S.

PY - 2019/8/15

Y1 - 2019/8/15

N2 - Fluorescence lifetime imaging microscopy (FLIM) provides additional contrast for fluorophores with overlapping emission spectra. The phasor approach to FLIM greatly reduces the complexity of FLIM analysis and enables a useful image segmentation technique by selecting adjacent phasor points and labeling their corresponding pixels with different colors. This phasor labeling process, however, is empirical and could lead to biased results. In this Letter, we present a novel and unbiased approach to automate the phasor labeling process using an unsupervised machine learning technique, i.e., K-means clustering. In addition, we provide an open-source, user-friendly program that enables users to easily employ the proposed approach. We demonstrate successful image segmentation on 2D and 3D FLIM images of fixed cells and living animals acquired with two different FLIM systems. Finally, we evaluate how different parameters affect the segmentation result and provide a guideline for users to achieve optimal performance.

AB - Fluorescence lifetime imaging microscopy (FLIM) provides additional contrast for fluorophores with overlapping emission spectra. The phasor approach to FLIM greatly reduces the complexity of FLIM analysis and enables a useful image segmentation technique by selecting adjacent phasor points and labeling their corresponding pixels with different colors. This phasor labeling process, however, is empirical and could lead to biased results. In this Letter, we present a novel and unbiased approach to automate the phasor labeling process using an unsupervised machine learning technique, i.e., K-means clustering. In addition, we provide an open-source, user-friendly program that enables users to easily employ the proposed approach. We demonstrate successful image segmentation on 2D and 3D FLIM images of fixed cells and living animals acquired with two different FLIM systems. Finally, we evaluate how different parameters affect the segmentation result and provide a guideline for users to achieve optimal performance.

UR - http://www.scopus.com/inward/record.url?scp=85070679809&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070679809&partnerID=8YFLogxK

U2 - 10.1364/OL.44.003928

DO - 10.1364/OL.44.003928

M3 - Article

C2 - 31415514

AN - SCOPUS:85070679809

VL - 44

SP - 3928

EP - 3931

JO - Optics Letters

JF - Optics Letters

SN - 0146-9592

IS - 16

ER -