A Rapid and Efficient 2D/3D Nuclear Segmentation Method for Analysis of Early Mouse Embryo and Stem Cell Image Data

Xinghua Lou, Minjung Kang, Panagiotis Xenopoulos, S Munoz-Descalzo, Anna-Katerina Hadjantonakis

Research output: Contribution to conferencePaper

42 Citations (Scopus)
76 Downloads (Pure)

Abstract

Segmentation is a fundamental problem that dominates the success of microscopic image analysis. In almost 25 years of cell detection
software development, there is still no single piece of commercial software that works well in practice when applied to early mouse
embryo or stem cell image data. To address this need, we developed MINS (modular interactive nuclear segmentation) as a MATLAB/
C++-based segmentation tool tailored for counting cells and fluorescent intensity measurements of 2D and 3D image data. Our aim
was to develop a tool that is accurate and efficient yet straightforward and user friendly. The MINS pipeline comprises three major
cascaded modules: detection, segmentation, and cell position classification. An extensive evaluation of MINS on both 2D and 3D images,
and comparison to related tools, reveals improvements in segmentation accuracy and usability. Thus, its accuracy and ease of use will
allow MINS to be implemented for routine single-cell-level image analyses.
Original languageEnglish
DOIs
Publication statusPublished - 2014

Fingerprint

Stem cells
Image analysis
MATLAB
Software engineering
Pipelines

Cite this

A Rapid and Efficient 2D/3D Nuclear Segmentation Method for Analysis of Early Mouse Embryo and Stem Cell Image Data. / Lou, Xinghua; Kang, Minjung; Xenopoulos, Panagiotis; Munoz-Descalzo, S; Hadjantonakis, Anna-Katerina.

2014.

Research output: Contribution to conferencePaper

Lou, Xinghua ; Kang, Minjung ; Xenopoulos, Panagiotis ; Munoz-Descalzo, S ; Hadjantonakis, Anna-Katerina. / A Rapid and Efficient 2D/3D Nuclear Segmentation Method for Analysis of Early Mouse Embryo and Stem Cell Image Data.
@conference{7eb1c1c7d2354917b8bbdc3110f0a8cd,
title = "A Rapid and Efficient 2D/3D Nuclear Segmentation Method for Analysis of Early Mouse Embryo and Stem Cell Image Data",
abstract = "Segmentation is a fundamental problem that dominates the success of microscopic image analysis. In almost 25 years of cell detectionsoftware development, there is still no single piece of commercial software that works well in practice when applied to early mouseembryo or stem cell image data. To address this need, we developed MINS (modular interactive nuclear segmentation) as a MATLAB/C++-based segmentation tool tailored for counting cells and fluorescent intensity measurements of 2D and 3D image data. Our aimwas to develop a tool that is accurate and efficient yet straightforward and user friendly. The MINS pipeline comprises three majorcascaded modules: detection, segmentation, and cell position classification. An extensive evaluation of MINS on both 2D and 3D images,and comparison to related tools, reveals improvements in segmentation accuracy and usability. Thus, its accuracy and ease of use willallow MINS to be implemented for routine single-cell-level image analyses.",
author = "Xinghua Lou and Minjung Kang and Panagiotis Xenopoulos and S Munoz-Descalzo and Anna-Katerina Hadjantonakis",
year = "2014",
doi = "10.1016/j.stemcr.2014.01.010",
language = "English",

}

TY - CONF

T1 - A Rapid and Efficient 2D/3D Nuclear Segmentation Method for Analysis of Early Mouse Embryo and Stem Cell Image Data

AU - Lou, Xinghua

AU - Kang, Minjung

AU - Xenopoulos, Panagiotis

AU - Munoz-Descalzo, S

AU - Hadjantonakis, Anna-Katerina

PY - 2014

Y1 - 2014

N2 - Segmentation is a fundamental problem that dominates the success of microscopic image analysis. In almost 25 years of cell detectionsoftware development, there is still no single piece of commercial software that works well in practice when applied to early mouseembryo or stem cell image data. To address this need, we developed MINS (modular interactive nuclear segmentation) as a MATLAB/C++-based segmentation tool tailored for counting cells and fluorescent intensity measurements of 2D and 3D image data. Our aimwas to develop a tool that is accurate and efficient yet straightforward and user friendly. The MINS pipeline comprises three majorcascaded modules: detection, segmentation, and cell position classification. An extensive evaluation of MINS on both 2D and 3D images,and comparison to related tools, reveals improvements in segmentation accuracy and usability. Thus, its accuracy and ease of use willallow MINS to be implemented for routine single-cell-level image analyses.

AB - Segmentation is a fundamental problem that dominates the success of microscopic image analysis. In almost 25 years of cell detectionsoftware development, there is still no single piece of commercial software that works well in practice when applied to early mouseembryo or stem cell image data. To address this need, we developed MINS (modular interactive nuclear segmentation) as a MATLAB/C++-based segmentation tool tailored for counting cells and fluorescent intensity measurements of 2D and 3D image data. Our aimwas to develop a tool that is accurate and efficient yet straightforward and user friendly. The MINS pipeline comprises three majorcascaded modules: detection, segmentation, and cell position classification. An extensive evaluation of MINS on both 2D and 3D images,and comparison to related tools, reveals improvements in segmentation accuracy and usability. Thus, its accuracy and ease of use willallow MINS to be implemented for routine single-cell-level image analyses.

UR - http://dx.doi.org/10.1016/j.stemcr.2014.01.010

U2 - 10.1016/j.stemcr.2014.01.010

DO - 10.1016/j.stemcr.2014.01.010

M3 - Paper

ER -