Active mask segmentation of fluorescence microscope images

Gowri Srinivasa, Matthew C. Fickus, Yusong Guo, Adam D. Linstedt, Jelena Kovacevic

Research output: Contribution to journalArticle

Abstract

We propose a new active mask algorithm for the segmentation of fluorescence microscope images of punctate patterns. It combines the (a) flexibility offered by active-contour methods, (b) speed offered by multiresolution methods, (c) smoothing offered by multiscale methods, and (d) statistical modeling offered by region-growing methods into a fast and accurate segmentation tool. The framework moves from the idea of the "contour" to that of "inside and outside," or masks, allowing for easy multidimensional segmentation. It adapts to the topology of the image through the use of multiple masks. The algorithm is almost invariant under initialization, allowing for random initialization, and uses a few easily tunable parameters. Experiments show that the active mask algorithm matches the ground truth well and outperforms the algorithm widely used in fluorescence microscopy, seeded watershed, both qualitatively, as well as quantitatively.

Original languageEnglish (US)
Pages (from-to)1817-1829
Number of pages13
JournalIEEE Transactions on Image Processing
Volume18
Issue number8
DOIs
StatePublished - Aug 10 2009

Fingerprint

Masks
Microscopes
Fluorescence
Fluorescence microscopy
Watersheds
Topology
Experiments

Keywords

  • Active contours
  • Active masks
  • Cellular automata
  • Fluorescence microscope
  • Multiresolution
  • Multiscale
  • Segmentation

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

Active mask segmentation of fluorescence microscope images. / Srinivasa, Gowri; Fickus, Matthew C.; Guo, Yusong; Linstedt, Adam D.; Kovacevic, Jelena.

In: IEEE Transactions on Image Processing, Vol. 18, No. 8, 10.08.2009, p. 1817-1829.

Research output: Contribution to journalArticle

Srinivasa, Gowri ; Fickus, Matthew C. ; Guo, Yusong ; Linstedt, Adam D. ; Kovacevic, Jelena. / Active mask segmentation of fluorescence microscope images. In: IEEE Transactions on Image Processing. 2009 ; Vol. 18, No. 8. pp. 1817-1829.
@article{b8cf0b62f29049aeb6f9e1d075e73bf2,
title = "Active mask segmentation of fluorescence microscope images",
abstract = "We propose a new active mask algorithm for the segmentation of fluorescence microscope images of punctate patterns. It combines the (a) flexibility offered by active-contour methods, (b) speed offered by multiresolution methods, (c) smoothing offered by multiscale methods, and (d) statistical modeling offered by region-growing methods into a fast and accurate segmentation tool. The framework moves from the idea of the {"}contour{"} to that of {"}inside and outside,{"} or masks, allowing for easy multidimensional segmentation. It adapts to the topology of the image through the use of multiple masks. The algorithm is almost invariant under initialization, allowing for random initialization, and uses a few easily tunable parameters. Experiments show that the active mask algorithm matches the ground truth well and outperforms the algorithm widely used in fluorescence microscopy, seeded watershed, both qualitatively, as well as quantitatively.",
keywords = "Active contours, Active masks, Cellular automata, Fluorescence microscope, Multiresolution, Multiscale, Segmentation",
author = "Gowri Srinivasa and Fickus, {Matthew C.} and Yusong Guo and Linstedt, {Adam D.} and Jelena Kovacevic",
year = "2009",
month = "8",
day = "10",
doi = "10.1109/TIP.2009.2021081",
language = "English (US)",
volume = "18",
pages = "1817--1829",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

TY - JOUR

T1 - Active mask segmentation of fluorescence microscope images

AU - Srinivasa, Gowri

AU - Fickus, Matthew C.

AU - Guo, Yusong

AU - Linstedt, Adam D.

AU - Kovacevic, Jelena

PY - 2009/8/10

Y1 - 2009/8/10

N2 - We propose a new active mask algorithm for the segmentation of fluorescence microscope images of punctate patterns. It combines the (a) flexibility offered by active-contour methods, (b) speed offered by multiresolution methods, (c) smoothing offered by multiscale methods, and (d) statistical modeling offered by region-growing methods into a fast and accurate segmentation tool. The framework moves from the idea of the "contour" to that of "inside and outside," or masks, allowing for easy multidimensional segmentation. It adapts to the topology of the image through the use of multiple masks. The algorithm is almost invariant under initialization, allowing for random initialization, and uses a few easily tunable parameters. Experiments show that the active mask algorithm matches the ground truth well and outperforms the algorithm widely used in fluorescence microscopy, seeded watershed, both qualitatively, as well as quantitatively.

AB - We propose a new active mask algorithm for the segmentation of fluorescence microscope images of punctate patterns. It combines the (a) flexibility offered by active-contour methods, (b) speed offered by multiresolution methods, (c) smoothing offered by multiscale methods, and (d) statistical modeling offered by region-growing methods into a fast and accurate segmentation tool. The framework moves from the idea of the "contour" to that of "inside and outside," or masks, allowing for easy multidimensional segmentation. It adapts to the topology of the image through the use of multiple masks. The algorithm is almost invariant under initialization, allowing for random initialization, and uses a few easily tunable parameters. Experiments show that the active mask algorithm matches the ground truth well and outperforms the algorithm widely used in fluorescence microscopy, seeded watershed, both qualitatively, as well as quantitatively.

KW - Active contours

KW - Active masks

KW - Cellular automata

KW - Fluorescence microscope

KW - Multiresolution

KW - Multiscale

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=68149132428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=68149132428&partnerID=8YFLogxK

U2 - 10.1109/TIP.2009.2021081

DO - 10.1109/TIP.2009.2021081

M3 - Article

C2 - 19380268

AN - SCOPUS:68149132428

VL - 18

SP - 1817

EP - 1829

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 8

ER -