Size-invariant cell nucleus segmentation in 3-D microscopy

Sundaresh Ram, Jeffrey J Rodriguez, Giovanni Bosco

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Accurate segmentation of 3-D cell nuclei in microscopy images is an essential task in many biological studies. Traditional image segmentation methods are challenged by the complexity and variability of microscope images, so there is a need to improve segmentation accuracy and reliability, as well as the level of automation. In this paper we present a novel automated algorithm for robust segmentation of 3-D cell nuclei using a combination of ideas. Our algorithm includes the following steps: image denoising, binarization, seed detection using the fast radial symmetric transform (FRST), initial segmentation using the random walker algorithm and the 3-D watershed algorithm, and final refinements using 3-D active contours. We show that our algorithm provides improved accuracy compared to existing segmentation algorithms.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation
Pages37-40
Number of pages4
DOIs
StatePublished - 2012
Event2012 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2012 - Santa Fe, NM, United States
Duration: Apr 22 2012Apr 24 2012

Other

Other2012 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2012
CountryUnited States
CitySanta Fe, NM
Period4/22/124/24/12

Fingerprint

Microscopic examination
Cells
Image denoising
Watersheds
Image segmentation
Seed
Microscopes
Automation

Keywords

  • Active contours
  • random walker algorithm
  • watershed algorithm

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Ram, S., Rodriguez, J. J., & Bosco, G. (2012). Size-invariant cell nucleus segmentation in 3-D microscopy. In Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation (pp. 37-40). [6202447] https://doi.org/10.1109/SSIAI.2012.6202447

Size-invariant cell nucleus segmentation in 3-D microscopy. / Ram, Sundaresh; Rodriguez, Jeffrey J; Bosco, Giovanni.

Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation. 2012. p. 37-40 6202447.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ram, S, Rodriguez, JJ & Bosco, G 2012, Size-invariant cell nucleus segmentation in 3-D microscopy. in Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation., 6202447, pp. 37-40, 2012 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2012, Santa Fe, NM, United States, 4/22/12. https://doi.org/10.1109/SSIAI.2012.6202447
Ram S, Rodriguez JJ, Bosco G. Size-invariant cell nucleus segmentation in 3-D microscopy. In Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation. 2012. p. 37-40. 6202447 https://doi.org/10.1109/SSIAI.2012.6202447
Ram, Sundaresh ; Rodriguez, Jeffrey J ; Bosco, Giovanni. / Size-invariant cell nucleus segmentation in 3-D microscopy. Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation. 2012. pp. 37-40
@inproceedings{f5708d50f0934c29a051140f097547be,
title = "Size-invariant cell nucleus segmentation in 3-D microscopy",
abstract = "Accurate segmentation of 3-D cell nuclei in microscopy images is an essential task in many biological studies. Traditional image segmentation methods are challenged by the complexity and variability of microscope images, so there is a need to improve segmentation accuracy and reliability, as well as the level of automation. In this paper we present a novel automated algorithm for robust segmentation of 3-D cell nuclei using a combination of ideas. Our algorithm includes the following steps: image denoising, binarization, seed detection using the fast radial symmetric transform (FRST), initial segmentation using the random walker algorithm and the 3-D watershed algorithm, and final refinements using 3-D active contours. We show that our algorithm provides improved accuracy compared to existing segmentation algorithms.",
keywords = "Active contours, random walker algorithm, watershed algorithm",
author = "Sundaresh Ram and Rodriguez, {Jeffrey J} and Giovanni Bosco",
year = "2012",
doi = "10.1109/SSIAI.2012.6202447",
language = "English (US)",
isbn = "9781467318303",
pages = "37--40",
booktitle = "Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation",

}

TY - GEN

T1 - Size-invariant cell nucleus segmentation in 3-D microscopy

AU - Ram, Sundaresh

AU - Rodriguez, Jeffrey J

AU - Bosco, Giovanni

PY - 2012

Y1 - 2012

N2 - Accurate segmentation of 3-D cell nuclei in microscopy images is an essential task in many biological studies. Traditional image segmentation methods are challenged by the complexity and variability of microscope images, so there is a need to improve segmentation accuracy and reliability, as well as the level of automation. In this paper we present a novel automated algorithm for robust segmentation of 3-D cell nuclei using a combination of ideas. Our algorithm includes the following steps: image denoising, binarization, seed detection using the fast radial symmetric transform (FRST), initial segmentation using the random walker algorithm and the 3-D watershed algorithm, and final refinements using 3-D active contours. We show that our algorithm provides improved accuracy compared to existing segmentation algorithms.

AB - Accurate segmentation of 3-D cell nuclei in microscopy images is an essential task in many biological studies. Traditional image segmentation methods are challenged by the complexity and variability of microscope images, so there is a need to improve segmentation accuracy and reliability, as well as the level of automation. In this paper we present a novel automated algorithm for robust segmentation of 3-D cell nuclei using a combination of ideas. Our algorithm includes the following steps: image denoising, binarization, seed detection using the fast radial symmetric transform (FRST), initial segmentation using the random walker algorithm and the 3-D watershed algorithm, and final refinements using 3-D active contours. We show that our algorithm provides improved accuracy compared to existing segmentation algorithms.

KW - Active contours

KW - random walker algorithm

KW - watershed algorithm

UR - http://www.scopus.com/inward/record.url?scp=84862854860&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862854860&partnerID=8YFLogxK

U2 - 10.1109/SSIAI.2012.6202447

DO - 10.1109/SSIAI.2012.6202447

M3 - Conference contribution

AN - SCOPUS:84862854860

SN - 9781467318303

SP - 37

EP - 40

BT - Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation

ER -