Shape statistics for cell division detection in time-lapse videos of early mouse embryo

M. Cicconet, K. Gunsalus, D. Geiger, M. Werman

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

Abstract

We describe a statistical approach to the problem of estimating the times of cell-division cycles in time-lapse movies of early mouse embryos. Our method is based on the likelihoods for cells of certain radii ranges to be in each frame - without actually locating or counting the cells. Computing the likelihoods consists of a voting scheme where votes come form quadruples of points in a way similar to the first step of the Randomized Hough Transform for ellipse detection. To locate divisions, we search for points of abrupt change in the matrix of likelihoods (built for all frames), and pick the two optimal division points using a dynamic programming algorithm. Our results for the first and second cell division cycles differ less than two frames from the medians of the annotated times in a database of 100 annotated videos, and outperform two other recent methods in the same set.

Original languageEnglish (US)
Title of host publication2014 IEEE International Conference on Image Processing, ICIP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3622-3625
Number of pages4
ISBN (Print)9781479957514
DOIs
StatePublished - Jan 28 2014

Fingerprint

Hough transforms
Dynamic programming
Cells
Statistics

Keywords

  • division detection
  • mouse embryo
  • shape statistics
  • time lapse
  • video analysis

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Cicconet, M., Gunsalus, K., Geiger, D., & Werman, M. (2014). Shape statistics for cell division detection in time-lapse videos of early mouse embryo. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 3622-3625). [7025735] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7025735

Shape statistics for cell division detection in time-lapse videos of early mouse embryo. / Cicconet, M.; Gunsalus, K.; Geiger, D.; Werman, M.

2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 3622-3625 7025735.

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

Cicconet, M, Gunsalus, K, Geiger, D & Werman, M 2014, Shape statistics for cell division detection in time-lapse videos of early mouse embryo. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7025735, Institute of Electrical and Electronics Engineers Inc., pp. 3622-3625. https://doi.org/10.1109/ICIP.2014.7025735
Cicconet M, Gunsalus K, Geiger D, Werman M. Shape statistics for cell division detection in time-lapse videos of early mouse embryo. In 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 3622-3625. 7025735 https://doi.org/10.1109/ICIP.2014.7025735
Cicconet, M. ; Gunsalus, K. ; Geiger, D. ; Werman, M. / Shape statistics for cell division detection in time-lapse videos of early mouse embryo. 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 3622-3625
@inproceedings{a2b0f26bb68e43989ce3eea90284bb55,
title = "Shape statistics for cell division detection in time-lapse videos of early mouse embryo",
abstract = "We describe a statistical approach to the problem of estimating the times of cell-division cycles in time-lapse movies of early mouse embryos. Our method is based on the likelihoods for cells of certain radii ranges to be in each frame - without actually locating or counting the cells. Computing the likelihoods consists of a voting scheme where votes come form quadruples of points in a way similar to the first step of the Randomized Hough Transform for ellipse detection. To locate divisions, we search for points of abrupt change in the matrix of likelihoods (built for all frames), and pick the two optimal division points using a dynamic programming algorithm. Our results for the first and second cell division cycles differ less than two frames from the medians of the annotated times in a database of 100 annotated videos, and outperform two other recent methods in the same set.",
keywords = "division detection, mouse embryo, shape statistics, time lapse, video analysis",
author = "M. Cicconet and K. Gunsalus and D. Geiger and M. Werman",
year = "2014",
month = "1",
day = "28",
doi = "10.1109/ICIP.2014.7025735",
language = "English (US)",
isbn = "9781479957514",
pages = "3622--3625",
booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Shape statistics for cell division detection in time-lapse videos of early mouse embryo

AU - Cicconet, M.

AU - Gunsalus, K.

AU - Geiger, D.

AU - Werman, M.

PY - 2014/1/28

Y1 - 2014/1/28

N2 - We describe a statistical approach to the problem of estimating the times of cell-division cycles in time-lapse movies of early mouse embryos. Our method is based on the likelihoods for cells of certain radii ranges to be in each frame - without actually locating or counting the cells. Computing the likelihoods consists of a voting scheme where votes come form quadruples of points in a way similar to the first step of the Randomized Hough Transform for ellipse detection. To locate divisions, we search for points of abrupt change in the matrix of likelihoods (built for all frames), and pick the two optimal division points using a dynamic programming algorithm. Our results for the first and second cell division cycles differ less than two frames from the medians of the annotated times in a database of 100 annotated videos, and outperform two other recent methods in the same set.

AB - We describe a statistical approach to the problem of estimating the times of cell-division cycles in time-lapse movies of early mouse embryos. Our method is based on the likelihoods for cells of certain radii ranges to be in each frame - without actually locating or counting the cells. Computing the likelihoods consists of a voting scheme where votes come form quadruples of points in a way similar to the first step of the Randomized Hough Transform for ellipse detection. To locate divisions, we search for points of abrupt change in the matrix of likelihoods (built for all frames), and pick the two optimal division points using a dynamic programming algorithm. Our results for the first and second cell division cycles differ less than two frames from the medians of the annotated times in a database of 100 annotated videos, and outperform two other recent methods in the same set.

KW - division detection

KW - mouse embryo

KW - shape statistics

KW - time lapse

KW - video analysis

UR - http://www.scopus.com/inward/record.url?scp=84949926486&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949926486&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7025735

DO - 10.1109/ICIP.2014.7025735

M3 - Conference contribution

AN - SCOPUS:84949926486

SN - 9781479957514

SP - 3622

EP - 3625

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -