SPF-CellTracker: Tracking Multiple Cells with Strongly-Correlated Moves Using a Spatial Particle Filter

Osamu Hirose, Shotaro Kawaguchi, Terumasa Tokunaga, Yu Toyoshima, Takayuki Teramoto, Sayuri Kuge, Takeshi Ishihara, Yuichi Iino, Ryo Yoshida

Research output: Contribution to journalArticle

Abstract

Tracking many cells in time-lapse 3D image sequences is an important challenging task of bioimage informatics. Motivated by a study of brain-wide 4D imaging of neural activity in C. elegans, we present a new method of multi-cell tracking. Data types to which the method is applicable are characterized as follows: (i) cells are imaged as globular-like objects, (ii) it is difficult to distinguish cells on the basis of shape and size only, (iii) the number of imaged cells in the several-hundred range, (iv) movements of nearly-located cells are strongly correlated, and (v) cells do not divide. We developed a tracking software suite that we call SPF-CellTracker. Incorporating dependency on the cells' movements into the prediction model is the key for reducing the tracking errors: the cell switching and the coalescence of the tracked positions. We model the target cells' correlated movements as a Markov random field and we also derive a fast computation algorithm, which we call spatial particle filter. With the live-imaging data of the nuclei of C. elegans neurons in which approximately 120 nuclei of neurons were imaged, the proposed method demonstrated improved accuracy compared to the standard particle filter and the method developed by Tokunaga et al. (2014).

Original languageEnglish
Article number8186251
Pages (from-to)1822-1831
Number of pages10
JournalIEEE/ACM Transactions on Computational Biology and Bioinformatics
Volume15
Issue number6
DOIs
Publication statusPublished - Nov 1 2018

Fingerprint

Cell Tracking
Particle Filter
Neurons
Imaging techniques
Cell
Coalescence
Cell Movement
Brain
Informatics
Software
Cell Count
Nucleus
Neuron
Imaging
3D Image
Image Sequence
Prediction Model
Random Field
Divides

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Genetics
  • Applied Mathematics

Cite this

SPF-CellTracker : Tracking Multiple Cells with Strongly-Correlated Moves Using a Spatial Particle Filter. / Hirose, Osamu; Kawaguchi, Shotaro; Tokunaga, Terumasa; Toyoshima, Yu; Teramoto, Takayuki; Kuge, Sayuri; Ishihara, Takeshi; Iino, Yuichi; Yoshida, Ryo.

In: IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 15, No. 6, 8186251, 01.11.2018, p. 1822-1831.

Research output: Contribution to journalArticle

Hirose, Osamu ; Kawaguchi, Shotaro ; Tokunaga, Terumasa ; Toyoshima, Yu ; Teramoto, Takayuki ; Kuge, Sayuri ; Ishihara, Takeshi ; Iino, Yuichi ; Yoshida, Ryo. / SPF-CellTracker : Tracking Multiple Cells with Strongly-Correlated Moves Using a Spatial Particle Filter. In: IEEE/ACM Transactions on Computational Biology and Bioinformatics. 2018 ; Vol. 15, No. 6. pp. 1822-1831.
@article{56e820dd2c054fe4b5656aba092e88d3,
title = "SPF-CellTracker: Tracking Multiple Cells with Strongly-Correlated Moves Using a Spatial Particle Filter",
abstract = "Tracking many cells in time-lapse 3D image sequences is an important challenging task of bioimage informatics. Motivated by a study of brain-wide 4D imaging of neural activity in C. elegans, we present a new method of multi-cell tracking. Data types to which the method is applicable are characterized as follows: (i) cells are imaged as globular-like objects, (ii) it is difficult to distinguish cells on the basis of shape and size only, (iii) the number of imaged cells in the several-hundred range, (iv) movements of nearly-located cells are strongly correlated, and (v) cells do not divide. We developed a tracking software suite that we call SPF-CellTracker. Incorporating dependency on the cells' movements into the prediction model is the key for reducing the tracking errors: the cell switching and the coalescence of the tracked positions. We model the target cells' correlated movements as a Markov random field and we also derive a fast computation algorithm, which we call spatial particle filter. With the live-imaging data of the nuclei of C. elegans neurons in which approximately 120 nuclei of neurons were imaged, the proposed method demonstrated improved accuracy compared to the standard particle filter and the method developed by Tokunaga et al. (2014).",
author = "Osamu Hirose and Shotaro Kawaguchi and Terumasa Tokunaga and Yu Toyoshima and Takayuki Teramoto and Sayuri Kuge and Takeshi Ishihara and Yuichi Iino and Ryo Yoshida",
year = "2018",
month = "11",
day = "1",
doi = "10.1109/TCBB.2017.2782255",
language = "English",
volume = "15",
pages = "1822--1831",
journal = "IEEE/ACM Transactions on Computational Biology and Bioinformatics",
issn = "1545-5963",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - SPF-CellTracker

T2 - Tracking Multiple Cells with Strongly-Correlated Moves Using a Spatial Particle Filter

AU - Hirose, Osamu

AU - Kawaguchi, Shotaro

AU - Tokunaga, Terumasa

AU - Toyoshima, Yu

AU - Teramoto, Takayuki

AU - Kuge, Sayuri

AU - Ishihara, Takeshi

AU - Iino, Yuichi

AU - Yoshida, Ryo

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Tracking many cells in time-lapse 3D image sequences is an important challenging task of bioimage informatics. Motivated by a study of brain-wide 4D imaging of neural activity in C. elegans, we present a new method of multi-cell tracking. Data types to which the method is applicable are characterized as follows: (i) cells are imaged as globular-like objects, (ii) it is difficult to distinguish cells on the basis of shape and size only, (iii) the number of imaged cells in the several-hundred range, (iv) movements of nearly-located cells are strongly correlated, and (v) cells do not divide. We developed a tracking software suite that we call SPF-CellTracker. Incorporating dependency on the cells' movements into the prediction model is the key for reducing the tracking errors: the cell switching and the coalescence of the tracked positions. We model the target cells' correlated movements as a Markov random field and we also derive a fast computation algorithm, which we call spatial particle filter. With the live-imaging data of the nuclei of C. elegans neurons in which approximately 120 nuclei of neurons were imaged, the proposed method demonstrated improved accuracy compared to the standard particle filter and the method developed by Tokunaga et al. (2014).

AB - Tracking many cells in time-lapse 3D image sequences is an important challenging task of bioimage informatics. Motivated by a study of brain-wide 4D imaging of neural activity in C. elegans, we present a new method of multi-cell tracking. Data types to which the method is applicable are characterized as follows: (i) cells are imaged as globular-like objects, (ii) it is difficult to distinguish cells on the basis of shape and size only, (iii) the number of imaged cells in the several-hundred range, (iv) movements of nearly-located cells are strongly correlated, and (v) cells do not divide. We developed a tracking software suite that we call SPF-CellTracker. Incorporating dependency on the cells' movements into the prediction model is the key for reducing the tracking errors: the cell switching and the coalescence of the tracked positions. We model the target cells' correlated movements as a Markov random field and we also derive a fast computation algorithm, which we call spatial particle filter. With the live-imaging data of the nuclei of C. elegans neurons in which approximately 120 nuclei of neurons were imaged, the proposed method demonstrated improved accuracy compared to the standard particle filter and the method developed by Tokunaga et al. (2014).

UR - http://www.scopus.com/inward/record.url?scp=85038382107&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038382107&partnerID=8YFLogxK

U2 - 10.1109/TCBB.2017.2782255

DO - 10.1109/TCBB.2017.2782255

M3 - Article

C2 - 29990224

AN - SCOPUS:85038382107

VL - 15

SP - 1822

EP - 1831

JO - IEEE/ACM Transactions on Computational Biology and Bioinformatics

JF - IEEE/ACM Transactions on Computational Biology and Bioinformatics

SN - 1545-5963

IS - 6

M1 - 8186251

ER -