Generator Platform of Benchmark Time-Lapsed Images Development of Cell Tracking Algorithms: Implementation of New Features Towards a Realistic Simulation of the Cell Spatial and Temporal Organization

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

Abstract

Recent developments in live-cell microscopy imaging have led to the emergence of Single Cell Biology. This field has also been supported by the development of cell segmentation and tracking algorithms for data extraction. The validation of these algorithms requires benchmark databases, with manually labeled or artificially generated images, so that the ground truth is known. To generate realistic artificial images, we have developed a simulation platform capable of generating biologically inspired objects with various shapes and size, which are able to grow, divide, move and form specific clusters. Using this platform, we compared four tracking algorithms: Simple Nearest-Neighbor (NN), NN with Morphology (NNm) and two DBSCAN-based methodologies. We show that Simple NN performs well on objects with small velocities, while the others perform better for higher velocities and when objects form clusters. This platform for benchmark images generation and image analysis algorithms testing is openly available at (http://griduni.uninova.pt/Clustergen/ClusterGen_v1.0.zip).

Original languageEnglish
Title of host publicationSimulation and Modeling Methodologies, Technologies and Applications - International Conference, SIMULTECH 2016, Revised Selected Papers
EditorsM. Obaidat, T. Ören, Y. Merkuryev
Place of PublicationCham
PublisherSpringer Verlag
Pages52-74
Number of pages23
ISBN (Electronic)978-3-319-69832-8
ISBN (Print)978-3-319-69831-1
DOIs
Publication statusPublished - 2018
Event6th International Conference on Simulation and Modeling Methodologies,Technologies and Applications, SIMULTECH 2016 - Lisbon, Portugal
Duration: 29 Jul 201631 Jul 2016

Publication series

NameAdvances in Intelligent Systems and Computing
PublisherSpringer Verlag
Volume676
ISSN (Print)2194-5357

Conference

Conference6th International Conference on Simulation and Modeling Methodologies,Technologies and Applications, SIMULTECH 2016
CountryPortugal
CityLisbon
Period29/07/1631/07/16

Fingerprint

Cytology
Image analysis
Microscopic examination
Imaging techniques
Testing

Keywords

  • Cell tracking
  • Cluster tracking
  • Microscopy
  • Synthetic time-lapse image simulation

Cite this

Martins, L., Canelas, P., Mora, A., Ribeiro, A. S., & Fonseca, J. (2018). Generator Platform of Benchmark Time-Lapsed Images Development of Cell Tracking Algorithms: Implementation of New Features Towards a Realistic Simulation of the Cell Spatial and Temporal Organization. In M. Obaidat, T. Ören, & Y. Merkuryev (Eds.), Simulation and Modeling Methodologies, Technologies and Applications - International Conference, SIMULTECH 2016, Revised Selected Papers (pp. 52-74). (Advances in Intelligent Systems and Computing; Vol. 676). Cham: Springer Verlag. https://doi.org/10.1007/978-3-319-69832-8_4
Martins, Leonardo ; Canelas, Pedro ; Mora, André ; Ribeiro, Andre S. ; Fonseca, José. / Generator Platform of Benchmark Time-Lapsed Images Development of Cell Tracking Algorithms: Implementation of New Features Towards a Realistic Simulation of the Cell Spatial and Temporal Organization. Simulation and Modeling Methodologies, Technologies and Applications - International Conference, SIMULTECH 2016, Revised Selected Papers. editor / M. Obaidat ; T. Ören ; Y. Merkuryev. Cham : Springer Verlag, 2018. pp. 52-74 (Advances in Intelligent Systems and Computing).
@inproceedings{c05475acf3eb45529c27a99d0195e393,
title = "Generator Platform of Benchmark Time-Lapsed Images Development of Cell Tracking Algorithms: Implementation of New Features Towards a Realistic Simulation of the Cell Spatial and Temporal Organization",
abstract = "Recent developments in live-cell microscopy imaging have led to the emergence of Single Cell Biology. This field has also been supported by the development of cell segmentation and tracking algorithms for data extraction. The validation of these algorithms requires benchmark databases, with manually labeled or artificially generated images, so that the ground truth is known. To generate realistic artificial images, we have developed a simulation platform capable of generating biologically inspired objects with various shapes and size, which are able to grow, divide, move and form specific clusters. Using this platform, we compared four tracking algorithms: Simple Nearest-Neighbor (NN), NN with Morphology (NNm) and two DBSCAN-based methodologies. We show that Simple NN performs well on objects with small velocities, while the others perform better for higher velocities and when objects form clusters. This platform for benchmark images generation and image analysis algorithms testing is openly available at (http://griduni.uninova.pt/Clustergen/ClusterGen_v1.0.zip).",
keywords = "Cell tracking, Cluster tracking, Microscopy, Synthetic time-lapse image simulation",
author = "Leonardo Martins and Pedro Canelas and Andr{\'e} Mora and Ribeiro, {Andre S.} and Jos{\'e} Fonseca",
note = "Work supported by the Portuguese Foundation for Science and Technology (FCT/MCTES) through a PhD Scholarship, ref. SFRH/BD/88987/2012 to LM, SADAC project (ref. PTDC/BBB-MET/1084/2012) and by FCT Strategic Program UID/EEA/00066/203 of UNINOVA, CTS. This work is also funded by the Academy of Finland [refs. 295027 and 305342 to ASR] and the Jane and Aatos Erkko Foundation [ref. 5-3416-12 to ASR].",
year = "2018",
doi = "10.1007/978-3-319-69832-8_4",
language = "English",
isbn = "978-3-319-69831-1",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "52--74",
editor = "M. Obaidat and T. {\"O}ren and Y. Merkuryev",
booktitle = "Simulation and Modeling Methodologies, Technologies and Applications - International Conference, SIMULTECH 2016, Revised Selected Papers",
address = "Germany",

}

Martins, L, Canelas, P, Mora, A, Ribeiro, AS & Fonseca, J 2018, Generator Platform of Benchmark Time-Lapsed Images Development of Cell Tracking Algorithms: Implementation of New Features Towards a Realistic Simulation of the Cell Spatial and Temporal Organization. in M Obaidat, T Ören & Y Merkuryev (eds), Simulation and Modeling Methodologies, Technologies and Applications - International Conference, SIMULTECH 2016, Revised Selected Papers. Advances in Intelligent Systems and Computing, vol. 676, Springer Verlag, Cham, pp. 52-74, 6th International Conference on Simulation and Modeling Methodologies,Technologies and Applications, SIMULTECH 2016, Lisbon, Portugal, 29/07/16. https://doi.org/10.1007/978-3-319-69832-8_4

Generator Platform of Benchmark Time-Lapsed Images Development of Cell Tracking Algorithms: Implementation of New Features Towards a Realistic Simulation of the Cell Spatial and Temporal Organization. / Martins, Leonardo; Canelas, Pedro; Mora, André; Ribeiro, Andre S.; Fonseca, José.

Simulation and Modeling Methodologies, Technologies and Applications - International Conference, SIMULTECH 2016, Revised Selected Papers. ed. / M. Obaidat; T. Ören; Y. Merkuryev. Cham : Springer Verlag, 2018. p. 52-74 (Advances in Intelligent Systems and Computing; Vol. 676).

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

TY - GEN

T1 - Generator Platform of Benchmark Time-Lapsed Images Development of Cell Tracking Algorithms: Implementation of New Features Towards a Realistic Simulation of the Cell Spatial and Temporal Organization

AU - Martins, Leonardo

AU - Canelas, Pedro

AU - Mora, André

AU - Ribeiro, Andre S.

AU - Fonseca, José

N1 - Work supported by the Portuguese Foundation for Science and Technology (FCT/MCTES) through a PhD Scholarship, ref. SFRH/BD/88987/2012 to LM, SADAC project (ref. PTDC/BBB-MET/1084/2012) and by FCT Strategic Program UID/EEA/00066/203 of UNINOVA, CTS. This work is also funded by the Academy of Finland [refs. 295027 and 305342 to ASR] and the Jane and Aatos Erkko Foundation [ref. 5-3416-12 to ASR].

PY - 2018

Y1 - 2018

N2 - Recent developments in live-cell microscopy imaging have led to the emergence of Single Cell Biology. This field has also been supported by the development of cell segmentation and tracking algorithms for data extraction. The validation of these algorithms requires benchmark databases, with manually labeled or artificially generated images, so that the ground truth is known. To generate realistic artificial images, we have developed a simulation platform capable of generating biologically inspired objects with various shapes and size, which are able to grow, divide, move and form specific clusters. Using this platform, we compared four tracking algorithms: Simple Nearest-Neighbor (NN), NN with Morphology (NNm) and two DBSCAN-based methodologies. We show that Simple NN performs well on objects with small velocities, while the others perform better for higher velocities and when objects form clusters. This platform for benchmark images generation and image analysis algorithms testing is openly available at (http://griduni.uninova.pt/Clustergen/ClusterGen_v1.0.zip).

AB - Recent developments in live-cell microscopy imaging have led to the emergence of Single Cell Biology. This field has also been supported by the development of cell segmentation and tracking algorithms for data extraction. The validation of these algorithms requires benchmark databases, with manually labeled or artificially generated images, so that the ground truth is known. To generate realistic artificial images, we have developed a simulation platform capable of generating biologically inspired objects with various shapes and size, which are able to grow, divide, move and form specific clusters. Using this platform, we compared four tracking algorithms: Simple Nearest-Neighbor (NN), NN with Morphology (NNm) and two DBSCAN-based methodologies. We show that Simple NN performs well on objects with small velocities, while the others perform better for higher velocities and when objects form clusters. This platform for benchmark images generation and image analysis algorithms testing is openly available at (http://griduni.uninova.pt/Clustergen/ClusterGen_v1.0.zip).

KW - Cell tracking

KW - Cluster tracking

KW - Microscopy

KW - Synthetic time-lapse image simulation

UR - http://www.scopus.com/inward/record.url?scp=85033717105&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-69832-8_4

DO - 10.1007/978-3-319-69832-8_4

M3 - Conference contribution

SN - 978-3-319-69831-1

T3 - Advances in Intelligent Systems and Computing

SP - 52

EP - 74

BT - Simulation and Modeling Methodologies, Technologies and Applications - International Conference, SIMULTECH 2016, Revised Selected Papers

A2 - Obaidat, M.

A2 - Ören, T.

A2 - Merkuryev, Y.

PB - Springer Verlag

CY - Cham

ER -

Martins L, Canelas P, Mora A, Ribeiro AS, Fonseca J. Generator Platform of Benchmark Time-Lapsed Images Development of Cell Tracking Algorithms: Implementation of New Features Towards a Realistic Simulation of the Cell Spatial and Temporal Organization. In Obaidat M, Ören T, Merkuryev Y, editors, Simulation and Modeling Methodologies, Technologies and Applications - International Conference, SIMULTECH 2016, Revised Selected Papers. Cham: Springer Verlag. 2018. p. 52-74. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-69832-8_4