Tampere University of Technology

TUTCRIS Research Portal

An image generator platform to improve cell tracking algorithms simulation of objects of various morphologies, kinetics and clustering

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

An image generator platform to improve cell tracking algorithms simulation of objects of various morphologies, kinetics and clustering. / Canelas, Pedro; Martins, Leonardo; Mora, André; S. Ribeiro, Andre; Fonseca, José.

SIMULTECH 2016 - Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications. SCITEPRESS, 2016. p. 44-55.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Canelas, P, Martins, L, Mora, A, S. Ribeiro, A & Fonseca, J 2016, An image generator platform to improve cell tracking algorithms simulation of objects of various morphologies, kinetics and clustering. in SIMULTECH 2016 - Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications. SCITEPRESS, pp. 44-55, INTERNATIONAL CONFERENCE ON SIMULATION AND MODELING METHODOLOGIES, TECHNOLOGIES AND APPLICATIONS, 1/01/00.

APA

Canelas, P., Martins, L., Mora, A., S. Ribeiro, A., & Fonseca, J. (2016). An image generator platform to improve cell tracking algorithms simulation of objects of various morphologies, kinetics and clustering. In SIMULTECH 2016 - Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications (pp. 44-55). SCITEPRESS.

Vancouver

Canelas P, Martins L, Mora A, S. Ribeiro A, Fonseca J. An image generator platform to improve cell tracking algorithms simulation of objects of various morphologies, kinetics and clustering. In SIMULTECH 2016 - Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications. SCITEPRESS. 2016. p. 44-55

Author

Canelas, Pedro ; Martins, Leonardo ; Mora, André ; S. Ribeiro, Andre ; Fonseca, José. / An image generator platform to improve cell tracking algorithms simulation of objects of various morphologies, kinetics and clustering. SIMULTECH 2016 - Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications. SCITEPRESS, 2016. pp. 44-55

Bibtex - Download

@inproceedings{a2a9d8da1c314fa99dff0dac955292b4,
title = "An image generator platform to improve cell tracking algorithms simulation of objects of various morphologies, kinetics and clustering",
abstract = "Several major advances in Cell and Molecular Biology have been made possible by recent advances in livecell microscopy imaging. To support these efforts, automated image analysis methods such as cell segmentation and tracking during a time-series analysis are needed. To this aim, one important step is the validation of such image processing methods. Ideally, the {"}ground truth{"} should be known, which is possible only by manually labelling images or in artificially produced images. To simulate artificial images, we have developed a platform for simulating biologically inspired objects, which generates bodies with various morphologies and kinetics and, that can aggregate to form clusters. Using this platform, we tested and compared four tracking algorithms: Simple Nearest-Neighbour (NN), NN with Morphology and two DBSCAN-based methods. We show that Simple NN works well for small object velocities, while the others perform better on higher velocities and when clustering occurs. Our new platform for generating new benchmark images to test image analysis algorithms 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 = "Pedro Canelas and Leonardo Martins and Andr{\'e} Mora and {S. Ribeiro}, Andre and Jos{\'e} Fonseca",
year = "2016",
language = "English",
pages = "44--55",
booktitle = "SIMULTECH 2016 - Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications",
publisher = "SCITEPRESS",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - An image generator platform to improve cell tracking algorithms simulation of objects of various morphologies, kinetics and clustering

AU - Canelas, Pedro

AU - Martins, Leonardo

AU - Mora, André

AU - S. Ribeiro, Andre

AU - Fonseca, José

PY - 2016

Y1 - 2016

N2 - Several major advances in Cell and Molecular Biology have been made possible by recent advances in livecell microscopy imaging. To support these efforts, automated image analysis methods such as cell segmentation and tracking during a time-series analysis are needed. To this aim, one important step is the validation of such image processing methods. Ideally, the "ground truth" should be known, which is possible only by manually labelling images or in artificially produced images. To simulate artificial images, we have developed a platform for simulating biologically inspired objects, which generates bodies with various morphologies and kinetics and, that can aggregate to form clusters. Using this platform, we tested and compared four tracking algorithms: Simple Nearest-Neighbour (NN), NN with Morphology and two DBSCAN-based methods. We show that Simple NN works well for small object velocities, while the others perform better on higher velocities and when clustering occurs. Our new platform for generating new benchmark images to test image analysis algorithms is openly available at (http://griduni.uninova.pt/Clustergen/ClusterGen-v1.0.zip).

AB - Several major advances in Cell and Molecular Biology have been made possible by recent advances in livecell microscopy imaging. To support these efforts, automated image analysis methods such as cell segmentation and tracking during a time-series analysis are needed. To this aim, one important step is the validation of such image processing methods. Ideally, the "ground truth" should be known, which is possible only by manually labelling images or in artificially produced images. To simulate artificial images, we have developed a platform for simulating biologically inspired objects, which generates bodies with various morphologies and kinetics and, that can aggregate to form clusters. Using this platform, we tested and compared four tracking algorithms: Simple Nearest-Neighbour (NN), NN with Morphology and two DBSCAN-based methods. We show that Simple NN works well for small object velocities, while the others perform better on higher velocities and when clustering occurs. Our new platform for generating new benchmark images to test image analysis algorithms 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

M3 - Conference contribution

SP - 44

EP - 55

BT - SIMULTECH 2016 - Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications

PB - SCITEPRESS

ER -