Characterization and Classification of Adherent Cells in Monolayer Culture using Automated Tracking and Evolutionary Algorithms

TY - JOUR

T1 - Characterization and Classification of Adherent Cells in Monolayer Culture using Automated Tracking and Evolutionary Algorithms

AU - Zhang, Zhen

AU - Bedder, Matthew

AU - Smith, Stephen Leslie

AU - Walker, Dawn

AU - Shabir, Saqib

AU - Southgate, Jennifer

N1 - © 2016 Published by Elsevier Ireland Ltd. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.

PY - 2016/8

Y1 - 2016/8

N2 - This paper presents a novel method for tracking and characterizing adherent cells in monolayer culture. A system of cell tracking employing computer vision techniques was applied to time-lapse videos of replicate normal human uro-epithelial cell cultures exposed to different concentrations of adenosine triphosphate (ATP) and a selective purinergic P2X antagonist (PPADS), acquired over a 24 hour period. Subsequent analysis following feature extraction demonstrated the ability of the technique to successfully separate the modulated classes of cell using evolutionary algorithms. Specifically, a Cartesian Genetic Program (CGP) network was evolved that identified average migration speed, in-contact angular velocity, cohesivity and average cell clump size as the principal features contributing to the separation. Our approach not only provides non-biased and parsimonious insight into modulated class behaviors, but can be extracted as mathematical formulae for the parameterization of computational models.

AB - This paper presents a novel method for tracking and characterizing adherent cells in monolayer culture. A system of cell tracking employing computer vision techniques was applied to time-lapse videos of replicate normal human uro-epithelial cell cultures exposed to different concentrations of adenosine triphosphate (ATP) and a selective purinergic P2X antagonist (PPADS), acquired over a 24 hour period. Subsequent analysis following feature extraction demonstrated the ability of the technique to successfully separate the modulated classes of cell using evolutionary algorithms. Specifically, a Cartesian Genetic Program (CGP) network was evolved that identified average migration speed, in-contact angular velocity, cohesivity and average cell clump size as the principal features contributing to the separation. Our approach not only provides non-biased and parsimonious insight into modulated class behaviors, but can be extracted as mathematical formulae for the parameterization of computational models.

U2 - 10.1016/j.biosystems.2016.05.009

DO - 10.1016/j.biosystems.2016.05.009

M3 - Article

SN - 0303-2647

VL - 146

SP - 110

EP - 121

JO - Biosystems

JF - Biosystems

ER -