Abstract
The problem of multi-cell tracking plays an important role in studying dynamic cell cycle behaviors. In this paper, a novel ant system with multiple tasks is modeled for jointly estimating the number of cells and individual states in cell image sequences. In our ant system, in addition to pure cooperative mechanism used in traditional ant colony optimization algorithm, we model and investigate another two types of ant working modes, namely, dual competitive mode and interactive mode with cooperation and competition to evaluate the tracking performance on spatially adjacent cells. For adjacent ant colonies, dual competitive mode encourages ant colonies with different tasks to work independently, whereas the interactive mode introduces a trade-off between cooperation and competition. In simulations of real cell image sequences, the multi-tasking ant system integrated with interactive mode yielded better tracking results than systems adopting pure cooperation or dual competition alone, both of which cause tracking failures by under-estimating and over-estimating the number of cells, respectively. Furthermore, the results suggest that our algorithm can automatically and accurately track numerous cells in various scenarios, and is competitive with state-of-the-art multi-cell tracking methods.
Similar content being viewed by others
References
Fuhai L, Xiaobo Z, Jinwen M, Wong STC (2010) Multiple nuclei tracking using integer programming for quantitative cancer cell cycle analysis. IEEE Trans Med Imaging 29:96–105
Padfield D, Rittscher J, Roysam B (2008) Spatio-temporal cell segmentation and tracking for automated screening. In: 5th IEEE international symposium on biomedical imaging: from nano to macro, ISBI 2008, pp 376–379
Quan W, Jean G, Luby-Phelps K (2007) Multiple interacting subcellular structure tracking by sequential Monte Carlo method. In: IEEE international conference on bioinformatics and biomedicine, BIBM 2007, pp 437–442
Xiaodong Y, Li H, Xiaobo Z (2006) Nuclei segmentation using marker-controlled watershed, tracking using mean-shift, and Kalman filter in time-lapse microscopy. IEEE Trans Circuits Syst I, Regul Pap 53:2405–2414
Ray N, Acton ST, Ley K (2002) Tracking leukocytes in vivo with shape and size constrained active contours. IEEE Trans Med Imaging 21:1222–1235
Mukherjee DP, Ray N, Acton ST (2004) Level set analysis for leukocyte detection and tracking. IEEE Trans Image Process 13:562–572
Hoseinnezhad R, Vo B-N, Vo B-T, Suter D (2012) Visual tracking of numerous targets via multi-Bernoulli filtering of image data. Pattern Recognit 45:3625–3635
Meijering E, Dzyubachyk O, Smal I, van Cappellen WA (2009) Tracking in cell and developmental biology. Semin Cell Dev Biol 20:894–902
Cuevas E, González M (2013) Multi-circle detection on images inspired by collective animal behavior. Appl Intell. doi:10.1007/s10489-012-0396-2
Cuevas E, Sención F, Zaldivar D, Pérez-Cisneros M, Sossa H (2012) A multi-threshold segmentation approach based on artificial bee colony optimization. Appl Intell 37:321–336
Debeir O, Van Ham P, Kiss R, Decaestecker C (2005) Tracking of migrating cells under phase-contrast video microscopy with combined mean-shift processes. IEEE Trans Med Imaging 24:697–711
Dorigo M (1992) Optimization, learning and natural algorithms. PhD Thesis, Politecnico di Milano, Italy
Dorigo M, Gambardella LM (1997) Ant colonies for the travelling salesman problem. Biosystems 43:73–81
Dorigo M, Gambardella LM (1997) Ant colony system: a cooperative learning approach to the traveling salesman problem. IEEE Trans Evol Comput 1:53–66
Blum C (2005) Beam-ACO—hybridizing ant colony optimization with beam search: an application to open shop scheduling. Comput Oper Res 32:1565–1591
Xu B, Chen Q, Wang X, Zhu J (2009) A novel estimator with moving ants. Simul Model Pract Theory 17:1663–1677
Duan H, Liu S, Wang D, Yu X (2009) Design and realization of hybrid ACO-based PID and LuGre friction compensation controller for three degree-of-freedom high precision flight simulator. Simul Model Pract Theory 17:1160–1169
Chialvo D, Millonas M (1995) How swarms build cognitive maps. In: Steels L (ed) The biology and technology of intelligent autonomous agents, vol 144. Springer, Berlin Heidelberg, pp 439–450
Kanade PM, Hall LO (2007) Fuzzy ants and clustering. IEEE Trans Syst Man Cybern, Part A, Syst Hum 37:758–769
Handl J, Knowles J, Dorigo M (2004) Strategies for the increased robustness of ant-based clustering. In: Engineering self-organising systems. Springer, Berlin, pp 90–104
Ramos V, Fernandes C, Rosa AC (2006) On self-regulated swarms, societal memory, speed and dynamics. In: Int conf on the simulation and synthesis of living systems, Bloomington, Indiana, USA, 3–7 June 2006. arXiv:cs/0512002
Wu J, Abbas-Turki A, El Moudni A (2012) Cooperative driving: an ant colony system for autonomous intersection management. Appl Intell 37:207–222
Rivero J, Cuadra D, Calle J, Isasi P (2012) Using the ACO algorithm for path searches in social networks. Appl Intell 36:899–917
Favuzza S, Graditi G, Sanseverino ER (2006) Adaptive and dynamic ant colony search algorithm for optimal distribution systems reinforcement strategy. Appl Intell 24:31–42
Huang Y, Essa I (2005) Tracking multiple objects through occlusions. In: IEEE computer society conference on computer vision and pattern recognition, CVPR 2005, vol 2, pp 1051–1058
Bose B, Wang X, Grimson E (2007) Multi-class object tracking algorithm that handles fragmentation and grouping. In: IEEE conference on computer vision and pattern recognition, CVPR’07, pp 1–8
Qian Y, Medioni G (2009) Multiple-target tracking by spatiotemporal Monte Carlo Markov chain data association. IEEE Trans Pattern Anal Mach Intell 31:2196–2210
Wei Q, Schonfeld D, Mohamed M (2007) Real-time distributed multi-object tracking using multiple interactive trackers and a magnetic-inertia potential model. IEEE Trans Multimed 9:511–519
Khan SM, Shah M (2009) Tracking multiple occluding people by localizing on multiple scene planes. IEEE Trans Pattern Anal Mach Intell 31:505–519
Cielniak G, Duckett T, Lilienthal AJ (2010) Data association and occlusion handling for vision-based people tracking by mobile robots. Robot Auton Syst 58:435–443
Tao Y, Quan P, Jing L, Li SZ (2005) Real-time multiple objects tracking with occlusion handling in dynamic scenes. In: IEEE computer society conference on computer vision and pattern recognition, CVPR 2005, vol 1, pp 970–975
Xue J, Zheng N, Geng J, Zhong X (2008) Tracking multiple visual targets via particle-based belief propagation. IEEE Trans Syst Man Cybern, Part B, Cybern 38:196–209
Xu B, Xu H, Zhu J (2011) Ant clustering PHD filter for multiple-target tracking. Appl Soft Comput 11:1074–1086
Dufour A, Shinin V, Tajbakhsh S, Guillen-Aghion N, Olivo-Marin JC, Zimmer C (2005) Segmenting and tracking fluorescent cells in dynamic 3-D microscopy with coupled active surfaces. IEEE Trans Image Process 14:1396–1410
Nguyen NH, Keller S, Norris E, Huynh TT, Clemens MG, Shin MC (2011) Tracking colliding cells in vivo microscopy. IEEE Trans Biomed Eng 58:2391–2400
Fuzhi Z, Yujing M, Na H, Hui L (2008) An ant-based fast text clustering approach using pheromone. In: Fifth international conference on fuzzy systems and knowledge discovery, FSKD ’08, pp 385–389
Lee J-W, Choi B-S, Lee J-J (2011) Energy-efficient coverage of wireless sensor networks using ant colony optimization with three types of pheromones. IEEE Trans Ind Inform 7:419–427
Misra S, Dhurandher SK, Obaidat MS, Verma K, Gupta P (2010) A low-overhead fault-tolerant routing algorithm for mobile ad hoc networks: a scheme and its simulation analysis. Simul Model Pract Theory 18:637–649
Ramos V, Almeida F (2004) Artificial ant colonies in digital image habitats-a mass behaviour effect study on pattern recognition. arXiv:cs/0412086
Merkle D, Middendorf M (2003) Ant colony optimization with global pheromone evaluation for scheduling a single machine. Appl Intell 18:105–111
Hartigan JA, Wong MA (1979) Algorithm AS 136: a k-means clustering algorithm. J R Stat Soc, Ser C, Appl Stat 28:100–108
Brutzer S, Hoferlin B, Heidemann G (2011) Evaluation of background subtraction techniques for video surveillance. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1937–1944
Wu M, Peng X (2010) Spatio-temporal context for codebook-based dynamic background subtraction. AEÜ, Int J Electron Commun 64:739–747
Barnich O, Van Droogenbroeck M (2011) ViBe: a universal background subtraction algorithm for video sequences. IEEE Trans Image Process 20:1709–1724
Bandi SR, Varadharajan A, Masthan M (2012) Performance evaluation of various foreground extraction algorithms for object detection in visual surveillance. Comput Eng Res 2:1339–1443
Smal I, Draegestein K, Galjart N, Niessen W, Meijering E (2008) Particle filtering for multiple object tracking in dynamic fluorescence microscopy images: application to microtubule growth analysis. IEEE Trans Med Imaging 27:789–804
Juang RR, Levchenko A, Burlina P (2009) Tracking cell motion using GM-PHD. In: IEEE international symposium on biomedical imaging: from nano to macro, ISBI’09, pp 1154–1157
Lu M, Xu B, Sheng A (2012) Cell automatic tracking technique with particle filter. In: Advances in swarm intelligence. Springer, Berlin, pp 589–595
Acknowledgements
This work is supported by national natural science foundation of China (No. 61273312), natural science foundation of Jiangsu province (No. BK2010261), and partially supported by national natural science foundation of China (No. 61104186).
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
Proof
The function q(t) in Eq. (9) can be rewritten as
Take a constant λ, let λ−Pλ=PR, then we have
Then, the Eq. (14) is reduced to
Due to q(0)=q 0, then
Substituting Eq. (18) into Eq. (15), we have
where A=q 0−λ,B=R+λ are constants, let ν is constant
The Eq. (18) can be rewritten as
Case 1: If ρ≠P, let κ is constant
Then Eq. (21) can be rewritten as
The above form can be rewritten as
where C is constant, due to τ 0=τ(0), then C=P(τ 0−ν)−κ, so we have
Due to ρ,P∈(0,1), when t>0, we have
So, we say,τ(t) is bounded
Case 2: If ρ=E, Then Eq. (21) can be rewritten as
The above form can be rewritten as
where C is constant, then
Due to P∈(0,1), we say τ(t) is bounded.
Rights and permissions
About this article
Cite this article
Lu, M., Xu, B., Sheng, A. et al. Modeling analysis of ant system with multiple tasks and its application to spatially adjacent cell state estimate. Appl Intell 41, 13–29 (2014). https://doi.org/10.1007/s10489-013-0496-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-013-0496-7