A PSO-based approach for multi-cell multi-parameter estimation

Due to various and unpredictable challenges occurring in studying the cycle of small size of multiple cells, such as varying number of cell population, cell morphological variation, and cell irregular motion, a particle swarm optimization (PSO) based approach is proposed for automatic estimation of biological cells´ contours and positions. The proposed approach is divided into two steps, i.e., the stage of approximate position estimation and the stage of accurate contour estimation of multiple cells, which are implemented by the PSO-based tracking module, PSO-based discovery module, and PSO-based contour module, respectively. The tracking procedure is tested over real cell image sequences and is shown to provide high accuracy both in position and contour estimations of each cell in various challenging cases. Furthermore, it is more competitive against the state-of-the-art multi-object tracking methods in terms of performance measures such as FAR, FNR, LTR, and LSR.