Multi-feature-based Robust Cell Tracking
post-template-default,single,single-post,postid-17484,single-format-standard,bridge-core-2.3.9,qode-page-transition-enabled,ajax_fade,page_not_loaded,,qode-title-hidden,qode-theme-ver-29.3,qode-theme-bridge,qode_header_in_grid,wpb-js-composer js-comp-ver-6.2.0,vc_responsive,elementor-default,elementor-kit-16106

Multi-feature-based Robust Cell Tracking

We present a fully automated, adaptive, and robust feature-based cell tracking algorithm for the accurate detection and tracking of cells using time-lapse images. Our algorithm tackles measurement limitations twofold. First, we use Hessian filtering and adaptive thresholding to detect the cells in images, overcoming spatial feature variations among the existing cells without manually changing the input thresholds. Second, cell feature parameters are measured, including position, diameter, mean intensity, area, and orientation, and these parameters are simultaneously used to accurately track the cells between subsequent frames, even under poor temporal resolution. Our technique achieved a minimum of 92 percent detection and tracking accuracy, compared to 16 percent from Mosaic and Trackmate. Our improved method allows for extended tracking and characterization of heterogeneous cell behavior that are of particular interest for intravital imaging users.

Figure 1: The identified cells at the initial experimental (PhC-C2DL-PSC) image frame from (a) MP, (b) Trackmate, (c) Mosaic, and at the final image frame from (d) MP, (e) Trackmate, and (f) Mosaic. The performance from each algorithm with respect to (g) the number of detected cells across the image sequence and (h) total displacement dtotal measured per cell. The overlay of accumulated cell trajectories over the image sequence (PhC-C2DL-PSC) from (i) MP, (j) Trackmate, and (k) Mosaic. The scale bar shows 100 ┬Ám.
Figure 2: The direction-intensity histogram calculated using the individual cell trajectories obtained from (a) synthetic cells, (b) MitoGen, (c) PhC-C2DL-PSC, and (d) Ca1h invasion using MP, Mosaic, and Trackmate. A cell-pairing measurement efficiency with respect to varying (e) normalized displacement, (f) percent feature (mean intensity, orientation, and diameter) change per frame, and (g) cell population density per frame.

Published Paper

Data Repository

No Comments

Post A Comment