A method for reliably tracking multiple cells during collision.
Incorporated Kalman filter and multiple hypotheses for cases of no-collision, collision, during-collision and post-collision.
Improve when is compared to a previously proposed multiple cell tracking method.
S. J. Schmugge, S. Keller, N.R. Nguyen, R. Souvenir, T. H. Huynh, M. Clemens, M. C. Shin. "Segmentation of Vessels Cluttered with Cells using a Physics based Model". 11th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), New York, September 6-10 2008.
(submitting) N.R. Nguyen, S. Keller, T.H. Huynh, M.C. Shin. “Tracking Colliding Cells”. Microscopic Image Analysis with Applications in Biology (MIAAB), NIH Campus, Bethesda, MD September 03-04 2009.
QUESTIONS / SUGGESTIONS
Compare against Eden et al RMSE : root mean squared errors of position PTP : Positions tracked percentage TL : Track length As we compare our method to a previously published paper of Eden et al Collision Cases Only All Data Eden’s Method This Method Improvement Eden’s Method This Method Improvement RMSE (pixel) 14.6 8.9 40% 7.3 7.0 4% PTP (%) 61.5 93.0 51% 71.9 80.6 12% TL (frames) 7.3 12.6 71% 8.6 13.9 60%