This page is devoted to our recently developed 2D contour-based image registration approach for compensation of nucleus motion and deformation in fluorescence microscopy time-lapse sequences.
The analysis of foci motion is a complex problem as living cells are moving and deforming during the imaging process. The observed motion of subcellular foci consists of two components: local motion of the foci and global motion of the nucleus, which includes nucleus displacement and deformation. To determine information about the pure subcellular foci motion, the global motion of the nucleus needs to be compensated. This is usually done by means of image registration. Namely all images of a dynamic image sequence are normalized to some reference time point (usually the first image of the sequence).
Our method is well suitable for the compensation on cell (or nucleus) motion in Single Particle Tracking (SPT) tasks. The source codes are available at gitlab.
The evaluation datasets together with the ground truth used in [Sorokin et al., ISBI2014] and [Sorokin et al., IEEE TMI 2018] can be found here:
The resources provided are free of charge for noncommerical and research purposes. Their use for any other purpose is generally possible, but solely with the explicit permission of the authors. In case of any questions, please do not hesitate to contact us at email@example.com and firstname.lastname@example.org.
In addition, you are expected to include adequate references whenever you present or publish results that are based on the resources provided.
Registration method and evaluation dataset (SeqA):
Evaluation dataset (SeqB):
Dmitry V. Sorokin, Jana Suchankova, Eva Bartova, and Pavel Matula. Visualizing stable features in live cell nucleus for evaluation of the cell global motion compensation. In Folia Biologica, 60, pp. 45–49, 2014.
Alexandr Y. Kondratiev and Dmitry V. Sorokin. Automatic detection of laser-induced structures in live cell fluorescent microscopy images using snakes with geometric constraints. In IEEE International Conference on Pattern Recognition (ICPR'2016), pp. 326–331, 2016.
This work was supported by the Czech Science Foundation project 302/12/G157, Russian Science Foundation grant 17-11-01279, and Federal Ministry of Education and Research (BMBF) project ImmunoQuant (e:Bio).