Proof-reading guidance in cell tracking by sampling from tracking-by-assignment models

Automated cell tracking methods are still error-prone. On very large data sets, uncertainty measures are thus needed to guide the expert to the most ambiguous events so these can be corrected with minimal effort. We present two easy-to-use methods to sample multiple proposal solutions from a tracking-by-assignment graphical model and experimentally evaluate the benefits of the uncertainty measures derived. Expert time for proof-reading is reduced greatly compared to random selection of predicted events.