Measures for ranking cell trackers without manual validation

• We develop measures for assessing cell tracking quality without manual validation.
• Information available without manual validation includes distances between cells.
• We use the distances to estimate the precision and recall of the cell tracker.
• We evaluate our measures under a variety of cell tracking conditions.
• In practical scenarios, our performance measures correlate with traditional measures.

Cell tracking is often implemented as cell detection and data association steps. For a particular detection output it is a challenge to automatically select the best association algorithm. We approach this challenge by developing novel measures for ranking the association algorithms according to their performance without the need for a ground truth. We formulate tracking as a binary classification task and develop our principal measure (ED-score) based on the definitions of precision and recall. On a range of real cell videos tested, ED-score has a strong correlation (−0.87) with F-score. However, ED-score does not require a ground truth for computation.