Abstract
Automatic tracking of Caenorhabditis elegans (C. egans) in standard Petri dishes is challenging due to high-resolution image requirements when fully monitoring a Petri dish, but mainly due to potential losses of individual worm identity caused by aggregation of worms, overlaps and body contact. To date, trackers only automate tests for individual worm behaviors, canceling data when body contact occurs. However, essays automating contact behaviors still require solutions to this problem. In this work, we propose a solution to this difficulty using computer vision techniques. On the one hand, a skeletonization method is applied to extract skeletons in overlap and contact situations. On the other hand, new optimization methods are proposed to solve the identity problem during these situations. Experiments were performed with 70 tracks and 3779 poses (skeletons) of C. elegans. Several cost functions with different criteria have been evaluated, and the best results gave an accuracy of 99.42% in overlapping with other worms and noise on the plate using the modified skeleton algorithm and 98.73% precision using the classical skeleton algorithm.
Highlights
On the one hand, a skeletonization method is applied to extract skeletons in overlap and contact situations
The intersection over the union (IoU) index was used to evaluate the percentage of success in tracking the worms and to compare both skeletonization methods
The area of worm bodies reconstructed from skeletons obtained manually and skeletons obtained with the two skeletonization methods was used to evaluate the IoU index
Summary
A skeletonization method is applied to extract skeletons in overlap and contact situations. This facilitates the study and treatment of aging, as well as age-related pathologies and neurodegenerative disorders in humans at advanced ages [2,3] Many of these studies have shown that automatic tracking applications based on computer vision systems help to reduce the manual cost of data acquisition and research hours, improving potential observation of the effects of drug trials [4] and improvements in lifespan or “shelflife” [5,6,7]. Group behavior assays are currently being performed, for example, research into the effect of 02 in food search analysis, and aggregation [11,12] These assays, like others, are visualized manually, due to the complexity of solving the identification problem during an overlapping or body contact of these worms. Plate noise was defined as segmentation errors due to edges, or opaque waste in the plate
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call