Deep learning for robust and flexible tracking in behavioral studies for C. elegans

• Type of Material: Article
• Authors: Kathleen Bates, Georgia Institute of Technology, Atlanta; Kim N Le, Georgia Institute of Technology, Atlanta; Hang Lu, Emory University
• Language: English
• Date: 2022-04-08
• Publisher: Public Library of Science (PLoS)
• Publication Version: Final Published Version
• Copyright Statement: © 2022 Bates et al
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1371/journal.pcbi.1009942
• Title of Journal or Parent Work: PLoS Computational Biology
• Volume: 18
• Issue: 4
• Grant/Funding Information: This study was funded by US NSF (1764406) and US NIH (R01AG056436, R01GM088333) grants to HL, US NIH F31 fellowship to KB (F31GM123662) and US NSF GRF to KL (DGE-1650044). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
• Keywords: Deep learning; behavioral studies
• Research Categories: Engineering, Biomedical

Abstract

Robust and accurate behavioral tracking is essential for ethological studies. Common methods for tracking and extracting behavior rely on user adjusted heuristics that can significantly vary across different individuals, environments, and experimental conditions. As a result, they are difficult to implement in large-scale behavioral studies with complex, heterogenous environmental conditions. Recently developed deep-learning methods for object recognition such as Faster R-CNN have advantages in their speed, accuracy, and robustness. Here, we show that Faster R-CNN can be employed for identification and detection of Caenorhabditis elegans in a variety of life stages in complex environments. We applied the algorithm to track animal speeds during development, fecundity rates and spatial distribution in reproductive adults, and behavioral decline in aging populations. By doing so, we demonstrate the flexibility, speed, and scalability of Faster R-CNN across a variety of experimental conditions, illustrating its generalized use for future large-scale behavioral studies.