DeepBhvTracking: A Novel Behavior Tracking Method for Laboratory Animals Based on Deep Learning

Abstract

Behavioral measurement and evaluation are broadly used to understand brain functions in neuroscience, especially for investigations of movement disorders, social deficits, and mental diseases. Numerous commercial software and open-source programs have been developed for tracking the movement of laboratory animals, allowing animal behavior to be analyzed digitally. In vivo optical imaging and electrophysiological recording in freely behaving animals are now widely used to understand neural functions in circuits. However, it is always a challenge to accurately track the movement of an animal under certain complex conditions due to uneven environment illumination, variations in animal models, and interference from recording devices and experimenters. To overcome these challenges, we have developed a strategy to track the movement of an animal by combining a deep learning technique, the You Only Look Once (YOLO) algorithm, with a background subtraction algorithm, a method we label DeepBhvTracking. In our method, we first train the detector using manually labeled images and a pretrained deep-learning neural network combined with YOLO, then generate bounding boxes of the targets using the trained detector, and finally track the center of the targets by calculating their centroid in the bounding box using background subtraction. Using DeepBhvTracking, the movement of animals can be tracked accurately in complex environments and can be used in different behavior paradigms and for different animal models. Therefore, DeepBhvTracking can be broadly used in studies of neuroscience, medicine, and machine learning algorithms.

Deconstruction of Vermal Cerebellum in Ramp Locomotion in Mice

“…Because of the camera wire and human interference in the task, the animal's movement in the L maze was tracked by a customized algorithm based on deep learning and a background subtraction algorithm—DeepBhvTracking. [ 59 ] To quantify the behavior, walking was divided into three groups based on the movement states and location in the L maze: 1) Uphill, defined by climbing up the ramp; 2) Downhill, defined by climbing down the ramp; 3) Flat walking. To avoid any other influence on flat walking, it was only measured in the vertical arm.…”

Using deep learning to study emotional behavior in rodent models

“…For research focused primarily on tracking kinematics or an animal’s location (e.g., presence within some ROI), this may be sufficient for the desired analyses. For example, DLC has been used in EPM, EZM, and open field tests to measure time spent in different areas, distance traveled, location, and velocity (Cui et al, 2021 ; Lu et al, 2021 ; Sun et al, 2021 ; Johnson et al, 2022 ; Sánchez-Bellot et al, 2022 ). However, pose estimation also offers the possibility of extracting more general information about an animal’s actions and behavioral state from moment to moment.…”

Computer vision analysis of mother-infant interaction identified efficient pup retrieval in V1b vasopressin receptor knockout mice

“…Recently, animal behaviors, such as eating, drinking, and grooming, were successfully detected using computer vision and deep learning in mice and other animals [32][33][34][35][36][37][38] . The main difficulty of analyzing mother-infant interaction lies in the ever-changing features of infants during the early phase of their development.…”