Open-source software for automated rodent behavioral analysis

Abstract

Rodent behavioral analysis is a major specialization in experimental psychology and behavioral neuroscience. Rodents display a wide range of species-specific behaviors, not only in their natural habitats but also under behavioral testing in controlled laboratory conditions. Detecting and categorizing these different kinds of behavior in a consistent way is a challenging task. Observing and analyzing rodent behaviors manually limits the reproducibility and replicability of the analyses due to potentially low inter-rater reliability. The advancement and accessibility of object tracking and pose estimation technologies led to several open-source artificial intelligence (AI) tools that utilize various algorithms for rodent behavioral analysis. These software provide high consistency compared to manual methods, and offer more flexibility than commercial systems by allowing custom-purpose modifications for specific research needs. Open-source software reviewed in this paper offer automated or semi-automated methods for detecting and categorizing rodent behaviors by using hand-coded heuristics, machine learning, or neural networks. The underlying algorithms show key differences in their internal dynamics, interfaces, user-friendliness, and the variety of their outputs. This work reviews the algorithms, capability, functionality, features and software properties of open-source behavioral analysis tools, and discusses how this emergent technology facilitates behavioral quantification in rodent research.

Rodent tests of depression and anxiety: Construct validity and translational relevance

“…The analysis of facial expressions soon emerged as a valuable tool for assessing the affective states of rodents, encompassing both negative (Defensor et al, 2012 ) and positive states (Finlayson et al, 2016 ). The availability of automated analysis tools that utilize artificial intelligence (Isik & Unal, 2023 ) transformed this labor-intensive technique to a relatively straightforward and reliable task. In a recent study, facial expressions of mice during exposure to aversive or rewarding stimuli were automatically detected and categorized via use of machine learning (Dolensek et al, 2020 ).…”

“…Recognizing the potential of posture analysis and employing machine learning techniques to analyze posture data across various tests has been proposed as a “pose-tracking revolution” (von Ziegler et al, 2020 ). Many open-source, AI-based software has been developed in recent years to track rodents during behavioral testing, perform pose estimation, and categorize their behaviors (refer to Isik & Unal, 2023 for a review). These novel tools did not only facilitate and accelerate behavioral analysis, but also unveiled micro-behavioral patterns that were otherwise unnoticeable to the naked human eye during manual analysis.…”

STPoseNet: A real-time spatiotemporal network model for robust mouse pose estimation

“… 11 As a result, there is an increasing focus on developing automated, reliable, and accurate methods for analyzing experimental videos of mice, particularly in the identification of mouse behavioral postures and the implementation of real-time interactive closed-loop experimental designs. 12 , 13 …”

Automated procedure to detect subtle motor alterations in the balance beam test in a mouse model of early Parkinson’s disease

“…Animal performances in the balance beam test can be quantified manually by measuring the time it takes for the mouse to traverse the beam, the maximum distance covered, the number of times a hind paw comes off the top of the beam, and the number of falls 10 , 11 . Nevertheless, manual analysis of rodent behaviour is limited by the reproducibility and repeatability of the findings due to low levels of inter-rater reliability between different observers 12 , as well as being highly labour intensive, susceptible to observer drift and limited to our senses 13 , 14 . Recent advances in the field of computational neuroethology have made it possible to automate animal behaviour analyses by capturing animal postures (pose estimation) and predicting behavioural patterns (behavioural classification) in recorded videos 13 , 15 , 16 .…”

“…Recent advances in the field of computational neuroethology have made it possible to automate animal behaviour analyses by capturing animal postures (pose estimation) and predicting behavioural patterns (behavioural classification) in recorded videos 13 , 15 , 16 . Such powerful tools are transforming research in terms of animal tracking, behaviour detection and classification, by utilising advances in computer vision, deep learning and computational algorithms like deep neural networks 12 , 17 . However, using these automated methods often require extensive computational knowledge and programming skills 14 .…”