RFID-supported video tracking for automated analysis of social behaviour in groups of mice

Peleh, Tatiana; Xue-sheng, Bai; Kas, Martien; Hengerer, Bastian

doi:10.1016/j.jneumeth.2019.108323

Cited by 47 publications

(39 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The possible methods used for activity monitoring in animals include, but are not limited to, video tracking, 9 piezoelectric floor sensors, 10 infrared or laser beam grids, 11 implanted accelerometers, 12 activity telemeters, 13 voluntary wheel running, 14 and neck or limb electromyography (EMG) recordings 15 . Piezoelectric floor sensors, laser grids, accelerometers, and telemeters record all types of movement but are limited in further classifying movement context.…”

Section: Resultsmentioning

confidence: 99%

Consensus Guidelines on Rodent Models of Restless Legs Syndrome

et al. 2020

View full text Add to dashboard Cite

Restless legs syndrome (RLS) is a chronic sensorimotor disorder diagnosed by clinical symptoms. It is challenging to translate the diagnostic self‐reported features of RLS to animals. To help researchers design their experiments, a task force was convened to develop consensus guidelines for experimental readouts in RLS animal models. The RLS clinical diagnostic criteria were used as a starting point. After soliciting additional important clinical features of RLS, a consensus set of methods and outcome measures intent on capturing these features—in the absence of a face‐to‐face interview—was generated and subsequently prioritized by the task force. These were, in turn, translated into corresponding methods and outcome measures for research on laboratory rats and mice and used to generate the final recommendations. The task force recommended activity monitoring and polysomnography as principal tools in assessing RLS‐like behavior in rodents. Data derived from these methods were determined to be the preferred surrogate measures for the urge to move, the principal defining feature of RLS. The same tools may be used to objectively demonstrate sleep‐state features highly associated with RLS, such as sleep disturbance and number and periodicity of limb movements. Pharmacological challenges and dietary or other manipulations that affect iron availability are desirable to aggravate or improve RLS‐like behavior and lend greater confidence that the animal model being proffered replicates key clinical features of RLS. These guidelines provide the first consensus experimental framework for researchers to use when developing new rodent models of RLS. © 2020 International Parkinson and Movement Disorder Society

show abstract

Section: Resultsmentioning

confidence: 99%

Consensus Guidelines on Rodent Models of Restless Legs Syndrome

et al. 2020

View full text Add to dashboard Cite

show abstract

“…RFID technology is increasingly used to study rodent social behavior in controlled laboratory settings (Freund et al 2013;Howerton et al 2012;Peleh et al 2019;Weissbrod et al 2013) and semi-natural to natural environments (König et al 2015;Smith et al 2018). However, many of these studies employ artificial habitats, burrows or nest boxes, while fewer record RFID activity at natural features of the environment.…”

Section: Discussionmentioning

confidence: 99%

Automated tracking reveals the social network of beach mice and their burrows

Bedford

Gable

et al. 2021

Preprint

View full text Add to dashboard Cite

Evolutionary biologists have long sought to understand the selective pressures driving phenotypic evolution. While most experimental data come from the study of morphological evolution, we know much less about the ultimate drivers of behavioral variation. Among the most striking examples of behavioral evolution are the long, complex burrows constructed by oldfield mice ( Peromyscus polionotus ssp.). Yet how these mice use burrows in the wild, and whether burrow length may affect fitness, remains unknown. A major barrier to studying behavior in the wild has been the lack of technologies to continuously monitor — in this case, nocturnal and underground — behavior. Here, we designed and implemented a novel radio frequency identification (RFID) system to track patterns of burrow use in a natural population of beach mice. We combine RFID monitoring with burrow measurements, genetic data, and social network analysis to uncover how these monogamous mice use burrows under fully natural ecological and social conditions. We first found that long burrows provide a more stable thermal environment and have higher juvenile activity than short burrows, underscoring the likely importance of long burrows for rearing young. We also find that adult mice consistently use multiple burrows throughout their home range and tend to use the same burrows at the same time as their genetic relatives, suggesting that inclusive fitness benefits may accrue for individuals that construct and maintain multiple burrows. Our study highlights how new automated tracking approaches can provide novel insights into animal behavior in the wild.

show abstract

“…Although SimBA can analyze two animals of different coat colors, or a single animal of any coat color, our method does not currently transfer to two or more animals of the same coat color. Current gold-standard methods for performing individual identifications in groups of similarly coat-colored individuals use RFID-data and depth camera systems 21,22 . Additional advances in machine vision has also addressed identification issues through dual segmentation/identification networks 75,76 or by including measures of optical flow 77 and part affinity fields 73 .…”

Section: Future Directions and Challengesmentioning

confidence: 99%

“…To overcome this, a range of elegant open-source tools ( Table 1) that use various forms of computer vision with synchronized RFID-tracking data and/or depth camera or multi-camera 3D systems have been developed for automated and precise classifications of animal behaviour [19][20][21][22][23][24] . Such methods can permit online classifications in semi-natural environments and are a foundation for impending closed-loop monitoring and forecasting systems 25 in behavioural neuroscience, but do require significant investment in specialized hardware and a working knowledge of computer science approaches.…”

Section: Introductionmentioning

confidence: 99%

Simple Behavioral Analysis (SimBA) – an open source toolkit for computer classification of complex social behaviors in experimental animals

Nilsson

Goodwin

Choong

et al. 2020

Preprint

193

191

View full text Add to dashboard Cite

Aberrant social behavior is a core feature of many neuropsychiatric disorders, yet the study of complex social behavior in freely moving rodents is relatively infrequently incorporated into preclinical models. This likely contributes to limited translational impact. A major bottleneck for the adoption of socially complex, ethology-rich, preclinical procedures are the technical limitations for consistently annotating detailed behavioral repertoires of rodent social behavior. Manual annotation is subjective, prone to observer drift, and extremely time-intensive. Commercial approaches are expensive and inferior to manual annotation. Open-source alternatives often require significant investments in specialized hardware and significant computational and programming knowledge. By combining recent computational advances in convolutional neural networks and pose-estimation with further machine learning analysis, complex rodent social behavior is primed for inclusion under the umbrella of computational neuroethology.Here we present an open-source package with graphical interface and workflow (Simple Behavioral Analysis, SimBA) that uses pose-estimation to create supervised machine learning predictive classifiers of rodent social behavior, with millisecond resolution and accuracies that can out-perform human observers. SimBA does not require specialized video acquisition hardware nor extensive computational background. Standard descriptive statistical analysis, along with graphical region of interest annotation, are provided in addition to predictive classifier generation. To increase ease-of-use for behavioural neuroscientists, we designed SimBA with accessible menus for pre-processing videos, annotating behavioural training datasets, selecting advanced machine learning options, robust classifier validation functions and flexible visualizations tools. This allows for predictive classifier transparency, explainability and tunability prior to, and during, experimental use. We demonstrate that this approach is flexible and robust in both mice and rats by classifying social behaviors that are commonly central to the study of brain function and social motivation. Finally, we provide a library of poseestimation weights and behavioral predictive classifiers for resident-intruder behaviors in mice and rats. All code and data, together with detailed tutorials and documentation, are available on the SimBA GitHub repository.Graphical abstractSimBA graphical interface (GUI) for creating supervised machine learning classifiers of rodent social behavior.(a) Pre-process videos. SimBA supports common video pre-processing functions (e.g., cropping, clipping, sampling, format conversion, etc.) that can be performed either on single videos, or as a batch.(b) Managing poseestimation data and creating classification projects. Pose-estimation tracking projects in DeepLabCut and DeepPoseKit can be either imported or created and managed within the SimBA graphical user interface, and the tracking results are imported into SimBA classification projects.SimBA also supports userdrawn region-of-interests (ROIs) for descriptive statistics of animal movements, or as features in machine learning classification projects.(c) Create classifiers, perform classifications, and analyze classification data. SimBA has graphical tools for correcting poseestimation tracking inaccuracies when multiple subjects are within a single frame, annotating behavioral events from videos, and optimizing machine learning hyperparameters and discrimination thresholds. A number of validation checkpoints and logs are included for increased classifier explainability and tunability prior to, and during, experimental use. Both detailed and summary data are provided at the end of classifier analysis. SimBA accepts behavioral annotations generated elsewhere (such as through JWatcher) that can be imported into SimBA classification projects.(d) Visualize classification results. SimBA has several options for visualizing machine learning classifications, animal movements and ROI data, and analyzing the durations and frequencies of classified behaviors.See the SimBA GitHub repository for a comprehensive documentation and user tutorials.

show abstract

RFID-supported video tracking for automated analysis of social behaviour in groups of mice

Cited by 47 publications

References 30 publications

Consensus Guidelines on Rodent Models of Restless Legs Syndrome

Consensus Guidelines on Rodent Models of Restless Legs Syndrome

Automated tracking reveals the social network of beach mice and their burrows

Simple Behavioral Analysis (SimBA) – an open source toolkit for computer classification of complex social behaviors in experimental animals

Contact Info

Product

Resources

About