Long-Term Deep Phenotyping of Behavioral Traits of Mental Disorders in Mice Using Homecage Monitoring

This paper outlines a comprehensive workflow for studying behavior of rodent cohorts in their home cages using video tracking and AI-supported image analysis. Key steps include the design of experimental setups with optimal camera and lighting configuration, video preprocessing, and animal tracking using contrast-based software or markerless pose estimation. In addition to supervised analysis, unsupervised pipelines remove bias from the interpretation of behaviors. Here, we propose a protocol that encompasses multiple pipelines for data acquisition and interpretation to ensure reproducible, high-quality data for neuroscience and behavioral research.