Data-driven Detection of Movement Impairments

Stroke research heavily relies on rodent behavior when assessing underlying disease mechanisms and treatment efficacy. Although functional motor recovery is considered the primary outcome, tests in rodents are still poorly reproducible, and often unsuitable for unravelling the complex behavior after injury. Ruslan Rust of the Institute for Regenerative Medicine at University of Zurich and colleagues now provide a comprehensive 3D gait analysis of mice after focal cerebral ischemia based on a deep learning-based software.

Weber and colleagues demonstrated high precision 3D tracking of ten body parts including all relevant joints and reference landmarks in mice. Building on this rigor motion tracking, a comprehensive post-analysis with >100 parameters unveiled new biologically relevant differences in locomotor profiles after a stroke over a time course of three weeks. Given the number of parameters raised in this setting, this approach might be particularly suited to assess treatment efficacy of drug interventions in preclinical stroke research. Watch an example of the gait analysis:

By: Ruslan Rust, Institute for Regenerative Medicine, University of Zurich.

Reference: Weber, R.Z., Mulders, G., Kaiser, J., Tackenberg, C. and Rust, R. Deep learning based behavioral profiling of rodent stroke recovery. BMC Biology (2022).