Related Experiment Video
Updated: Jun 14, 2025
07:21
Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury
Published on: May 27, 2022
3.1K
A deep learning-based approach for unbiased kinematic analysis in CNS injury
Maureen C Ascona1, Ethan Kim Tieu1, Erick Gonzalez-Vega1
1The Miami Project to Cure Paralysis, Department of Neurological Surgery, University of Miami Miller School of Medicine, Miami, FL, USA.
Experimental Neurology
|September 6, 2024
Summary
New deep-learning tools, MotorBox and MotoRater, offer objective kinematic analysis for mouse locomotion after spinal cord injury (SCI). These systems improve upon traditional methods, enhancing the accuracy and reproducibility of functional assessment in SCI research.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Animal Models of Disease
Background:
- Traumatic spinal cord injury (SCI) affects over 300,000 individuals in the US, leading to sensorimotor deficits and paralysis.
- Despite advancements in understanding SCI pathology and identifying therapeutic targets, clinical translation of treatments remains limited.
- Current functional assessment methods, like the Basso Mouse Scale (BMS), have limitations in sensitivity, reproducibility, and objectivity.
Purpose of the Study:
- To develop and validate novel, markerless kinematic analysis systems for assessing mouse locomotion after SCI.
- To overcome the shortcomings of traditional behavioral assessment scales by introducing objective, data-driven metrics.
- To enhance the accuracy, sensitivity, and reproducibility of functional outcome measures in SCI research.
Main Methods:
- Developed two markerless kinematic analysis paradigms, MotorBox (custom chamber) and MotoRater (commercial device), using DeepLabCut deep-learning algorithms.
- Validated the MotorBox and MotoRater systems by comparing their performance against the established Basso Mouse Scale (BMS) in mice with SCI.
- Extracted detailed metrics of mouse movement and gait to quantify locomotor function post-injury.
Main Results:
- The MotorBox and MotoRater systems provide accurate and sensitive representations of mouse locomotor function following SCI.
- These deep-learning-based kinematic analyses effectively eliminate investigator bias and variability inherent in traditional scoring methods.
- The extracted gait and movement metrics offer a comprehensive view of functional recovery.
Conclusions:
- MotorBox and MotoRater represent significant advancements in objective functional assessment for SCI research.
- Integrating these kinematic tools with traditional scales like BMS can provide richer, more reliable data on SCI outcomes.
- These improved assessment methods are crucial for increasing the rigor and success rate of clinical translation for SCI therapies.
