Markerless analysis of hindlimb kinematics in spinal cord-injured mice through deep learning
Introduction
Potential treatments for spinal cord injury commonly occur in rodent models. In recent decades, various interventions have been developed, including cell replacement therapy (Kajikawa et al., 2020; Kamata et al., 2021; Kojima et al., 2019; Nori et al., 2011; Okubo et al., 2018; Tsuji et al., 2019), a combination of multiple treatments (Ito et al., 2018; Maier et al., 2009), and genetically modified animals (Takeoka et al., 2014), and consequently, gait patterns after interventions have become more diverse and complex. Thus, these rodent studies require reliable, consistent, and objective behavioral assessments of gait function to accurately determine the effects of these treatments.
Kinematic analyses using reflective markers attached on animals’ skin have been used for evaluating locomotor deficits; however, this marker-based approach has some issues to consider in both recording and analysis. First, the attached markers are potentially distracting to animals (Pérez-Escudero et al., 2014). Moreover, it is empirically known that SCI mice tend to have low motivation for stable walking, causing them to fail to complete their walking task. Second, reflective markers placed on distal joints such as the toe or the metatarsophalangeal (MTP) joint may affect the natural gait of mice. Notably, this effect is even more pronounced in SCI mice that have difficulty locomotion. Finally, the marker positions are often manually digitized afterward, which is a labor-intensive and time-consuming procedure that constrains the number of groups, mice, and evaluations that can be included within the experimental plan.
Besides the recording and analysis issues described above, reflective markers placed on the skin surface relative to the bone are a primary factor limiting the resolution of detailed joint movements. Soft tissue movement around the knee joint is the principal source of error during locomotion in rodents (Bauman and Chang, 2010). Previous kinematic analyses have either neglected to account for skin error or utilized a triangulation algorithm for estimating the knee joint position (Filipe et al., 2006).
Developing markerless-based analyses would avoid the drawbacks of reflective marker-based analyses (Sheets et al., 2013). Recently, machine learning-based motion capture has become common. In the present study, we demonstrate that markerless kinematic analysis using deep learning can quantitatively assess locomotion in intact and SCI mice. Using this method, we present a variety of gait parameters and show that these parameters change robustly after SCI.
Section snippets
Animals
Female C57Bl6/J mice (8 weeks old, 18–20 g, n = 30) were used in the present study. The animals were housed under a 12 h light/dark cycle, with food and water ad libitum. All animal experiments were approved by the ethics committee of Keio University (#13020) and were in accordance with the guidelines of the National Institutes of Health.
Experimental procedures
Mice were anesthetized with an intraperitoneal injection of ketamine (100 mg/kg) and xylazine (10 mg/kg), and a contusive SCI was produced at Th10 using an IH
Deep neural network performance
The datasets generated in this study used training images of intact mice for tracking the location of the joints in intact mice (Fig. 1), and training images of SCI mice to track the joints’ location in SCI mice. The time required for manual labeling was approximately 1 h per 100 images. To verify whether a single dataset can track the labeled body parts of intact and SCI mice, we created combined datasets using training images of intact and SCI mice.
Discussion
In the present study, we demonstrated a markerless 2D kinematic analysis in intact and SCI mice using a deep learning approach to evaluate the abnormal gait caused by SCI accurately. Using this method, we were able to record enough steps to analyze from SCI mice which tend to have low motivation for stable walking, to exclude the effect of distracting markers on natural gait, to reduce the error by skin movement, and to avoid the hand-digitized joint tracking procedure which is time-consuming
Author contributions
RS performed the animal surgeries. RS, YS, and TK performed behavioral tests. YS, TK, and MS analyzed the data. YS, TK, MS, NN, JU, MN, and HO designed the study. MS, NN, JU, MN, and HO supervised the study.
This work has not been published elsewhere and is not under review with another journal.
Declaration of Competing Interest
HO is a compensated scientific consultant of San Bio, Co., Ltd., and K Pharma, Inc., and has received research funding from Dainippon Sumitomo Pharmaceutical Co., Ltd. MN is a compensated scientific consultant at K Pharma, Inc. JU is a founder and the Representative Director of the University Startup Company, Connect Inc., for the research, development, and sale of rehabilitation devices including the brain-computer interface. He received a salary from Connect Inc. and held shares in Connect
Acknowledgments
We thank Akito Kosugi and Seitaro Iwama for their technical assistance. This research was supported by AMED under grant No. JP21bm0204001h (to H.O. and M.N.), and JSPS KAKENHI Grant Nos. JP19H03983, 19K16190, and JP20H05480.
References (26)
- et al.
High-speed x-ray video demonstrates significant skin movement errors with standard optical kinematics during rat locomotion
J. Neurosci. Methods
(2010) - et al.
Kinematic gait parameters are highly sensitive measures of motor deficits and spinal cord injury in mice subjected to experimental autoimmune encephalomyelitis
Behav. Brain Res.
(2017) - et al.
Effect of skin movement on the analysis of hindlimb kinematics during treadmill locomotion in rats
J. Neurosci. Methods
(2006) - et al.
Treatment with a gamma-secretase inhibitor promotes functional recovery in human ipsc- derived transplants for chronic spinal cord injury
Stem Cell Rep.
(2018) - et al.
Main functional roles of knee flexors/extensors in able-bodied gait using principal component analysis (i)
Knee
(2002) - et al.
Muscle spindle feedback directs locomotor recovery and circuit reorganization after spinal cord injury
Cell
(2014) - et al.
Kinematic study of locomotor recovery after spinal cord clip compression injury in rats
J. Neurotrauma
(2011) - et al.
Basso mouse scale for locomotion detects differences in recovery after spinal cord injury in five common mouse strains
J. Neurotrauma
(2006) - et al.
The need for speed in rodent locomotion analyses
Anat. Rec. (Hoboken)
(2014) - et al.
Performance of locomotion and foot grasping following a unilateral thoracic corticospinal tract lesion in monkeys (macaca mulatta)
Brain
(2005)
Transformation of nonfunctional spinal circuits into functional states after the loss of brain input
Nat. Neurosci.
Delving deep into rectifiers: surpassing human-level performance on imagenet classification
Proceedings of the IEEE International Conference on Computer Vision
Lotus inhibits neuronal apoptosis and promotes tract regeneration in contusive spinal cord injury model mice
eNeuro
Cited by (2)
The development of methods to evaluate experimental animal behavior using images
2023, Folia Pharmacologica JaponicaTreadmill Training for Common Marmoset to Strengthen Corticospinal Connections After Thoracic Contusion Spinal Cord Injury
2022, Frontiers in Cellular Neuroscience
- 1
These authors contributed equally to this work.