Deep neural networks enable quantitative movement analysis using single-camera videos
Deep neural networks enable quantitative movement analysis using single-camera videos
复制标题
DOI：
10.1038/s41467-020-17807-z
复制
发表时间：
2020-08-13
影响因子：
16.6
通讯作者：
Schwartz, Michael H.
中科院分区：
文献类型：
--
作者：
Kidzinski, Lukasz;Yang, Bryan;Schwartz, Michael H.
许多神经和肌肉骨骼疾病损害运动，限制了人们的功能和社会参与。运动的定量评估对医疗决策至关重要，但目前只有昂贵的运动捕捉系统和训练有素的人员才有可能。在这里，我们提出了一种用于从患者的普通视频预测临床相关运动参数的方法。我们的机器学习模型预测的参数包括步行速度（r=0.73），节奏（r=0.79），最大伸展时的膝关节屈曲角度（r=0.83）和步态偏差指数（GDI），步态障碍的综合指标（r=0.75）。这些相关性值接近我们的患者人群中这些指标的自然变异性所施加的准确性的理论极限。我们使用商用相机量化步态病理的方法增加了在诊所和家中进行定量运动分析的机会，并使研究人员能够对神经和肌肉骨骼疾病进行大规模研究。
Many neurological and musculoskeletal diseases impair movement, which limits people's function and social participation. Quantitative assessment of motion is critical to medical decision-making but is currently possible only with expensive motion capture systems and highly trained personnel. Here, we present a method for predicting clinically relevant motion parameters from an ordinary video of a patient. Our machine learning models predict parameters include walking speed (r=0.73), cadence (r=0.79), knee flexion angle at maximum extension (r=0.83), and Gait Deviation Index (GDI), a comprehensive metric of gait impairment (r=0.75). These correlation values approach the theoretical limits for accuracy imposed by natural variability in these metrics within our patient population. Our methods for quantifying gait pathology with commodity cameras increase access to quantitative motion analysis in clinics and at home and enable researchers to conduct large-scale studies of neurological and musculoskeletal disorders.