He Rong, You Zijing, Zhou Yongqiang, Chen Guilan, Diao Yanan, Jiang Xiantai, Ning Yunkun, Zhao Guoru, Liu Ying
Department of Rehabilitation Medicine, University of Hong Kong-Shenzhen Hospital, Shenzhen, China.
CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Research Center for Neural Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
Front Bioeng Biotechnol. 2024 Dec 23;12:1520831. doi: 10.3389/fbioe.2024.1520831. eCollection 2024.
Parkinson's disease (PD) is characterized by muscle stiffness, bradykinesia, and balance disorders, significantly impairing the quality of life for affected patients. While motion pose estimation and gait analysis can aid in early diagnosis and timely intervention, clinical practice currently lacks objective and accurate tools for gait analysis.
This study proposes a multi-level 3D pose estimation framework for PD patients, integrating monocular video with Transformer and Graph Convolutional Network (GCN) techniques. Gait temporal and spatial parameters were extracted and verified for 59 healthy elderly and PD patients, and an early prediction model for PD patients was established.
The repeatability of the gait parameters showed strong consistency, with most of the estimated parameters yielding an Intraclass Correlation Coefficient (ICC) greater than 0.70. Furthermore, these parameters exhibited a high correlation with VICON and ATMI results ( > 0.80). The classification model based on the extracted parameter features, using a Random Forest (RF) classifier, achieved an accuracy of 93.3%.
The proposed 3D pose estimation method demonstrates high reliability and effectiveness in providing accurate 3D human pose parameters, with strong potential for early prediction of PD.
This markerless method offers significant advantages in terms of low cost, portability, and ease of use, positioning it as a promising tool for monitoring and screening PD patients in clinical settings.
帕金森病（PD）的特征是肌肉僵硬、运动迟缓及平衡障碍，严重损害患者的生活质量。虽然运动姿态估计和步态分析有助于早期诊断和及时干预，但临床实践目前缺乏用于步态分析的客观准确工具。
本研究提出了一种针对帕金森病患者的多层次3D姿态估计框架，将单目视频与Transformer和图卷积网络（GCN）技术相结合。提取并验证了59名健康老年人和帕金森病患者的步态时空参数，并建立了帕金森病患者的早期预测模型。
步态参数的重复性显示出很强的一致性，大多数估计参数的组内相关系数（ICC）大于0.70。此外，这些参数与VICON和ATMI结果具有高度相关性（>0.80）。基于提取的参数特征，使用随机森林（RF）分类器的分类模型准确率达到93.3%。
所提出的3D姿态估计方法在提供准确的3D人体姿态参数方面显示出高可靠性和有效性，在帕金森病早期预测方面具有强大潜力。
这种无标记方法在低成本、便携性和易用性方面具有显著优势，使其成为临床环境中监测和筛查帕金森病患者的有前途的工具。
