4.7 Article

A Self-Supervised Metric Learning Framework for the Arising-From-Chair Assessment of Parkinsonians With Graph Convolutional Networks

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2022.3163959

关键词

Videos; Task analysis; Bones; Convolution; Training; Representation learning; Sun; Parkinson's disease; video-based assessment; self-supervised learning; metric learning; graph convolutional network

资金

  1. National Natural Science Foundation of China [62171273]
  2. Natural Science Foundation of Shanghai [22ZR1432100]
  3. Med-Engineering Crossing Foundation from Shanghai Jiao Tong University [AH0820009, YG2022QN007]

向作者/读者索取更多资源

This paper proposes a vision-based method for automated assessment of Parkinson's disease motor symptoms. By using a self-supervised metric learning scheme and a graph convolutional network, it improves the spatial-temporal representations of human skeleton sequences extracted from videos. The method achieves effective aggregation of skeletal joint features and maximizes the potential consistency between joint and bone information streams. Experimental results demonstrate the superiority of this method over existing sensor-based methods, making it a reliable tool for real-time PD diagnosis or remote continuous monitoring.
The onset and progression of Parkinson's disease (PD) gradually affect the patient's motor functions and quality of life. The PD motor symptoms are usually assessed using the Movement Disorder Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Automated MDS-UPDRS assessment has been recently required as an invaluable tool for PD diagnosis and telemedicine, especially with the recent novel coronavirus pandemic outbreak. This paper proposes a novel vision-based method for automated assessment of the arising-from-chair task, which is one of the key MDS-UPDRS components. The proposed method is based on a self-supervised metric learning scheme with a graph convolutional network (SSM-GCN). Specifically, for human skeleton sequences extracted from videos, a self-supervised intra-video quadruplet learning strategy is proposed to construct a metric learning formulation with prior knowledge, for improving the spatial-temporal representations. Afterwards, a vertex-specific convolution operation is designed to achieve effective aggregation of all skeletal joint features, where each joint or feature is weighted differently based on its relative factor of importance. Finally, a graph representation supervised mechanism is developed to maximize the potential consistency between the joint and bone information streams. Experimental results on a clinical dataset demonstrate the superiority of the proposed method over the existing sensor-based methods, with an accuracy of 70.60% and an acceptable accuracy of 98.65%. The analysis of discriminative spatial connections makes our predictions more clinically interpretable. This method can achieve reliable automated PD assessment using only easily-obtainable videos, thus providing an effective tool for real-time PD diagnosis or remote continuous monitoring.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据