TY - JOUR
T1 - Bradykinesia recognition in Parkinson's disease via single RGB video
AU - Lin, Bo
AU - Luo, Wei
AU - Luo, Zhiling
AU - Wang, Bo
AU - Deng, Shuiguang
AU - Yin, Jianwei
AU - Zhou, Mengchu
N1 - Funding Information:
This work is supported in part by the National Natural Science Foundation of China under Grant No.: 61772459, in part by the National Key Research and Development Program of China under Grant No.: 2017YFC1001703, in part by the National Science and Technology Major Project of China under Grant No.: 50-D36B02-9002-16/19, and in part by the Fundamental Research Funds for the Central Universities under Grant No.: 2018FZA118. Authors’ addresses: B. Lin, Z. Luo, and J. Yin, College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; emails: {rainbowlin, luozhiling}@zju.edu.cn, zjuyjw@cs.zju.edu.cn; W. Luo and B. Wang, Department of Neurology, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310009, China; emails: luoweirock@zju.edu.cn, wangke1121@163.com; S. Deng (Corresponding author), Department of Medical Oncology, First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China; email: dengsg@zju.edu.cn; M. Zhou, Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ 07102; email: mengchu.zhou@njit.edu. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. © 2020 Association for Computing Machinery. 1556-4681/2020/02-ART16 $15.00 https://doi.org/10.1145/3369438
Publisher Copyright:
© 2020 Association for Computing Machinery.
PY - 2020/2
Y1 - 2020/2
N2 - Parkinson's disease is a progressive nervous system disorder afflicting millions of patients. Among its motor symptoms, bradykinesia is one of the cardinal manifestations. Experienced doctors are required for the clinical diagnosis of bradykinesia, but sometimes they also miss subtle changes, especially in early stages of such disease. Therefore, developing auxiliary diagnostic methods that can automatically detect bradykinesia has received more and more attention. In this article, we employ a two-stage framework for bradykinesia recognition based on the video of patient movement. First, convolution neural networks are trained to localize keypoints in each video frame. These time-varying coordinates form motion trajectories that represent the whole movement. From the trajectory, we then propose novel measurements, namely stability, completeness, and self-similarity, to quantify different motor behaviors. We also propose a periodic motion model called PMNet. An encoder-decoder structure is applied to learn a low dimensional representation of a motion process. The compressed motion process and quantified motor behaviors are combined as inputs to a fully-connected neural network. Different from the traditional means, our solution extends the application scenario outside the hospital and can be easily transplanted to conduct similar tasks. A commonly used clinical assessment is served as a case study. Experimental results based on real-world data validate the effectiveness of our approach for bradykinesia recognition.
AB - Parkinson's disease is a progressive nervous system disorder afflicting millions of patients. Among its motor symptoms, bradykinesia is one of the cardinal manifestations. Experienced doctors are required for the clinical diagnosis of bradykinesia, but sometimes they also miss subtle changes, especially in early stages of such disease. Therefore, developing auxiliary diagnostic methods that can automatically detect bradykinesia has received more and more attention. In this article, we employ a two-stage framework for bradykinesia recognition based on the video of patient movement. First, convolution neural networks are trained to localize keypoints in each video frame. These time-varying coordinates form motion trajectories that represent the whole movement. From the trajectory, we then propose novel measurements, namely stability, completeness, and self-similarity, to quantify different motor behaviors. We also propose a periodic motion model called PMNet. An encoder-decoder structure is applied to learn a low dimensional representation of a motion process. The compressed motion process and quantified motor behaviors are combined as inputs to a fully-connected neural network. Different from the traditional means, our solution extends the application scenario outside the hospital and can be easily transplanted to conduct similar tasks. A commonly used clinical assessment is served as a case study. Experimental results based on real-world data validate the effectiveness of our approach for bradykinesia recognition.
KW - Bradykinesia
KW - Computer vision
KW - Parkinson's disease
KW - RGB video
KW - Time sequence analysis
UR - http://www.scopus.com/inward/record.url?scp=85079808823&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85079808823&partnerID=8YFLogxK
U2 - 10.1145/3369438
DO - 10.1145/3369438
M3 - Article
AN - SCOPUS:85079808823
SN - 1556-4681
VL - 14
JO - ACM Transactions on Knowledge Discovery from Data
JF - ACM Transactions on Knowledge Discovery from Data
IS - 2
M1 - 16
ER -