基于Kinect的帕金森病步态不对称性识别方法

doi:10.3969/j.issn.1006-9771.2018.07.007

《中国康复理论与实践》 ›› 2018, Vol. 24 ›› Issue (7): 795-801.doi: 10.3969/j.issn.1006-9771.2018.07.007

基于Kinect的帕金森病步态不对称性识别方法

张幼安¹, 侯振杰², 坎标³, 姚恩¹, 张家玮¹

1.常州大学华罗庚学院,江苏常州市 213164;
2.常州大学信息数理学院,江苏常州市 213164;
3.常州大学机械工程学院,江苏常州市 213164

收稿日期:2018-01-26 修回日期:2018-05-08 出版日期:2018-07-25 发布日期:2018-08-01
通讯作者: 侯振杰。E-mail: YAZhangwork@163.com
作者简介:张幼安(1996-),男,江苏泰兴市人,本科生。通讯作者：侯振杰(1973-),男,内蒙古呼和浩特市人,博士,教授,硕士生导师,主要研究方向：机器视觉。
基金资助:
1.国家自然科学基金项目(No. 61063021); 2.江苏省产学研前瞻性联合研究项目(No. BY2015027-12); 3.江苏省物联网移动互联技术工程重点实验室开放课题项目(No. JSWLW-2017-013)

Identification of Asymmetry Gait in Parkinson's Disease Based on Kinect

ZHANG You-an¹, HOU Zhen-jie², KAN Biao³, YAO En¹, ZHANG Jia-wei¹

1. Changzhou University Hua Loo-keng Honors College, Changzhou, Jiangsu 213164, China;
2. Changzhou University School of Information Science and Technology, Changzhou, Jiangsu 213164, China;
3. Changzhou University College of Mechanical Engineering, Changzhou, Jiangsu 213164, China

Received:2018-01-26 Revised:2018-05-08 Published:2018-07-25 Online:2018-08-01
Contact: HOU Zhen-jie. E-mail: YAZhangwork@163.com
Supported by:
Supported by National Natural Science Foundation of China (No. 61063021), Jiangsu Industry-University-Research Cooperation Program (No. BY2015027-12) and Jiangsu Key Laboratory of Internet of Things and Mobile Internet Open Project (No. JSWLW-2017-013)

摘要/Abstract

摘要： 目的开发一种基于深度图像的非接触式帕金森病步态不对称性识别方法,以辅助医疗诊断和评估,解决穿戴型传感设备费用高、影响正常生活且检查流程复杂的问题。方法 2016年7月至8月,对帕金森病患者8例和健康人10例,采用Kinect V2.0采集行走6 m的运动数据;对左右脚参数滤波处理后分别聚类,使用相似度矩阵算法分别计算健康人和帕金森病患者相似度值;使用隐马尔科夫模型验证该方法的识别效果。结果所有患者左右脚参数聚类序列相似度小于健康人;从患者中提取的14条数据,成功识别12条(85.71%);从健康人中提取的46条数据,成功区别35条(76.09%)。结论基于左右脚位移过程中步态参数聚类结果不对称性的非接触式识别方法,对于帕金森病患者有一定识别效果。

关键词: 帕金森病, 步态对称性, Kinect, 字符串相似度矩阵算法, 隐马尔可夫模型

Abstract: Objective To develop a non-contact identification method for gait asymmetry in Parkinson's disease based on depth image to assist medical diagnosis and assessment, to avoid the cost, impact on normal life, and complex process of high wear-out sensing equipment. Methods From July to August, 2016, eight patients with Parkinson's disease and ten healthy subjects were collected the gait parameters of walking six meters with Kinect V2.0. The parameters of left and right foot were filtered and clustered. Then similarity matrix algorithm was used to find the difference between healthy subject and patient similarity values. Finally, the recognition effect of this method was verified by Hidden Markov Model. Results The similarity of clustering sequences of left and right foot parameters was less in the patients than in the healthy individuals. There were twelve of 14 data identified in patients, and 35 of 46 in the healthy. Conclusion A non-contact identification method for the asymmetry of gait has been developed based on the parameter clustering results of left and right foot, which is some effective on identifying Parkinson's patients.

Key words: Parkinson's disease, gait symmetry, Kinect, matrix algorithm for string similarity, Hidden Markov Model

中图分类号:

R742.5

张幼安, 侯振杰, 坎标, 姚恩, 张家玮. 基于Kinect的帕金森病步态不对称性识别方法[J]. 《中国康复理论与实践》, 2018, 24(7): 795-801.

ZHANG You-an, HOU Zhen-jie, KAN Biao, YAO En, ZHANG Jia-wei. Identification of Asymmetry Gait in Parkinson's Disease Based on Kinect[J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2018, 24(7): 795-801.

参考文献

[1] Ellis JM, Fell MJ.Current approaches to the treatment of Parkinson's disease[J]. Bioorg Med Chem Lett, 2017, 27(18): 4247-4255.
[2] 刘疏影,陈彪. 帕金森病流行现状[J]. 中国现代神经疾病杂志, 2016, 16(2): 98-101.
[3] Dickson DW, Braak H, Duda JE, et al.Neuropathological assessment of Parkinson's disease: refining the diagnostic criteria[J]. Lancet Neurol, 2009, 8(12): 1150-1157.
[4] Simioni AC, Dagher A, Fellows LK.Compensatory striatal-cerebellar connectivity in mild-moderate Parkinson's disease[J]. Neuro Image Clin, 2015, 10: 54-62.
[5] 高中宝,王洁,王炜,等. 帕金森病诊断与治疗新进展[J]. 中国现代神经疾病杂志, 2015, 15(10): 777-781.
[6] 周琛,庞伟,吴岚. 针灸联合美多芭治疗帕金森病的临床效果和安全性分析[J]. 中国医药科学, 2016, 6(22): 11-13.
[7] Wu B, Han L, Sun BM, et al.Influence of deep brain stimulation of the subthalamic nucleus on cognitive function in patients with Parkinson's disease[J]. Neurosci Bull, 2014, 30(1): 153-161.
[8] 陈路. 培养肝肾复方治疗帕金森病及其肠功能障碍的疗效研究[D]. 北京:北京中医药大学, 2013.
[9] 刘峘,谢雁鸣,易丹辉,等. 帕金森综合征患者合并病特征与临床用药特点分析[J]. 中国中药杂志, 2014, 39(18): 3493-3498.
[10] Gray WK, Hildreth A, Bilclough JA, et al.Physical assessment as a predictor of mortality in people with Parkinson's disease: a study over 7 years[J]. Mov Disord, 2009, 24(13): 1934-1940.
[11] 刘志红,卢健军,郑文华,等. 帕金森病患者采用Synapsys静动态平衡仪进行平衡和步态训练的效果观察[J]. 护理学报, 2016, 23(2): 48-52.
[12] Goetz CG.The Unified Parkinson's Disease Rating Scale (UPDRS): status and recommendations[J]. Mov Disord, 2003, 18(7): 738-750.
[13] Williams JR, Hirsch ES, Anderson K, et al.A comparison of nine scales to detect depression in Parkinson disease: Which scale to use?[J]. Neurology, 2012, 78(13): 998-1106.
[14] Ginis P, Heremans E, Ferrari A, et al.External input for gait in people with Parkinson's disease with and without freezing of gait: one size does not fit all[J]. J Neurol, 2017, 264(7): 1488-1496.
[15] Kusakunniran W.Attribute-based learning for gait recognition using spatio-temporal interest points[J]. Image Vision Computing, 2014, 32(12): 1117-1126.
[16] Wei Z, Cong W.View-invariant gait recognition via deterministic learning[J]. Neurcomputing, 2016, 175(A): 324-335.
[17] 刘玉栋,苏开娜,马丽. 一种基于模型的步态识别方法[J]. 计算机工程与应用, 2005, 41(9): 88-92.
[18] 李彬. 计算字符串相似度的矩阵算法[J]. 现代电子技术, 2007, 30(24): 106-108.
[19] Bekkers EMJ, Dijkstra BW, Dockx K, et al.Clinical balance scales indicate worse postural control in people with Parkinson's disease who exhibit freezing of gait compared to those who do not: A meta-analysis[J]. Gait Posture, 2017, 56: 134-140.
[20] 王人成,张美芹,华超,等. 基于Fitts定律的人体步态对称性评定指标[J]. 清华大学学报(自然科学版), 2005, 45(2): 190-192.
[21] Shorter KA, Polk JD, Rosengren KS, et al.A new approach to detecting asymmetries in gait[J]. Clin Biomech (Bristol, Avon), 2008, 23(4): 459-467.
[22] 邹亚,汪丰,高帅锋,等. 基于可穿戴系统的PD病人运动功能评价系统[J]. 中国医疗设备, 2015, 30(1): 10-14.
[23] Lee N, Andrzej W, Krzysztof D, et al.Adjustment in gait symmetry with walking speed in trans-femora and trans-tibial amputees[J]. Gait Posture, 2003, 17(2): 142-151.
[24] Patterson KK, Gage WH, Brooks D, et al.Evaluation of gait symmetry after stroke: a comparison of current methods and recommendations for standardization[J]. Gait Posture, 2010, 31(2): 241-246.
[25] 廖福元,王珏. 帕金森病对步态对称性的影响[J]. 西安交通大学学报, 2006, 40(2): 228-230.

基于Kinect的帕金森病步态不对称性识别方法

Identification of Asymmetry Gait in Parkinson's Disease Based on Kinect

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	胡晓诗, 张琦, 岳青, 梁艳华, 李晓松, 冯啊美, 张燕庆. 矫形弹力绷带对痉挛性偏瘫脑性瘫痪患儿步态对称性和步行能力的效果[J]. 《中国康复理论与实践》, 2023, 29(9): 1083-1089.
[2]	王靖萱, 吕迪阳, 方伯言. 帕金森病步态异常非药物康复循证研究：基于ClinicalTrials.gov数据库分析[J]. 《中国康复理论与实践》, 2023, 29(7): 816-821.
[3]	吴佳玉, 孟德涛, 梁潇潇. 体力活动水平对帕金森病发病风险的影响：基于CHARLS数据的横断面分析[J]. 《中国康复理论与实践》, 2023, 29(10): 1135-1139.
[4]	石曼欣妤,孟德涛,方伯言. 帕金森病康复研究进展的可视化分析[J]. 《中国康复理论与实践》, 2022, 28(9): 1060-1064.
[5]	王洁萍,彭娟,张斐雪,樊必双,胥方元. 肢体协调训练对早期原发性帕金森病患者肺功能的效果[J]. 《中国康复理论与实践》, 2022, 28(8): 966-971.
[6]	张文波,瞿畅,周建萍,张小萍,张啸天. 基于Azure Kinect骨骼追踪的腕关节活动度测量方法[J]. 《中国康复理论与实践》, 2022, 28(8): 981-988.
[7]	谭茗丹,冯锭瑶,陈曦,刘汉军,李咏雪. 中文版构音障碍影响程度量表对帕金森病患者的信度和效度[J]. 《中国康复理论与实践》, 2022, 28(6): 696-703.
[8]	席晓明,毕鸿雁. 腹部扭转运动对帕金森病患者抑郁、便秘、运动症状和生活质量的效果[J]. 《中国康复理论与实践》, 2022, 28(2): 220-226.
[9]	刘阳,张孝权,王恒,齐莉萍. 虚拟现实技术对帕金森病患者综合平衡能力改善的Meta分析[J]. 《中国康复理论与实践》, 2021, 27(9): 1048-1058.
[10]	曹海豪,孙文玉,席晓明,王丽敏,毕鸿雁. 五禽戏对帕金森病患者平衡功能、步行能力及生活质量的效果[J]. 《中国康复理论与实践》, 2021, 27(9): 1087-1092.
[11]	肖琳娜,李晓红. 帕金森病冲动控制障碍的Scoping综述[J]. 《中国康复理论与实践》, 2021, 27(7): 774-779.
[12]	马惠姿,房进平,冯涛,蒋莹. 帕金森病患者不同程度抑郁在汉密尔顿抑郁量表的结构差异[J]. 《中国康复理论与实践》, 2021, 27(7): 829-833.
[13]	柳欣,尹志科,冯涛,邓永梅,赵越颖,董可,王春雪,马惠姿. 帕金森病并发淡漠的危险因素研究[J]. 《中国康复理论与实践》, 2021, 27(6): 719-723.
[14]	厉坤鹏,周宗磊,张梓楠,施伯翰,陈浩,罗云,朱燕. 呼吸训练对帕金森病患者肺功能和运动功能的效果[J]. 《中国康复理论与实践》, 2021, 27(3): 320-324.
[15]	蒋莹,房进平,冯涛,马惠姿. 帕金森病患者不同焦虑程度在汉密尔顿焦虑量表的结构差异[J]. 《中国康复理论与实践》, 2021, 27(3): 325-328.