A vision-based regression model to evaluate Parkinsonian gait from monocular image sequences

详细信息    查看全文

• 作者：You-Yin Chen^a ; ^{irradiance@so-net.net.tw} ; Chien-Wen Cho^a ; Sheng-Huang Lin^b ; ^c ; Hsin-Yi Lai^a ; Yu-Chun Lo^c ; Shin-Yuan Chen^d ; Yuan-Jen Chang^e ; Wen-Tzeng Huang^f ; Chin-Hsing Chen^e ; Fu-Shan Jaw^c ; Siny Tsang^g ; Sheng-Tsung Tsai^d
• 关键词：Human motion analysis ; Parkinsonian gait ; Linear discriminant analysis (LDA) ; Classification ; Regression
• 刊名：Expert Systems with Applications
• 出版年：2012
• 出版时间：January, 2012
• 年：2012
• 卷：39
• 期：1
• 页码：520-526
• 全文大小：575 K

文摘

Parkinson¡¯s Disease (PD) is a common neurodegenerative disorder with progressive loss of dopaminergic and other sub-cortical neurons. Among various approaches, gait analysis is commonly used to help identify the biometric features of PD. There have been some studies to date on both the classification of PD and estimation of gait parameters. However, it is also important to construct a regression system that can evaluate the degree of abnormality in PD patients. In this paper, we intended to develop a PD gait regression model that is capable of predicting the severity of motor dysfunction from given gait image sequences. We used a model-free strategy and thus avoided the critical demands of segmentation and parameter estimation. Furthermore, we used linear discriminant analysis (LDA) to increase the feature efficiency by maximizing and minimizing the between- and within-group variations. Regression was also achieved by assessing the spatial and temporal information through classification and finally by using these two new indices for linear regression. According to the experiments, the outcomes significantly correlated with the sum of sub-scores from the Unified Parkinson¡¯s Disease Rating Scale (UPDRS): motor examination section with r = 0.92 and 0.85 for training and testing, respectively, with p < 0.0001. Compared with conventional methods, our system provided a better evaluation of PD abnormality.