Browsing by Author "Chao, Wen-Hung"

Now showing 1 - 7 of 7

A vision-based analysis system for gait recognition in patients with Parkinson's disease
(2009-04-01)
Cho, Chien-Wen
;
Chao, Wen-Hung
;
Lin, Sheng-Huang
;
Chen, You-Yin
;
電控工程研究所
Recognition of specific Parkinsonian gait patterns is helpful in the diagnosis of Parkinson's disease (PD). However, there are few computer-aided methods to identify the specific gait patterns of PD. We propose a vision-based diagnostic system to aid in recognition of the gait patterns of Parkinson's disease. The proposed system utilizes an algorithm combining principal component analysis (PCA) with linear discriminant analysis (LDA). This scheme not only addresses the high data dimensionality problem during image processing but also distinguishes different gait categories simultaneously. The feasibility of the proposed system for the recognition of PD gait was tested by using gait videos of PD and normal subjects. The efficiency of feature extraction using PCA and LDA coefficients are also compared. Experimental results showed that LDA had a recognition rate for Parkinsonian gait of 95.49%, which is higher than the conventional PCA feature extraction method. The proposed system is a promising aid in identifying the gait of Parkinson's disease patients and can discriminate the gait patterns of PD patients and normal people with a very high classification rate. Crown Copyright (C) 2008 Published by Elsevier Ltd. All rights reserved.
Automatic segmentation of magnetic resonance images using a decision tree with spatial information
(2009-03-01)
Chao, Wen-Hung
;
Chen, You-Yin
;
Lin, Sheng-Huang
;
Shih, Yen-Yu I.
;
Tsang, Siny
Here we proposed an automatic segmentation method based on a decision tree to classify the brain tissues in magnetic resonance (MR) images. Two types of data - phantom MR images obtained from IBSR (http://www.cma.mgh.harvard.edu/ibsr) and simulated brain MR images obtained from BrainWeb (http://www.bic.mni.mcgill.ca/brainweb) - were segmented using an automatic decision tree algorithm to obtain images with improved visual rendition. Spatial information on the general gray level (G), spatial gray level (S), and two-dimensional wavelet transform (M was combined in-plane in two coordinate systems (Euclidean coordinates (x,y) or polar coordinates (r,theta)). The decision tree was constructed based on a binary tree with nodes created by splitting the distribution of input features of the tree. The spatial information obtained from MR images with different noise levels and inhomogeneities were segmented to compare whether the use of a decision tree improved the identification of human anatomical structures in a neuroimage. The average accuracy rates of segmentation for phantom images with a noise variation of 15 gray levels were 0.9999 and 0.9973 with spatial information (G, x,y, r, theta) and (S, x, y, r, theta), respectively, and 0.9999 and 0.9819 with spatial information (G, x, y, S, r, theta) and (W, x, y, G, r, theta). The average accuracy rates of segmentation for simulated MR images with a noise level of 5% were 0.9532 and 0.9439 with spatial information (G, x, y, r, theta) and (S, x, y, r, theta), respectively, and 0.9446 and 0.9287 with spatial information (G, x, y, S, r, theta) and (W, x, y, G, r, theta). The accuracy rates of segmentation were highest for both simulated phantom and brain MR images, having the lowest noise levels, from a reduction of overlapping gray levels in the images. The accuracies of segmentation were higher when the spatial information included the general gray level than when it included the spatial gray level, which in turn were higher than when it included the wavelet transform. Furthermore, the performance of segmentation was also evaluated with a boundary detection methodology that is based on the Hausdorff distance to compare with the mean computer to observer difference (COD) and mean interobserver difference (IOD) for gray matter (GM), white matter (WM), and all areas (ALL) from images segmented using the decision tree. The values of mean COD are similar and around 12 mm for GM segmented using the decision tree. Our segmentation method based on a decision tree algorithm presented an easy way to perform automatic segmentation for both phantom and tissue regions in brain MR images. (C) 2008 Published by Elsevier Ltd.
Automatic spike sorting for extracellular electrophysiological recording using unsupervised single linkage clustering based on grey relational analysis
(2011-06-01)
Lai, Hsin-Yi
;
Chen, You-Yin
;
Lin, Sheng-Huang
;
Lo, Yu-Chun
;
Tsang, Siny
Automatic spike sorting is a prerequisite for neuroscience research on multichannel extracellular recordings of neuronal activity. A novel spike sorting framework, combining efficient feature extraction and an unsupervised clustering method, is described here. Wavelet transform (WT) is adopted to extract features from each detected spike, and the Kolmogorov-Smirnov test (KS test) is utilized to select discriminative wavelet coefficients from the extracted features. Next, an unsupervised single linkage clustering method based on grey relational analysis (GSLC) is applied for spike clustering. The GSLC uses the grey relational grade as the similarity measure, instead of the Euclidean distance for distance calculation; the number of clusters is automatically determined by the elbow criterion in the threshold-cumulative distribution. Four simulated data sets with four noise levels and electrophysiological data recorded from the subthalamic nucleus of eight patients with Parkinson's disease during deep brain stimulation surgery are used to evaluate the performance of GSLC. Feature extraction results from the use of WT with the KS test indicate a reduced number of feature coefficients, as well as good noise rejection, despite similar spike waveforms. Accordingly, the use of GSLC for spike sorting achieves high classification accuracy in all simulated data sets. Moreover, J-measure results in the electrophysiological data indicating that the quality of spike sorting is adequate with the use of GSLC.
Correction of inhomogeneous magnetic resonance images using multiscale retinex for segmentation accuracy improvement
(2012-03-01)
Chao, Wen-Hung
;
Lai, Hsin-Yi
;
Shih, Yen-Yu I.
;
Chen, You-Yin
;
Lo, Yu-Chun
The purpose of this study was to improve the accuracy of tissue segmentation on brain magnetic resonance (MR) images preprocessed by multiscale retinex (MSR), segmented with a combined boosted decision tree (BDT) and MSR algorithm (hereinafter referred to as the MSRBDT algorithm). Simulated brain MR (SBMR) T1-weighted images of different noise levels and RF inhomogeneities were adopted to evaluate the outcome of the proposed method; the MSRBDT algorithm was used to identify the gray matter (GM), white matter (WM), and cerebral-spinal fluid (CSF) in the brain tissues. The accuracy rates of GM, WM, and CSF segmentation, with spatial features (G, x, y, r, theta), were respectively greater than 0.9805, 0.9817, and 0.9871. In addition, images segmented with the MSRBDT algorithm were better than those obtained with the expectation maximization (EM) algorithm; brain tissue segmentation in MR images was significantly more precise. The proposed MSRBDT algorithm could be beneficial in clinical image segmentation. (C) 2011 Elsevier Ltd. All rights reserved.
Design and fabrication of a polyimide-based microelectrode array: Application in neural recording and repeatable electrolytic lesion in rat brain
(2009-08-30)
Chen, You-Yin
;
Lai, Hsin-Yi
;
Lin, Sheng-Huang
;
Cho, Chien-Wen
;
Chao, Wen-Hung
The design and testing of a new microelectrode array, the NCTU (National Chiao Tung University) probe, was presented. Evaluation results showed it has good biocompatibility, high signal-to-noise ratio (SNR: the root mean square of background noise to the average peak-to-peak amplitude of spikes) during chronic neural recordings, and high reusability for electrolytic lesions. The probe was a flexible, polyimide-based microelectrode array with a long shaft (14.9 mm in length) and 16 electrodes (5 mu m-thick and 16 mu m in radius); its performance in chronic in vivo recordings was examined in rodents. To improve the precision of implantation, a metallic, impact-resistant layer was sandwiched between the polyimide layers to strengthen the probe. The three-dimensional (3D) structure of electrodes fabricated by electroplating produced rough textures that increased the effective surface area. The in vitro impedance of electrodes on the NCTU probe was 2.4 +/- 0.52 M Omega at 1 kHz. In addition, post-surgical neural recordings of implanted NCTU probes were conducted for up to 40 days in awake, normally behaving rats. The electrodes on the NCTU probe functioned well and had a high SNR (range: 4-5) with reliable in vivo impedance (<0.7 M Omega). The electrodes were also robust enough to functionally record events, even after the anodal current (30 mu A, 10 s) was repeatedly applied for 60 times. With good biocompatibility, high and stable SNR for chronic recording, and high tolerance for electrolytic lesion, the NCTU probe would serve as a useful device in future neuroscience research. (C) 2009 Elsevier B.V. All rights reserved.
Driving style classification by analyzing EEG responses to unexpected obstacle dodging tasks
(2006)
Lin, Chin-Teng
;
Liang, Sheng-Fu
;
Chao, Wen-Hung
;
Ko, Li-Wei
;
Chao, Chih-Feng
Driving safely has received increasing attention of the publics due to the growing number of traffic accidents that the driver's driving style is highly correlated to many accidents. The purpose of this study is to investigate the relationship between driver's driving style and driver's ERP response. In our research, a virtual reality (VR) driving environment is developed to provide stimuli to subjects. Independent component analysis (ICA) is used to decompose the electroencephalogram (EEG) data. The power spectrum analysis of ICA components and correlation analysis are employed to investigate the EEG activities related to driving style. Experimental results demonstrate that we may classify the drivers into aggressive or gentle styles based on the observed ERP difference corresponding to the proposed unexpected obstacle dodging tasks.
Improving segmentation accuracy for magnetic resonance imaging using a boosted decision tree
(2008-11-15)
Chao, Wen-Hung
;
Chen, You-Yin
;
Cho, Chien-Wen
;
Lin, Sheng-Huang
;
Shih, Yen-Yu I.
The purpose of this study was to improve the accuracy rate of brain tissue classification in magnetic resonance (MR) imaging using a boosted decision tree segmentation algorithm. Herein. we examined simulated phantom MR (SPMR) images, simulated brain MR (SBMR) images, and a real data. The accuracy rate and k index when classifying brain tissues as gray matter (GM), white matter (WM), or cerebral-spinal fluid (CSF) were better when using the boosted decision tree algorithm combined with a fuzzy threshold than when using a statistical region-growing (SRG) algorithm [Wolf 1, Vetter M, Wegner 1, Bottger T, Nolden M, Schobinger M, et al. The medical imaging interaction toolkit. Med Imag Anal 2005;9:594-604] and an adaptive segmentation (AS) algorithm [Wells WM, Crimson WEL, Kikinis R, Jolesz FA. Adaptive segmentation of MRI data. IEEE Trans Med Imag 1996; 15:429-42]. The segmentation performance when using this algorithm on real data from brain MR images was also better than those of SRG and AS algorithm. Segmentation of a real data using the boosted decision tree produced particularly clear brain MR imaging and permitted more accurate brain tissue segmentation. In conclusion, a decision tree with appropriate boost trials successfully improved the accuracy rate of MR brain tissue segmentation. Crown Copyright (C) 2008 Published by Elsevier B.V. All rights reserved.