Bio-Medical Materials and Engineering - Volume 24, issue 6

Authors: Zhu, Junjiang | He, Lingsong | Gao, Zhiqiang

Article Type: Research Article

Abstract: Feature extraction is a crucial aspect of computer-aided arrhythmia diagnosis using an electrocardiogram (ECG). A location, width and magnitude (LWM) model is proposed for extracting each wave's features in the ECG. The model is a stream of Gaussian function in which three parameters (the expected value, variance and amplitude) are applied to approximate the P wave, QRS wave and T wave. Moreover, the features such as the P–Q intervals, S–T intervals, and so on are easily obtained. Then, a mixed approach is presented for estimating the parameters of a real ECG signal. To illustrate this model's associated advantages, the extracted …parameters combined with R–R intervals are fed to three classifiers for arrhythmia diagnoses. Two kinds of arrhythmias, including the premature ventricular contraction (PVC) heartbeats and the atrial premature complexes (APC) heartbeats, are diagnosed from normal beats using the data from the MIT–BIH arrhythmia database. The results in this study demonstrate that using these parameters results in more accurate and universal arrhythmia diagnoses. Show more

Keywords: ECG, feature extraction, classification, arrhythmia diagnosis, parametric Gaussian functions

DOI: 10.3233/BME-141107

Citation: Bio-Medical Materials and Engineering, vol. 24, no. 6, pp. 2883-2891, 2014

Authors: Zhang, Yaonan | Gao, Yuan | Jiao, Jinling | Li, Xian | Li, Sai | Yang, Jun

Article Type: Research Article

Abstract: Information regarding the motion, strain and synchronization are important for cardiac diagnosis and therapy. Extraction of such information from ultrasound images remains an open problem till today. In this paper, a novel method is proposed to extract the boundaries of left ventricles and track these boundaries in ultrasound image sequences. The initial detection of boundaries was performed by an active shape model scheme. Subsequent refinement of the boundaries was done by using local variance information of the images. The main objective of this paper is the formulation of a new boundary tracking algorithm using ant colony optimization technique. The experiments …conducted on the simulated image sequences and the real cardiac ultrasound image sequences shows a positive and promising result. Show more

Keywords: Active shape model, image segmentation, boundary tracking, ant colony optimization, motion estimation

DOI: 10.3233/BME-141108

Citation: Bio-Medical Materials and Engineering, vol. 24, no. 6, pp. 2893-2899, 2014

Authors: Tian, Yin | Li, Fali | Xu, Peng | Yuan, Zhen | Zhao, Dechun | Zhang, Haiyong

Article Type: Research Article

Abstract: Steady-state visual evoked potentials (SSVEP) are the visual system responses to a repetitive visual stimulus flickering with the constant frequency and of great importance in the study of brain activity using scalp electroencephalography (EEG) recordings. However, the reference influence for the investigation of SSVEP is generally not considered in previous work. In this study a new approach that combined the canonical correlation analysis with infinite reference (ICCA) was proposed to enhance the accuracy of frequency recognition of SSVEP recordings. Compared with the widely used periodogram method (PM), ICCA is able to achieve higher recognition accuracy when extracts frequency within a …short span. Further, the recognition results suggested that ICCA is a very robust tool to study the brain computer interface (BCI) based on SSVEP. Show more

Keywords: Steady-state visual evoked potentials, canonical correlation analysis with infinite reference, frequency recognition, periodogram, brain computer interface

DOI: 10.3233/BME-141109

Citation: Bio-Medical Materials and Engineering, vol. 24, no. 6, pp. 2901-2908, 2014

Authors: Deng, Zhipeng | Zhang, Chungang | Yu, Ping | Shao, Jun | Liang, Fuyou

Article Type: Research Article

Abstract: Continuous monitoring of stroke volume (SV) or cardiac output (CO) has long been the subject of numerous studies. The majority of existing methods are calibration-dependent, requiring invasive measurements of CO to initialize the estimation algorithms, thus limiting their application to the clinical setting. In the present study, a new calibration-free method aimed at home-based use has been developed, which allows noninvasive estimation of SV from oscillometric signals measured at the wrist. The estimation equation was constructed based on the PRAM method, with significant modifications to incorporate more patient-specific information. Furthermore, the estimation equation was optimized based on the clinical data …acquired from 96 patients (the ‘Training’ group) to obtain the best comparison of estimated SV with echocardiographic SV. The resulting estimation equation was then applied directly to another patient group (the ‘Testing’ group) to examine its validity. Obtained results demonstrate that our estimations correlated closely with the measurements in both patient groups. In addition to being noninvasive and calibration-free, the proposed method can be fully automated, which may be valuable for the future development of home-based cardiac monitoring systems. Show more

Keywords: Stroke volume, oscillometric signals, noninvasive estimation, coefficient optimization

DOI: 10.3233/BME-141110

Citation: Bio-Medical Materials and Engineering, vol. 24, no. 6, pp. 2909-2918, 2014

Authors: Jiang, Jun | Zhou, Zongtan | Yin, Erwei | Yu, Yang | Hu, Dewen

Article Type: Research Article

Abstract: Recently, the integration of different electrophysiological signals into an electroencephalogram (EEG) has become an effective approach to improve the practicality of brain-computer interface (BCI) systems, referred to as hybrid BCIs. In this paper, a hybrid BCI was designed by combining an EEG with electrocardiograph (EOG) signals and tested using a target selection experiment. Gaze direction from the EOG and the event-related (de)synchronization (ERD/ERS) induced by motor imagery from the EEG were simultaneously detected as the output of the BCI system. The target selection mechanism was based on the synthesis of the gaze direction and ERD activity. When an ERD activity …was detected, the target corresponding to the gaze direction was selected; without ERD activity, no target was selected, even when a subjects gaze was directed at the target. With this mechanism, the operation of the BCI system is more flexible and voluntary. The accuracy and completion time of the target selection tasks during the online testing were 89.3% and 2.4 seconds, respectively. These results show the feasibility and practicality of this hybrid BCI system, which can potentially be used in the rehabilitation of disabled individuals. Show more

Keywords: hybrid brain computer interface, EEG, EOG, event-related (de)synchronization, target selection

DOI: 10.3233/BME-141111

Citation: Bio-Medical Materials and Engineering, vol. 24, no. 6, pp. 2919-2925, 2014

Authors: Cao, Rui | Wu, Zheng | Li, Haifang | Xiang, Jie | Chen, Junjie

Article Type: Research Article

Abstract: Generally, an alcoholic's brain shows explicit damage. However, in cognitive tasks, the correlation between the topological structural changes of the brain networks and the brain damage is still unclear. Scalp electrodes and synchronization likelihood (SL) were applied to the constructions of the EGG functional networks of 28 alcoholics and 28 healthy volunteers. The graph-theoretic analysis showed that in cognitive tasks, compared with the healthy control group, the brain networks of alcoholics had smaller clustering coefficients in β1 bands, shorter characteristic path lengths, increased global efficiency, but similar small-world properties. The abnormal topological structure of the alcoholics may be related to …the local-function brain damage and the compensation mechanism adopted to complete tasks. This conclusion provides a new perspective for alcoholrelated brain damage. Show more

Keywords: alcoholic, EEG, brain functional network, graph theory

DOI: 10.3233/BME-141112

Citation: Bio-Medical Materials and Engineering, vol. 24, no. 6, pp. 2927-2936, 2014

Authors: Wei, Yu | Jun, Yang | Lin, Sun | Hong, Li

Article Type: Research Article

Abstract: Electroencephalograph (EEG) signals feature extraction and processing is one of the most difficult and important part in the brain-computer interface (BCI) research field. EEG signals are generally unstable, complex and have low signal-noise ratio, which is difficult to be analyzed and processed. To solve this problem, this paper disassembles EEG signals with the empirical mode decomposition (EMD) algorithm, extracts the characteristic values of the major intrinsic mode function (IMF) components, and then classifies them with fuzzy C-means (FCM) method. Also, comparison research is done between the proposed method and several current EEG classification methods. Experimental results show that the classification …accuracy based on the EEG signals of the second BCI competition in 2003 is up to 78%, which is superior to those of the comparative EEG classification methods. Show more

Keywords: Brain-computer interface (BCI), intrinsic mode function (IMF), fuzzy C-means (FCM)

DOI: 10.3233/BME-141113

Citation: Bio-Medical Materials and Engineering, vol. 24, no. 6, pp. 2937-2943, 2014

Authors: Lu, Meng | Di, Jia

Article Type: Research Article

Abstract: Diffusion tensor imaging (DTI) is a tractography algorithm that provides the only means of mapping white matter fibers. Furthermore, because of its wealth of applications, diffusion MRI tractography is gaining importance in clinical and neuroscience research. This paper presents a novel brain white matter fiber reconstruction method based on the snake model by minimizing the energy function, which is composed of both external energy and internal energy. Internal energy represents the assembly of the interaction potential between connected segments, whereas external energy represents the differences between predicted DTI signals and measured DTI signals. Through comparing the proposed method with other …tractography algorithms in the Fiber Cup test, the present method was shown to perform superiorly to the majority of the other methods. In fact, the proposed test performed the third best out of the ten available methods, which demonstrates that present method can accurately formulate the brain white matter fiber reconstruction. Show more

Keywords: Diffusion tensor imaging, brain white matter, fiber tracking, snake model, energy minimization

DOI: 10.3233/BME-141114

Citation: Bio-Medical Materials and Engineering, vol. 24, no. 6, pp. 2945-2953, 2014

Authors: Liu, Dazhong | Zhong, Ning

Article Type: Research Article

Abstract: This paper reviewed the meaning of the statistic index and the properties of the complex network models and their physiological explanation. By analyzing existing problems and construction strategies, this paper attempted to construct complex brain networks from a different point of view: that of clustering first and constructing the brain network second. A clustering-guided (or led) construction strategy towards complex brain networks was proposed. The research focused on the discussion of the task-induced brain network. To discover different networks in a single run, a combined-clusters method was applied. Afterwards, a complex local brain network was formed with a complex network …method on voxels. In a real test dataset, it was found that the network had small-world characteristics and had no significant scale-free properties. Meanwhile, some key bridge nodes and their characteristics were identified in the local network by calculating the betweenness centrality. Show more

Keywords: Complex brain network, functional connectivity, clustering, functional magnetic resonance imaging

DOI: 10.3233/BME-141115

Citation: Bio-Medical Materials and Engineering, vol. 24, no. 6, pp. 2955-2962, 2014

Authors: Wang, Linyuan | Tong, Li | Yan, Bin | Lei, Yu | Wang, Lijun | Zeng, Ying | Hu, Guoen

Article Type: Research Article

Abstract: Statistical model is essential for constraint-free visual image reconstruction, as it may overfit training data and have poor generalization. In this study, we investigate the sparsity of the distributed patterns of visual representation and introduce a suitable sparse model for the visual image reconstruction experiment. We use elastic net regularization to model the sparsity of the distributed patterns for local decoder training. We also investigate the relationship between the sparsity of the visual representation and sparse models with different parameters. Our experimental results demonstrate that the sparsity needed by visual reconstruction models differs from the sparsest one, and the l2-norm …regularization introduced in the EN model improves not only the robustness of the model but also the generalization performance of the learning results. We therefore conclude that the sparse learning model for visual image reconstruction should reflect the spasity of visual perceptual experience, and have a solution with high but not the highest sparsity, and some robustness as well. Show more

Keywords: sparse learning model, visual image reconstruction, sparsity, elastic net

DOI: 10.3233/BME-141116

Citation: Bio-Medical Materials and Engineering, vol. 24, no. 6, pp. 2963-2969, 2014