ABSTRACT
A new method based on convolution kernel compensation (CKC) for decomposing multi-channel surface electromyogram (sEMG) signals is proposed in this paper. Unsupervised learning and clustering function of self-organizing map (SOM) neural network are employed in this method. An initial innervations pulse train (IPT) is firstly estimated, some time instants corresponding to the highest peaks from the initial IPT are clustered by SOM neural network. Then the final IPT can be obtained from the observations corresponding to these time instants. In this paper, the proposed method was tested on the simulated signal, the influence of signal to noise ratio (SNR), the number of groups clustered by SOM and the number of highest peaks selected from the initial pulse train on the number of reconstructed sources and the pulse accuracy were studied, and the results show that the proposed approach is effective in decomposing multi-channel sEMG signals.
Subject(s)
Algorithms , Cluster Analysis , Electromyography , Neural Networks, ComputerABSTRACT
We reviewed the research progress and prospect of electrical properties tomography for prostate in this paper. After the introduction of the basic principles of electrical impedance tomography (EIT) and magnetic resonance electric impedance tomography (MREIT), we presented the applications of the two techniques in electrical properties tomography of the prostate in detail. We then discussed the application prospects of induced current magnetic resonance electric impedance tomography (IC-MREIT) and magnetic resonance electrical properties tomography (MREPT) in the diagnoses of prostate cancer.
Subject(s)
Humans , Male , Electric Impedance , Magnetic Resonance Imaging , Methods , Prostate , Physiology , Prostatic Neoplasms , Diagnosis , TomographyABSTRACT
In this paper, a review of a new electrical impedance tomography technique-magnetic resonance electrical impedance tomography (MREIT) is presented. Some medical imaging methods are briefly introduced. The basic theory of MREIT is given as well as its realization methods and developing status. The merits and challenges of this new trend are also demonstrated.
Subject(s)
Humans , Electric Impedance , Image Processing, Computer-Assisted , Methods , Magnetic Resonance Imaging , Methods , Tomography , Methods , Tomography, X-Ray Computed , MethodsABSTRACT
Finite element realistic geometry head modeling is of significance in high-resolution electroencephalogram research. A new adaptive method of finite element realistic head modeling method is presented. An automatic refinement algorithm is developed to perform local adaptive meshing, which improves the efficiency of the modeling.
Subject(s)
Humans , Algorithms , Finite Element Analysis , Head , Imaging, Three-Dimensional , Magnetic Resonance Imaging , Models, AnatomicABSTRACT
Medical image segmentation is an important application of image segmentation. However it is the bottleneck that restrains medical image application in clinical practice. In this paper, the aim and significance of medical image segmentation are discussed, the development of medical image segmentation techniques is sketched, and a review of the medical image segmentation techniques is given.
Subject(s)
Algorithms , Cluster Analysis , Fuzzy Logic , Image Interpretation, Computer-Assisted , Methods , Models, Statistical , Neural Networks, ComputerABSTRACT
We have investigated spatio-temporal source modeling (STSM) of the electroencephalogram (EEG) by using a Quasi-Newton method based on Independent Component Analysis (ICA) for localization of multiple dipole sources from the scalp EEG. The problem of multiple dipole localization was transformed into several single dipole localization problems. Another benefit of the present method is that the number of independent sources can be estimated. Computer simulation studies were conducted to evaluate the performance of this approach. The present simulation results indicate that the ICA-based method is superior to the conventional nonlinear methods in localization accuracy, computation time and anti-noise performance, for multiple dipole localization when the sources are stationary over the period of interest.
Subject(s)
Humans , Brain , Physiology , Brain Mapping , Methods , Computer Simulation , Data Interpretation, Statistical , Electroencephalography , Models, StatisticalABSTRACT
We have developed a new three dimensional (3-D) conductivity imaging approach and have used it to detect human brain conductivity changes corresponding to acute cerebral stroke. The proposed Magnetic Resonance Electrical Impedance Tomography (MREIT) approach is based on the J-Substitution algorithm and is expanded to imaging 3-D subject conductivity distribution changes. Computer simulation studies have been conducted to evaluate the present MREIT imaging approach. Simulations of both types of cerebral stroke, hemorrhagic stroke and ischemic stroke, were performed on a four-sphere head model. Simulation results showed that the correlation coefficient (CC) and relative error (RE) between target and estimated conductivity distributions were 0.9245+/-0.0068 and 8.9997%+/-0.0084%, for hemorrhagic stroke, and 0.6748+/-0.0197 and 8.8986%+/-0.0089%, for ischemic stroke, when the SNR (signal-to-noise radio) of added GWN (Gaussian White Noise) was 40. The convergence characteristic was also evaluated according to the changes of CC and RE with different iteration numbers. The CC increases and RE decreases monotonously with the increasing number of iterations. The present simulation results show the feasibility of the proposed 3-D MREIT approach in hemorrhagic and ischemic stroke detection and suggest that the method may become a useful alternative in clinical diagnosis of acute cerebral stroke in humans.