Objective To register two breath-hold lung volumes image from one subject with deep expiration and deep inspiration.Methods Three pairs of thoracic high resolution CT serial from three subjects were collected under two breath-hold respiration stages.The lung parenchyma of every serial was segmented using the serial segmentation algorithm.Left and right lungs were stored separately.Expiration and inspiration volume images of single lung were registered.Firstly,affine transformation parameters were found based on the anatomic flag surfaces and expiration image volume was re-sampled with affine transformation.Secondly,"Demons" algorithm was employed to register two image volumes non-rigidly.Results Two lung surfaces and the inner structures have a nice registration.The average volume overlap of two images before registration is 0.7982.After global affine transformation,it improves to 0.8936.After "Demons",it is up to 0.9544.The average descending percentage of root mean square errors is 19.83%(after the global affine transformation) and 49.43%(after the "Demons" non-rigid registration).Conclusion The intra-subject registration between two lung image volumes with large deformations described here has an effective registration result.It offers a good base to analyze the lung respiration function.

Objective To search an approach based on Support Vector Machine (SVM) for detection of different abnormalities including micro-calcifications and masses from digital mammograms. Methods Such detections were formulated as supervised-learning problems and SVM was applied to the detection algorithm. After the regions of interest were pre-processed by specific rectangular windows, three kinds of parameters were extracted, including the direct pixel value parameter, the parameters from Spatial Grey Level Dependency (SGLD) matrices and from Discrete Cosine Transform (DCT). At first, each kind of parameter was taken as the input of SVM to train and test the machine respectively. Then all the parameters were incorporated into the input of SVM. Results the classification accuracy is 92.28%, 90.35% and 91.12% respectively when only one parameter input. The classification accuracy reaches 99.23% when all the parameter incorporated. Conclusion The parameters extracted from the regions of interest in digital mammograms can reflect the characteristics of different regions and SVM is a powerful tool for the detection of abnormalities from digital mammograms.

Objective: To develop a way of high-quality real-time three dimension surface reconstruction for high-resolution volume data.Method 3D surface point sets of single organ were using a method of binding the threshold and morphological operations.The normal vector of every surface point was calculated.According to the gray gradients of volume data,the triangle face was replaced by surface points to describe the organ surface,and the surface was displayed with OpenGL interface of display card after defining the color and transparent of the organ surface.Result Based on hardware platform of personal computer,the reconstruction of skeleton and skin for the digitized virtual Chinese man No.1(VCH-M1) from CT database was constructed,the rendering speed was faster than 25 F/s.Conclusion The algorithm is capable of realizing a real-time rendering for 512?512?1720 high resolution volume data.

Some noises still exist in the single-trial averaged visual evoked potentials (VEP), so further extraction of the above results is of significance. Independent component analysis (ICA)can separate the sources from their mixtures and make the output statistically as independent as possible; it can remove noises effectively. In this paper, the principle, experiment analyses and results of ICA based on quasi-Newton iteration rule for VEP feature extraction are introduced, It is compared with the fixed-point FastICA algorithm. The experiment results show that the provided algorithm may reinforce signals effectively and extract distinct P300 from the single-trial averaged VEP. It is of good applicability.
Algorithms ; Event-Related Potentials, P300 ; physiology ; Evoked Potentials, Visual ; physiology ; Humans ; Pattern Recognition, Automated ; methods ; Principal Component Analysis ; Signal Processing, Computer-Assisted

Traditional sleep scoring system describes the sleep EEG characterized by features in time domain as well as frequency domain. Power Spectral Density (PSD) is one of the well-used methods to observe the occurrence of specified rhythms. However, the parameter model based PSD estimation is used with the assumption that the model order is determined as low as possible through prior knowledge. This paper briefs the development of Autoregressive Model Order (ARMO) criterion, and provides the distribution of ARMOs for specified sleep EEG, which shows that ARMOs concentrate on several well separated regions that are indicative of the microstructure and transition states. This study suggests the promising perspective of ARMO as a special EEG feature for weighing complexity, randomness and rhythm components.
Delta Rhythm ; Electroencephalography ; Humans ; Models, Neurological ; Regression Analysis ; Signal Processing, Computer-Assisted ; Sleep Stages ; physiology

In order to study event-related desynchronization (ERD) related to voluntary movement, we designed two experiments. In the first experiment, untrained subjects were required to imagine the action of typing with left or right index finger for about 1 second before real action, whereas they were required to type instantly after instruction in the second experiment. By analyzing spontaneous EEG signals between the instruction and the action, we predicted which finger was used. The prediction accuracy in the first experiment fell from 85% to 71% with the progress of experiment, the average accuracy being 78%, whereas the prediction result was almost random guess in the second experiment. The results demonstrate that (1) ERD patterns are significantly affected by the effective duration of motion imagination, (2) unconscious reduction of this duration can decrease the prediction accuracy. Therefore, when designing subsequent BCI experiments, we should devote our attention to the question of how to keep the effective duration of motion imagination.
Brain ; physiology ; Cortical Synchronization ; Electroencephalography ; Humans ; Man-Machine Systems ; Task Performance and Analysis ; User-Computer Interface

In this paper, we discuss the relation betw een matched filter and wavelet transform(WT), and point out that wavelet transf orm is just the matched filter with changeable detection template. According to this idea, the method of signal detection based on hybrid wavelet transform (HWT ) is proposed. HWT in this paper means that in WT decomposition and reconstructi on, we use two different mother wavelets. One is used as a changeable template for the pulses detection and the other is used for the characteristic enhancement of detected pulse. This method has been applied to the interference pulse dete ction in EEG signal. The experiment result shows that HWT has the good property for instantaneous signal detection.

Residues in protein sequences can be classified into two (exposed / buried) or three (exposed/intermediate/buried) states according to their relative solvent accessibility. Markov chain model (MCM) had been adopted for statistical modeling and prediction. Different orders of MCM and classification thresholds were explored to find the best parameters. Prediction results for two different data sets and different cut-off thresholds were evaluated and compared with some existing methods, such as neural network, information theory and support vector machine. The best prediction accuracies achieved by the MCM method were 78.9% for the two-state prediction problem and 67.7% for the three-state prediction problem, respectively. A comprehensive comparison for all these results shows that the prediction accuracy and the correlative coefficient of the MCM method are better than or comparable to those obtained by the other prediction methods. At the same time, the advantage of this method is the lower computation complexity and better time-consuming performance.
Algorithms ; Computational Biology ; methods ; Databases, Protein ; Markov Chains ; Models, Chemical ; Models, Molecular ; Proteins ; chemistry ; classification ; Sequence Analysis, Protein ; methods ; Solubility

Mental workload research is important to people's health and work efficiency, Psychophysiological measures such as electroencephalography (EEG), ECG and respiration measures can be used to predict mental workload level. A Multi-channel phase-space reconstruction method is proposed in this paper which rearranges signal serials by the correlation coefficients and select time delay by signal determinism. The study of determinism and correlation dimension on simulative data exhibits a good performance. The result of EEG series shows a clearly consistency to workload level variety. The method is useful for multi-channel signals nonlinear analysis and mental workload detection.
Adult ; Algorithms ; Electroencephalography ; Humans ; Mental Processes ; physiology ; Nonlinear Dynamics ; Signal Processing, Computer-Assisted ; Task Performance and Analysis ; Workload

It is important to simulate the excitation propagation process of cardiac bio-electricity in the research of ECG forward problem. Traditional methods describe them with wave simulation algorithm such as LFX simulation algorithm and vector propagation algorithm etc, these methods have some problems to certain extent, due to the presence of discreteness of space and time and asymmetry of the myocardium. This paper discussed the simulation algorithm in 2-dimension space under the circumstance of layered and non-layered structure of myocardium. By calculating the theoretic values of simulating time based on Huygen's principle, we found that there were errors in LFX algorithm and no errors in vector propagation algorithm under the circumstance of non-layered structure of the myocardium, no mater what myocardium is isotropic or anisotropic. However, there exist errors from both algorithms when the myocardium has the layered structure. An improved algorithm is proposed and the simulations have been performed to examine the efficacy of the new algorithm, and the errors are reduced obviously. By increasing the number of myocardial blocks in the model, we also analyzed its influence on the error of simulation algorithm.
Algorithms ; Computer Simulation ; Heart ; physiology ; Models, Cardiovascular