This paper discusses image segmentation of liver by MITK and maximum entropy in VC++ 6.0.MITK supports an extensive set of image processing and 3D visualization algorithms,which is a very convenient tool.After filtered by Wavelet transform,good segmentation results could be obtained by maximum entropy method and MITK interactive segmentation.

A real-time tele-monitoring system for physiological multi-parameter based on Internet is introduced,and physiological signals are transmitted by P2P network technology.The experiment results show that the speed of data transfer has been improved greatly using P2P technology,and physiological signals,such as ECG,can be monitored in real-time.

The method for ultrasonic detection of air bubble in race track is studied in this paper. A automatic detection system is established, which mainly consists of the ultrasound emitter and receiver, high-speed A/D acquisition card and PC.

The Internet -based multiple physiological parameters tele -monitoring system is composed of an information collector for multiple physiological parameters, a personal computer and a central server. A P2P structure mixed with a C/S structure is adopted in the software design. To make tele-monitoring and tele-diagnosis available, the system is applied to real-time measuring, analyzing, monitoring and tele-transmitting of multiple physiological parameters. The system is suitable to be used in community hospital and family.

Hyperthermia is a significant and promising technique for tumor treatment. Temperature is the key parameter which influences the treatment effectiveness. Therefore, real-time and precise noninvasive temperature monitoring is the pivotal issue in further development of hyperthermia. This paper introduced the noninvasive monitoring theories and techniques of hyperthermia based on ultrasonic image texture features, and reviewed the achievements both abroad and at home. In addition, some problems to be solved necessary were also pointed out.
Animals ; Body Temperature ; Humans ; Hyperthermia, Induced ; methods ; Monitoring, Physiologic ; methods ; Neoplasms ; therapy ; Thermometers ; Ultrasonics ; methods

The purpose of using brain-computer interface (BCI) is to build a bridge between brain and computer for the disable persons, in order to help them to communicate with the outside world. Electroencephalography (EEG) has low signal to noise ratio (SNR), and there exist some problems in the traditional methods for the feature extraction of EEG, such as low classification accuracy, lack of spatial information and huge amounts of features. To solve these problems, we proposed a new method based on time domain, frequency domain and space domain. In this study, independent component analysis (ICA) and wavelet transform were used to extract the temporal, spectral and spatial features from the original EEG signals, and then the extracted features were classified with the method combined support vector machine (SVM) with genetic algorithm (GA). The proposed method displayed a better classification performance, and made the mean accuracy of the Graz datasets in the BCI Competitions of 2003 reach 96%. The classification results showed that the proposed method with the three domains could effectively overcome the drawbacks of the traditional methods based solely on time-frequency domain when the EEG signals were used to describe the characteristics of the brain electrical signals.
Algorithms ; Brain ; physiology ; Brain-Computer Interfaces ; Electroencephalography ; Humans

This paper introduces an adaptive filter method for enhancing ventricular late potentials. The adaptive filter has only one signal electrode and does not need the reference electrode. The experiment results show that this adaptive filter method can effectively improve signal-to-noise ratio of ventricular late potentials.
Action Potentials ; Algorithms ; Computer Simulation ; Electrocardiography ; Humans ; Signal Processing, Computer-Assisted ; instrumentation ; Ventricular Function

OBJECTIVE: In this paper, an intelligent system using BP neural networks (BPNN) is presented for early detection coronary artery disease (CAD). METHODS: Based on the four features of ECG signals and six basic parameters of patients, BPNN was built and trained. Especially the method which combined feature extraction and classification was discussed. RESULTS: The performance of the intelligent system has been evaluated in 20 samples. The test results showed that this system was effective in detecting CAD. The correct classification rate was about 90% for normal subjects and 100% for abnormal subjects. CONCLUSION: BPNN could quite accurately detect abnormal subjects. Because it is not expensive and noninvasive, it is fit to examine health of the elderly and has good application foreground.
Aged ; Classification ; Coronary Artery Disease* ; Coronary Vessels* ; Diagnosis* ; Electrocardiography ; Humans

Voxel based morphometry (VBM) methods are used to detect the difference in brain structures between the posttraumatic stress disorder (PTSD) sufferers and the normal controls. Standard VBM method can detect the difference of the gray matter or white matter densities while the optimized VBM method can detect the difference of gray matter or white matter volumes in the whole brain. The experiments showed that for the patient group, gray matter density or volumes significantly increased in the right frontal lobe, middle frontal gyrus, vermis, left caudate and parietal lobe, compared with the normal controls. However, in the left frontal lobe and middle frontal gyrus, gray matter density significantly decreased. There is no significant difference in white matter between the two groups. These results are consistent with those of the fMRI, which not only provide the evidence for further study of the pathogeny in PTSD but also validate the efficiency of the VBM methods for detecting the difference in the whole brain structure.
Adult ; Brain ; pathology ; Female ; Frontal Lobe ; pathology ; Humans ; Image Processing, Computer-Assisted ; Magnetic Resonance Imaging ; Male ; Parietal Lobe ; pathology ; Stress Disorders, Post-Traumatic ; pathology

Fetal electrocardiogram (ECG) signals provide important clinical information for early diagnosis and intervention of fetal abnormalities. In this paper, we propose a new method for fetal ECG signal extraction and analysis. Firstly, an improved fast independent component analysis method and singular value decomposition algorithm are combined to extract high-quality fetal ECG signals and solve the waveform missing problem. Secondly, a novel convolutional neural network model is applied to identify the QRS complex waves of fetal ECG signals and effectively solve the waveform overlap problem. Finally, high quality extraction of fetal ECG signals and intelligent recognition of fetal QRS complex waves are achieved. The method proposed in this paper was validated with the data from the PhysioNet computing in cardiology challenge 2013 database of the Complex Physiological Signals Research Resource Network. The results show that the average sensitivity and positive prediction values of the extraction algorithm are 98.21% and 99.52%, respectively, and the average sensitivity and positive prediction values of the QRS complex waves recognition algorithm are 94.14% and 95.80%, respectively, which are better than those of other research results. In conclusion, the algorithm and model proposed in this paper have some practical significance and may provide a theoretical basis for clinical medical decision making in the future.
Algorithms ; Neural Networks, Computer ; Electrocardiography ; Databases, Factual ; Fetus