Zhongguo Liu

Microscopic Image Analysis and Recognition On Pathological Cells

According to the features of the configuration and color information on the cancer cells, an adaptive automatic threshold segmentation based on the RGB and HIS color spaces is presented, which is available to segment suspected cancer cells and nucleus from the complex backgrounds in the microscopic images. The edges of the suspected cancer cells and nucleus are detected by using Canny operator. Using the technology of eight-chain code tracking, the feature values of suspected cancer cells are extracted. The feature values consists of the perimeter, the area, the height, the width, the circularity, the rectangularity, the extension and the area ratio between the nucleus and the cytolympth. Based on feature values, a two-round recognition scheme combined with morphologic and colourometry is proposed to recognize and classify the pathological and normal cells. The results show that the proposed algorithm can efficiently segment cell images and receive higher accuracy of cancer cell diagnosis.

Medical Image Conversion with DICOM

As the standard especially for the storage and transmission of medical images, the standard of Digital Imaging and Communications in Medicine (DICOM) is popular to the people of the world. And as a result, almost all the outputs of the computerized tomography (CT), magnetic resonance (MR), digital subtraction angiography (DSA) and ultrasonography (US) are saved as DICOM format. However, the DICOM format files can be opened by the original programs of windows OS, which is not convenient with the further research in image processing. The paper mainly does some research in the conversion from DICOM format files into general image/ media files. The procedure is to convert DICOM format files into bitmaps and then convert the bitmaps into other general image/ media files. The images then can be viewed directly by the original programs of Windows OS, which will facilitate the further researches on image process. The DICOM format files can be displayed while being converted; the images displayed can also be done with some further operations, such as the process of lightness and contrast gradient of image, image filtering and segmentation.

Wearable monitoring system with multiple physiological parameters

A wearable monitoring system with multiple physiological parameter is studied in this paper. It is a physiological monitoring terminal of Home Assistant Robot. Non-invasive monitoring technology is used in this system. The details of ECG monitoring, blood pressure monitoring, blood glucose monitoring and temperature monitoring are discussed in this paper. This system is for home application. It is small in size, easy to use. It plays a positive role in promoting the level of home health care and the first aid of emergency illness.

Study of Feature Classification Methods in BCI Based on Neural Networks

Feature classification is one of the important aspects in brain-computer interfaces (BCI) system. It has been known that a higher precision can be achieved if use neutral networks in a proper way for feature classification. In this paper, three feature identification ways were introduced and discussed. In the experiment of left-right hand classification, the arithmetic of the small mean square difference is proposed and studied, so as to get a good converging in the task classification. The design method of input and output layer for the BP neural network was discussed. Experiment results show that it is a feasible processing algorithm to classify the different events

An embedded EEG analyzing system based on μC/os-II

An EEG analyzing system based on advanced RISC machines (ARM) and μC/os-II real time operating system is discussed in this paper. The detailed system design including the producing of event signals and the synchronization between event signals and EEG signals is described. The details of data acquisition, data preprocessing, data transmitting through USB and system configurations are also contained in the system design. In this paper the design of high capability amplifier and the software of embedded subsystem are discussed. Also the design of realizing multi-task system in μC/os-II, the definition of communicating protocols between PC and the equipment and the detail configurations of USB are given out. The final test shows that the filter behaviors of this equipment are feasible.

Automatic Segmentation on Cell Image Fusing Gray and Gradient Information

To develop an automatic classifying and diagnostic system for the hematopoietic cells from the blood and bone marrow smears stained with Wright-Giemsa, an automated segmentation algorithm fusing gray level, colorful information and mathematical morphological gradient is proposed for segmentation of the nucleated hematopoietic cells (including nucleus and cytoplasm). For the accurate segmentation of the nucleus, the conventional iterative threshold segmentation has been improved. Color information and prior knowledge are fully used by transaction of color spaces for the purpose of cytoplasm segmentation. In order to prevent over-segmentation, the morphological gradient information is used to mark the background, nucleus and cytoplasm. The edge detection is implemented in gray gradient image since the morphological gradient can detect the contour better than other conventional edge detection operators. The success rate is 95.5 % for nucleus and 92.6 % for cytoplasm. The results show that the method is valid and efficient to segment color images from blood and bone marrow smears.

Brainwave Classification Based on Wavelet Entropy and Event-Related Desynchronization

For many years brain-computer interfaces research programs have been very popular. The classification algorithm of the EEG signals has attracted much attention. In this paper, an experiment is designed on imaginary left or right hand movements and a new algorithm is proposed to identify different EEG patterns. Butterworth filter has been applied to retrieve the useful signals. Interference noise has been eliminated using a digital filter. The wavelet entropy is treated as one feature in our approach. The adaptive autoregressive model combined with the event-related desynchronization is used in our research to obtain the other feature. Two obtained features reflect time domain and frequency domain features of EEG signal, and will be used by a BP neural network for training. Simulation has been carried out and the results of the simulation show that this approach can restrain noise disturbance and can effectively express mental states. When used in the classification of special events in brain-computer interface, this approach has some advantage. Moreover, it can be used for the online analysis.

Self Spectrum Window Method in Wigner-Ville Distribution

Wigner-Ville distribution (WVD) is an important type of time-frequency analysis in biomedical signal processing. The cross-term interference in WVD has a disadvantageous influence on its application. In this research, the self spectrum window (SSW) method was put forward to suppress the cross-term interference, based on the fact that the cross-term and auto-WVD-terms in integral kernel function are orthogonal. With the self spectrum window (SSW) algorithm, a real auto-WVD function was used as a template to cross-correlate with the integral kernel function, and the short time Fourier transform (STFT) spectrum of the signal was used as window function to process the WVD in time-frequency plane. The SSW method was confirmed by computer simulation with good analysis results. Satisfactory time-frequency distribution was obtained

Influence of inter-stimulus interval on auditory evoked potentials

In this research, the influence of the preceding auditor stimulus on the auditory-evoked potential (AEP) of the succeeding stimuli was investigated, when the human subjects were presented with a pair of auditory stimuli. We found that the evoked potential of the succeeding stimulus was inhibited completely by the preceding stimulus, when the inter-stimulus interval (ISI) was shorter than 150 ms. The influence was depended on the ISI of two stimuli, the longer was the ISI, the stronger would be the influence. The inhibitory influence by the preceding stimulus might be caused by the neural refractory effect

Extraction of VEP based on third-order correlation based filters and wavelet thresholding denoising method

A new wavelet thresholding function which has continuous derivative was discussed in this research. The wavelet thresholding denoising method and TOC (third-order correlations)-based filtering approach were used in extracting visual evoked potential (VEP). The experimental results showed that the new thresholding function combined with TOC-based filters have good performance in analyzing visual evoked potential (VEP)