Fok-Ching Chong

A Study of Heart Sound and Lung Sound Separation by Independent Component Analysis Technique

In the hospital, using percussion and auscultation are the most common ways for physical examination. Recently, in order to develop tele-medicine and home care system and to assist physician getting better auscultation results; electric stethoscope and computer analysis have become an inevitable trend. However, two important physical signals heart sound and lung sound recorded from chest overlap on spectrum chart. Therefore, in order to reduce human factor (ex. misplace or untrained of using) and minimize correlated effect in computer analysis; its necessary for separated heart sound and lung sound. Independent component analysis can divide these sounds efficiency. In this paper, we use two microphones to collect signals from left and right chest. We have successfully divide heart and lung sounds by fast ICA algorithm. Therefore, it can assist physician examine and also using on tele-medicine and home care by this way

Respiratory Wheeze Detection System

Respiratory sound is associated with many lung diseases. By observing respiratory sound symptoms, we can know more about lung conditions. In this research, we construct an efficient lung sound recording system according to CORSA, and develop a spectrogram process flow technique to object wheeze. It is a low cost and efficient system. In clinic test, we also can precisely objective wheeze up to about 89%

SECURITY BIOSIGNAL TRANSMISSION BASED ON FACE RECOGNITION FOR TELEMEDICINE

In telemedicine, an insecure and vulnerability medicine information system is important for nursing staff and patients. Relatively private information stolen by others still can be corrected. However, if attacked by hackers, mistakes in diagnosis can threaten the patients life. In order to simplify the procedures in the authentication of telemedicine and to emphasize security in the patients data, this paper proposes utilizing the symmetric key cryptography and the biometric authentication. We use a face eigenvector to insert the patients physiological signals and to combine symmetric key cryptography thus protecting the integrity of the patients data and improving the mode of operations.

TWO-DIMENSIONAL STATIC AND DYNAMIC DISPLAY SYSTEM OF BOWEL SOUND MAGNITUDE MAP FOR EVALUATION OF INTESTINAL MOTILITY

The aim of this work is to develop a new technique of two-dimensional (2D) bowel sound magnitude map (BSMM) with multichannel electronic stethoscopes to evaluate the location, intensity, and track of intestinal motility from the abdominal surface in real time. The static BSMM, obtained from the interpolation of captured one-dimensional (1D) signals, demonstrated an activity level of intestinal motility with different colors. It enabled spatial visualization of the sound origin to locate the peristaltic position of bowels. The dynamic BSMM, displayed in either time series or continuous mode, clearly showed the tracking pattern of intestinal motility on the whole abdomen. Our results verified the validation of this system with a computer simulation and the specific detection of bowel sounds (BSs). The detection of physiologic intestinal motility, including that before and after meal or before defecation, is also available with BSMMs. A simple, noninvasive, low-cost, visualizable, and real-time device has been successfully developed in this work.

MRA Images Identification of the Artery Blood Vessel of the Knee with SOM LVQ Neural Networks as Auxiliary

The ways of angiography are divided into two kinds at present: the invasive type and the non invasive type. Because the magnetic resonance angiography (MRA) has advantages of the non invasive type, thus people can accept MRA more easily. Presently, to diagnoses for the initial stage triage of the blood vessel on clinic by MRA mostly. We to be allowed to see clearly that the shape of lower limb artery which like the dendrite and the blood vessel is thick from the trunk to the thin branch, also we can see the narrow embolism and the blocked place through MRA. This study aims to image the artery of blood vessel by MRA assay, and is attempting to use two-dimensional structure of SOM and LVQ to make out topologies for the shape of artery of blood vessel. We expect that MRA could be useful tools for earlier on the quick triage and auxiliary diagnosis of doctors. By actual examples truly prove that patients after peripheral arterial occlusive disease (PAOD) treatment can diagnose effectively, shorten the time of patients waiting for reports and improve the whole efficiency of the medical treatment system

EVALUATING THE UNCERTAINTY OF MEASUREMENT ON BLOOD'S GLUCOSE LEVEL

Judging from the continuous increase in population suffering from chronic illnesses in the past 30 years in Taiwan, we can predict that the number of diabetes victims will reach 1.5 million in 15 years. This increase is global. According to an estimate provided by WTO, one out of two diabetes sufferers is not identified as the illness victim. An estimate of 100 million people in the world are diabetes patients. Although there is currently no way to completely cure diabetes, this disease can be controlled, monitored, and improved through education, research and development of new medication and techniques. However, the quality control of glucose monitoring has posed a stubborn problem to all fields related to the medical realm in Taiwan. By contrast, there is already a well-developed management system of blood glucose measurement in the West. All the standard-setting organizations, such as NCCLS and ISO, have published relevant Standard Operation Procedure (SOP). In Taiwan, we havent had any similar certification mechanism. It is urgent for Taiwan to establish such standards specifically for the yellow race. Now, CNLA has introduced ISO 17025 in clinical test. Although it offers a general guideline, it doesnt specify detailed operation steps. As a result, it cannot offer an accurate result in blood glucose measurement. This paper is focused on ways to evaluate the uncertainty of measurement on blood glucose level based on the standard environment lab for medical device testing in the biomedical engineering department of National Taiwan University Hospital, so as to establish a function of uncertainty of measurement on blood glucose level and make it a stepping stone for certification of the measurement.

AN IMAGE PROCESSING ARCHITECTURE TO ENHANCE IMAGE CONTRAST

To have a good image contrast is an important issue in medical images. This paper introduces a feedback-type image processing architecture that can enhance image contrast without further digital image processing technique, e.g. histogram equalization. Compared with the conventional open-loop imaging system, the images derived by the proposed method has a full-range histogram without causing image distortion, and this is difficult to attain for open-loop imaging system.

The topographic mapping of EEG using the first positive Lyapunov exponent

The electroencephalogram (EEG) signal is known to be chaotic, and it has the characteristics of unpredictability. Dimensional analysis of a chaotic signal is an important index to quantify and qualify its dynamical characteristics. The first positive Lyapunov exponent is one of the dimensional analysis methods, and is a standard method of checking whether a time series is chaotic or not. Here, the authors present a new method to derive the topographic mapping of the EEG. Using the first positive Lyapunov exponent, the derived mapping shows the chaotic state at each site of the cerebral cortex which would be important for neurophysiologists and psychologists.

Neural network for automatic detection of EEG spikes

This paper proposes a scheme for detecting epileptiform of EEG. The scheme uses 16 heuristic features as the input of a back propagation neural network. 300 sharp transients (ST), i.e. spike and sharp waves (SSW), obtained from 12 epilepsy patients and 1000 non-SSW obtained from 10 nonnal subjects are used lo evaluate the performance of this classifier. The overall spike detection accuracy comparing with the inspection of esperienced physicians is 88.7%.

Simulation and solution of the electric dipole model for localizing the EEG spike foci

A scheme bascd on the four-layer inhomogeneous spherical model of t he head with an slcctric dipole in i t , is proposed for localizing the cpilcptic focus. Potential distributions of several siniulated dipoles are used to observe the effect of dipole parameters. According to the results. the highest potential does not always appear in the region near to the dipole location. Spikes for two patients with different disorders are used for localizing the epileptic discharge souces. For one patient with lateralized spikes. we obtain the dipole location close to the inspection of clinical physicians. And for another one with generalized spikes. we fail to localize the discharge source with acceptable accuracy. According to our results, the electric dipole model is concluded to be valuable to localize epileptic discharge sources with the lateralized spikes.