Search PubMed⌕ Search

Biomedical subjects

E Micheli-Tzanakou

Publications and source records attributed to E Micheli-Tzanakou.

At least 19 recordsLinked to original sources
PubMed2000

Detection of multiple sclerosis with visual evoked potentials--an unsupervised computational intelligence system.

This paper describes the application of a novel unsupervised pattern recognition system to the classification of the Visual Evoked Potentials (VEP's) of normal and multiple sclerosis (MS) patients. The method combines a traditional statistical feature extractor with a fuzzy clustering method, all implemented in a parallel neural network architecture. The optimization routine, ALOPEX, is used to train the network while decreasing the likelihood of local solutions. The unsupervised system includes a feature extraction and clustering module, trained by the optimization routine ALOPEX. Through maximization of the output variance of each node, and an architecture which excludes redundancy, the feature extraction network retains the most significant Karhunen-Loeve expansion vectors. The clustering module uses a modification to the Fuzzy c-Means (FCM) clustering algorithms, where ALOPEX adjusts a set of cluster centers to minimize an objective error function. The result combines the power of the FCM algorithms with the advantage of a more global solution from ALOPEX. The new pattern recognition system is used to cluster the VEP's of 13 normal and 12 MS subjects. The classification with this technique can, without supervision, separate the patient population into two groups which largely correspond to the MS and control subject groups. A suitable threshold can be chosen so that the recognizer chooses no false negatives. The use of multiple stimulation patterns appears to improve the reliability of the decision. The reasoning of most neural networks in their decision making cannot easily be extracted upon the completion of training. However, due to the linearity of the network nodes, the cluster prototypes of this unsupervised system can be reconstructed to illustrate the reasoning of the system. In this application, this analysis hints at the usefulness of previously unused portions of the VEP in detecting MS. It also indicates a possible use of the system as a training aide.

Adult↗
PubMed2000

Quantitative on-line analysis of physiological data for lesion placement in pallidotomy.

A computerized method of determining the focal point of electrical activity in the pallidum of parkinsonian patients was developed using on-line quantitative physiological data analysis. Thirty patients in a series of 70 were studied in depth. Neuronal activity was recorded from the pallidum using a semi-microelectrode. The signal is inspected visually while its average power, characteristic frequency and complexity are computed. The target locus was indicated by the highest level of global activity in the vicinity of the electrode (signal power maximum), maximal signal complexity and minimal characteristic frequency. Most often, the vertical coordinate required correction. The postoperative clinical and imaging results have indicated the effectiveness of this method.

Adult↗
PubMed1999

Electrophysiological recordings in pallidotomy localized to 3D stereoscopic imaging.

A quantitative on-line analysis of electrical activity in the pallidum of Parkinsonian patients has been developed to determine the focal point of lesioning. A 3D volume image system has been developed to display basal ganglia anatomy and coregister the electrophysiological data within the globus pallidus. Thirty patients undergoing 41 pallidotomies are presented. Neuronal activity from the pallidum is recorded using a semi-microelectrode. Based on this activity, lesioning is performed. Postlesion recordings are made to determine the necessity of additional lesioning. A stereoscopic 3D volume MR image system has been developed that along with on-line signal processing allows visualization of high neural activity in the pallidum and postlesion residual activity.

Action Potentials↗
PubMed1998

Classification of retinal damage by a neural network based system.

The objective of this research is to provide an ophthalmologist with a helpful system, capable of classifying a degree of patients' retinal hemorrhage. The system is composed of four modules: (a) data acquisition module, (b) image Database module, (c) image processing module, (d) image classification module. The system was trained with a modular neural network on a set of 25 images, and tested on a set of 160 images. A training performance of greater than 95% was achieved. The classifying part of the system showed 79% recognition accuracy. Since the testing images were taken from independent sources, we assume that the system should also provide an accurate classification of other image types.

Algorithms↗
PubMed1997

Phase information in visual evoked potentials.

The Visual Evoked Potential (VEP) is an electrophysiological commonly used test in investigating various neurophysiological disorders. Through the years many methods have been developed, but there are not many objective criteria in distinguishing a normal VEP waveform from an abnormal. In this communication we use the phase characteristics of the power spectrum as a criterion of distinguishing normals and abnormals. From our analysis, it was shown that the phase spectrum of a VEP has a certain periodicity in the 0- to 40-Hz region. By studying these periodicities we were able to determine the range of the period that characterizes normal and abnormal populations and to establish an experimental method for objectively examining any kind of VEP waveforms.

Alzheimer Disease↗
PubMed1997

A mobile automated mammography system.

Automated processing of mammograms has been studied for several years. Until the last few years much of the efforts have produced marginal results due to the limitations of inexpensive hardware. Even with the advanced hardware no one has yet taken an entire mammogram and determined whether it is normal or abnormal. We outline a method here to attempt to do just that.

Breast Diseases↗
PubMed1997

Neural networks and blood cell identification.

The objective of this project is to propose a method of identifying cells found in human blood and to classify them based upon their morphological features using neural networks. The project focuses on three major blood cell types, namely, erythrocytes, leukocytes and platelets. The data are collected using peripheral blood smears from clinical patients. The image acquisition requires 100x magnification on all the blood smears, the preprocessing involves the use of median and edge enhance filters; the feature extraction is done by performing the wavelet transform on the images. Finally classification of the blood cell types is done using ALOPEX and Back Propagation trained neural networks. The efficacy of both networks is then compared by comparing their outputs and number of iterations required to reach the final result.

Algorithms↗
PubMed1997

Analysis of pattern reversal visual evoked potentials (PRVEP's) by spline wavelets.

In this study, the pattern-reversal visual evoked potentials (PRVEP's) collected from normal and demented subjects are investigated by applying the quadratic spline wavelet analysis. The data are decomposed into six octave frequency bands. For quantitative purposes, the wavelet coefficients in the residual waveform representing the delta-theta band activity (0-8 Hz) are explored to characterize the (N70-P100-N130) complex. Specifically, the coefficients corresponding to the location of N70, P100, and N130 peaks are investigated for their sign in order to test whether they represent a consistent (N70-P100-N130) complex in the averaged waveform. Waveforms with normal latency (N70-P100-N130) complex are observed to have positive second, negative third, and positive fourth coefficients in amplitude in their residual scale standing for the delta-theta (0-8 Hz) band activity. The method allows for the analysis of oscillatory-phase behavior of the normal and pathological PRVEP's in their delta-theta band based on a few quantitative measures consistent with the time-frequency occurrence of the major components of the evoked potential.

Alzheimer Disease↗
PubMed1995

The protective effects of education on simulated brain injury.

Disturbed intellectual function is an important determinant of long-term recovery after head injury. Residual behavioral disability depends largely upon which hemisphere is damaged and the site of injury within the hemisphere. Resulting neurobehavioral syndromes vary with the pattern of brain insult. While this correlation is important, it is still not well understood how damage to single neurons translates into abnormal behavior. In addition, no currently available technology permits in vivo evaluation of such cells in normal or injured states. While research into brain trauma traditionally emphasize single cell pathology, this level of study is insufficient to clarify how individual cell activity contributes to higher cognition. In contrast, neural network simulations may partially fill this void by predicting biological function. Here, we present data generated by a three-layer neural network that employs the ALOPEX algorithm, capable of learning 10 words. The addition of Gaussian distributed noise into connection weights strengths damaged the network's function; interestingly, the rate and extent of network impairment depended upon the level of learning that occurred during the training period, in agreement with human studies that demonstrate a protective effect of education on subsequent brain injury. Damage to input signals resulted in similar effects on network function. Accordingly, such simulations offer powerful evidence that human behavior may be considered in terms of neuronal cell populations and efforts to preserve brain function at the time of injury should emphasize maintaining neural connections.

Algorithms↗
PubMed1993

Cardiovascular applications of the ALOPEX optimization technique.

ALOPEX is a general optimization process incorporating a cost function containing a large number of parameters which may be simultaneously adjusted until the cost function reaches an optimum (maximum or minimum); local extremes are avoided by introducing random noise into the procedure. In this paper, ALOPEX is incorporated into a simple haemodynamic study in which an electric analogue model of the left ventricle is used to develop equations of myocardial stroke work. Pilot experiments were undertaken in rabbits (n = 5) to gauge the effectiveness of this optimizing technique. In the control state, calculated stroke work for the rabbit was determined to be 50 +/- 7 mmHg ml, while ALOPEX predicted a stroke work of 51 +/- 7 mmHg ml. ALOPEX is capable of following changing cardiovascular states when pharmacological agents are introduced. For example, after nitroprusside treatment, stroke work was reduced by 38 +/- 6% (P < 0.05) while ALOPEX predicted a 42 +/- 4% reduction from baseline (P < 0.05). Methoxamine treatment increased stroke work by 74 +/- 34%, while ALOPEX predicted a 73 +/- 43% increase above control values. There were no statistical differences between calculated and ALOPEX predicted values. Individual model parameters such as maximum left ventricular elastance (Emax) and left ventricular end diastolic volume (EDV) were also predicted correctly by ALOPEX. We have found that the ALOPEX optimization technique is useful in predicting components of multi-parametric functions. In particular, we have shown it to be adaptable to a simple haemodynamic model.

Algorithms↗
PubMed1991

A PC data-base with analytical applications for evoked potentials.

Visual Evoked Potentials (VEPs) are gaining ground in the research for diagnosis of neurological disorders and visual defects, as a non-invasive diagnostic tool. Yet, the methods used towards these goals are not universal and far from able to provide a common ground among researchers in collecting, analyzing and comparing their results. This paper is an attempt to close the gap. We have developed a PC data-base and a set of analysis programs with graphic capabilities, frequency analysis, as well as an objective way of describing the signals obtained during VEP experiments.

Database Management Systems↗
PubMed1989

A parallel implementation of the ALOPEX process.

Optimization techniques have found many applications in science, engineering, and industry. In all applications, the best value of a "cost function" is sought in a well-defined domain; this cost function in general depends on many parameters. An iterative optimization technique has been developed (ALOPEX) that uses feedback in order to optimize the response of a system. The cost function for this process is problem dependent and therefore quite flexible. The method has been applied successfully to different optimization problems such as pattern recognition, receptive field studies in the visual system of animals, curve fitting, etc. We present two special purpose hardware implementations for ALOPEX. The first method takes time O(logN + logm) and uses O(mN2) processing elements. The second method takes O(logN + m) time and uses O(N2) processing elements. Our basic architecture is a binary tree with N2 leaves (equal to the length of the vectors) and therefore had depth O(logN). Different implications of the two approaches will be discussed including similarities with the biological visual process.

Algorithms↗
PubMed1989

A PC-based system for visual evoked potential studies.

An interactive PC-based computer controlled system is described that can be used for collection and analysis of data of Visual Evoked Potentials (VEPs). Visual stimuli are generated on a high-resolution color monitor driven by an Enhanced Graphics Adaptor (EGA). The VEP waveforms are digitized by an A/D converter at a sampling rate of 1 KHz and stored on a hard disk for further analysis. The analysis software includes both time and frequency analysis routines as well as some innovative techniques for the use of the VEPs as a diagnostic measure for various diseases.

Computer Systems↗
PubMed1989

An adaptive approach to spectral analysis of pattern-reversal visual evoked potentials.

A method for spectral analysis of pattern-reversal visual evoked potentials (PRVEP's) is presented that results in spectral peaks of uniform width in the frequency domain for signals with a wide range of time-domain duration. Uniformity of spectral peak width is necessary for accurate comparison of spectra. The desired frequency domain characteristics can be achieved through the application of "tunable" data windows prior to transformation. The Io-sinh (Kaiser), Gaussian, and cosine-taper (Tukey) windows were evaluated as to their ability to produce power spectra with uniform spectral peak width. Objective comparison of power spectra is based on the "spectral parameter," which is a numerical index of power distribution. Application of the method to PRVEP waveforms of normal subjects (N = 20) and to a population of Alzheimer's Disease patients (N = 15) showed the Io-sinh window to be the most effective method, yielding correct classification of all normal and abnormal subjects. The Gaussian window also performed well, with only two misclassifications. Use of the rectangular window resulted in seven misclassifications. The tapered-cosine window was very limited in its applicability, and was about equal in performance to the rectangular window.

Adult↗
PubMed1985

Screen design and visual evoked potentials.

In this paper we present a method to complement the sophisticated mathematical analyses on screen designs. The use of an objective measure of screen "goodness" is employed, namely, the Visual Evoked Potential (VEP) of the humans performing the test. After the screen is designed, the text on the screen is transformed into an intensity pattern using a recursive algorithm. This intensity pattern is used as a stimulus to obtain wave forms from the scalp of the subject, and the wave forms are analyzed as to their frequency content. A 2-D Fourier transform of the screen design is performed and the frequency components of the power spectrum are compared to the frequency components of the wave form. Our results indicate that when a "balanced" and well-designed screen is used as a stimulus, the second harmonic of the VEP wave form is always smaller than the first harmonic. The implications of such an analysis are discussed.

Adult↗
PubMed1984

An automated system for visual studies.

An interactive computer-controlled system is described that is used for visual studies including Visual Evoked Potentials in humans and animals and Visual Receptive Field recordings in animals. Visual stimuli are generated by a display system and the brain activity is monitored by microelectrodes (for animal recordings) and scalp electrodes (for human recordings). The signals are amplified, digitized, and stored. The software uses a response feedback algorithm for mapping the receptive fields. Initially random patterns are presented on a TV monitor and the neural response is recorded. Depending on the response to the pattern and the light distribution in it, the algorithm calculates a new pattern, always trying to maximize the response. As the process goes on, the stimuli patterns become near optimal and thus the receptive field of the neuron is mapped automatically, as a result that for many years has been formed by trial and error. The same system is used for analysis of the recorded results and recordings of the Visual Evoked Potentials in animals and humans. For the human evoked potentials different patterns are generated on the display monitor with a variety of choices, ranging from the simplest (checkerboard and gratings) to the most complicated ones (faces and scenes).

Animals↗
PubMedDate not supplied

Collection and storage of data for evoked potential studies: a database.

A detailed description of a set of programs is presented which is designed for use with subjects tested in a research laboratory primarily with visual evoked potentials (VEPs). It has been written in a way which accommodates other modalities such as brain-stem auditory evoked potentials (BAEPs) and somatosensory evoked potentials (SEPs). It can be used in a clinic or a hospital for collecting patient information, data recordings, and analysis. The programs are implemented on an LSI-11/23 microcomputer and allow for initial subject data entry, entry of data acquired at subsequent visits, data analysis, lists of patient files and data sorts and tabulations. In their present form they are intended to be run by a staff who have little experience with computers and technical skills.

Computers↗