SEARCH · PubMed Health

Results for “Neural Networks, Computer”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 631 records · Page 35Linked to original sources

PubMed1995

Identification of a hypoperfused segment in bull's-eye myocardial perfusion images using a feed forward neural network.

Artificial neural networks are computer systems which can be trained to recognize similarities in patterns and which learn by example; one of the more straightforward types being the feed forward neural network (FFNN). We previously reported the use of FFNNs for classification of hypoperfusion patterns in bull's-eye representation of 201Tl single photon emission tomography myocardial perfusion studies and showed that, when such an image was divided into 24 segments, FFNNs could detect perfusion defects without direct comparison to a normal data base. This has been extended in this investigation to assess the ability of an FFNN, trained on data in which only a single segment was hypoperfused, to detect this abnormal segment when the hypoperfusion pattern of the other segments in the image varied. The results indicated that the network could reliably determine whether a segment was normally or under perfused, with accuracies of 99% and 100%, respectively, if all other segments were normally perfused. It could also reliably detect a normally perfused segment, even if other segments were hypoperfused, with accuracies of 95% and 98%. The network was less reliable, however, in detecting a hypoperfused segment when other segments were also hypoperfused, showing accuracies of only 74% and 88%.

Blood Flow Velocity↗

PubMedDate not supplied

Prognostic markers in localized prostate cancer: from microscopes to molecules.

Management of patients diagnosed with localized prostate cancer is complicated by the diverse natural history of the disease and variable response to treatment. Prognostic criteria currently in use cannot fully predict tumor behavior and thus limit the ability to recommend treatment regimens with the assurance that they are the best course of action for each individual patient. The search for better prognostic markers is now focussed on the molecular mechanisms which underlay tumor behavior, such as altered cell cycle progression, apoptosis, neuroendocrine differentiation, and angiogenesis. As the number of potential molecular markers increases, it is becoming evident that no single marker will provide the prognostic information necessary to make a significant improvement in patient care. In addition, it seems likely that traditional methods of assessing the prognostic value of this multitude of new markers will prove inadequate. In this review, we briefly examine the current state of prognostication in localized prostate cancer and some of the promising new molecular markers. Next, we examine how new technologies may allow the multiplex analysis of vast numbers of markers and how computational methods such as artificial neural networks will provide meaningful interpretation of the data. In the near future, such an integrated approach may provide a comprehensive prognostic tool for localized prostate cancer.

Antigens, Surface↗

PubMed2005

Synchronized pseudorandom systems and their application to speech communication.

An approach to the synchronization of pseudorandom systems is proposed and applied to secure speech communication. The encoding signal produced by the pseudorandom synchronization scheme passes the random test, and shows much more complex dynamics, better random properties, and greater sensitivity to parameter mismatches than that produced by the active-passive decomposition scheme. Also, two coupled pseudorandom systems can be exactly synchronized despite their different initial states or seeds. Pseudorandom encoding and synchronization may yield great security in communication.

Biophysical Phenomena↗

PubMed2004

A computational model of auditory selective attention.

The human auditory system is able to separate acoustic mixtures in order to create a perceptual description of each sound source. It has been proposed that this is achieved by an auditory scene analysis (ASA) in which a mixture of sounds is parsed to give a number of perceptual streams, each of which describes a single sound source. It is widely assumed that ASA is a precursor of attentional mechanisms, which select a stream for attentional focus. However, recent studies suggest that attention plays a key role in the formation of auditory streams. Motivated by these findings, this paper presents a conceptual framework for auditory selective attention in which the formation of groups and streams is heavily influenced by conscious and subconscious attention. This framework is implemented as a computational model comprising a network of neural oscillators, which perform stream segregation on the basis of oscillatory correlation. Within the network, attentional interest is modeled as a Gaussian distribution in frequency. This determines the connection weights between oscillators and the attentional process, which is modeled as an attentional leaky integrator (ALI). Acoustic features are held to be the subject of attention if their oscillatory activity coincides temporally with a peak in the ALI activity. The output of the model is an "attentional stream," which encodes the frequency bands in the attentional focus at each epoch. The model successfully simulates a range of psychophysical phenomena.

Action Potentials↗

PubMed2002

Prediction of response to hormonal treatment in metastatic breast cancer.

Prediction of outcome and individualization of therapeutic strategies are challenging problems in oncology. Predictive parameters for response to hormonal treatment include the expression of hormone receptor, the extent and location of metastatic spread, disease-free interval, patient age, response to prior hormonal therapy, grading, and more recently, some molecular markers like the expression of HER-2/neu. The use of conventional statistics for prediction of response to hormonal treatment is limited by non-linearities and complex interactions between predictive factors. Modern computational mathematical models like artificial neural networks, entropy-based inductive algorithms or chi(2) interaction detection algorithms can describe these interactions and generate classification models and decision structures. They can be used to predict the clinical outcome for individual patients. In contrast to conventional methods, the level of confidence for the predictions can reach 90% and more. This might be an important step towards further individualization of therapeutic strategies.

Antineoplastic Agents, Hormonal↗

PubMedDate not supplied

Geocomputation techniques for spatial analysis: are they relevant to health data?

Geocomputation is an emerging field of research that advocates the use of computationally intensive techniques such as neural networks, heuristic search, and cellular automata for spatial data analysis. Since increasing amounts of health-related data are collected within a geographical frame of reference, geocomputational methods show increasing potential for health data analysis. This paper presents a brief survey of the geocomputational field, including some typical applications and references for further reading.

Cluster Analysis↗

PubMed1996

Modeling Hermissenda: II. Effects of variations in type-B cell excitability, synaptic strength, and network architecture.

Because the Hermissenda eye is relatively simple and its cells well characterized, it provides an attractive preparation for detailed computational analysis. To examine the neural mechanisms of learning in this system, we developed multicompartmental models of the type-A and type-B photoreceptors, simulated the eye, and asked three questions: First, how do conductance changes affect cells in a network as compared with those in isolation; second, what are the relative contributions of increases in B-cell excitability and synaptic strength to network output; and third, how do these contributions vary as a function of network architecture? We found that reductions in the type-B cells of two K+ currents, IA and IC, differentially affected the type-B cells themselves, with IC reductions increasing firing rate (excitability) in response to light, and IA reductions increasing quantal output (synaptic strength) onto postsynaptic targets. Increases in either type-B cel excitability or synaptic strength, induced directly or indirectly, each suppressed A-cell photoresponses, and the combined effect of both changes occurring together was greater than either alone. To examine the effects of network architecture, we compared the full network with a simple feedforward B-A pair and intermediate configurations. Compared with a feedforward pair, the complete network exhibited greater A-cell sensitivity to B-cell changes. This was due to many factors, including an increased number of B-cells (which increased B-cell impact on A-cells), A-B feedback inhibition (which slowed both cell types and altered spike timing relationships), and B-B lateral inhibition (which reduced B-cell sensitivity to intrinsic biophysical modifications). These results suggest that an emergent property of the network is an increase both in the rate of information acquisition ("learning") and in the amount of information that can be stored ("memory").

Animals↗

PubMed2000

Application of similarity matrices and genetic neural networks in quantitative structure-activity relationships of 2- or 4-(4-Methylpiperazino)pyrimidines: 5-HT(2A) receptor antagonists.

Antagonists of the 5-HT(2A) receptor are being used to treat many psychiatric disorders. The present work focuses on a group of 27 antagonists possessing varying affinities toward the receptor. These are 26 title compounds and clozapine as a reference antagonist. The active conformers of the conformationally flexible ligands were proposed by using the active rigid analogue approach and performing similarity calculations. The calculations involved genetic neural network (GNN) computations deriving QSARs from similarity matrices (SM) with cross-validated correlation coefficients exceeding 0.92. The performance of neural networks with variety of architectures was studied. As the computations were performed for cations and neutral molecules separately, the relevance of the ligand charging is discussed.

Animals↗

PubMed2000

A computerized mastitis decision aid using farm-based records: an artificial neural network approach.

A computer module was developed and tested that used field survey and Dairy Herd Improvement Association (DHIA) data to broadly classify bacterial causes of mastitis in dairy herds. Further development of the computer model could aid interpretation of DHIA data by dairy record processing centers and herd consultants. This diagnostic module was developed with an artificial neural network, a technology that processes complex data in a manner similar to human brain function. Information describing herd management practices, quarter milk samples, and monthly DHIA data was collected from Pennsylvania dairy herds with moderate to high somatic cell counts. This information was used to develop or train an artificial neural network model that discriminated among four categories of bacterial organisms (contagious, environmental, no significant growth, and other) associated with clinical and subclinical mastitis. After training the model, new DHIA and management data were presented to the model to assess its ability to classify bacteriological etiology. When the artificial neural network was used, the probabilities of diagnosing the bacteriologic status from three randomly selected cow groups and from new untested herds ranged from 57 to 71%. Performance of the artificial neural network model was best in herds with higher frequency of minor and contagious pathogens. Prediction results for the same test data with linear discriminant analysis were less successful, ranging from 42 to 57%.

Animals↗

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↗

PubMed2003

Multistability analysis for recurrent neural networks with unsaturating piecewise linear transfer functions.

Multistability is a property necessary in neural networks in order to enable certain applications (e.g., decision making), where monostable networks can be computationally restrictive. This article focuses on the analysis of multistability for a class of recurrent neural networks with unsaturating piecewise linear transfer functions. It deals fully with the three basic properties of a multistable network: boundedness, global attractivity, and complete convergence. This article makes the following contributions: conditions based on local inhibition are derived that guarantee boundedness of some multistable networks, conditions are established for global attractivity, bounds on global attractive sets are obtained, complete convergence conditions for the network are developed using novel energy-like functions, and simulation examples are employed to illustrate the theory thus developed.

Linear Models↗

PubMed1997

Gaussian neural networks for glass bottles inspection: a learning procedure.

In glass bottle inspection, the defects detection is of first importance. For online system detection, high speed and robust detection of faults are highly required. Neural networks have recently, and successfully, been applied to fault detection in many manufacturing processes. In this study, a Gaussian neural network, an extension of the RBF network, trained through a competitive algorithm, has been chosen for fault detection. Four parameters extracted from images of the bottles are used as inputs of the network. The number of Gaussian units is adjusted by an informational criterion. Experimental results show that the performance of this network are better than classical parametric and non parametric classifiers.

Algorithms↗

PubMedDate not supplied

A controlled attractor network model of path integration in the rat.

Cells in several areas of the hippocampal formation show place specific firing patterns, and are thought to form a distributed representation of an animal's current location in an environment. Experimental results suggest that this representation is continually updated even in complete darkness, indicating the presence of a path integration mechanism in the rat. Adopting the Neural Engineering Framework (NEF) presented by Eliasmith and Anderson (2003) we derive a novel attractor network model of path integration, using heterogeneous spiking neurons. The network we derive incorporates representation and updating of position into a single layer of neurons, eliminating the need for a large external control population, and without making use of multiplicative synapses. An efficient and biologically plausible control mechanism results directly from applying the principles of the NEF. We simulate the network for a variety of inputs, analyze its performance, and give three testable predictions of our model.

Action Potentials↗

PubMed1992

Segmenting ultrasound images of the prostate using neural networks.

This paper describes a method for segmenting transrectal ultrasound images of the prostate using feedforward neural networks. Segmenting two-dimensional images of the prostate into prostate and nonprostate regions is required when forming a three-dimensional image of the prostate from a set of parallel two-dimensional images. Three neural network architectures are presented as examples and discussed. Each of these networks was trained using a small portion of a training image segmented by an expert sonographer. The results of applying the trained networks to the entire training image and to adjacent images in the two-dimensional image set are presented and discussed. The final network architecture was also trained with additional data from two other images in the set. The results of applying this retrained network to each of the images in the set are presented and discussed.

Adult↗

PubMed2005

The comparison of different feed forward neural network architectures for ECG signal diagnosis.

The electrocardiograms (ECGs) record the electrical activity of the heart and are used to diagnose many heart disorders. This paper proposes a two-stage feed forward neural network for ECG signal classification. The research is aimed at the design of an intelligent ECG diagnosis tool that can recognise heart abnormalities while reducing the complexity, cost, and response time of the system. A number of neural network architectures are designed and compared for their ability to classify six different heart conditions. Two network architectures based on one stage and two stage feed forward neural networks are chosen for this investigation. The training and testing ECG signals are obtained from MIT-BIH database. The network inputs are comprised of 12 ECG features and 13 compressed components of each heart beat signal. The performance of the different modules as well as the efficiency of the whole system is presented. Among different architectures, a proposed multi-stage network named NET_BST possesses the highest recognition rate of around 93%. Therefore, this network proves to be a suitable candidate in ECG signal diagnosis systems.

Algorithms↗

PubMed2000

Controlling activity fluctuations in large, sparsely connected random networks.

Controlling activity in recurrent neural network models of brain regions is essential both to enable effective learning and to reproduce the low activities that exist in some cortical regions such as hippocampal region CA3. Previous studies of sparse, random, recurrent networks constructed with McCulloch-Pitts neurons used probabilistic arguments to set the parameters that control activity. Here, we extend this work by adding an additional, biologically appropriate, parameter to control the magnitude and stability of activity oscillations. The new constant can be considered to be the rest conductance in a shunting model or the threshold when subtractive inhibition is used. This new parameter is critical for large networks run at low activity levels. Importantly, extreme activity fluctuations that act to turn large networks totally on or totally off can now be avoided. We also show how the size of external input activity interacts with this parameter to affect network activity. Then the model based on fixed weights is extended to estimate activities in networks with distributed weights. Because the theory provides accurate control of activity fluctuations, the approach can be used to design a predictable amount of pseudorandomness into deterministic networks. Such nonminimal fluctuations improve learning in simulations trained on the transitive inference problem.

Computer Simulation↗

PubMedDate not supplied

The intelligent systems in biomedicine laboratory in the Department of Automatic Control and Systems Engineering at the University of Sheffield, UK.

The group has been engaged in research into modelling and control in biomedicine for many years. Initially, this used quantitative approaches but increasingly this has moved towards qualitative techniques, in particular that of fuzzy logic. The current emphasis is on hybrid models (quantitative/qualitative) and hybrid intelligent algorithms (fuzzy logic, neural networks, evolutionary computing) applied into anaesthesia.

Algorithms↗

PubMed2001

Neural network in communication with medical computer system.

The paper presents a concept of an experimental module designed to recognize spoken utterances that cover a limited range of words indispensable in dialogs with computer medical systems. Research into the recognition of spoken words by a module based on artificial neural network is described. Usefulness of the obtained results for surgery-assisting multimedia systems and for a patient simulator supporting medical education of students in case history-taking and diagnosing is also discussed.

Computer Systems↗