PubMed Health⌕ Search

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 1,459 records · Page 81Linked to original sources
PubMed1993

A decision aid for diagnosis of liver lesions on MRI.

Abdominal magnetic resonance imaging (MRI) plays an important role in the evaluation of liver abnormalities. The interpretation of MR images requires expert training in a rapidly changing field. DAFODILL (Decision Aid for Diagnosing Liver Lesions) is a decision-support tool designed to aid radiologists in the diagnosis of hepatic lesions seen on MRI. DAFODILL uses a knowledge base of MRI findings and a belief-network inference engine to generate probabilistic differential diagnoses of the most commonly encountered hepatic lesions. DAFODILL performs limited image processing to identify clinically relevant features, which are presented to the user for confirmation before they are used by the network. Preliminary evaluation of an initial version of the system suggests that DAFODILL may be a useful tool for radiology residents and nonexpert radiologists in interpreting MR images of the liver.

Artificial Intelligence↗
PubMed2005

How to find decision makers in neural networks.

Nervous systems often face the problem of classifying stimuli and making decisions based on these classifications. The neurons involved in these tasks can be characterized as sensory or motor, according to their correlation with sensory stimulus or motor response. In this study we define a third class of neurons responsible for making perceptual decisions. Our mathematical formalism enables the weighting of neuronal units according to their contribution to decision making, thus narrowing the field for more detailed studies of underlying mechanisms. We develop two definitions of a contribution to decision making. The first definition states that decision making activity can be found at the points of emergence for behavioral correlations in the system. The second definition involves the study of propagation of noise in the network. The latter definition is shown to be equivalent to the first one in the cases when they can be compared. Our results suggest a new approach to analyzing decision making networks.

Animals↗
PubMed1995

Neural networks as an aid in the diagnosis of lymphocyte-rich effusions.

Neural network (NN) technology was applied to digital image analysis data for 112 Papanicolaou-fixed and -stained smears of lymphocyte-rich effusions (LREs). The smears were analyzed with an inexpensive image analysis system assembled in our laboratory. Several models were developed using backpropagation NN development software in an effort to optimize classification of the LREs as reactive lymphocytosis or malignant lymphoma and to analyze the effects of various parameters on classification rates. The greatest specificity and sensitivity of LRE classification were achieved with NN models that consisted of 7 input neurons, including 5 morphometric and 2 densitometric variables, 10 hidden-layer neurons and 1 output neuron. This NN architecture with a sigmoidal transfer function provided a true cross-validation rate of 89.3% of testing data, with a sensitivity of 76.9%, specificity of 93.0% and shrinkage of 10.7%. The same NN architecture with a step transfer function provided a true cross-validation rate of 95.3%, sensitivity of 85.7%, specificity of 97.6% and shrinkage of 0%. The effects of various parameters, such as network size, shrinkage and ratio of sample size to input layer size, on NN accuracy are discussed.

Ascitic Fluid↗
PubMed1998

A self-organizing neural network architecture for navigation using optic flow.

This article describes a self-organizing neural network architecture that transforms optic flow and eye position information into representations of heading, scene depth, and moving object locations. These representations are used to navigate reactively in simulations involving obstacle avoidance and pursuit of a moving target. The network's weights are trained during an action-perception cycle in which self-generated eye and body movements produce optic flow information, thus allowing the network to tune itself without requiring explicit knowledge of sensor geometry. The confounding effect of eye movement during translation is suppressed by learning the relationship between eye movement outflow commands and the optic flow signals that they induce. The remaining optic flow field is due to only observer translation and independent motion of objects in the scene. A self-organizing feature map categorizes normalized translational flow patterns, thereby creating a map of cells that code heading directions. Heading information is then recombined with translational flow patterns in two different ways to form maps of scene depth and moving object locations. Most of the learning processes take place concurrently and evolve through unsupervised learning. Mapping the learned heading representations onto heading labels or motor commands requires additional structure. Simulations of the network verify its performance using both noise-free and noisy optic flow information.

Computer Simulation↗
PubMed1997

Image segmentation based on oscillatory correlation.

We study the image segmentation on the basis of locally excitatory, globally inhibitory oscillator networks (LEGION), whereby the phases of oscillators encode the binding of pixels. We introduce a lateral potential for each oscillators so that only oscillators with strong connections from their neighborhood can develop high potentials. Based on the concept of the lateral potential, a solution to remove noisy regions in an image is proposed for LEGION, so that it suppresses the oscillators corresponding to noisy regions but without affecting those corresponding to major regions. We show that the resulting oscillator network separates an image into several major regions, plus a background consisting of all noisy regions, and we illustrate network properties by computer stimulation. The network exhibits a natural capacity in segmenting images. The oscillatory dynamics leads to a computer algorithm, which is applied successfully to segmenting real gray-level images. A number of issues regarding biological plausibility and perceptual organization are discussed. We argue that LEGION provides a novel and effective framework for image segmentation and figure-ground segregation.

Algorithms↗
PubMed1994

Quantitation of grey matter, white matter, and cerebrospinal fluid from spin-echo magnetic resonance images using an artificial neural network technique.

An operator independent technique has been developed to quantitate the volume of white matter (WM), grey matter (GM), and cerebrospinal fluid (CSF) using spin-echo magnetic resonance images. Using skull stripped spin-echo images, CSF was removed using an automated thresholding technique. The bimodal histogram of the remaining images was used to train a perceptron and a single hidden layer neural network to output the percentage of GM and WM in the image. The output values were compared with those of a semiautomated technique employing a least square fitting technique [graduated nonconvexity algorithm (GNC)] applied to the bimodal histogram. This semiautomated technique allowed for intervention by the radiologist. Fourteen normal volunteers with eight contiguous slices each were analyzed. The individual percentages of WM, GM, and CSF of 40 slices from five subjects not used in the training set as well as the total percentages of GM, WM, and CSF in each individual were predicted using the two artificial network architectures. GM, WM, and CSF percentages were predicted within 7% for individual slices while total percentages of WM, GM, and CSF were computed accurately with an absolute error of less than 5% when compared to the semiautomated technique involving a trained neuroradiologist.

Adult↗
PubMed1998

Neural dynamics of short and medium-term motor control effects of levodopa therapy in Parkinson's disease.

A neural network model of movement control in normal and Parkinson's disease (PD) conditions is proposed to simulate the time-varying dose-response relationship underlying the effects of levodopa on movement amplitude and movement duration in PD patients. Short and long-term dynamics of cell activations and neurotransmitter mechanisms underlying the differential expression of neuropeptide messenger RNA within the basal ganglia striatum are modeled to provide a mechanistic account for the effects of levodopa medication on motor performance (e.g. the pharmacodynamics). Experimental and neural network simulation data suggest that levodopa therapy in Parkinson's disease has differential effects on cell activities, striatal neuropeptides, and motor behavior. In particular, it is shown how dopamine depletion in the striatum may modulate differentially the level of substance P and enkephalin messenger RNA in the direct and indirect basal ganglia pathways. This dissociation in the magnitude and timing of peptide expression causes an imbalance in the opponently organized basal ganglia pathways which results in Parkinsonian motor deficits. The model is validated with experimental data obtained from handwriting movements performed by PD subjects before and after medication intake. The results suggest that fine motor control analysis and network modeling of the effects of dopamine in motor control are useful tools in drug development and in the optimization of pharmacological therapy in PD patients.

Aged↗
PubMed2005

Modeling and output tracking of transverse flux permanent magnet machines using high gain observer and RBF neural network.

This paper deals with modeling and adaptive output tracking of a transverse flux permanent magnet machine as a nonlinear system with unknown nonlinearities by utilizing high gain observer and radial basis function networks. The proposed model is developed based on computing the permeance between rotor and stator using quasiflux tubes. Based on this model, the techniques of feedback linearization and Hinfinity control are used to design an adaptive control law for compensating the unknown nonlinear parts, such as the effect of cogging torque, as a disturbance is decreased onto the rotor angle and angular velocity tracking performances. Finally, the capability of the proposed method in tracking both the angle and the angular velocity is shown in the simulation results.

Algorithms↗
PubMed2004

Context-dependent selection of visuomotor maps.

BACKGROUND: Behavior results from the integration of ongoing sensory signals and contextual information in various forms, such as past experience, expectations, current goals, etc. Thus, the response to a specific stimulus, say the ringing of a doorbell, varies depending on whether you are at home or in someone else's house. What is the neural basis of this flexibility? What mechanism is capable of selecting, in a context-dependent way an adequate response to a given stimulus? One possibility is based on a nonlinear neural representation in which context information regulates the gain of stimulus-evoked responses. Here I explore the properties of this mechanism. RESULTS: By means of three hypothetical visuomotor tasks, I study a class of neural network models in which any one of several possible stimulus-response maps or rules can be selected according to context. The underlying mechanism based on gain modulation has three key features: (1) modulating the sensory responses is equivalent to switching on or off different subpopulations of neurons, (2) context does not need to be represented continuously, although this is advantageous for generalization, and (3) context-dependent selection is independent of the discriminability of the stimuli. In all cases, the contextual cues can quickly turn on or off a sensory-motor map, effectively changing the functional connectivity between inputs and outputs in the networks. CONCLUSIONS: The modulation of sensory-triggered activity by proprioceptive signals such as eye or head position is regarded as a general mechanism for performing coordinate transformations in vision. The present results generalize this mechanism to situations where the modulatory quantity and the input-output relationships that it selects are arbitrary. The model predicts that sensory responses that are nonlinearly modulated by arbitrary context signals should be found in behavioral situations that involve choosing or switching between multiple sensory-motor maps. Because any relevant circumstancial information can be part of the context, this mechanism may partly explain the complex and rich behavioral repertoire of higher organisms.

Action Potentials↗
PubMed2004

Neural network model to generate head swing in locomotion of Caenorhabditis elegans.

Computer simulation of the neural network composed of the head neurons of Caenorhabditis elegans was performed to reconstruct the realistic changes in the membrane potential of motoneurons in swinging the head for coordinated forward locomotion. The model neuron had ion channels for calcium and potassium, whose parameters were obtained by fitting the experimental data. Transmission properties of the chemical synapses were set as graded. The neural network involved in forward movement was extracted by tracing the neuronal activity flow upstream from the motoneurons connected to the head muscles. Simulations were performed with datasets, which included all combinations of the excitatory and inhibitory properties of the neurons. In this model, a pulse input entered only from motoneuron VB1, and activation of the stretch receptors on SAA neurons was necessary for the periodic bending. The synaptic output property of each neuron was estimated for the alternate contraction of the dorsal and ventral muscles. The AIB neuron was excitatory, RIV and SMD neurons seemed to be excitatory and RMD and SAA neurons seemed to be inhibitory. With datasets violating Dale's principle for the SMB neuron, AIB neuron was excitatory and RMD neuron was inhibitory. RIA, RIV and SMD neurons seemed to be excitatory.

Animals↗
PubMed2005

An analysis of neural models for walking control.

A large space of different neural models exists from simple mathematical abstractions to detailed biophysical representations with strongly differing levels of complexity and biological relevance. Previous comparisons between models have looked at biological realism or mathematical tractability rather than expressive power. This paper, however, investigates whether more sophisticated models are better suited to a complex sensorimotor control task than simpler ones, or whether the more general nature of groups of the simpler neurons allows them to collectively solve complex tasks better despite their individual simplicity. Many models have been proposed or used for sensorimotor control tasks such as the control of locomotion. Four such neural models with varying levels of complexity were chosen. Controllers made of networks of each neural type were evolved to generate locomotion in a simulated dynamically stable four-legged robot using a genetic algorithm. The problem domain was chosen as one for which no simple solution could be hand crafted and which, with its tight sensorimotor coupling, had strongly time-dependent properties as is common in many biological control tasks. Analysis of the results shows that the most complex and biologically based model is significantly better at walking control, even producing recognizable gaits.

Algorithms↗
PubMed2006

Self-organizing path integration using a linked continuous attractor and competitive network: path integration of head direction.

A key issue is how networks in the brain learn to perform path integration, that is update a represented position using a velocity signal. Using head direction cells as an example, we show that a competitive network could self-organize to learn to respond to combinations of head direction and angular head rotation velocity. These combination cells can then be used to drive a continuous attractor network to the next head direction based on the incoming rotation signal. An associative synaptic modification rule with a short term memory trace enables preceding combination cell activity during training to be associated with the next position in the continuous attractor network. The network accounts for the presence of neurons found in the brain that respond to combinations of head direction and angular head rotation velocity. Analogous networks in the hippocampal system could self-organize to perform path integration of place and spatial view representations.

Action Potentials↗
PubMed1992

Neural network models of sound localization based on directional filtering by the pinna.

Three-layer neural-network functions were developed to transform spectral representations of pinna-filtered stimuli at the input to a space-mapped representation of sound-source direction at the output. The inputs are modeled after transfer functions of the external ear of the cat; the output is modeled on the spatial sensitivity of superior colliculus neurons. Network solutions are obtained by backpropagation and by a method that enforces uniform task distribution in the hidden layer of the model. Solutions are characterized using bandlimited inputs to study the relative strength of potential sound localization cues in various frequency regions. This analysis suggests that the frequency region containing the first spectral notch (5-18 kHz) provides the best localization cues. Response properties of model neurons were studied using input patterns modeled after auditory nerve response profiles to pure tones at various frequencies and sound levels. The response properties of hidden layer model neurons resemble cochlear nucleus types III and IV and their composites. Neurons in both hidden and output layers show the properties of spectral notch detectors. Although neural networks have limitations as models of real neural systems, the results illustrate how they can provide insight into the computation of complex transformations in the nervous system.

Auditory Perception↗
PubMed2005

A novel wavelet neural network based pathological stage detection technique for an oral precancerous condition.

AIM: To describe a novel neural network based oral precancer (oral submucous fibrosis; OSF) stage detection method. METHOD: The wavelet coefficients of transmission electron microscopy images of collagen fibres from normal oral submucosa and OSF tissues were used to choose the feature vector which, in turn, was used to train the artificial neural network. RESULTS: The trained network was able to classify normal and oral precancer stages (less advanced and advanced) after obtaining the image as an input. CONCLUSIONS: The results obtained from this proposed technique were promising and suggest that with further optimisation this method could be used to detect and stage OSF, and could be adapted for other conditions.

Algorithms↗
PubMed1992

A neural network model rapidly learning gains and gating of reflexes necessary to adapt to an arm's dynamics.

Effects of dynamic coupling, gravity, inertia and the mechanical impedances of the segments of a multi-jointed arm are shown to be neutralizable through a reflex-like operating three layer static feedforward network. The network requires the proprioceptively mediated actual state variables (here angular velocity and position) of each arm segment. Added neural integrators (and/or differentiators) can make the network exhibit dynamic properties. Then, actual feedback is not necessary and the network can operate in a pure feedforward fashion. Feedforward of an additional load can easily be implemented into the network using "descendent gating", and a negative feedback control loop added to the feedforward control reduces errors due to external noise. A training, which combines a least squared error based simultaneous learning rule (LSQ-rule) with a "self-imitation algorithm" based on direct inverse modeling, enables the network to acquire the whole inverse dynamics, limb parameters included, during one short training movement. The considerations presented also hold for multi-jointed manipulators.

Animals↗
PubMedDate not supplied

Neural network analysis of breast cancer from MRI findings.

PURPOSE: To evaluate how much the experience of radiologists affects the performance of an artificial neural network (ANN) trained by two highly experienced radiologists. MATERIALS AND METHODS: Before biopsy two experienced radiologists reviewed the MR images of 100 adult patients with suspicious breast lesions and evaluated their findings based on six features. This database was then used to train a three-layered feed-forward neural network. The network's generalizing ability was then tested to predict the outcome of biopsy in 56 new patients' records which were extracted by 10 participating radiologists. The MRI findings of each reader were presented to the ANN to evaluate the effect of various levels of experience on the output of the ANN. The performance of the ANN was then compared with that of attendant physicians in terms of sensitivity, specificity, and accuracy as well as ROC analysis. RESULTS: The best ANN outcome offered a correct diagnosis in 40 of 41 of the patients with malignant breast cancer and 10 of 15 with benign entity presented in the testing set. The output of the trained ANN outperformed the attendant radiologists with low levels of experience and showed comparable performance with radiologists with higher levels of experience. CONCLUSIONS: The ANN is able to work as a backup system to assist radiologists in the diagnosis of breast cancer.

Adolescent↗
PubMedDate not supplied

Integration of form and motion within a generative model of visual cortex.

One of the challenges faced by the visual system is integrating cues within and across processing streams for inferring scene properties and structure. This is particularly apparent in the inference of object motion, where psychophysical experiments have shown that integration of motion signals, distributed across space, must also be integrated with form cues. This has led several to conclude that there exist mechanisms which enable form cues to 'veto' or completely suppress ambiguous motion signals. We describe a probabilistic approach which uses a generative network model for integrating form and motion cues using the machinery of belief propagation and Bayesian inference. We show, using computer simulations, that motion integration can be mediated via a local, probabilistic representation of contour ownership, which we have previously termed 'direction of figure'. The uncertainty of this inferred form cue is used to modulate the covariance matrix of network nodes representing local motion estimates in the motion stream. We show with results for two sets of stimuli that the model does not completely suppress ambiguous cues, but instead integrates them in a way that is a function of their underlying uncertainty. The result is that the model can account for the continuum of bias seen for motion coherence and perceived object motion in psychophysical experiments.

Bayes Theorem↗