Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Neural network”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 883 records · Page 49Linked to original sources
PubMed2000

PCR based high risk HPV testing is superior to neural network based screening for predicting incident CIN III in women with normal cytology and borderline changes.

BACKGROUND/AIMS: To improve the accuracy of conventional cytology in cervical cancer screening, high risk human papillomavirus (HPV) testing and neural network based screening have been developed. This study assessed the power of both techniques to detect women at risk of developing incident CIN III; that is, CIN III detected during the follow up of women with normal cytology and borderline nuclear changes. METHODS: A cohort of 2250 women, 34-54 years of age, who attended population based cervical cancer screening from 1988 to 1991 and had normal smears or borderline nuclear changes was followed. All smears were tested for high risk HPV and the smears were rescreened using neural network based screening. The value of neural network based screening for predicting incident CIN III during a mean follow up period of 6.4 years was compared with that of high risk HPV testing. In addition, morphological markers presumed to be related to HPV were correlated with HPV status. RESULTS: Thirteen (0.6%) women had incident CIN III. Both high risk HPV positivity and abnormal cytology were associated with an increased risk for incident CIN III (odds ratio, 240 and 22, respectively) and high risk HPV positivity was associated with abnormal cytology. The sensitivity of high risk HPV testing for predicting incident CIN III was much higher than that of neural network based screening (92% and 46%, respectively). None of the morphological markers assessed, including koilocytosis, was correlated with high risk HPV status. CONCLUSION: High risk HPV testing is superior to neural network based screening in identifying women at risk of developing CIN III. For women with normal cytology and borderline changes and a negative high risk HPV test, the screening interval can be considerably prolonged.

Adult↗
PubMed2001

Estimation of oxygen mass transfer coefficient in stirred tank reactors using artificial neural networks.

The estimation of volumetric mass transfer coefficient, k(L)a, in stirred tank reactors using artificial neural networks has been studied. Several operational conditions (N and V(s)), properties of fluid (µ(a)) and geometrical parameters (D and T) have been taken into account. Learning sets of input-output patterns were obtained by k(L)a experimental data in stirred tank reactors of different volumes. The inclusion of prior knowledge as an approach which improves the neural network prediction has been considered. The hybrid model combining a neural network together with an empirical equation provides a better representation of the estimated parameter values. The outputs predicted by the hybrid neural network are compared with experimental data and some correlations previously proposed in the literature for tanks of different sizes.

Journal Article↗
PubMed2004

Artificial neural network modelling of megavoltage photon dose distributions.

An artificial neural network (NN) has been used to model the two-dimensional dose distributions from a Varian 2100C linac. The network was trained using depth dose data for 6 and 10 MV x-rays, collected during the linac commissioning phase. During training, the number of iterations and hidden nodes was adjusted manually until acceptable agreement between measured and predicted data was obtained. In order to validate the network a subset of the data was set aside and not used for training. This enabled the performance of the network to be investigated in terms of generalization and accuracy, together with its ability to interpolate between different field sizes and positions in the beam. Finally, the network was used to generate data points over a 2D grid so that isodose distributions could be visualized. Good agreement was found between measured data and that produced by the trained neural network.

Body Burden↗
PubMed1994

Simulator for neural networks and action potentials: description and application.

1. We describe a simulator for neural networks and action potentials (SNNAP) that can simulate up to 30 neurons, each with up to 30 voltage-dependent conductances, 30 electrical synapses, and 30 multicomponent chemical synapses. Voltage-dependent conductances are described by Hodgkin-Huxley type equations, and the contributions of time-dependent synaptic conductances are described by second-order differential equations. The program also incorporates equations for simulating different types of neural modulation and synaptic plasticity. 2. Parameters, initial conditions, and output options for SNNAP are passed to the program through a number of modular ASCII files. These modules can be modified by commonly available text editors that use a conventional (i.e., character based) interface or by an editor incorporated into SNNAP that uses a graphical interface. The modular design facilitates the incorporation of existing modules into new simulations. Thus libraries can be developed of files describing distinctive cell types and files describing distinctive neural networks. 3. Several different types of neurons with distinct biophysical properties and firing properties were simulated by incorporating different combinations of voltage-dependent Na+, Ca2+, and K+ channels as well as Ca(2+)-activated and Ca(2+)-inactivated channels. Simulated cells included those that respond to depolarization with tonic firing, adaptive firing, or plateau potentials as well as endogenous pacemaker and bursting cells. 4. Several types of simple neural networks were simulated that included feed-forward excitatory and inhibitory chemical synaptic connections, a network of electrically coupled cells, and a network with feedback chemical synaptic connections that simulated rhythmic neural activity. In addition, with the use of the equations describing electrical coupling, current flow in a branched neuron with 18 compartments was simulated. 5. Enhancement of excitability and enhancement of transmitter release, produced by modulatory transmitters, were simulated by second-messenger-induced modulation of K+ currents. A depletion model for synaptic depression was also simulated. 6. We also attempted to simulate the features of a more complicated central pattern generator, inspired by the properties of neurons in the buccal ganglia of Aplysia. Dynamic changes in the activity of this central pattern generator were produced by a second-messenger-induced modulation of a slow inward current in one of the neurons.

Action Potentials↗
PubMed2002

Explosives detection using prompt-gamma neutron activation and neural networks.

This work describes a study of the application of a neural network to determine the presence of explosives using the neutron capture prompt gamma-ray spectra of the substances as patterns which were simulated via Monte Carlo N-particle transport code, version 4B. After the training of the neural networks, it was possible to determine the presence of the C-4 explosive, even when they were occluded by several materials. The neural network was a powerful tool, able to recognize prompt gamma-ray explosive patterns in spite of the presence of occluding materials. Besides that, the network was able to generalize, identify the presence of explosive in cases in which it had not been trained. In that way, it was revealed as a potential tool for in situ inspection systems.

Explosions↗
PubMed2001

Impact of different variables on the outcome of patients with clinically confined prostate carcinoma: prediction of pathologic stage and biochemical failure using an artificial neural network.

BACKGROUND: The advent of advanced computing techniques has provided the opportunity to analyze clinical data using artificial intelligence techniques. This study was designed to determine whether a neural network could be developed using preoperative prognostic indicators to predict the pathologic stage and time of biochemical failure for patients who undergo radical prostatectomy. METHODS: The preoperative information included TNM stage, prostate size, prostate specific antigen (PSA) level, biopsy results (Gleason score and percentage of positive biopsy), as well as patient age. All 309 patients underwent radical prostatectomy at the University of Colorado Health Sciences Center. The data from all patients were used to train a multilayer perceptron artificial neural network. The failure rate was defined as a rise in the PSA level > 0.2 ng/mL. The biochemical failure rate in the data base used was 14.2%. Univariate and multivariate analyses were performed to validate the results. RESULTS: The neural network statistics for the validation set showed a sensitivity and specificity of 79% and 81%, respectively, for the prediction of pathologic stage with an overall accuracy of 80% compared with an overall accuracy of 67% using the multivariate regression analysis. The sensitivity and specificity for the prediction of failure were 67% and 85%, respectively, demonstrating a high confidence in predicting failure. The overall accuracy rates for the artificial neural network and the multivariate analysis were similar. CONCLUSIONS: Neural networks can offer a convenient vehicle for clinicians to assess the preoperative risk of disease progression for patients who are about to undergo radical prostatectomy. Continued investigation of this approach with larger data sets seems warranted.

Adult↗
PubMed1996

Evolutionary optimization in quantitative structure-activity relationship: an application of genetic neural networks.

A new hybrid method (GNN) combining a genetic algorithm and an artificial neural network has been developed for quantitative structure-activity relationship (QSAR) studies. A suitable set of molecular descriptors are selected by a genetic algorithm. This set serves as input to a neural network, in which model-free mapping of multivariate data is performed. Multiple predictors are generated that are superior to results obtained from previous studies of the Selwood data set, which is used to test the method. The neural network technique provides a graphical description of the functional form of the descriptors that play an important role in determining drug activity. This can serve as an aid in future design of drug analogues. The effectiveness of GNN is tested by comparing its results with a benchmark obtained by exhaustive enumeration. Different fitness strategies that tune the evolution of genetic models are examined, and QSARs with higher predictiveness are found. From these results, a composite model is constructed by averaging predictions from several high-ranking models. The predictions of the resulting QSAR should be more reliable than those derived from a single predictor because it makes greater use of information and also permits error estimation. An analysis of the sets of descriptors selected by GNN shows that it is essential to have one each for the steric, electrostatic, and hydrophobic attributes of a drug candidate to obtain a satisfactory QSAR for this data set. This type of result is expected to be of general utility in designing and understanding QSAR.

Algorithms↗
PubMed1998

Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results.

In this paper, we present a review of some recent works on approximation by feedforward neural networks. A particular emphasis is placed on the computational aspects of the problem, i.e. we discuss the possibility of realizing a feedforward neural network which achieves a prescribed degree of accuracy of approximation, and the determination of the number of hidden layer neurons required to achieve this accuracy. Furthermore, a unifying framework is introduced to understand existing approaches to investigate the universal approximation problem using feedforward neural networks. Some new results are also presented. Finally, two training algorithms are introduced which can determine the weights of feedforward neural networks, with sigmoidal activation neurons, to any degree of prescribed accuracy. These training algorithms are designed so that they do not suffer from the problems of local minima which commonly affect neural network learning algorithms.

Journal Article↗
PubMed2005

[Exemplary classification of otolaryngologic data using the Kohonen artificial neural network].

An exemplary classification of otolaryngological data with use of the Kohonen artificial neural network is presented along with an evaluation of grouping effectiveness. The study was based on 220 patients with otosclerosis, including 184 women and 36 men, aged 16-68, operated at the Otosurgery Department, Medical University of Lodz in 1984-1992. The neural network distinguished 3 clusters considerably differing in air and bone conduction preoperatively and as a result in the values of postoperative air-bone gap. The effectiveness of classification was also exhibited in congruent with previous knowledge differences between clusters in many other variables not presented to the neural network.

Adolescent↗
PubMed2000

Associative memory retrieval induced by fluctuations in a pulsed neural network.

An associative memory retrieval in a pulsed neural network composed of the FitzHugh-Nagumo neurons is investigated. The memory is represented in the spatio-temporal firing pattern of the neurons, and the memory retrieval is accomplished using the fluctuations in the system. The storage capacity of the network is investigated numerically. It is demonstrated that this pulsed neural network is capable of an alternate retrieval of two patterns.

Action Potentials↗
PubMed1996

Neural networks in petroleum engineering: a case study.

A multilayer neural network has been used for deciding which oil reservoir layer has to be perforated. Many network architectures were tested until we found those with the best generalization capability. The network performs better than human experts and its achievements are higher than the historical average in the test area. As in other applications of neural networks, the learning capability improves with more hidden neurons but the generalization does not.

Algorithms↗
PubMed2002

Predicting the presence of acute pulmonary embolism: a comparative analysis of the artificial neural network, logistic regression, and threshold models.

OBJECTIVE: The objective of this study was to determine whether an artificial neural network, a new data analysis method, offers increased performance over conventional logistic regression in predicting the presence of a pulmonary embolism for patients in a well-known data set. MATERIALS AND METHODS: Data from the 1064 patients who received an angiographically based diagnosis of pulmonary embolism in the Prospective Investigation of Pulmonary Embolism Diagnosis study were encoded using a previously described method. The 21 input variables represented abnormalities identified on each patient's ventilation-perfusion scan and chest radiograph. Two methods-an artificial neural network with one hidden layer and a multivariate logistic regression-were compared for accuracy in predicting the presence or absence of pulmonary embolism on subsequent pulmonary arteriography. RESULTS: No significant difference was observed between the two methods. Areas under the receiver operating characteristic curves +/- standard deviation were 0.78 +/- 0.02 for the artificial neural network model and 0.79 +/- 0.02 for the logistic regression model. Furthermore, use of these two methods resulted in no more diagnostic accuracy than did the use of a simple threshold model based only on the number of subsegmental perfusion defects, which was the dominant input variable. CONCLUSION: In the study population, the usefulness of data from ventilation-perfusion scans as predictors of the presence of a pulmonary embolism was similar for the three analytic methods, a finding that reinforces the importance of making comparisons to simpler or more established methods when performing studies involving complex analytic models, such as artificial neural networks.

Acute Disease↗
PubMed2005

Application of artificial neural network to fMRI regression analysis.

We used an artificial neural network (ANN) to detect correlations between event sequences and fMRI (functional magnetic resonance imaging) signals. The layered feed-forward neural network, given a series of events as inputs and the fMRI signal as a supervised signal, performed a non-linear regression analysis. This type of ANN is capable of approximating any continuous function, and thus this analysis method can detect any fMRI signals that correlated with corresponding events. Because of the flexible nature of ANNs, fitting to autocorrelation noise is a problem in fMRI analyses. We avoided this problem by using cross-validation and an early stopping procedure. The results showed that the ANN could detect various responses with different time courses. The simulation analysis also indicated an additional advantage of ANN over non-parametric methods in detecting parametrically modulated responses, i.e., it can detect various types of parametric modulations without a priori assumptions. The ANN regression analysis is therefore beneficial for exploratory fMRI analyses in detecting continuous changes in responses modulated by changes in input values.

Adult↗
PubMed2003

Automatic assessment of levodopa-induced dyskinesias in daily life by neural networks.

We developed an objective and automatic procedure to assess the severity of levodopa-induced dyskinesia (LID) in patients with Parkinson's disease during daily life activities. Thirteen patients were continuously monitored in a home-like situation for a period of approximately 2.5 hours. During this time period, the patients performed approximately 35 functional daily life activities. Behavior of the patients was measured using triaxial accelerometers, which were placed at six different positions on the body. A neural network was trained to assess the severity of LID using various variables of the accelerometer signals. Neural network scores were compared with the assessment by physicians, who evaluated the continuously videotaped behavior of the patients off-line. The neural network correctly classified dyskinesia or the absence of dyskinesia in 15-minute intervals in 93.7, 99.7, and 97.0% for the arm, trunk, and leg, respectively. In the few cases of misclassification, the rating by the neural network was in the class next to that indicated by the physicians using the AIMS score (scale 0-4). Analysis of the neural networks revealed several new variables, which are relevant for assessing the severity of LID. The results indicate that the neural network can accurately assess the severity of LID and could distinguish LID from voluntary movements in daily life situations.

Activities of Daily Living↗
PubMed2006

A stable learning algorithm for block-diagonal recurrent neural networks: application to the analysis of lung sounds.

A novel learning algorithm, the Recurrent Neural Network Constrained Optimization Method (RENNCOM) is suggested in this paper, for training block-diagonal recurrent neural networks. The training task is formulated as a constrained optimization problem, whose objective is twofold: (1) minimization of an error measure, leading to successful approximation of the input/output mapping and (2) optimization of an additional functional, the payoff function, which aims at ensuring network stability throughout the learning process. Having assured the network and training stability conditions, the payoff function is switched to an alternative form with the scope to accelerate learning. Simulation results on a benchmark identification problem demonstrate that, compared to other learning schemes with stabilizing attributes, the RENNCOM algorithm has enhanced qualities, including, improved speed of convergence, accuracy and robustness. The proposed algorithm is also applied to the problem of the analysis of lung sounds. Particularly, a filter based on block-diagonal recurrent neural networks is developed, trained with the RENNCOM method. Extensive experimental results are given and performance comparisons with a series of other models are conducted, underlining the effectiveness of the proposed filter.

Algorithms↗
PubMed2006

Global exponential stability of recurrent neural networks with time-varying delays in the presence of strong external stimuli.

This paper presents new theoretical results on the global exponential stability of recurrent neural networks with bounded activation functions and bounded time-varying delays in the presence of strong external stimuli. It is shown that the Cohen-Grossberg neural network is globally exponentially stable, if the absolute value of the input vector exceeds a criterion. As special cases, the Hopfield neural network and the cellular neural network are examined in detail. In addition, it is shown that criteria herein, if partially satisfied, can still be used in combination with existing stability conditions. Simulation results are also discussed in two illustrative examples.

Animals↗
PubMed2000

Neural network prediction of prostate tissue composition based on magnetic resonance imaging analysis. A pilot study.

OBJECTIVE: To develop a neural network model that estimates prostate histology using magnetic resonance imaging (MRI). STUDY DESIGN: Fifty-three men with lower urinary tract symptoms (average age = 63.8 +/- 8.9 years) underwent a prostate MRI (T2) and sextant biopsy of the prostate. Masson Trichome and immunohistochemical prostate-specific antigen staining of the biopsy material were used to calculate the amount of stroma and epithelium in the inner gland (central plus transition zone). MRIs were normalized to the mean intensity of the obturator internus muscle for comparative analyses. Gray scale and texture features were extracted from the inner gland in the midsection transverse MRI slice. Clinical and image variables were used in two neural networks predicting a high amount of stroma and a high amount of epithelium, respectively. RESULTS: The positive and negative predictive values of the stroma and epithelium neural networks were 95%, 69% and 65%, 92%, respectively. CONCLUSION: These data suggest that the combined use of these neural networks may predict patient response to medical therapy targeting prostatic stroma or epithelium.

Adult↗
PubMed2000

Use of artificial neural networks to predict drug dissolution profiles and evaluation of network performance using similarity factor.

PURPOSE: To use artificial neural networks for predicting dissolution profiles of matrix-controlled release theophylline pellet preparation, and to evaluate the network performance by comparing the predicted dissolution profiles with those obtained from physical experiments using similarity factor. METHODS: The Multi-Layered Perceptron (MLP) neural network was used to predict the dissolution profiles of theophylline pellets containing different ratios of microcrystalline cellulose (MCC) and glyceryl monostearate (GMS). The concepts of leave-one-out as well as a time-point by time-point estimation basis were used to predict the rate of drug release for each matrix ratio. All the data were used for training, except for one set which was selected to compare with the predicted output. The closeness between the predicted and the reference dissolution profiles was investigated using similarity factor (f2). RESULTS: The f2 values were all above 60, indicating that the predicted dissolution profiles were closely similar to the dissolution profiles obtained from physical experiments. CONCLUSION: The MLP network could be used as a model for predicting the dissolution profiles of matrix-controlled release theophylline pellet preparation in product development.

Cellulose↗