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 199 records · Page 11Linked to original sources
PubMed1999

Sonographic prediction of malignancy in adnexal masses using an artificial neural network.

OBJECTIVE: To generate a neural network algorithm which computes a probability of malignancy score for pre-operative discrimination between malignant and benign adnexal tumours. DESIGN: A retrospective analysis of previously collected data. Information from 75% of the study group was used to train an artificial neural network and the remainder was used for validation. SETTING: The Gynaecological Ultrasound Research Unit at King's College Hospital, London. POPULATION: Sixty-seven women with known adnexal mass who had been examined using transvaginal B-mode ultrasonography and colour Doppler imaging with pulse spectral analysis immediately before surgery. The excised masses were classified histologically as benign (n = 52) or malignant (n = 15), of which three were borderline. METHODS: The variables that were put into the artificial neural network were: age, menopausal status, maximum tumour diameter, tumour volume, locularity, the presence of papillary projections, the presence of random echogenicity, the presence of analysable blood flow velocity waveforms, the peak systolic velocity, time-averaged maximum velocity, the pulsatility index, and resistance index. Histological classification, categorised as benign or malignant, was the output result. RESULTS: A variant of the back propagation method was selected to train the network. The overall architecture of the network with the best performance contained an input layer with four variables (age, time-averaged maximum velocity, papillary projection score and maximum tumour diameter), a hidden layer with three units and an output layer with one. The sensitivity and specificity at the optimum diagnostic decision value for the artificial neural network output (0.45) were 100% (95% CI 78.2%-100%) and 98.1% (95% CI 89.5%-100%), respectively. These values were significantly better than those obtained from the independent use of the resistance index, pulsatility index, time-averaged maximum velocity or peak systolic velocity at their optimum decision values (P < 0.01). CONCLUSION: Artificial neural networks may be used on clinical and ultrasound derived end-points to accurately predict ovarian malignancy. There is a need for a prospective evaluation of this technique using a larger number of patients.

Adnexal Diseases↗
PubMed2002

Prediction of the disulfide bonding state of cysteines in proteins with hidden neural networks.

A hybrid system (hidden neural network) based on a hidden Markov model (HMM) and neural networks (NN) was trained to predict the bonding states of cysteines in proteins starting from the residue chains. Training was performed using 4136 cysteine-containing segments extracted from 969 non-homologous proteins of well-resolved 3D structure and without chain-breaks. After a 20-fold cross-validation procedure, the efficiency of the prediction scores as high as 80% using neural networks based on evolutionary information. When the whole protein is taken into account by means of an HMM, a hybrid system is generated, whose emission probabilities are computed using the NN output (hidden neural networks). In this case, the predictor accuracy increases up to 88%. Further, when tested on a protein basis, the hybrid system can correctly predict 84% of the chains in the data set, with a gain of at least 27% over the NN predictor.

Cysteine↗
PubMed2005

Pattern recognition using asymmetric attractor neural networks.

The asymmetric attractor neural networks designed by the Monte Carlo- (MC-) adaptation rule are shown to be promising candidates for pattern recognition. In such a neural network with relatively low symmetry, when the members of a set of template patterns are stored as fixed-point attractors, their attraction basins are shown to be isolated islands embedded in a "chaotic sea." The sizes of these islands can be controlled by a single parameter. We show that these properties can be used for effective pattern recognition and rejection. In our method, the pattern to be identified is attracted to a template pattern or a chaotic attractor. If the difference between the pattern to be identified and the template pattern is smaller than a predescribed threshold, the pattern is attracted to the template pattern automatically and thus is identified as belonging to this template pattern. Otherwise, it wanders in a chaotic attractor for ever and thus is rejected as an unknown pattern. The maximum sizes of these islands allowed by this kind of neural networks are determined by a modified MC-adaptation rule which are shown to be able to dramatically enlarge the sizes of the islands. We illustrate the use of our method for pattern recognition and rejection with an example of recognizing a set of Chinese characters.

Journal Article↗
PubMed1998

Applications of neural networks in urologic oncology.

Artificial neural networks are computer-based statistical models that can be used to imitate biologic neural processes. They have been applied to a variety of problems in medicine, including diagnosis and outcomes predictions. In the area of urologic oncology, these neural networks have been used to assist in the diagnosis of prostate cancer, predicting response to therapy and recurrence in prostate cancer, predicting the presence of renal cell carcinoma in cystic renal lesions, and predicting the presence of occult metastatic disease in nonseminomatous testicular germ cell tumors. This article reviews the basic concepts of artificial neural networks and summarizes their application in urologic oncology. Neural network technology remains in its infancy in urologic oncology, and many more retrospective and prospective studies are needed to determine its clinical utility.

Computer Simulation↗
PubMed2001

Nucleus accumbens, entorhinal cortex and latent inhibition: a neural network model.

A neural network model of classical conditioning (Schmajuk, Lam, and Gray, J. Exp. Psychol.: Anim. Behav. Process, 22, 1996, 321-349) is applied to the description of the neural substrates of latent inhibition. Experimental data suggest that latent inhibition might be controlled by a circuit that involves the hippocampus, the entorhinal cortex, the nucleus accumbens, and the mesolimbic dopaminergic projection from the ventral tegmental area to the accumbens. By mapping different nodes and connections in the model onto this brain circuit, computer simulations demonstrate that, in most cases, the model provides a good quantitative description of: (1) the impairment of latent inhibition by lesions of the shell of the nucleus accumbens; (2) the restoration of latent inhibition by haloperidol following lesions of the shell; (3) the preservation of latent inhibition by lesions of the core of the nucleus accumbens; (4) the facilitation of latent inhibition by combined shell core lesions and by core lesions with extended conditioning; (5) the impairment of latent inhibition following lesions of the entorhinal cortex or the hippocampus; and (6) the restoration of latent inhibition by haloperidol following lesions of the entorhinal cortex and ventral subiculum. In addition, the model is able to describe neural activity in the nucleus accumbens.

Animals↗
PubMed1995

Artificial neural networks for medical classification decisions.

Neural networks are growing in popularity. However, empirically comparing them with traditional methods of solving medical classification decisions is not trivial. Following a brief description and comparison with the statistical technique, discriminant analysis, the methodology for comparing neural networks with discriminant analysis is described. The advantages and disadvantages of neural networks are summarized to support a conclusion that neural networks are beneficial and destined to proliferate. Areas of fruitful future research are identified.

Decision Making, Computer-Assisted↗
PubMed2003

On motion detection through a multi-layer neural network architecture.

A neural network model called lateral interaction in accumulative computation for detection of non-rigid objects from motion of any of their parts in indefinite sequences of images is presented. Some biological evidences inspire the model. After introducing the model, the complete multi-layer neural architecture is offered in this paper. The architecture consists of four layers that perform segmentation by gray level bands, accumulative charge computation, charge redistribution by gray level bands and moving object fusion. The lateral interaction in accumulative computation associated learning algorithm is also introduced. Some examples that explain the usefulness of the system we propose are shown at the end of this article.

Motion Perception↗
PubMed2001

Artificial neural networks: opening the black box.

Artificial neural networks now are used in many fields. They have become well established as viable, multipurpose, robust computational methodologies with solid theoretic support and with strong potential to be effective in any discipline, especially medicine. For example, neural networks can extract new medical information from raw data, build computer models that are useful for medical decision-making, and aid in the distribution of medical expertise. Because many important neural network applications currently are emerging, the authors have prepared this article to bring a clearer understanding of these biologically inspired computing paradigms to anyone interested in exploring their use in medicine. They discuss the historical development of neural networks and provide the basic operational mathematics for the popular multilayered perceptron. The authors also describe good training, validation, and testing techniques, and discuss measurements of performance and reliability, including the use of bootstrap methods to obtain confidence intervals. Because it is possible to predict outcomes for individual patients with a neural network, the authors discuss the paradigm shift that is taking place from previous "bin-model" approaches, in which patient outcome and management is assumed from the statistical groups in which the patient fits. The authors explain that with neural networks it is possible to mediate predictions for individual patients with prevalence and misclassification cost considerations using receiver operating characteristic methodology. The authors illustrate their findings with examples that include prostate carcinoma detection, coronary heart disease risk prediction, and medication dosing. The authors identify and discuss obstacles to success, including the need for expanded databases and the need to establish multidisciplinary teams. The authors believe that these obstacles can be overcome and that neural networks have a very important role in future medical decision support and the patient management systems employed in routine medical practice.

Decision Theory↗
PubMed2005

Landmine detection and classification with complex-valued hybrid neural network using scattering parameters dataset.

Neural networks have been applied to landmine detection from data generated by different kinds of sensors. Real-valued neural networks have been used for detecting landmines from scattering parameters measured by ground penetrating radar (GPR) after disregarding phase information. This paper presents results using complex-valued neural networks, capable of phase-sensitive detection followed by classification. A two-layer hybrid neural network structure incorporating both supervised and unsupervised learning is proposed to detect and then classify the types of landmines. Tests are also reported on a benchmark data.

Algorithms↗
PubMed1993

Protein secondary structure prediction with partially recurrent neural networks.

Partially recurrent neural networks with different topologies are applied for secondary structure prediction of proteins. The state of some activations in the network is available after a pattern presentation via feedback connections as additional input during the processing of the next pattern in a sequence. A reference data set containing 91 proteins in the training set and 15 non-homologous proteins in the test set is used for training and testing a network with a modified, hierarchical Elman architecture. The network predicts the secondary structures alpha-helix, beta-sheet, and "coil" for each amino acid. The percentage of correctly classified amino acids is 67.83% on the training set and 63.98% on the test set. The best performance of a three-layer feedforward network is 62.7% on the same test set. A cascaded network, where the outputs of the recurrent network are processed by a second net with 13 x 3 inputs, four hidden and three output units has a predictive performance of 64.49%. The best corresponding feedforward net has a performance of 64.3%.

Amino Acid Sequence↗
PubMed1996

Classifying individuals among infra-specific taxa using microsatellite data and neural networks.

The method of neural networks was tested for its ability to assign individuals on the basis of their multilocus genotypes, using a data collection of 430 honeybees and 8 microsatellite loci. This data set includes various taxonomical levels (populations within the same subspecies, various subspecies belonging to the same evolutionary lineage, and the 3 lineages of the species). Qualitative genotypic data have been submitted to 2 types of transformation (simple coding and coding plus factorial correspondence analysis), and they have been partitioned in 2 sets, a training set of 300 individuals and a testing set of 103 individuals. Two procedures ("leave one out" and "hold out") were applied to evaluate the quality of prediction. Compared to discriminant analysis, neural networks performed better in terms of correctly classified individuals at any taxonomical level. For instance, with the simple coding and the hold out procedure, the proportions of correctly assigned individuals from the testing set were 66.2%, 82.3% and 100% at the populations, subspecies and lineage level, respectively. The potential use of neural networks in populations genetics is discussed.

Animals↗
PubMed1994

Relationship between a fuzzy logic and a steepest descent approach to optimize a feedforward artificial neural network configuration.

The neural network designer must take into consideration many factors when selecting an appropriate network configuration. The performance of a given network configuration is influenced by many different factors such as: accuracy, training time, sensitivity, and the number of neurons used in the implementation. Using a cost function based on the four criteria mentioned previously, the various network paradigms can be evaluated relative to one another. If the mathematical models of the evaluation criteria as functions of the network configuration are known, then traditional techniques (such as the steepest descent method) could be used to determine the optimal network configuration. The difficulty in selecting an appropriate network configuration is due to the difficulty involved in determining the mathematical models of the evaluation criteria. This difficulty can be avoided by using fuzzy logic techniques to perform the network optimization as opposed to the traditional techniques. Fuzzy logic avoids the need of a detailed mathematical description of the relationship between the network performance and the network configuration, by using heuristic reasoning and linguistic variables. A comparison will be made between the fuzzy logic approach and the steepest descent method for the optimization of the cost function. The fuzzy optimization procedure could be applied to other systems where there is a priori information about their characteristics.

Electronic Data Processing↗
PubMed1994

The beauty of molecular surfaces as revealed by self-organizing neural networks.

The Kohonen neural network is a self-organizing network that can be used for the projection of the surface properties of molecules. This allows one to view properties on a molecular surface, like the electrostatic potential in a single picture. These maps are useful for the comparison of molecules and provide a new definition of molecular similarity.

Base Composition↗
PubMed2001

String matching artificial neural networks.

Three artificial neural networks (ANNs) are proposed for solving a variety of on- and off-line string matching problems. The ANN structure employed as the building block of these ANNs is derived from the harmony theory (HT) ANN, whereby the resulting string matching ANNs are characterized by fast match-mismatch decisions, low computational complexity, and activation values of the ANN output nodes that can be used as indicators of substitution, insertion (addition) and deletion spelling errors.

Artificial Intelligence↗
PubMed1994

Response classification in psychological testing using a neural network.

A feedforward neural network with error backpropagation has been designed to recognize hand-drawn patterns in a cognitive test. The architecture uses both position and direction sensitivity in the input layer. The training set consisted of 659 icons which were shifted horizontally and vertically to give a total training set of 5931 icons. In testing on an independent set of 31,192 icons produced by 557 subjects from a Danish standard population sample, the rate of misclassification was 0.12% compared with an average rate of sequence errors of 1.6%.

Humans↗
PubMed1993

A note on the low-dimensional display of multivariate data using neural networks.

A novel neural network technique has been proposed (Livingstone et al. J. Mol. Graphics 1991, 9, 115-118) which is useful for a low-dimensional display of multivariate data sets. The method makes use of the activity values of the hidden neurons in a trained three-layer feed-forward network to produce the low-dimensional display. It was claimed that in contrast to conventional techniques, such as principal components analysis or nonlinear mapping, this technique could be used also to reconstruct, from a given point in the low-dimensional display, the corresponding multivariate input vector via the completely known weight matrices of a suitably trained network. We show here that this claim is unjustified in this general form. When previously unknown, grossly different input vectors are presented to the trained network, they can occupy, for example, exactly the same point in the low-dimensional display which is occupied also by a given training vector, if certain linear relationships between the vector components are fulfilled. Thus, an infinite set of different linearly dependent input vectors is projected onto one single point in the low-dimensional display. Reconstruction of a multivariate vector, starting from this point in the low-dimensional display, is able to lead back to only one multivariate vector (in the example given, to the original training vector).

Guanine↗
PubMed2002

Predictive non-linear modeling of complex data by artificial neural networks.

An artificial neural network (ANN) is an artificial intelligence tool that identifies arbitrary nonlinear multiparametric discriminant functions directly from experimental data. The use of ANNs has gained increasing popularity for applications where a mechanistic description of the dependency between dependent and independent variables is either unknown or very complex. This machine learning technique can be roughly described as a universal algebraic function that will distinguish signal from noise directly from experimental data. The application of ANNs to complex relationships makes them highly attractive for the study of biological systems. Recent applications include the analysis of expression profiles and genomic and proteomic sequences.

Biochemical Phenomena↗